WO2016017577A1 - 端末装置、情報提供システム、情報提示方法および情報提供方法 - Google Patents
端末装置、情報提供システム、情報提示方法および情報提供方法 Download PDFInfo
- Publication number
- WO2016017577A1 WO2016017577A1 PCT/JP2015/071237 JP2015071237W WO2016017577A1 WO 2016017577 A1 WO2016017577 A1 WO 2016017577A1 JP 2015071237 W JP2015071237 W JP 2015071237W WO 2016017577 A1 WO2016017577 A1 WO 2016017577A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- language
- sound
- terminal device
- identification information
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 79
- 230000005540 biological transmission Effects 0.000 claims abstract description 24
- 238000000605 extraction Methods 0.000 claims abstract description 19
- 230000008569 process Effects 0.000 claims description 26
- 230000005236 sound signal Effects 0.000 claims description 25
- 239000000284 extract Substances 0.000 abstract description 8
- 238000004891 communication Methods 0.000 description 74
- 238000013519 translation Methods 0.000 description 45
- 230000008901 benefit Effects 0.000 description 33
- 238000012545 processing Methods 0.000 description 32
- 238000010586 diagram Methods 0.000 description 28
- 230000015572 biosynthetic process Effects 0.000 description 23
- 238000003786 synthesis reaction Methods 0.000 description 23
- 230000004048 modification Effects 0.000 description 22
- 238000012986 modification Methods 0.000 description 22
- 238000006243 chemical reaction Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 9
- 230000009466 transformation Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000010365 information processing Effects 0.000 description 4
- 239000004065 semiconductor Substances 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 3
- 238000002156 mixing Methods 0.000 description 3
- 238000013179 statistical model Methods 0.000 description 3
- 230000001960 triggered effect Effects 0.000 description 3
- 206010011878 Deafness Diseases 0.000 description 2
- 208000032041 Hearing impaired Diseases 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000007480 spreading Effects 0.000 description 2
- 230000002194 synthesizing effect Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 125000002066 L-histidyl group Chemical group [H]N1C([H])=NC(C([H])([H])[C@](C(=O)[*])([H])N([H])[H])=C1[H] 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/42—Data-driven translation
- G06F40/47—Machine-assisted translation, e.g. using translation memory
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/263—Language identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L19/00—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
- G10L19/018—Audio watermarking, i.e. embedding inaudible data in the audio signal
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
Definitions
- the present invention relates to a technique for providing information to a user of a terminal device.
- Patent Document 1 discloses an automatic reproduction voice guidance system using a transmission device installed in the vicinity of each exhibit such as an art museum or a museum and a portable receiver carried by the user.
- the transmission device intermittently transmits an identification code unique to the exhibit to the surroundings by radio waves or infrared rays.
- the portable receiver reproduces the guidance voice corresponding to the identification code received from the transmitting device among the plurality of guidance voices stored in advance in its recording medium.
- an exhibit in the range is triggered by the fact that the portable receiver moves and receives an identification code within a range (around the exhibit) where radio waves and infrared rays from the transmitting device reach.
- the guidance voice to explain is played back.
- an object of the present invention is to provide a variety of information to a user without requiring a dedicated communication device for wireless communication.
- the terminal device releases a signal in accordance with an acoustic signal that includes an acoustic signal that represents the sound to be reproduced and a modulation signal that includes identification information of the sound to be reproduced.
- Sound collecting means for picking up sound that has been picked up to generate a sound pickup signal
- information extraction means for extracting identification information from the sound pickup signal generated by the sound pickup means, and identification information extracted by the information extraction means
- Transmitting means for transmitting an information request to the information providing means, receiving means for receiving any of a plurality of related information corresponding to the identification information included in the information request and related to the sound to be reproduced from the information providing means; and receiving means Output means for outputting the related information received.
- the identification information is extracted from the collected sound signal obtained by collecting the sound emitted according to the acoustic signal including the acoustic signal representing the reproduction target sound and the modulation signal including the identification information of the reproduction target sound. Is done. That is, the identification information is notified to the terminal device by acoustic communication using the sound emitted together with the reproduction target sound. Therefore, the sound collection device of the terminal device, which is used for voice calls and voice recording, can be used for acquisition of identification information, and the playback target sound is not required without the need for a communication device dedicated to wireless communication using infrared or radio waves. It is possible to provide the user with related information corresponding to the identification information.
- the transmitting means transmits an information request including language information indicating a language designated by the terminal device
- the receiving means corresponds to the identification information of the information request and has a plurality of different information Of the plurality of related information corresponding to the language, the related information corresponding to the language specified by the language information of the information request is received.
- the related information corresponding to the language specified by the language information in the information request is received among the plurality of related information corresponding to the plurality of different languages, various users having different languages can be used. There is an advantage that related information that can be understood can be provided.
- the related information corresponding to the language specified by the language information of the information request is an acoustic signal representing a sound generated by generating a character string obtained by translating the pronunciation content of the reproduction target sound into the specified language. Or a character string obtained by translating the pronunciation content of the reproduction target sound into the designated language. Therefore, even if the user of the terminal device cannot understand the voice in the first language that is emitted according to the acoustic signal representing the sound to be reproduced, the user of the terminal device can view the converted character string in the second language or listen to the voice in the second language. By doing so, it is possible to grasp the content of the reproduction target sound.
- the output means is specified by the language information of the information request in parallel with the sound of the reproduction target sound expressed in the first language among the plurality of languages (sound from the sound emitting system).
- the related information corresponding to a language other than the first language is output.
- the related information corresponding to a language other than the first language is output in parallel with the sound emission of the reproduction target sound expressed in the first language, for example, the related information is displayed after the reproduction of the sound of the reproduction target sound is completed.
- the output configuration there is an advantage that the user can easily recognize the correspondence between the reproduction target sound and the related information.
- An information providing system includes a sound emitting unit that emits sound according to an acoustic signal including an acoustic signal representing a reproduction target sound and a modulation signal including identification information of the reproduction target sound.
- the information request including the identification information extracted from the sound emitted by the sound emitting means is received from the terminal device, and corresponds to the identification information included in the information request and any of a plurality of related information related to the reproduction target sound Information providing means for transmitting to the terminal device.
- the sound corresponding to the acoustic signal including the acoustic signal representing the reproduction target sound and the modulation signal including the identification information of the reproduction target sound is emitted from the sound emitting means.
- the identification information is notified to the terminal device by acoustic communication using the sound emitted together with the reproduction target sound. Therefore, it is possible to provide the user with related information corresponding to the identification information of the reproduction target sound without requiring a communication device dedicated to wireless communication using infrared rays or radio waves.
- the information providing means receives an information request including language information indicating a language specified by the terminal device, and corresponds to a plurality of different languages corresponding to the identification information of the information request.
- Related information corresponding to the language specified by the language information of the information request among the plurality of related information is transmitted to the terminal device.
- the related information corresponding to the language specified in the language information of the information request is preferably an acoustic signal representing a sound produced by sounding a character string obtained by translating the pronunciation content of the reproduction target sound into the specified language, or the reproduction target This is a character string obtained by translating the pronunciation of a sound into the specified language.
- the present invention is also specified as the operation method (information presentation method) of the terminal device and the operation method (information provision method) of the information providing system according to each of the above aspects.
- sound is emitted in a terminal device in accordance with an acoustic signal that includes an acoustic signal that represents a reproduction target sound and a modulation signal that includes identification information of the reproduction target sound.
- Collect sound and generate sound collection signal extract identification information from sound collection signal, send information request including identification information to information providing means, respond to identification information included in information request and playback target
- One of a plurality of related information related to the sound is received from the information providing means, and the received related information is output.
- the information request includes language information indicating a language specified by the terminal device, and corresponds to identification information of the information request and a plurality of related information corresponding to a plurality of different languages. Related information corresponding to the language specified in the language information of the information request is received. Further, the information providing method according to the present invention emits a sound corresponding to an acoustic signal including an acoustic signal representing a reproduction target sound and a modulation signal including identification information of the reproduction target sound, and from the emitted sound. An information request including the extracted identification information is received from the terminal device, and one of a plurality of related information corresponding to the identification information included in the information request and related to the reproduction target sound is transmitted to the terminal device.
- the information request includes language information indicating a language designated by the terminal device, and corresponds to identification information of the information request and includes a plurality of related information corresponding to a plurality of different languages.
- the related information corresponding to the language specified in the language information of the information request is transmitted to the terminal device.
- the terminal device and the information providing system according to each aspect described above are realized by a dedicated electronic circuit, and also by the cooperation of a general-purpose arithmetic processing device such as a CPU (Central Processing Unit) and a program.
- the program of the present invention can be provided in a form stored in a computer-readable recording medium and installed in the computer.
- the computer-readable recording medium according to the present invention emits a sound according to an acoustic signal containing an acoustic signal representing a sound to be reproduced and a modulation signal including identification information of the sound to be reproduced.
- Information including the sound collection process for collecting the collected sound to generate a sound collection signal, the information extraction process for extracting identification information from the sound collection signal generated by the sound collection process, and the identification information extracted by the information extraction process
- a transmission process for transmitting a request to the information providing means, a reception process for receiving any of a plurality of related information corresponding to the identification information included in the information request and related to the sound to be reproduced from the information providing means, and a reception process.
- a program for executing an output process for outputting the received related information is recorded.
- the information request includes language information indicating a language designated by the terminal device
- the reception process corresponds to the identification information of the information request and includes a plurality of related information corresponding to a plurality of different languages.
- Relevant information corresponding to the language specified in the language information of the information request is received.
- the information presentation method, the information providing method, the program, or the computer-readable recording medium in which the program is recorded according to each aspect the same effects as those of the terminal device or the information providing system according to each aspect described above can be obtained.
- FIG. 1 is a configuration diagram of a communication system according to a first embodiment of the present invention. It is a block diagram of an information management system. It is a block diagram of an acoustic signal acquisition part and a related information acquisition part. It is a block diagram of a signal processing part. It is explanatory drawing of operation
- mode 1 of an acoustic signal acquisition part and a related information acquisition part.
- FIG. 1 is a configuration diagram of a communication system 100 according to the first embodiment of the present invention.
- the communication system 100 includes an information providing system 10 and a terminal device 12.
- the information providing system 10 is a computer system that provides various information to the terminal device 12.
- the terminal device 12 is a portable information processing device such as a mobile phone or a smartphone.
- information to be provided is provided from the information providing system 10 to the terminal device 12.
- the terminal device 12 Although only one terminal device 12 is illustrated in FIG. 1 for the sake of convenience, actually, information can be provided from the information providing system 10 to each of the plurality of terminal devices 12.
- the information providing system 10 of the first embodiment includes an information management system 14 and a sound emission system 16.
- the sound emission system 16 is installed in the exhibition facility M and used for voice guidance of the facility.
- the sound emission system 16 of the first embodiment is a voice that guides the user in a specific language (hereinafter referred to as “first language”) (hereinafter “guidance voice V”).
- the terminal device 12 is notified of the identification information D given in advance to the guidance voice V.
- the guidance voice V is, for example, a voice that explains an exhibit or a sound that guides a route in the exhibition facility M.
- the identification information D of the guidance voice V is notified to the terminal device 12 by wireless information communication.
- the case where the identification information D is notified to the terminal device 12 from the sound emission system 16 by the acoustic communication which uses the sound (sound wave) as an air vibration as a transmission medium is illustrated. That is, the identification information D is radiated from the sound emitting system 16 together with the guidance voice V as sound.
- the information management system 14 is a computer system that manages information provided to the terminal device 12.
- the terminal device 12 can communicate with the information management system 14 via a communication network 18 including a mobile communication network and the Internet.
- the terminal device 12 transmits an information request R including the identification information D notified from the sound emission system 16 to the information management system 14.
- the information management system 14 transmits the related information Q corresponding to the identification information D specified by the information request R received via the communication network 18 to the requesting terminal device 12.
- the related information Q is information related to the guidance voice V.
- the terminal device 12 is provided with related information Q indicating translation obtained by converting the guidance in the first language pronounced as the guidance voice V into another language (hereinafter referred to as “second language”).
- a user who can understand the first language grasps the guidance of the exhibition facility M by listening to the guidance voice V, and a user who can understand the second language refers to the related information Q to display the exhibition facility M. Know the guidance of.
- Specific configurations and functions of the elements of the communication system 100 outlined above will be described in detail below.
- FIG. 2 is a configuration diagram of the information management system 14.
- the information management system 14 of the first embodiment includes a control device 142, a storage device 144, an input device 146, and a display device 148.
- the storage device 144 stores a program executed by the control device 142 and various data used by the control device 142.
- a known recording medium such as a semiconductor recording medium or a magnetic recording medium or a combination of a plurality of types of recording media is arbitrarily employed as the storage device 144.
- the input device 146 is an operating device that is operated by an administrator who operates the information management system 14 for various instructions to the information management system 14, and includes, for example, a plurality of operators that can be operated by the administrator.
- the manager can arbitrarily designate a character string (hereinafter referred to as “designated character string ST”) expressing guidance of each exhibit of the exhibition facility M by appropriately operating the input device 146, for example.
- the display device 148 is a device (for example, a liquid crystal display panel) that displays various types of information such as speech recognition and machine translation results under the control of the control device 142. Note that a touch panel in which the input device 146 and the display device 148 are integrally configured may be employed.
- the control device 142 is, for example, a CPU (Central Processing Unit), and realizes each function of the information management system 14 in cooperation with a program stored in the storage device 144. That is, the control device 142 executes a program stored in the storage device 144, thereby managing a plurality of functions (acoustic signal acquisition unit 22, related information acquisition unit 24, An identification information setting unit 26, a signal processing unit 32, a correspondence management unit 34, and an information providing unit 36) are realized.
- a configuration in which each function of the control device 142 is distributed to a plurality of devices, or a configuration in which a dedicated electronic circuit realizes a part of the function of the control device 142 may be employed.
- the acoustic signal acquisition unit 22 acquires an acoustic signal SG representing the guidance voice V.
- the acoustic signal acquisition unit 22 represents a time waveform of the guidance voice V that pronounces the designated character string ST in the first language that is designated by the administrator through an operation on the input device 146.
- the acoustic signal SG is generated by speech synthesis.
- a known technique can be arbitrarily employed for the speech synthesis performed by the acoustic signal acquisition unit 22. For example, a unit connection for generating an acoustic signal SG by connecting in time series speech units corresponding to each character of the designated character string ST among a plurality of speech units (phoneme unit or phoneme chain) prepared in advance.
- Type speech synthesis and statistical model type speech synthesis that generates an acoustic signal SG corresponding to a specified character string ST using a statistical model such as HMM (Hidden Markov Model) is an acoustic signal SG by the acoustic signal acquisition unit 22
- HMM Hidden Markov Model
- the related information acquisition unit 24 in FIG. 2 generates related information Q related to the guidance voice V.
- the related information acquisition unit 24 according to the first embodiment provides the second guide for the exhibition facility M by machine translation (automatic translation) for the designated character string ST in the first language designated by the administrator.
- a character string expressed in a language hereinafter referred to as “converted character string CT”
- a known technique can be arbitrarily adopted for machine translation of the designated character string ST.
- a rule-based machine translation that converts a word order or a word by referring to a result of parsing a specified character string ST and a linguistic rule, or a statistical model that expresses a statistical tendency of a language (translation model and language Statistical machine translation that translates the designated character string ST into the second language using the model) can be used to generate the related information Q by the related information acquisition unit 24.
- the related information Q is generated by machine translation with respect to a character string indicating the pronunciation of the guidance voice V (that is, the designated character string ST)
- the related information Q in a language different from the language of the guidance voice V is generated. There is an advantage that it is not necessary to prepare in advance.
- the identification information D is a unique code for identifying the guidance voice V and is set for each guidance voice V.
- the identification information setting unit 26 sets a series of random numbers generated by a known method so as not to overlap each other between different guidance voices V as the identification information D.
- the signal processing unit 32 generates the acoustic signal S by synthesizing the identification information D set by the identification information setting unit 26 with the acoustic signal SG of the guidance voice V.
- synthesizing the identification information D with the acoustic signal SG acoustic watermarking
- the signal processing unit 32 includes a modulation processing unit 322 and a mixing processing unit 324 as illustrated in FIG.
- the modulation processing unit 322 includes the identification information D as an acoustic component in a predetermined frequency band by sequentially executing spread modulation of the identification information D using a spread code and frequency conversion using a carrier wave of a predetermined frequency.
- An acoustic signal (hereinafter referred to as “modulation signal”) SD is generated.
- the frequency band of the modulation signal SD is a frequency band that can be emitted by the sound emission system 16 and collected by the terminal device 12, and the frequency of sound such as voice or musical sound that the user listens to in a normal environment.
- the frequency band for example, 18 kHz or more and 20 kHz or less
- exceeding the band for example, about 16 kHz or less within the audible range
- a modulated signal SD within a specific frequency band can be generated by frequency-modulating a carrier wave such as a sine wave having a predetermined frequency with the identification information D.
- the mixing processing unit 324 in FIG. 4 generates the acoustic signal S by superimposing (typically adding) the acoustic signal SG acquired by the acoustic signal acquiring unit 22 and the modulation signal SD generated by the modulation processing unit 322.
- the acoustic signal S includes an acoustic component (acoustic signal SG) of the guidance voice V and an acoustic component (modulation signal SD) including the identification information D of the guidance voice V.
- FIG. 5 is an explanatory diagram of a temporal relationship between the acoustic signal SG of the guidance voice V and the modulation signal SD including the identification information D.
- the modulation signal SD including the identification information D of the guidance voice V is repeatedly added multiple times to different sections on the time axis of the acoustic signal SG of the guidance voice V. That is, the acoustic component of the identification information D of the guidance voice V is mixed at a plurality of points on the time axis in the guidance voice V.
- the modulation signals SD can be continuous with each other on the time axis.
- the signal processing unit 32 of the first embodiment stores the acoustic signal S in the storage device 144 as an acoustic file in a predetermined format (for example, WAV format or MP3 format).
- a predetermined format for example, WAV format or MP3 format.
- the correspondence management unit 34 in FIG. 2 associates the identification information D set by the identification information setting unit 26 for each guidance voice V with the related information Q acquired by the related information acquisition unit 24 for the guidance voice V, and stores the information. 144 stored. Therefore, as illustrated in FIG. 2, the storage device 144 stores related information Q for each identification information D of the guidance voice V.
- an acoustic signal S and related information Q are generated for each of a plurality of guidance voices V emitted in the exhibition facility M.
- the acoustic signal SG acoustic signal S
- the related information Q are associated with each other via the identification information D.
- the acoustic signal S and the related information Q may be stored in separate recording media. Further, it is possible to adopt a configuration in which one or more external devices that are connected to the information management system 14 and can exchange data with the system are employed as a storage device that stores the acoustic signal S and the related information Q. is there.
- the 2 receives the information request R including the identification information D from the terminal device 12, and the identification information D specified by the information request R among the plurality of related information Q stored in the storage device 144. Is selected and transmitted to the requesting terminal device 12. The transmission of the related information Q to the terminal device 12 will be described later.
- FIG. 6 is a flowchart of processing (hereinafter referred to as “information generation processing”) in which the information management system 14 generates the acoustic signal S and the related information Q.
- the information generation process in FIG. 6 is started by an operation on the input device 146 from the administrator (specifically, designation of the designated character string ST).
- the control device 142 the acoustic signal acquisition unit 22 and the related information acquisition unit 24
- the control device 142 outputs the acoustic signal SG of the guidance voice V corresponding to the designated character string ST and the related information Q related to the guidance voice V.
- the control device 142 (identification information setting unit 26) sets the identification information D of the guidance voice V (SA2).
- control device 142 (the signal processing unit 32) generates an acoustic signal S in which the modulation signal SD including the identification information D of the guidance voice V is superimposed on the acoustic signal SG of the guidance voice V, and stores the acoustic signal S in the storage device 144. (SA3). Then, the control device 142 (correspondence management unit 34) stores the related information Q of the guidance voice V and the identification information D in the storage device 144 in association with each other (SA4).
- a plurality of acoustic signals S (acoustic files) generated by the information management system 14 in the information generation processing exemplified above are transferred to the sound emission system 16 of FIG.
- the method of transferring the plurality of acoustic signals S is arbitrary. For example, a method of transferring each acoustic signal S from the information management system 14 to the sound emitting system 16 via the communication network 18 or a portable recording medium such as a semiconductor recording medium. A method of transferring each acoustic signal S from the information management system 14 to the sound emitting system 16 via the recording medium of FIG.
- FIG. 7 is a configuration diagram of the sound emission system 16.
- the sound emission system 16 of the first embodiment includes a control device 162, a storage device 164, and a plurality of sound emission devices 166.
- the storage device 164 is configured by a known recording medium such as a semiconductor recording medium or a magnetic recording medium or a combination of a plurality of types of recording media.
- a plurality of acoustic signals S transferred from the information management system 14 are stored in the storage device 164.
- the control device 162 comprehensively controls each element of the sound emission system 16.
- the control device 162 of the first embodiment supplies each acoustic signal S stored in the storage device 164 to each sound emitting device 166.
- Each of the plurality of sound emitting devices 166 is installed in the vicinity of different exhibits in the exhibition facility M.
- the sound signal S corresponding to the guidance voice V of the exhibit is supplied to the sound emitting device 166 installed in the vicinity of any one exhibit.
- Each sound emitting device 166 is an acoustic device that emits sound according to the acoustic signal S supplied from the control device 162.
- illustration of the D / A converter which converts the acoustic signal S from digital to analog is abbreviate
- the acoustic signal S includes the acoustic signal SG representing the guidance voice V and the modulation signal SD including the identification information D of the guidance voice V. Therefore, from the sound emitting device 166 corresponding to any one exhibition, the guidance voice V of the exhibition and the sound indicating the identification information D are emitted. As illustrated in FIG. 5, since the modulation signal SD of the identification information D is repeatedly added to the acoustic signal SG multiple times, the sound of the identification information D of the guidance voice V is reproduced in parallel with the reproduction of the guidance voice V. Are repeatedly emitted multiple times.
- the frequency band of the modulation signal SD including the identification information D is located on the high frequency side (for example, 18 kHz or more and 20 kHz or less) compared to the frequency band of the sound that the user listens in a normal environment.
- the sound of the identification information D is hardly perceived by the user. That is, it is possible to transmit the identification information D to the terminal device 12 by acoustic communication without affecting the listening of the guidance voice V by the user.
- FIG. 8 is a configuration diagram of the terminal device 12.
- One sound emitting device 166 of the sound emitting system 16 is also shown in FIG.
- the terminal device 12 of the first embodiment includes a control device 50, a storage device 52, a communication device 54, a sound collection device 56, and an output device 58.
- the storage device 52 stores a program executed by the control device 50 and data used by the control device 50.
- a known recording medium such as a semiconductor recording medium or a magnetic recording medium or a combination of a plurality of types of recording media is arbitrarily adopted as the storage device 52.
- the sound pickup device 56 is an acoustic device (microphone) that picks up surrounding sounds, and is used for voice calls between the terminal devices 12 and voice recording during moving image shooting.
- the sound collection device 56 of the first embodiment collects the sound emitted from the sound emission device 166 in the exhibition facility M, and an acoustic signal (hereinafter referred to as a time waveform of the sound).
- X referred to as “sound pickup signal”. Therefore, the sound collection signal X contains the acoustic component (acoustic signal SG) of the guidance voice V and the acoustic component (modulation signal SD) of the identification information D of the guidance voice V.
- the A / D converter that converts the sound collection signal X generated by the sound collection device 56 from analog to digital is not shown for convenience.
- the control device 50 comprehensively controls each element of the terminal device 12.
- the control device 50 of the first embodiment is, for example, a CPU, and functions as the information extraction unit 51 by executing a program stored in the storage device 52.
- the information extraction unit 51 extracts the identification information D of the guidance voice V by demodulating the sound collection signal X generated by the sound collection device 56. Specifically, the information extraction unit 51 selects the band component of the high frequency band (18 kHz or more and 20 kHz or less) including the identification information D from the collected sound signal X by using, for example, a high-pass filter, and the identification information The identification information D is extracted by passing through a matched filter whose coefficient is a spreading code used for D spread modulation.
- the communication device 54 is a communication device that communicates with the information providing system 10 via the communication network 18.
- the communication method between the communication device 54 and the communication network 18 is arbitrary, but typically, wireless communication is different from acoustic communication for notifying the terminal device 12 of the identification information D from the sound emitting system 16. (For example, information communication using radio waves or infrared rays as a transmission medium) is employed.
- the communication device 54 of the first embodiment includes a transmission unit 542 and a reception unit 544.
- the transmission unit 542 transmits an information request R including the identification information D extracted from the collected sound signal X by the information extraction unit 51 to the information management system 14.
- the receiving unit 544 receives the related information Q transmitted from the information management system 14 in response to the information request R.
- the information extraction unit 51 since the modulation signal SD of the identification information D is repeatedly added to the acoustic signal SG of the guidance voice V a plurality of times, the information extraction unit 51 has one identification information D. Can be repeatedly extracted multiple times at different points in time, but the transmission of the information request R and the reception of the related information Q are executed when the information extraction unit 51 first extracts the new identification information D. Only.
- the identification information D is acquired due to noise around the terminal device 12. Even if it fails, there is an advantage that the identification information D can be acquired again.
- the output device 58 of the first embodiment is a display device that displays a converted character string CT in the second language indicated by the related information Q. That is, in parallel with the reproduction of the first language guidance voice V by the sound emission device 166 of the sound emission system 16, the terminal device 12 displays (presents) the converted character string CT of the second language. Therefore, even when the user of the terminal device 12 cannot understand the first language, the user can grasp the guidance of the exhibit by viewing the converted character string CT in the second language.
- FIG. 9 is an explanatory diagram of an operation in which the terminal device 12 acquires the related information Q.
- the sound of the identification information D is repeatedly emitted from each sound emitting device 166 of the sound emitting system 16 in parallel with the reproduction of the guidance voice V.
- the sound collecting device 56 of the terminal device 12 causes the sound component of the guidance voice V and the sound of the identification information D to be heard.
- a sound pickup signal X containing the components is generated (SB1).
- the control device 50 (information extraction unit 51) extracts the identification information D by demodulating the collected sound signal X (SB2), and the transmission unit 542 of the communication device 54 sends the information request R including the identification information D to the information management system 14. (SB3).
- the information providing unit 36 of the information management system 14 receives the information request R transmitted from the terminal device 12 from the communication network 18 and is designated by the information request R among the plurality of related information Q stored in the storage device 144.
- the related information Q corresponding to the identified information D is selected (SB4), and the related information Q is transmitted to the requesting terminal device 12 (SB5).
- the receiving unit 544 of the terminal device 12 receives the related information Q transmitted from the information management system 14 (SB6), and the output device 58 outputs the related information Q (SB7).
- the terminal device 12 picks up the sound of the identification information D emitted from the sound emitting device 166 of the sound emitting system 16 in parallel with the reproduction of the guidance voice V (that is, the sound is released). Triggered by the movement of the terminal device 12 within the reach of the sound wave from the sound device 166), transmission of the information request R including the identification information D (SB3) and acquisition of the related information Q corresponding to the identification information D ( SB6) is executed.
- the identification information D is notified to the terminal device 12 by acoustic communication using sound emitted together with the guidance voice. Therefore, there is an advantage that the sound collecting device 56 used for voice call and voice recording can be used for obtaining the identification information D, and there is no need for a communication device dedicated to wireless communication of the identification information D.
- the sound emission system 16 also does not require a communication device dedicated to the transmission of the identification information D, and the existing sound emission device 166 used for voice guidance can be used for notification of the identification information D to the terminal device 12. There is.
- attains is easy, and it is collectively with respect to several terminal device 12
- the identification information D can be notified.
- the identification information D notified to the terminal device 12 together with the sound of the guidance voice V and the related information Q related to the guidance voice V are associated with each other in the information management system 14.
- the related information Q corresponding to the identification information D notified to the terminal device 12 is provided to the terminal device 12. Therefore, it is not necessary to store a plurality of related information Q in the storage device 52 of the terminal device 12 in advance. According to the above configuration, there is an advantage that the storage capacity required for the terminal device 12 for storing the related information Q is reduced. In the configuration in which a plurality of related information Q is stored in each terminal device 12, when the related information Q needs to be updated, the related information Q needs to be individually updated in each terminal device 12.
- the related information Q held in the storage device 144 of the information management system 14 is updated. Then, the updated related information Q can be provided to each terminal device 12. That is, there is an advantage that it is not necessary to update the related information Q for each terminal device 12 individually.
- the related information Q corresponding to the identification information D is concurrently reproduced with the reproduction of the guidance voice V. It can be output by the terminal device 12. Therefore, for example, there is an advantage that the user can easily recognize the correspondence between the guidance voice V and the related information Q as compared with the configuration in which the related information Q is output after the reproduction of the guidance voice V is completed.
- Japanese Patent Application Laid-Open No. 2011-109629 includes a transmitter installed in the vicinity of each exhibit such as a museum or a museum and a portable receiver carried by a user.
- a self-playing voice guidance system is disclosed.
- the transmission device intermittently transmits an identification code unique to the exhibit to the surroundings by radio waves or infrared rays.
- the portable receiver reproduces the guidance voice corresponding to the identification code received from the transmitting device among the plurality of guidance voices stored in advance in its recording medium.
- the portable receiver moves within the range where the radio waves and infrared rays from the transmitting device reach (around the exhibit) and receives the identification code, the exhibits in the range are displayed.
- the guidance voice to explain is played back.
- the identification code of each exhibit is transmitted from the transmitter by radio waves or infrared rays, it is necessary to install a dedicated communication device for transmitting and receiving radio waves and infrared rays in the transmitter and portable receiver. is there.
- sound corresponding to the acoustic signal S including the acoustic signal SG of the guidance voice V and the modulation signal SD including the identification information D of the guidance voice V is emitted. That is, the identification information D is notified to the terminal device 12 by acoustic communication using the sound emitted together with the guidance voice V.
- the sound collecting device 56 used for voice call and voice recording can be used for obtaining the identification information D, and there is no need for a communication device dedicated to wireless communication of the identification information D.
- the sound emission system 16 also does not require a communication device dedicated to the transmission of the identification information D, and the existing sound emission device 166 used for voice guidance can be used for notification of the identification information D to the terminal device 12. There is. That is, the identification information D can be exchanged with a simple configuration using elements that emit and collect sound.
- attains is easy, and it is collectively with respect to several terminal device 12
- the identification information D can be notified.
- Prior Art 2 additional information is added to an audio signal to be reproduced in a manner that does not affect the listening of sound according to the audio signal.
- An information processing apparatus that generates an output audio signal by adding is disclosed.
- the server adds information (for example, translation) related to voice guidance as additional information when transmitting information as voice guidance to a user via a speaker.
- the additional information is superimposed on the audio signal by, for example, spectrum spreading.
- the above-mentioned acoustic communication using sound waves as air vibration as a transmission medium tends to have a lower communication speed and communication capacity than, for example, wireless communication using radio waves as a transmission medium.
- Prior art 2 transmits additional information (that is, related information) itself by acoustic communication.
- the identification information D is transmitted by acoustic communication. Therefore, the structure of 1st Embodiment has the advantage that the data amount transmitted via acoustic communication can be suppressed by transmitting the identification information D whose data size is smaller than related information.
- identification information is transmitted by acoustic communication, and related information corresponding to the identification information is distributed from the information management system 14, so that it is also used for various related information (for example, voice and images) with a large amount of data. Can be presented to the person.
- the acoustic signal SG is generated by speech synthesis using the designated character string ST instructed by the administrator of the information management system 14 and the related information Q is generated by machine translation of the designated character string ST.
- the method for acquiring (typically generating) the signal SG and the related information Q is not limited to the above examples. Other methods for acquiring the acoustic signal SG and the related information Q will be exemplified below.
- the execution order of the acquisition (or generation) process of the acoustic signal SG and the acquisition (or generation) process of the related information Q is not limited.
- the acoustic signal acquisition unit 22 of the information management system 14 generates the acoustic signal SG of the guidance voice V by voice synthesis with respect to the designated character string ST, as in the first embodiment.
- the related information acquisition unit 24 acquires the designated character string ST designated by the administrator as the related information Q. That is, the related information Q is a character string expressing the pronunciation content of the guidance voice V in the first language common to the guidance voice V.
- the terminal device 12 displays the character string of the pronunciation content of the guidance voice V in parallel with the reproduction of the guidance voice V by the sound emission system 16.
- a hearing-impaired person can confirm the content of the guidance voice V.
- a step of acquiring the acoustic signal SG of the guidance voice V corresponding to the designated character string ST and the related information Q related to the guidance voice V (SA1). Is understood to include generating the acoustic signal SG of the guidance voice V corresponding to the designated character string ST by voice synthesis and acquiring the designated character string ST as the related information Q.
- the acoustic signal acquisition unit 22 of the information management system 14 generates the acoustic signal SG of the guidance voice V by speech synthesis for the designated character string ST in the first language, as in the first embodiment. Generate.
- the administrator of the information management system 14 specifies a character string (conversion character string CT) expressing the guidance voice V in the second language by appropriately operating the input device 146.
- the related information acquisition unit 24 acquires the converted character string CT of the second language designated by the administrator as the related information Q.
- an appropriate conversion character string CT cannot be generated when the accuracy of machine translation is low.
- step SA1 of the information generation process (FIG. 6) generates the acoustic signal SG of the guidance voice V corresponding to the designated character string ST by voice synthesis and the designated conversion character string CT (that is, guidance).
- the acoustic signal acquisition unit 22 of the information management system 14 generates the acoustic signal SG of the guidance voice V by voice synthesis with respect to the designated character string ST, as in the first embodiment.
- the related information acquisition unit 24 generates a converted character string CT of the second language by machine translation with respect to the designated character string ST of the first language, and also generates the converted voice string V of the second language by speech synthesis with respect to the converted character string CT.
- An acoustic signal is generated as related information Q.
- the output device 58 of the terminal device 12 is a sound emitting device (speaker or earphone) that emits sound (second language guidance voice V) corresponding to the acoustic signal indicated by the related information Q provided from the information management system 14. Include. That is, in parallel with the reproduction of the first language guidance voice V by the sound emission system 16, the terminal device 12 reproduces the second language guidance voice V. Therefore, even when the user of the terminal device 12 cannot understand the first language, he / she can understand the guidance of the exhibit by listening to the guidance voice V in the second language. In this aspect, step SA1 of the information generation process (FIG.
- a converted character string CT indicating the translation of the guidance voice V is generated by machine translation with respect to the voice V). Further, an acoustic signal (that is, the guidance voice) indicating the guidance voice V that pronounces the converted character string CT is generated. It is grasped as including generating by sound synthesis a sound signal indicating a sound obtained by pronounced a character string obtained by translating the pronunciation of V into the second language.
- the acoustic signal acquisition unit 22 of the information management system 14 acquires the acoustic signal SG of the guidance voice V from the signal supply device 200.
- the signal supply device 200 collects ambient sounds and generates an acoustic signal SG, a playback device that acquires and outputs the acoustic signal SG from a portable or built-in recording medium, and the communication network 18. It is a communication apparatus which receives and outputs the acoustic signal SG from.
- the related information acquisition unit 24 acquires, as the related information Q, the designated character string ST instructed by the administrator, as in the first and second aspects.
- the guidance voice V corresponding to the acoustic signal SG generated by the signal supply device 200 is emitted from the sound emitting device 166, and the designated character string ST corresponding to the instruction from the administrator is displayed on the terminal device 12.
- the related information acquisition unit 24 can also acquire an acoustic signal (for example, an acoustic signal of the guidance voice V in the second language) from the signal supply device 200 as the related information Q.
- the acoustic signal SG of the guidance voice V is acquired from the signal supply device 200, and the designated character string ST (that is, the pronunciation content of the guidance voice V). Is acquired as the related information Q.
- the acoustic signal acquisition unit 22 of the information management system 14 generates the acoustic signal SG of the guidance voice V by voice synthesis with respect to the designated character string ST, as in the first embodiment.
- the related information acquisition unit 24 acquires an image IMG (still image or moving image) related to the guidance voice V as the related information Q. Therefore, in parallel with the reproduction of the first language guidance voice V corresponding to the designated character string ST, the terminal device 12 displays the image IMG related to the guidance voice V.
- the image IMG related to the guidance voice V is acquired as the related information Q, there is an advantage that it is not necessary to store the image IMG in the terminal device 12 in advance.
- step SA1 of the information generation process (FIG. 6) generates the acoustic signal SG of the guidance voice V corresponding to the designated character string ST by voice synthesis, and the image IMG related to the guidance voice V is related information. To be acquired as Q.
- the acoustic signal acquisition unit 22 of the information management system 14 acquires the acoustic signal SG of the guidance voice V from the same signal supply device 200 as in FIG. 13 (Aspect 4).
- the related information acquisition unit 24 generates a character string representing the pronunciation content of the guidance voice V as the related information Q by voice recognition with respect to the acoustic signal SG supplied from the signal supply device 200.
- voice recognition of the acoustic signal SG a known technique such as a recognition technique using an acoustic model such as an HMM and a language model indicating linguistic restrictions can be arbitrarily adopted.
- the pronunciation content of the guidance voice V is reproduced in the terminal device 12 in parallel with the reproduction of the guidance voice V by the sound emission system 16. Is displayed. Therefore, even if the terminal device 12 is not provided with a means for separately acquiring and storing a character string indicating the pronunciation content of the guidance voice V, a user who misses the emitted guidance voice V or a user who is difficult to hear it. There is an advantage that the contents of the guidance voice V can be confirmed (for example, a hearing impaired person). That is, the storage capacity required for the terminal device 12 for storing the character string indicating the pronunciation content of the guidance voice V is reduced.
- the related information acquisition unit 24 of the information management system 14 generates a character string indicating the pronunciation content of the guidance voice V from the acoustic signal SG indicating the guidance voice V supplied from the signal supply device 200 by voice recognition.
- the management system 14 has an advantage that the administrator does not need to separately designate the character string as the designated character string ST.
- step SA1 of the information generation process (FIG. 6) acquires the acoustic signal SG of the guidance voice V supplied from the signal supply device 200, and the voice for the acoustic signal SG supplied from the signal supply device 200. By recognition, it is grasped as including that the character string expressing the pronunciation content of guidance voice V is generated as related information Q.
- the acoustic signal acquisition unit 22 of the information management system 14 acquires the acoustic signal SG of the first language guidance voice V from the signal supply device 200 as in the aspect 6.
- the related information acquisition unit 24 generates a character string of the guidance voice V by voice recognition with respect to the acoustic signal SG similarly to the aspect 6, and expresses the guidance voice V in the second language by machine translation of the character string.
- the conversion character string CT is generated as the related information Q.
- a known technique can be arbitrarily employed for the machine translation.
- step SA1 of the information generation process (FIG.
- a character string expressing the pronunciation content of the guidance voice V is generated by recognition, and related information Q indicating translation of the guidance voice V is generated by machine translation of the character string (that is, the pronunciation content of the guidance voice V is changed to the second language). Generating a translated character string as related information Q).
- the acoustic signal of the second language guidance voice V can be generated as the related information Q by voice synthesis with respect to the converted character string CT generated by machine translation.
- the terminal device 12 reproduces the guidance voice V in a second language different from the first language of the guidance voice V. Therefore, even when the user of the terminal device 12 cannot understand the guidance voice V in the first language, there is an advantage that the reproduction content can be understood by listening to the guidance voice V in the second language.
- step SA1 in FIG. 6 obtains the acoustic signal SG of the guidance voice V supplied from the signal supply device 200, and recognizes the acoustic signal SG supplied from the signal supply device 200 to recognize the guidance voice V.
- Generates a character string that expresses the pronunciation content generates a converted character string CT that indicates the translation of the guidance voice V by machine translation of the character string, and further synthesizes an acoustic signal that indicates the voice that pronounced the converted character string CT Generating.
- the manager OP who refers to the character string in the first language generated by the speech recognition of the acoustic signal SG on the display device 148 appropriately operates the input device 146 to translate the guidance voice V in the second language.
- the related information acquisition unit 24 uses the converted character string CT in the second language instructed by the administrator as the related information Q. get.
- the administrator OP since the administrator OP itself obtains the conversion character string CT indicating the result of human translation of the first language character string as the related information Q, it is compared with the case where the conversion character string CT is generated by machine translation.
- step SA1 in FIG. 6 obtains the acoustic signal SG of the guidance voice V supplied from the signal supply apparatus 200 and the guidance voice generated by voice recognition for the acoustic signal SG supplied from the signal supply apparatus 200.
- a character string indicating translation of the guidance voice V designated by an operation on the input device 146 with respect to a character string expressing the pronunciation contents of V that is, a character string obtained by translating the pronunciation contents of the guidance voice V into the second language.
- the administrator OP can operate the input device 146. It is also possible for the related information acquisition unit 24 to acquire the result of editing (typically correcting) the converted character string CT as the related information Q. According to this configuration, since the content edited by the administrator OP of the second language conversion character string CT generated by machine translation is acquired as the related information Q, only the character string indicating the translation of the guidance voice V is machine translated. It is possible to obtain a translated sentence translated with high quality in comparison with the mode generated by the method, while reducing the workload of the administrator OP compared with the case of obtaining a translated sentence only by human translation.
- step SA1 in FIG. 6 obtains the acoustic signal SG of the guidance voice V supplied from the signal supply apparatus 200 and the guidance voice generated by voice recognition for the acoustic signal SG supplied from the signal supply apparatus 200.
- a character string representing the pronunciation content of V is generated
- a converted character string CT indicating the translation of the guidance voice V is generated by machine translation of the character string
- the guidance voice V edited by an operation on the input device 146 is generated.
- a character string indicating the translation of i.e., a character string obtained by translating the pronunciation content of the guidance voice V into the second language.
- the character string obtained by translating the pronunciation content of the guidance voice V into the second language is, for example, a designated conversion character string CT (Aspect 2 [FIG. 11]), a conversion character string CT generated by machine translation (Aspect 3). [FIGS. 12, 16, and 17]), a human-translated converted character string CT (mode 7 [FIG. 18]), and an operation on the input device 146 with respect to the converted character string CT generated by machine translation. It is grasped as including the character string (mode 7 [Drawing 19]) edited by.
- the related information acquisition unit 24 of the information management system 14 performs content or content information related to the acoustic signal SG (for example, automatic content recognition (ACR)) for the acoustic signal SG (for example, Content name) is acquired as related information Q.
- ACR automatic content recognition
- the related information acquisition unit 24 analyzes the feature quantity (for example, MFCC, fundamental frequency, etc.) of the acoustic signal SG, and selects the content that matches the feature quantity of the acoustic signal SG among the plurality of contents prepared in advance. Search and get as Q. Note that the automatic content recognition in FIG.
- step SA1 of the information generation process is related to obtaining the acoustic signal SG of the guidance voice V supplied from the signal supply device 200 and the acoustic signal SG supplied from the signal supply device 200. Acquiring the content to be processed as related information Q.
- the related information acquisition unit 24 acquires the related information Q by selectively executing voice recognition and automatic content recognition (FIG. 21). For example, either voice recognition or automatic content recognition is selected according to the type of the guidance voice V represented by the acoustic signal SG. Specifically, when the sound of the sound signal SG is a human utterance (speech), the related information acquisition unit 24 generates the related information Q by voice recognition for the sound signal SG, and the sound of the sound signal SG Is music (for example, singing sound or musical instrument performance sound), the related information Q is acquired by automatic content recognition for the acoustic signal SG. It is also possible to use voice recognition and automatic content recognition in combination (FIG. 22).
- the related information acquisition unit 24 acquires the related information Q by automatic content recognition for a character string as a result of speech recognition for the acoustic signal SG, or a character string as a result of speech recognition for content specified by automatic content recognition.
- a configuration in which the related information acquisition unit 24 acquires the related information Q is assumed.
- a sound collection device that collects the guidance voice V radiated from the sound source (for example, a speaker) to generate the acoustic signal SG, and the acoustic signal SG that is generated by the sound collection device includes the communication network 18.
- the related information Q is transmitted in real time in parallel with the sound generation of the guidance voice V by the sound source and the reproduction of the guidance voice V by the sound emission system 16. It can be provided to the device 12.
- the acoustic signal SG is supplied from the signal supply device 200.
- the related information Q is generated by speech recognition of the acoustic signal SG of the guidance speech V generated by various speech synthesis. It is also possible to do.
- the method by which the acoustic signal acquisition unit 22 acquires the acoustic signal SG and the method by which the related information acquisition unit 24 acquires the related information Q are not limited to the above examples.
- the related information acquisition unit 24 generates a converted character string CT of the second language as related information Q by machine translation of the designated character string ST of the first language, and performs speech synthesis on the converted character string CT generated by the machine translation.
- the acoustic signal acquisition unit 22 can also generate the acoustic signal SG of the guidance voice V in the second language.
- the acoustic signal acquisition unit 22 is included as an element that acquires the acoustic signal SG of the guidance voice V, and the element that generates the acoustic signal SG by acoustic processing such as speech synthesis, 13 and the element which acquires acoustic signal SG from external apparatuses, such as 13 signal supply apparatuses 200, are included.
- the related information acquisition unit 24 is included as an element for acquiring the related information Q related to the guidance voice V, and performs information processing such as voice recognition, machine translation, or voice synthesis, or two or more of these processes.
- the related information acquisition unit 24 itself generates the related information Q and the related information Q such as the character string (designated character string ST or converted character string CT) or the image related to the guidance voice V from the external device. Includes all of the elements to be acquired and combinations of these two elements.
- Second Embodiment A second embodiment of the present invention will be described. Regarding the elements whose functions and functions are the same as those of the first embodiment in each aspect exemplified below, the detailed description of each is appropriately omitted by using the reference numerals used in the description of the first embodiment.
- FIG. 23 is an explanatory diagram of processing in which the signal processing unit 32 of the information management system 14 in the second embodiment generates the acoustic signal S.
- a plurality of sections (hereinafter referred to as “playback sections”) T having different positions on the time axis are set in the acoustic signal SG of the guidance voice V acquired by the acoustic signal acquisition unit 22.
- the acoustic signal SG is divided into a plurality of reproduction sections T (T1, T2,...) For each content (purpose and object) of the guidance voice V.
- the acoustic signal SG is divided into playback sections T for each scene.
- the start point or end point of the playback section T (boundary of the adjacent playback section T) is typically instructed according to an operation by the administrator with respect to the input device 146.
- the boundary of the silent section of the acoustic signal S It is also possible to define a plurality of playback sections T.
- the time length of each playback section T is made equal for the sake of convenience, but the time length of each playback section T may be different.
- the identification information setting unit 26 of the second embodiment sets different identification information D (D1, D2,%) For each reproduction section T of the acoustic signal SG.
- the signal processing unit 32 adds different identification information D set by the identification information setting unit 26 for each reproduction section T of the acoustic signal SG. That is, as illustrated in FIG. 23, the signal processing unit 32 applies the modulation signal SD of the identification information D set for the reproduction section T by the identification information setting unit 26 to each of the plurality of reproduction sections T of the acoustic signal SG.
- the acoustic signal S is generated by repeatedly adding. That is, the acoustic component of the identification information D of the reproduction section T is repeatedly mixed at a plurality of time points in any one reproduction section T of the guidance voice V.
- the acoustic signal S generated by the signal processing unit 32 is transferred to the sound emitting system 16 as in the first embodiment.
- the related information acquisition unit 24 of the second embodiment acquires the related information Q for each reproduction section T of the acoustic signal SG.
- the related information acquisition unit 24 divides the designated character string ST for each reproduction section T of the guidance voice V and executes machine translation, so that the related information Q indicating the converted character string CT of the second language is reproduced in the reproduction section. Generated every T.
- the correspondence management unit 34 associates the identification information D set by the identification information setting unit 26 with the related information Q acquired by the related information acquisition unit 24 for each reproduction section T of the guidance voice V. That is, the correspondence management unit 34 associates the identification information D of each reproduction section T set by the identification information setting unit 26 with the related information Q acquired by the related information acquisition unit 24 for the reproduction section T. Store in the storage device 144.
- the sound emitting device 166 of the sound emitting system 16 emits sound according to the acoustic signal S transferred from the information management system 14 as in the first embodiment. That is, in parallel with the reproduction of the guidance voice V corresponding to the acoustic signal SG, the sound of the identification information D that is different for each reproduction section T of the acoustic signal SG is repeatedly emitted. Therefore, every time the reproduction point of the guidance voice V changes from an arbitrary reproduction period T to the immediately subsequent reproduction period T, the identification information D notified to the terminal device 12 is changed. On the other hand, the information extraction unit 51 of the terminal device 12 sequentially extracts the identification information D of each reproduction section T of the guidance voice V from the collected sound signal X.
- the related information Q output from the output device 58 is sequentially changed as the guidance voice V is reproduced. Specifically, the output content (related information Q) by the output device 58 is changed with the start of any one playback section T of the guidance voice V (transition of the playback section T) as a trigger.
- the same effect as in the first embodiment is realized.
- the setting of the identification information D and the association of the identification information D and the related information Q are executed for each of the plurality of playback sections T obtained by dividing the guidance voice V on the time axis. It is possible to change the related information Q presented to the user of the terminal device 12 in conjunction with the progress of the reproduction of the guidance voice V.
- FIG. 24 is an explanatory diagram of the operation of the third embodiment of the present invention.
- the storage device 144 of the information management system 14 stores a plurality (N) of related information Q (for each identification information D of the guidance voice V expressed by the acoustic signal SG).
- Q1, Q2,... are stored.
- N pieces of related information Q representing the sound of a character string obtained by expressing the guidance voice V of the first language in a plurality of different languages other than the first language is one piece of the guidance voice V. It is stored in association with the identification information D.
- the method of preparing N pieces of related information Q in a plurality of different languages is arbitrary. For example, as illustrated in FIG.
- a plurality of languages different in machine translation for the designated character string ST in the first language It is possible to generate N conversion character strings CT expressed by the following, and generate N pieces of related information Q representing guidance voices V of N different languages in the speech synthesis for each conversion character string CT. .
- a character string of the guidance voice V is generated by voice recognition with respect to the acoustic signal SG of the guidance voice V supplied from the signal supply device 200, and machine translation for the character string is performed.
- Generates N converted character strings CT expressed in a plurality of different languages and generates N pieces of related information Q representing guidance voices V of N different languages in speech synthesis for each converted character string CT. It is also possible to do.
- the transmission unit 542 of the terminal device 12 obtains the identification information D and the language information L.
- the included information request R is transmitted to the information management system 14 (SB3).
- the language information L is information for designating a language used in the terminal device 12.
- the method for acquiring the language information L is arbitrary, for example, a configuration in which the transmission unit 542 generates the language information L with reference to the language setting of the OS (Operating System) of the terminal device 12 may be employed. In this case, there is an advantage that the user does not need to specify a language.
- generates the language information L which shows the language arbitrarily designated by the user of the terminal device 12 may be employ
- the information providing unit 36 of the information management system 14 When the information providing unit 36 of the information management system 14 receives the information request R from the terminal device 12, the information providing unit 36 stores the N pieces of related information Q stored in the storage device 144 corresponding to the identification information D specified by the information request R. Among them, the related information Q of the language indicated by the language information L specified by the information request R is selected (SB4), and the related information Q is transmitted to the requesting terminal device 12 (SB5).
- the receiving unit 544 of the terminal device 12 receives the related information Q transmitted from the information management system 14 (SB6), and the output device 58 (sound emitting device 166) emits the guidance voice V indicated by the related information Q. To the user (SB7).
- the guidance voice V in one kind of language designated by the language information L among the N kinds of languages other than the first language is obtained. It is output from the output device 58 of the terminal device 12. Therefore, for example, there is an advantage that the user can easily recognize the correspondence between the guidance voice V and the related information Q as compared with the configuration in which the related information Q is output after the reproduction of the guidance voice V is completed.
- the same effect as in the first embodiment is realized. Further, in the third embodiment, since any of the N related information Q having different languages is selectively provided to the terminal device 12, the related information Q that can be understood by various users having different languages. There is an advantage that can be provided.
- the related information Q representing the voice in each language has been exemplified.
- a configuration using the related information Q representing the character string (converted character string CT) representing the guidance voice V in each language is also employed. obtain.
- the method for generating the related information Q is arbitrary, but as illustrated in FIG. 16, the first language character string generated by the speech recognition from the acoustic signal SG of the guidance voice V supplied from the signal supply device.
- the output device 58 (display device) of the terminal device 12 presents the related information Q to the user by displaying the character string.
- FIG. 11 configuration for acquiring the input converted character string CT
- FIG. 18 configuration for acquiring the character string translated by the administrator OP itself
- FIG. A generation (acquisition) method shown in a configuration in which a character string edited by the administrator OP is acquired from the converted character string CT generated by machine translation
- the configuration of the second embodiment can be applied to the third embodiment.
- the terminal device 12 sequentially acquires related information Q corresponding to the identification information D for each sound collection of the identification information D (every time the user approaches each exhibit).
- the correspondence management unit 34 associates a plurality of pieces of related information Q corresponding to different exhibits in the exhibition facility M with one piece of identification information D, and is released from the sound emitting device 166 of the sound emitting system 16.
- the terminal device 12 picks up the sound of the identification information D that is sounded, the terminal device 12 can collectively acquire a plurality of related information Q corresponding to the identification information D from the information providing unit 36. is there.
- a user enters a specific exhibition facility M or when the identification information D is first acquired in the exhibition facility M, a plurality of pieces of related information Q relating to each exhibit of the exhibition facility M are displayed on the terminal device 12. May be adopted in a collective manner.
- the contents of the related information Q are not limited to the examples in the above-described embodiments.
- the terminal device 12 from the information providing unit 36 with at least two types of combinations of the sound, the image, and the character string exemplified as the related information Q in each embodiment described above as the related information Q.
- link information for example, URL
- link information indicating the location of information related to the guidance voice V for example, related information Q exemplified in each of the above-described embodiments
- Configurations can also be employed.
- each of a plurality of pieces of identification information D (D1, D2, D3,...) Corresponding to different playback sections T of the guidance voice V is played back.
- a configuration in which the terminal device 12 is repeatedly transmitted to the terminal device 12 a plurality of times within the section T has been illustrated.
- the terminal device 12 acquires the identification information D1 transmitted at a time close to the end of the playback section T1 and the identification information D2 transmitted at a time close to the head of the immediately subsequent playback section T2.
- the terminal device 12 receives the related information Q corresponding to the identification information D2 during the reproduction of the related information Q corresponding to the identification information D1.
- each identification information D is assigned to the first period (for example, the first half of the reproduction period T) so that the reproduction periods by the terminal device 12 do not overlap each other among a plurality of related information Q corresponding to different identification information D. It is also possible to transmit to the terminal device 12 only in (period).
- the reproduction of the related information Q of the identification information D1 is completed.
- a configuration may be employed in which the reproduction of the related information Q of the identification information D2 is started after that.
- the reproduction of the related information Q of the identification information D2 is triggered by an operation from the user. Can be started (reproduction of the related information of the identification information D1 is interrupted). For example, when the related information Q corresponding to the identification information D2 is received, a “Next” button is displayed, and when the user operates the button, reproduction of the related information Q of the identification information D2 is started.
- the output method (for example, display method) of the related information Q is arbitrary.
- the terminal device 12 includes an imaging device (not shown) that captures an image (still image or moving image), an image captured by the imaging device and an image indicated by the related information Q (still image, moving image, character string, etc.) Can be combined and displayed on the display device of the output device 58.
- a situation is assumed in which a robot 300 equipped with a sound emission function for emitting various reproduction target sounds such as guidance voices is displayed as an exhibit at an exhibition facility M such as a museum.
- the storage device 144 of the information management system 14 stores an acoustic signal S including the acoustic signal SG of the reproduction target sound and the modulation signal SD of the identification information D, and a character string expressing the pronunciation content of the reproduction target sound.
- Related information Q is stored in correspondence with the identification information D.
- the control device 50 of the terminal device 12 includes an image (typically a moving image) G of the robot 300 captured by the imaging device and characters of the related information Q provided from the information management system 14. The columns are superimposed on the display device of the output device 58 and displayed in real time (overlay display).
- the user needs to frequently move his / her line of sight between the display image (related information Q) by the display device and the robot 300 which is an actual exhibit.
- the image G and the related information Q are displayed so as to overlap each other on a single display screen, and thus it is necessary to frequently move the line of sight between the display device and the robot 300.
- the character string of the reproduction target sound is displayed together with the image G, for example, a special effect is realized that the deaf person can easily confirm both the operation of the robot 300 and the content of the reproduction target sound. .
- the information provision system 10 was utilized for the guidance in the exhibition facility M, the scene where the information provision system 10 is utilized is not limited to the above illustration.
- the information providing system 10 can be used for voice guidance of transportation facilities such as trains and buses.
- a sound emission system 16 is installed in a vehicle such as a train or a bus, and an acoustic signal S obtained by adding identification information D to an acoustic signal SG of a guidance voice V for guiding a stop (a train station or a stop) is information management. After being generated by the system 14, it is transferred to the sound emission system 16.
- an acoustic signal S corresponding to the stop is supplied to the sound emission device 166 of the sound emission system 16, and the identification information D is emitted together with the guidance voice V that guides arrival at the stop, etc.
- the terminal device 12 in the vehicle outputs the related information Q provided from the information management system 14 in response to the information request R including the identification information D from the output device 58.
- the voice translated from the first language guidance voice V into the second language for example, voice or an image (still image or moving picture) indicating the tourist guidance in the vicinity of the stop immediately after is related information.
- Q can be prepared.
- the storage device 144 stores the acoustic signal S including the acoustic signal SG of the reproduction target sound and the modulation signal SD of the identification information D, and the related information Q for each identification information D (
- the acoustic signal SG corresponding to the common guidance voice V and the related information Q are illustrated as being associated with each other via the identification information D), but the acoustic signal SG and the related information Q are associated with each other.
- the specific method of can be changed as appropriate. For example, a configuration is assumed in which auxiliary information specifying the position and time (or each range) at which the related information Q is to be provided is stored in the storage device 144 in association with the related information Q.
- the auxiliary information specifies, for example, the position and time at which the acoustic signal SG is reproduced.
- the terminal device 12 transmits to the information management system 14 an information request R including the position information of the own device detected by position detecting means such as GPS (Global Positioning System) and the current time.
- the information providing unit 36 of the information management system 14 obtains, from among the plurality of related information Q stored in the storage device 144, the related information Q corresponding to the position information specified by the information request R and the position and time close to the current time.
- the related information Q is transmitted to the requesting terminal device 12 (SB5).
- the related information Q corresponding to the acoustic signal SG can be provided to the terminal device 12 as in the above-described embodiments without using the identification information D.
- the sound of the acoustic signal S including the acoustic signal SG of the guidance voice V and the modulation signal SD of the identification information D is emitted from the sound emitting device 166.
- the method for notifying the terminal device 12 of the identification information D is not limited to the above example.
- a collation unit 15 is added to the information providing system 10 similar to the above-described embodiments.
- the collation unit 15 is realized by a server that can communicate with the terminal device 12 via the communication network 18, for example.
- Recognition information W (W1, W2,%) Representing the characteristic amount of the acoustic signal SG of the guidance voice V emitted from the sound emitting device 166 of the sound emission system 16, and identification information D (D1, D) of the guidance voice V
- the collation unit 15 holds a search table TBL that associates D2,.
- the sound emitting device 166 of the sound emitting system 16 emits the guidance voice V represented by the acoustic signal SG, but does not emit the acoustic component of the identification information D.
- the control device 50 of the terminal device 12 stores the collected sound signal X of the guidance voice V collected by the sound collecting device 56 in the storage device 52 for a predetermined time (for example, several seconds), and the transmission unit 542 of the communication device 54
- the collected sound signal X is transmitted to the verification unit 15. That is, the terminal device 12 inquires the collation unit 15 for the identification information D of the guidance voice V collected by the sound collection device 56.
- the collation unit 15 analyzes the feature quantity of the collected sound signal X received from the terminal device 12 via the communication network 18, and searches the search table TBL for the feature quantity recognition information W that is similar to or matches the feature quantity.
- the method of searching the recognition information W is arbitrary, for example, an automatic content recognition technique is preferably used.
- the collation unit 15 acquires the identification information D corresponding to the retrieved recognition information W from the search table TBL and transmits it to the terminal device 12. That is, the identification information D of the guidance voice V emitted from the sound emitting device 166 is notified to the terminal device 12.
- the operation in which the terminal device 12 acquires the related information Q corresponding to the identification information D notified from the verification unit 15 from the information management system 14 is the same as in each of the above-described embodiments.
- the recognition information W representing the feature amount of the acoustic signal SG is illustrated, but the content of the recognition information W is changed as appropriate.
- the acoustic signal SG itself (for example, waveform data) can be registered as the recognition information W in the search table TBL.
- the matching unit 15 searches the search table TBL for the waveform recognition information W that is similar to or matches the sound collection signal X received from the terminal device 12. Further, the collation unit 15 can be mounted on the information management system 14 or the terminal device 12.
- the frequency band of the modulation signal SD including the identification information D (for example, 18 kHz or more and 20 kHz or less) Is required. 26 has an advantage that the terminal device 12 can be notified of the identification information D regardless of the reproducible band of the sound emitting device 166. Therefore, for example, in the situation where the existing sound emitting device 166 that cannot reproduce the high frequency side of the audible band is used, the configuration of FIG. 26 is preferable.
- the collation unit 15 for retrieving the identification information D from the sound signal X is unnecessary.
- the information management system 14 in each embodiment described above can be realized as a single device, or as a plurality of devices (servers) configured separately from each other.
- the information management system 14 of each form described above is distributed to a first server including the identification information setting unit 26 and a second server including elements other than the identification information setting unit 26, and the first server and the second server A configuration in which servers communicate with each other via, for example, the communication network 18 may also be employed.
- the information providing system 10 of the present invention includes both a single device and a collection of a plurality of devices. Further, the entire information providing system 10 including the information management system 14 and the sound emission system 16 can be realized as a single device.
- the reproduction of the guidance sound V for the purpose of guiding the exhibition facility M has been exemplified.
- the type of sound emitted by the sound emitting device 166 of the sound emitting system 16 is limited to the guidance sound V.
- the above-described embodiments can also be adopted when reproducing various sounds such as music.
- the acoustic signals SG of the above-described forms are comprehensively expressed as signals indicating the sound to be reproduced (reproduction target sound).
- the sound emission device 166 of the sound emission system 16 emits sound corresponding to the acoustic signal S including the acoustic signal SG representing the guidance voice V and the modulation signal SD including the identification information D.
- the reproduction of the guidance voice V may be omitted.
- the signal processing unit 32 of the information management system 14 transfers the modulation signal SD including the identification information D set by the identification information setting unit 26 to the sound emission system 16 as an acoustic signal S (acoustic file).
- the sound emitting system 16 emits the sound of the identification information D by supplying the sound signal S to the sound emitting device 166.
- the terminal device 12 extracts the identification information D from the sound collection signal X generated by the sound collection device 56 by the sound collection of the sound emitted by the sound emission system 16, and manages the related information Q corresponding to the identification information D.
- the sound collection device 56 is an element that collects sound emitted according to the acoustic signal S including the modulation signal SD including the identification information D and generates the sound collection signal X. The presence or absence of the acoustic signal SG of the guidance voice V in the acoustic signal S is not questioned.
- acoustic communication is used to notify the terminal device 12 of the identification information D.
- the communication method for notifying the terminal device 12 of the identification information D is not limited to the above examples.
- the method of generating the acoustic signal SG of the guidance voice and the related information Q is not limited to the methods (FIGS. 3, 10 to 22) exemplified in the above embodiments.
- the information management system 14 only needs to include the information providing unit 36 and the storage device 144, and the acoustic signal acquisition unit 22, the related information acquisition unit 24, the identification information setting unit 26, and the signal processing.
- the unit 32 and the correspondence management unit 34 are not essential elements. That is, by providing these elements in a separate device, a configuration in which the acoustic signal S and the related information Q are stored in the storage device 144 from the separate device may be employed.
- the information management system, the sound emission system, and the terminal device according to each of the aspects described above are realized not only by the cooperation of the control device and the program but also by a dedicated electronic circuit.
- the program of the present invention can be provided in a form stored in a computer-readable recording medium and installed in the computer.
- the recording medium is, for example, a non-transitory recording medium, and an optical recording medium (optical disc) such as a CD-ROM is a good example. Any known recording medium such as a recording medium may be included.
- the program of the present invention can be provided in the form of distribution via a communication network and installed in a computer.
- DESCRIPTION OF SYMBOLS 100 Communication system, 10 ... Information provision system, 12 ... Terminal device, 14 ... Information management system, 142 ... Control device, 144 ... Storage device, 146 ... Input device, 148 ... Display device, 16 ... Sound emission system, 162 ... Control device, 164 ... Storage device, 166 ... Sound emission device, 18 ... Communication network, 22 ... Acoustic signal acquisition unit, 24 ... Related information acquisition unit, 26 ... ... identification information setting unit, 32 ... signal processing unit, 322 ... modulation processing unit, 324 ... mixing processing unit, 34 ... correspondence management unit, 36 ... information providing unit, 50 ... control device, 51 ... Information extraction unit 52... Storage device 54... Communication device 542... Transmission unit 544... Reception unit 56.
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Business, Economics & Management (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Telephonic Communication Services (AREA)
Abstract
Description
また、好ましくは、複数の言語のうち第1言語で表現された再生対象音の放音(放音システムからの放音)に並行して、出力手段は、情報要求の言語情報で指定された、第1言語以外の言語に対応する関連情報を出力する。この態様では、第1言語で表現された再生対象音の放音に並行して第1言語以外の言語に対応する関連情報を出力するから、例えば再生対象音の音声の再生終了後に関連情報を出力する構成と比較して、再生対象音と関連情報との対応を利用者が認識し易いという利点がある。
情報要求の言語情報で指定された言語に対応する関連情報は、好ましくは、再生対象音の発音内容を当該指定された言語に翻訳した文字列を発音した音声を表す音響信号、または、再生対象音の発音内容を当該指定された言語に翻訳した文字列である。
具体的には、本発明に係る情報提示方法は、端末装置において、再生対象音を表す音響信号と当該再生対象音の識別情報を含む変調信号とを含有する音響信号に応じて放音された音響を収音して収音信号を生成し、収音信号から識別情報を抽出し、識別情報を含む情報要求を情報提供手段に送信し、情報要求に含まれる識別情報に対応するとともに再生対象音に関連する複数の関連情報の何れかを情報提供手段から受信し、受信した関連情報を出力する。
この情報提示方法において、好ましくは、情報要求は、当該端末装置にて指定された言語を示す言語情報を含み、情報要求の識別情報に対応するとともに相異なる複数の言語に対応する複数の関連情報のうち情報要求の言語情報で指定された言語に対応する関連情報を受信する。
また、本発明に係る情報提供方法は、再生対象音を表す音響信号と当該再生対象音の識別情報を含む変調信号とを含有する音響信号に応じた音響を放音し、放音した音響から抽出される識別情報を含む情報要求を端末装置から受信し、情報要求に含まれる識別情報に対応するとともに再生対象音に関連する複数の関連情報の何れかを端末装置に送信する。
この情報提供方法において、好ましくは、情報要求は、端末装置にて指定された言語を示す言語情報を含み、情報要求の識別情報に対応するとともに相異なる複数の言語に対応する複数の関連情報のうち情報要求の言語情報で指定された言語に対応する関連情報を端末装置に送信する。
好ましくは、情報要求は、当該端末装置にて指定された言語を示す言語情報を含み、受信処理は、情報要求の識別情報に対応するとともに相異なる複数の言語に対応する複数の関連情報のうち情報要求の言語情報で指定された言語に対応する関連情報を受信する。
これら各態様に係る情報提示方法、情報提供方法、プログラム、または当該プログラムを記録したコンピュータ読み取り可能な記録媒体によれば、上記各態様に係る端末装置または情報提供システムと同様の効果が得られる。
図1は、本発明の第1実施形態に係る通信システム100の構成図である。図1に例示される通り、第1実施形態の通信システム100は、情報提供システム10と端末装置12とを包含する。情報提供システム10は、端末装置12に各種の情報を提供するコンピュータシステムである。端末装置12は、例えば携帯電話機やスマートフォン等の可搬型の情報処理装置である。以下の説明では、美術品や資料等の複数の展示物が展示された美術館や博物館等の施設(以下「展示施設」という)Mに端末装置12の利用者が所在し、各展示物に関連する情報が情報提供システム10から端末装置12に提供される場合を便宜的に想定する。なお、図1では1個の端末装置12のみを便宜的に図示したが、実際には複数の端末装置12の各々に対して情報提供システム10から情報が提供され得る。
図2は、情報管理システム14の構成図である。図2に例示される通り、第1実施形態の情報管理システム14は、制御装置142と記憶装置144と入力装置146と表示装置148とを具備する。記憶装置144は、制御装置142が実行するプログラムや制御装置142が使用する各種のデータを記憶する。半導体記録媒体や磁気記録媒体等の公知の記録媒体または複数種の記録媒体の組合せが記憶装置144として任意に採用される。入力装置146は、情報管理システム14を運営する管理者が情報管理システム14に対する各種の指示のために操作する操作機器であり、例えば管理者が操作可能な複数の操作子を包含する。管理者は、例えば入力装置146を適宜に操作することで、展示施設Mの各展示物の案内を表現した文字列(以下「指定文字列ST」という)を任意に指示することが可能である。表示装置148は、制御装置142による制御のもと音声認識や機械翻訳の結果等各種の情報を表示する装置(例えば液晶表示パネル)である。なお、入力装置146と表示装置148とが一体に構成したタッチパネルを採用することも可能である。
図7は、放音システム16の構成図である。図7に例示される通り、第1実施形態の放音システム16は、制御装置162と記憶装置164と複数の放音装置166とを具備する。記憶装置164は、例えば半導体記録媒体や磁気記録媒体等の公知の記録媒体または複数種の記録媒体の組合せで構成される。情報管理システム14から転送された複数の音響信号Sが記憶装置164に格納される。
図8は、端末装置12の構成図である。放音システム16の1個の放音装置166が図8では併記されている。図8に例示される通り、第1実施形態の端末装置12は、制御装置50と記憶装置52と通信装置54と収音装置56と出力装置58とを具備する。記憶装置52は、制御装置50が実行するプログラムや制御装置50が使用するデータを記憶する。半導体記録媒体や磁気記録媒体等の公知の記録媒体または複数種の記録媒体の組合せが記憶装置52として任意に採用される。
ところで、空気振動としての音波を伝送媒体として利用する前掲の音響通信では、例えば電波を伝送媒体として利用する無線通信と比較して通信速度や通信容量が小さいという傾向がある。先行技術2は付加情報(すなわち関連情報)自体を音響通信により送信する。他方、第1実施形態では識別情報Dを音響通信により送信する。したがって、第1実施形態の構成は、関連情報よりもデータサイズが小さい識別情報Dを送信することにより、音響通信を介して送信されるデータ量を抑制できるという利点がある。また、音響通信では通信容量が小さいので、先行技術2のもとで送信できる付加情報は、実際にはデータ量が小さい情報に制限される。第1実施形態では、音響通信により識別情報を送信し、その識別情報に対応する関連情報が情報管理システム14から配信されるので、データ量が大きく多様な関連情報(例えば音声や画像)でも利用者に提示できる。
第1実施形態では、情報管理システム14の管理者が指示した指定文字列STを適用した音声合成で音響信号SGを生成するとともに指定文字列STの機械翻訳で関連情報Qを生成したが、音響信号SGや関連情報Qの取得(典型的には生成)の方法は以上の例示に限定されない。音響信号SGおよび関連情報Qを取得する他の方法を以下に例示する。なお、以下に示す各態様における音響信号SGや関連情報Qの取得処理において、音響信号SGの取得(または生成)処理と関連情報Qの取得(または生成)処理の実行順は不問である。
図10に例示された態様1において、情報管理システム14の音響信号取得部22は、第1実施形態と同様に、指定文字列STに対する音声合成で案内音声Vの音響信号SGを生成する。他方、関連情報取得部24は、管理者が指示した指定文字列STを関連情報Qとして取得する。すなわち、関連情報Qは、案内音声Vと共通の第1言語で当該案内音声Vの発音内容を表現する文字列である。以上の構成では、放音システム16による案内音声Vの再生に並行して端末装置12では当該案内音声Vの発音内容の文字列が表示される。したがって、例えば、難聴者(聴覚障碍者)が案内音声Vの内容を確認できるという利点がある。
この態様では、本実施形態に係る情報生成処理(図6)において、指定文字列STに対応する案内音声Vの音響信号SGと案内音声Vに関連する関連情報Qとを取得するステップ(SA1)は、指定文字列STに対応する案内音声Vの音響信号SGを音声合成により生成することと、指定文字列STを関連情報Qとして取得すること、とを含むものとして把握される。
図11に例示された態様2において、情報管理システム14の音響信号取得部22は、第1実施形態と同様に、第1言語の指定文字列STに対する音声合成で案内音声Vの音響信号SGを生成する。他方、情報管理システム14の管理者は、入力装置146を適宜に操作することで、案内音声Vを第2言語で表現した文字列(変換文字列CT)を指定する。関連情報取得部24は、管理者が指示した第2言語の変換文字列CTを関連情報Qとして取得する。前掲の図3の構成では、機械翻訳の精度が低い場合に適切な変換文字列CTを生成できないが、図11に例示された態様2によれば、指定文字列STの機械翻訳(図3)が不要であるから、例えば人翻訳(human translation)で作成された、適切な第2言語で案内音声Vを表現した関連情報Qを用意できるという利点がある。
この態様では、情報生成処理(図6)のステップSA1は、指定文字列STに対応する案内音声Vの音響信号SGを音声合成により生成することと、指定された変換文字列CT(すなわち、案内音声Vの発音内容を第2言語に翻訳した文字列)を関連情報Qとして取得すること、とを含むものとして把握される。
図12に例示される態様3において、情報管理システム14の音響信号取得部22は、第1実施形態と同様に、指定文字列STに対する音声合成で案内音声Vの音響信号SGを生成する。他方、関連情報取得部24は、第1言語の指定文字列STに対する機械翻訳で第2言語の変換文字列CTを生成するとともに、変換文字列CTに対する音声合成で第2言語の案内音声Vの音響信号を関連情報Qとして生成する。端末装置12の出力装置58は、情報管理システム14から提供された関連情報Qが示す音響信号に応じた音響(第2言語の案内音声V)を放音する放音装置(スピーカやイヤホン)を包含する。すなわち、放音システム16による第1言語の案内音声Vの再生に並行して、端末装置12では第2言語の案内音声Vが再生される。したがって、端末装置12の利用者は、第1言語を理解できない場合でも第2言語の案内音声Vを聴取することで展示物の案内を理解することが可能である。
この態様では、情報生成処理(図6)のステップSA1は、指定文字列STに対応する案内音声Vの音響信号SGを音声合成により生成することと、指定された指定文字列ST(すなわち、案内音声Vの発音内容を示す文字列)に対する機械翻訳で案内音声Vの翻訳を示す変換文字列CTを生成し、さらに、変換文字列CTを発音した案内音声Vを示す音響信号(すなわち、案内音声Vの発音内容を第2言語に翻訳した文字列を発音した音声を示す音響信号)を音声合成により生成すること、とを含むものとして把握される。
図13に例示される態様4において、情報管理システム14の音響信号取得部22は、信号供給装置200から案内音声Vの音響信号SGを取得する。信号供給装置200は、周囲の音響を収音して音響信号SGを生成する収音装置や、可搬型または内蔵型の記録媒体から音響信号SGを取得して出力する再生装置や、通信網18から音響信号SGを受信して出力する通信装置である。他方、関連情報取得部24は、前掲の態様1や態様2と同様に、管理者が指示した指定文字列STを関連情報Qとして取得する。したがって、信号供給装置200が生成した音響信号SGに応じた案内音声Vが放音装置166から放音されるとともに、端末装置12では管理者からの指示に応じた指定文字列STが表示される。なお、関連情報取得部24が信号供給装置200から音響信号(例えば第2言語の案内音声Vの音響信号)を関連情報Qとして取得することも可能である。
この態様では、情報生成処理(図6)のステップSA1は、信号供給装置200から案内音声Vの音響信号SGを取得することと、指定された指定文字列ST(すなわち、案内音声Vの発音内容を示す文字列)を関連情報Qとして取得すること、とを含むものとして把握される。
図14に例示される態様5において、情報管理システム14の音響信号取得部22は、第1実施形態と同様に、指定文字列STに対する音声合成で案内音声Vの音響信号SGを生成する。他方、関連情報取得部24は、案内音声Vに関連する画像IMG(静止画または動画)を関連情報Qとして取得する。したがって、指定文字列STに対応する第1言語の案内音声Vの再生に並行して端末装置12では案内音声Vに関連する画像IMGが表示される。この態様によれば、案内音声Vに関連する画像IMGが関連情報Qとして取得されるから、画像IMGを予め端末装置12に記憶する必要がないという利点がある。データサイズの大きな画像データを記憶すると端末装置12の記憶容量を圧迫するから、本態様によれば、案内音声Vに関連する画像IMGの記憶のために端末装置12に必要な記憶容量が大きく削減され得る。
この態様では、情報生成処理(図6)のステップSA1は、指定文字列STに対応する案内音声Vの音響信号SGを音声合成により生成することと、案内音声Vに関連する画像IMGを関連情報Qとして取得すること、とを含むものとして把握される。
図15に例示される態様6において、情報管理システム14の音響信号取得部22は、図13(態様4)と同様の信号供給装置200から案内音声Vの音響信号SGを取得する。他方、関連情報取得部24は、信号供給装置200から供給される音響信号SGに対する音声認識により、案内音声Vの発音内容を表現する文字列を関連情報Qとして生成する。音響信号SGの音声認識には、例えばHMM等の音響モデルと言語的な制約を示す言語モデルとを利用した認識技術等の公知の技術が任意に採用され得る。以上の説明から理解される通り、態様6では、前掲の態様1(図10)と同様に、放音システム16による案内音声Vの再生に並行して端末装置12では当該案内音声Vの発音内容の文字列が表示される。したがって、案内音声Vの発音内容を示す文字列を別途取得し記憶する手段を端末装置12に設けずとも、放音された案内音声Vを聞き逃した利用者や、その聴取が困難な利用者(例えば難聴者)が案内音声Vの内容を確認できるという利点がある。すなわち、案内音声Vの発音内容を示す文字列の記憶のために端末装置12に必要な記憶容量が削減される。また、情報管理システム14の関連情報取得部24は、信号供給装置200から供給される案内音声Vを示す音響信号SGから案内音声Vの発音内容を示す文字列を音声認識により生成するから、情報管理システム14においては当該文字列を指定文字列STとして管理者が別途指定する必要がなくなるという利点がある。
この態様では、情報生成処理(図6)のステップSA1は、信号供給装置200から供給される案内音声Vの音響信号SGを取得することと、信号供給装置200から供給される音響信号SGに対する音声認識により、案内音声Vの発音内容を表現する文字列を関連情報Qとして生成すること、とを含むものとして把握される。
図16に例示される態様7において、情報管理システム14の音響信号取得部22は、態様6と同様に信号供給装置200から第1言語の案内音声Vの音響信号SGを取得する。他方、関連情報取得部24は、態様6と同様に音響信号SGに対する音声認識で案内音声Vの文字列を生成するとともに、当該文字列に対する機械翻訳により、案内音声Vを第2言語で表現した変換文字列CTを関連情報Qとして生成する。機械翻訳には公知の技術が任意に採用され得る。すなわち、態様7では、放音システム16による第1言語の案内音声Vの再生に並行して端末装置12では案内音声Vを第2言語に翻訳した変換文字列CTが表示される。したがって、情報管理システム14においては当該文字列を指定文字列STとして管理者が別途指定する必要がなくなることに加え、案内音声Vの発音内容を示す文字列に対する機械翻訳で関連情報Qが生成されるから、案内音声Vの言語とは相違する言語の関連情報Qを事前に用意する必要がないという利点がある。
この態様では、情報生成処理(図6)のステップSA1は、信号供給装置200から供給される案内音声Vの音響信号SGを取得することと、信号供給装置200から供給される音響信号SGに対する音声認識により案内音声Vの発音内容を表現する文字列を生成し、当該文字列に対する機械翻訳で案内音声Vの翻訳を示す関連情報Qを生成(すなわち、案内音声Vの発音内容を第2言語に翻訳した文字列を関連情報Qとして生成)すること、とを含むものとして把握される。
この場合、図6のステップSA1は、信号供給装置200から供給される案内音声Vの音響信号SGを取得することと、信号供給装置200から供給される音響信号SGに対する音声認識により案内音声Vの発音内容を表現する文字列を生成し、当該文字列に対する機械翻訳で案内音声Vの翻訳を示す変換文字列CTを生成し、さらに、変換文字列CTを発音した音声を示す音響信号を音声合成により生成すること、とを含む。
この場合、図6のステップSA1は、信号供給装置200から供給される案内音声Vの音響信号SGを取得することと、信号供給装置200から供給される音響信号SGに対する音声認識により生成した案内音声Vの発音内容を表現する文字列に対し、入力装置146への操作により指定された案内音声Vの翻訳を示す文字列(すなわち、案内音声Vの発音内容を第2言語に翻訳した文字列)を関連情報Qとして取得すること、とを含む。
この場合、図6のステップSA1は、信号供給装置200から供給される案内音声Vの音響信号SGを取得することと、信号供給装置200から供給される音響信号SGに対する音声認識により生成した案内音声Vの発音内容を表現する文字列を生成し、当該文字列に対する機械翻訳で案内音声Vの翻訳を示す変換文字列CTを生成し、さらに、入力装置146への操作により編集された案内音声Vの翻訳を示す文字列(すなわち、案内音声Vの発音内容を第2言語に翻訳した文字列)を関連情報Qとして取得すること、とを含む。
すなわち、案内音声Vの発音内容を第2言語に翻訳した文字列は、例えば、指定された変換文字列CT(態様2[図11])、機械翻訳により生成された変換文字列CT(態様3[図12,図16,図17])、人翻訳された変換文字列CT(態様7[図18])、および、機械翻訳により生成された変換文字列CTに対して入力装置146への操作により編集された文字列(態様7[図19])を含むものとして把握される。
図20に例示される態様8において、情報管理システム14の関連情報取得部24は、音響信号SGに対する自動コンテンツ認識(ACR:Automatic Content Recognition)により、音響信号SGに関連するコンテンツまたはコンテンツ情報(例えばコンテンツ名)を関連情報Qとして取得する。自動コンテンツ認識には種々の技術が任意に採用され得る。例えば、関連情報取得部24は、音響信号SGの特徴量(例えばMFCCや基本周波数等)を解析し、事前に用意された複数のコンテンツのうち音響信号SGの特徴量に整合するコンテンツを関連情報Qとして検索および取得する。なお、図20の自動コンテンツ認識には、音響信号SGの特徴量を解析および照合するフィンガープリント技術や、音響信号SGの可聴帯域または非可聴帯域に情報を埋込む音響透かし(Audio Watermark)技術を適用することが可能である。この態様においては、関連情報Qの取得に自動コンテンツ認識を採用するので、案内音声Vに関連した各種の情報(例えば、案内音声Vから派生するサービスの情報)に端末装置12の利用者を簡易な構成で誘導することが可能である。
この態様では、情報生成処理(図6)のステップSA1は、信号供給装置200から供給される案内音声Vの音響信号SGを取得することと、信号供給装置200から供給される音響信号SGに関連するコンテンツを関連情報Qとして取得すること、とを含む。
音響信号取得部22が音響信号SGを取得する方法や、関連情報取得部24が関連情報Qを取得する方法は以上の例示に限定されない。例えば、関連情報取得部24が第1言語の指定文字列STの機械翻訳により第2言語の変換文字列CTを関連情報Qとして生成し、機械翻訳で生成された変換文字列CTに対する音声合成で音響信号取得部22が第2言語の案内音声Vの音響信号SGを生成することも可能である。
本発明の第2実施形態を説明する。以下に例示する各態様において作用や機能が第1実施形態と同様である要素については、第1実施形態の説明で使用した符号を流用して各々の詳細な説明を適宜に省略する。
図24は、本発明の第3実施形態の動作の説明図である。図24に例示される通り、第3実施形態における情報管理システム14の記憶装置144には、音響信号SGで表現される案内音声Vの識別情報D毎に複数(N個)の関連情報Q(Q1,Q2,……)が記憶される。具体的には、第1言語の案内音声Vを第1言語以外の相異なる複数の言語で表現した文字列を発音した音声を表すN個の関連情報Qが、当該案内音声Vの1個の識別情報Dに対応付けて記憶される。相異なる複数の言語のN個の関連情報Qを用意する方法は任意であるが、例えば、前掲の図12に例示した通り、第1言語の指定文字列STに対する機械翻訳で相異なる複数の言語で表現されたN個の変換文字列CTを生成し、各変換文字列CTに対する音声合成で相異なるN種類の言語の案内音声Vを表すN個の関連情報Qを生成することが可能である。また、例えば、前掲の図17に例示するように、信号供給装置200から供給される案内音声Vの音響信号SGに対する音声認識で案内音声Vの文字列を生成するとともに、当該文字列に対する機械翻訳により相異なる複数の言語で表現されたN個の変換文字列CTを生成し、各変換文字列CTに対する音声合成で相異なるN種類の言語の案内音声Vを表すN個の関連情報Qを生成することも可能である。
また、第2実施形態の構成を第3実施形態に適用することも可能である。
以上に例示した各態様は多様に変形され得る。具体的な変形の態様を以下に例示する。以下の例示から任意に選択された2個以上の態様は、相互に矛盾しない範囲で適宜に併合され得る。
Claims (17)
- 再生対象音を表す音響信号と当該再生対象音の識別情報を含む変調信号とを含有する音響信号に応じて放音された音響を収音して収音信号を生成する収音手段と、
前記収音手段が生成した収音信号から識別情報を抽出する情報抽出手段と、
前記情報抽出手段が抽出した識別情報を含む情報要求を情報提供手段に送信する送信手段と、
前記情報要求に含まれる識別情報に対応するとともに前記再生対象音に関連する複数の関連情報の何れかを前記情報提供手段から受信する受信手段と、
前記受信手段が受信した関連情報を出力する出力手段と
を具備する端末装置。 - 前記送信手段は、当該端末装置にて指定された言語を示す言語情報を含む前記情報要求を送信し、
前記受信手段は、前記情報要求の識別情報に対応するとともに相異なる複数の言語に対応する複数の関連情報のうち前記情報要求の言語情報で指定された言語に対応する関連情報を受信する
請求項1の端末装置。 - 前記言語情報は、当該端末装置のOSの言語設定で指定された言語を示す
請求項2の端末装置。 - 前記言語情報は、当該端末装置の利用者が指定した言語を示す
請求項2の端末装置。 - 前記情報要求の言語情報で指定された言語に対応する関連情報は、前記再生対象音の発音内容を当該指定された言語に翻訳した文字列を発音した音声を表す音響信号である
請求項2から請求項4の何れかの端末装置。 - 前記情報要求の言語情報で指定された言語に対応する関連情報は、前記再生対象音の発音内容を当該指定された言語に翻訳した文字列である
請求項2から請求項4の何れかの端末装置。 - 前記複数の言語のうち第1言語で表現された前記再生対象音の放音に並行して、前記出力手段は、前記情報要求の言語情報で指定された、前記第1言語以外の言語に対応する関連情報を出力する
請求項2から請求項6の何れかの端末装置。 - 再生対象音を表す音響信号と当該再生対象音の識別情報を含む変調信号とを含有する音響信号に応じた音響を放音する放音手段と、
前記放音手段が放音した音響から抽出される識別情報を含む情報要求を端末装置から受信し、前記情報要求に含まれる識別情報に対応するとともに前記再生対象音に関連する複数の関連情報の何れかを前記端末装置に送信する情報提供手段と
を具備する情報提供システム。 - 前記情報提供手段は、前記端末装置にて指定された言語を示す言語情報を含む前記情報要求を受信し、前記情報要求の識別情報に対応するとともに相異なる複数の言語に対応する複数の関連情報のうち当該情報要求の言語情報で指定された言語に対応する関連情報を前記端末装置に送信する
請求項8の情報提供システム。 - 前記情報要求の言語情報で指定された言語に対応する関連情報は、前記再生対象音の発音内容を当該指定された言語に翻訳した文字列を発音した音声を表す音響信号である
請求項9の情報提供システム。 - 前記情報要求の言語情報で指定された言語に対応する関連情報は、前記再生対象音の発音内容を当該指定された言語に翻訳した文字列を発音した音声を表す文字列である
請求項9の情報提供システム。 - 端末装置において、
再生対象音を表す音響信号と当該再生対象音の識別情報を含む変調信号とを含有する音響信号に応じて放音された音響を収音して収音信号を生成し、
前記収音信号から識別情報を抽出し、
前記識別情報を含む情報要求を情報提供手段に送信し、
前記情報要求に含まれる識別情報に対応するとともに前記再生対象音に関連する複数の関連情報の何れかを前記情報提供手段から受信し、
前記受信した関連情報を出力する
情報提示方法。 - 前記情報要求は、当該端末装置にて指定された言語を示す言語情報を含み、
前記情報要求の識別情報に対応するとともに相異なる複数の言語に対応する複数の関連情報のうち前記情報要求の言語情報で指定された言語に対応する関連情報を受信する
請求項12の情報提示方法。 - 再生対象音を表す音響信号と当該再生対象音の識別情報を含む変調信号とを含有する音響信号に応じた音響を放音し、
前記放音した音響から抽出される識別情報を含む情報要求を端末装置から受信し、前記情報要求に含まれる識別情報に対応するとともに前記再生対象音に関連する複数の関連情報の何れかを前記端末装置に送信する
情報提供方法。 - 前記情報要求は、前記端末装置にて指定された言語を示す言語情報を含み、
前記情報要求の識別情報に対応するとともに相異なる複数の言語に対応する複数の関連情報のうち前記情報要求の言語情報で指定された言語に対応する関連情報を前記端末装置に送信する
請求項14の情報提供方法。 - コンピュータに、
再生対象音を表す音響信号と当該再生対象音の識別情報を含む変調信号とを含有する音響信号に応じて放音された音響を収音して収音信号を生成する収音処理と、
前記収音処理で生成した収音信号から識別情報を抽出する情報抽出処理と、
前記情報抽出処理で抽出した識別情報を含む情報要求を情報提供手段に送信する送信処理と、
前記情報要求に含まれる識別情報に対応するとともに前記再生対象音に関連する複数の関連情報の何れかを前記情報提供手段から受信する受信処理と、
前記受信処理で受信した関連情報を出力する出力処理と
を実行させるプログラムを記録したコンピュータ読み取り可能な記録媒体。 - 前記情報要求は、当該端末装置にて指定された言語を示す言語情報を含み、
前記受信処理は、前記情報要求の識別情報に対応するとともに相異なる複数の言語に対応する複数の関連情報のうち前記情報要求の言語情報で指定された言語に対応する関連情報を受信する
請求項16のコンピュータ読み取り可能な記録媒体。
Priority Applications (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/327,753 US10733386B2 (en) | 2014-07-29 | 2015-07-27 | Terminal device, information providing system, information presentation method, and information providing method |
KR1020177005255A KR101796429B1 (ko) | 2014-07-29 | 2015-07-27 | 단말 디바이스, 정보 제공 시스템, 정보 제시 방법, 및 정보 제공 방법 |
AU2015297648A AU2015297648B2 (en) | 2014-07-29 | 2015-07-27 | Terminal device, information providing system, information presentation method, and information providing method |
CN201580040538.8A CN106537496B (zh) | 2014-07-29 | 2015-07-27 | 终端装置、信息提供系统、信息呈现方法和信息提供方法 |
KR1020177031874A KR20170125415A (ko) | 2014-07-29 | 2015-07-27 | 단말 디바이스, 정보 제공 시스템, 정보 제시 방법, 및 정보 제공 방법 |
EP15827950.5A EP3176782B8 (en) | 2014-07-29 | 2015-07-27 | Terminal device, information providing system, information presentation method and information providing method |
Applications Claiming Priority (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2014-154118 | 2014-07-29 | ||
JP2014154118 | 2014-07-29 | ||
JP2014-217346 | 2014-10-24 | ||
JP2014217346 | 2014-10-24 | ||
JP2015092283A JP5871088B1 (ja) | 2014-07-29 | 2015-04-28 | 端末装置、情報提供システム、情報提供方法およびプログラム |
JP2015-092283 | 2015-04-28 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2016017577A1 true WO2016017577A1 (ja) | 2016-02-04 |
Family
ID=55217478
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2015/071237 WO2016017577A1 (ja) | 2014-07-29 | 2015-07-27 | 端末装置、情報提供システム、情報提示方法および情報提供方法 |
Country Status (7)
Country | Link |
---|---|
US (1) | US10733386B2 (ja) |
EP (1) | EP3176782B8 (ja) |
JP (1) | JP5871088B1 (ja) |
KR (2) | KR20170125415A (ja) |
CN (1) | CN106537496B (ja) |
AU (1) | AU2015297648B2 (ja) |
WO (1) | WO2016017577A1 (ja) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2017201445A (ja) * | 2016-05-02 | 2017-11-09 | 株式会社Co3 | 音声ガイド提供システム |
WO2019044520A1 (ja) * | 2017-08-31 | 2019-03-07 | ヤマハ株式会社 | 情報提供方法および情報提供装置 |
US11211076B2 (en) | 2017-11-28 | 2021-12-28 | Google Llc | Key phrase detection with audio watermarking |
Families Citing this family (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6484958B2 (ja) | 2014-08-26 | 2019-03-20 | ヤマハ株式会社 | 音響処理装置、音響処理方法およびプログラム |
JP6780305B2 (ja) * | 2016-06-06 | 2020-11-04 | ヤマハ株式会社 | 情報処理装置および情報提供方法 |
JP6834634B2 (ja) * | 2017-03-15 | 2021-02-24 | ヤマハ株式会社 | 情報提供方法および情報提供システム |
JP6809319B2 (ja) * | 2017-03-16 | 2021-01-06 | ヤマハ株式会社 | 音響通信のための装置および方法 |
CN107734036B (zh) * | 2017-10-19 | 2021-01-19 | 威盛电子股份有限公司 | 通信方法与使用此方法的通信系统 |
JP6962158B2 (ja) * | 2017-12-01 | 2021-11-05 | ヤマハ株式会社 | 機器制御システム、機器制御方法、及びプログラム |
JP6955452B2 (ja) * | 2018-01-26 | 2021-10-27 | Toa株式会社 | 放送音形成装置、及び情報提示システム |
JP6600374B2 (ja) * | 2018-03-01 | 2019-10-30 | ヤマハ株式会社 | 情報処理方法、情報処理装置およびプログラム |
JP7196426B2 (ja) * | 2018-05-30 | 2022-12-27 | ヤマハ株式会社 | 情報処理方法および情報処理システム |
JP2019219872A (ja) * | 2018-06-19 | 2019-12-26 | 株式会社iTest | インフォメーション提供システム |
EP3820060A4 (en) * | 2018-07-02 | 2022-03-30 | Yamaha Corporation | BROADCASTING SYSTEM, TERMINAL DEVICE, BROADCASTING METHOD, TERMINAL DEVICE OPERATING METHOD AND PROGRAM |
JP7279310B2 (ja) * | 2018-07-17 | 2023-05-23 | カシオ計算機株式会社 | 電子機器、学習支援装置、学習支援システム、電子機器の制御方法、学習支援装置の制御方法、電子機器の制御プログラム及び学習支援装置の制御プログラム |
JP6883562B2 (ja) * | 2018-10-05 | 2021-06-09 | 株式会社京三製作所 | 情報案内システム |
JP7099241B2 (ja) * | 2018-10-11 | 2022-07-12 | ヤマハ株式会社 | 情報取得装置および情報取得方法 |
JP6791228B2 (ja) * | 2018-11-09 | 2020-11-25 | ヤマハ株式会社 | 情報提供方法、情報提供システム、端末装置の動作方法、端末装置およびプログラム |
US11304013B2 (en) * | 2019-02-08 | 2022-04-12 | Starkey Laboratories, Inc. | Assistive listening device systems, devices and methods for providing audio streams within sound fields |
JP7074116B2 (ja) * | 2019-10-03 | 2022-05-24 | ヤマハ株式会社 | 情報処理方法および情報処理装置 |
JP7385531B2 (ja) * | 2020-06-17 | 2023-11-22 | Toa株式会社 | 音響通信システム、音響送信装置、音響受信装置、プログラムおよび音響信号送信方法 |
US11812213B2 (en) | 2020-09-30 | 2023-11-07 | Starkey Laboratories, Inc. | Ear-wearable devices for control of other devices and related methods |
JP7126590B1 (ja) * | 2021-05-18 | 2022-08-26 | 三菱電機株式会社 | 音響コミュニケーション用送受信装置及び音響コミュニケーションシステム |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH02190888A (ja) * | 1989-01-20 | 1990-07-26 | Hitachi Ltd | 案内情報再生装置及びそれを用いた案内システム |
JPH11252121A (ja) * | 1998-03-05 | 1999-09-17 | Ntt Data Corp | 位置依存情報提供システム |
JP2002092236A (ja) * | 2000-09-20 | 2002-03-29 | Victor Co Of Japan Ltd | 情報配信システム |
JP2008058953A (ja) * | 2006-07-26 | 2008-03-13 | Nec (China) Co Ltd | 音声透かしをベースとするメディア・プログラムの識別方法及び装置 |
JP2009180893A (ja) * | 2008-01-30 | 2009-08-13 | Dainippon Printing Co Ltd | 音響信号で制御されるコンテンツ再生装置 |
Family Cites Families (86)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US3263207A (en) | 1964-03-27 | 1966-07-26 | Herbert L West | Transistor underwater telephone system |
US7064749B1 (en) * | 1992-11-09 | 2006-06-20 | Adc Technology Inc. | Portable communicator |
JPH088855A (ja) | 1994-06-07 | 1996-01-12 | Neptune:Kk | 輸送機用案内放送装置 |
JPH0879199A (ja) | 1994-09-02 | 1996-03-22 | Sony Corp | 文字情報提供システム |
US5615301A (en) * | 1994-09-28 | 1997-03-25 | Rivers; W. L. | Automated language translation system |
JP3558239B2 (ja) | 1995-06-30 | 2004-08-25 | 株式会社リコー | 情報配信システム |
JPH10174190A (ja) | 1996-12-16 | 1998-06-26 | Matsushita Electric Ind Co Ltd | 音響再生装置 |
JPH1115827A (ja) | 1997-06-19 | 1999-01-22 | Fujitsu Ltd | 翻訳装置および記録媒体 |
JP3348831B2 (ja) | 1998-05-11 | 2002-11-20 | 日本電信電話株式会社 | 文字併用音声通信システム、通信サーバ装置、及び通信表示装置 |
JP2000207170A (ja) * | 1999-01-14 | 2000-07-28 | Sony Corp | 情報処理装置および情報処理方法 |
WO2000076154A1 (fr) | 1999-06-02 | 2000-12-14 | Fujitsu Limited | Systeme de construction d'espace de communication virtuel correspondant a de l'information de detection du monde reel |
GB9917985D0 (en) | 1999-07-30 | 1999-09-29 | Scient Generics Ltd | Acoustic communication system |
US6546365B1 (en) * | 2000-02-04 | 2003-04-08 | International Business Machines Corporation | System for national language support and automated translation table |
US20010055391A1 (en) | 2000-04-27 | 2001-12-27 | Jacobs Paul E. | System and method for extracting, decoding, and utilizing hidden data embedded in audio signals |
JP2002217839A (ja) | 2001-01-12 | 2002-08-02 | Nec Corp | 弾性波による通信システム |
JP4657471B2 (ja) | 2001-03-05 | 2011-03-23 | 泉陽興業株式会社 | 観覧施設案内システム |
US20040220995A1 (en) | 2001-04-23 | 2004-11-04 | Takehiko Tsutsumi | Method, program, and apparatus for delegating information processing |
US6542200B1 (en) * | 2001-08-14 | 2003-04-01 | Cheldan Technologies, Inc. | Television/radio speech-to-text translating processor |
JP2003186500A (ja) * | 2001-12-17 | 2003-07-04 | Sony Corp | 情報伝達システム、情報符号化装置および情報復号装置 |
US7062339B2 (en) * | 2002-05-09 | 2006-06-13 | Matsushita Electric Industrial Co., Ltd. | Method and apparatus for communicating between a portable device and a server |
TW200417228A (en) * | 2002-09-17 | 2004-09-01 | Ginganet Corp | Sign language image presentation apparatus, sign language image input/output apparatus, and system for sign language translation |
US7460684B2 (en) * | 2003-06-13 | 2008-12-02 | Nielsen Media Research, Inc. | Method and apparatus for embedding watermarks |
US20050192095A1 (en) * | 2004-02-27 | 2005-09-01 | Chiu-Hao Cheng | Literal and/or verbal translator for game and/or A/V system |
US7516881B1 (en) * | 2004-07-07 | 2009-04-14 | Diebold Self-Service Systems Division Of Diebold, Incorporated | Cash dispensing automated banking machine user interface system and method |
JP2006251676A (ja) | 2005-03-14 | 2006-09-21 | Akira Nishimura | 振幅変調を用いた音響信号への電子透かしデータの埋め込み・検出装置 |
JP3822224B1 (ja) | 2005-06-28 | 2006-09-13 | 株式会社フィールドシステム | 情報提供システム |
JP4899416B2 (ja) | 2005-10-27 | 2012-03-21 | 大日本印刷株式会社 | ネットワーク接続装置 |
JP4343896B2 (ja) | 2005-12-02 | 2009-10-14 | ソニー株式会社 | 再生端末装置及び出力方法 |
US20070135135A1 (en) * | 2005-12-09 | 2007-06-14 | Kenneth Brown | Electronic equipment with content management function and program for providing same |
JP2007164659A (ja) | 2005-12-16 | 2007-06-28 | Absurd Spear:Kk | 音楽情報を利用した情報配信システム及び情報配信方法 |
WO2007086860A1 (en) | 2006-01-27 | 2007-08-02 | Thomson Licensing | Closed-captioning system and method |
US7822606B2 (en) * | 2006-07-14 | 2010-10-26 | Qualcomm Incorporated | Method and apparatus for generating audio information from received synthesis information |
EP1902906B1 (en) * | 2006-09-22 | 2017-07-26 | Harman Becker Automotive Systems GmbH | Add-on module for externally controlling a speech dialog system |
JP4024285B1 (ja) | 2007-01-11 | 2007-12-19 | 有 小山 | 警報表示システム |
JP2008299032A (ja) | 2007-05-31 | 2008-12-11 | Akira Nishimura | 語学教材および文字データ再生装置 |
US20090012788A1 (en) * | 2007-07-03 | 2009-01-08 | Jason Andre Gilbert | Sign language translation system |
JP2009020291A (ja) * | 2007-07-11 | 2009-01-29 | Yamaha Corp | 音声処理装置および通信端末装置 |
US8676273B1 (en) * | 2007-08-24 | 2014-03-18 | Iwao Fujisaki | Communication device |
JP2009205485A (ja) | 2008-02-28 | 2009-09-10 | Fujitsu Fsas Inc | 乗降車通知方法及び乗降車通知システム |
GB2460306B (en) | 2008-05-29 | 2013-02-13 | Intrasonics Sarl | Data embedding system |
JP2010011282A (ja) | 2008-06-30 | 2010-01-14 | Yamaha Corp | 変調装置、復調装置、情報伝達システム、変調方法および復調方法 |
CN101933242A (zh) | 2008-08-08 | 2010-12-29 | 雅马哈株式会社 | 调制装置以及解调装置 |
JP5589308B2 (ja) | 2009-05-29 | 2014-09-17 | ヤマハ株式会社 | オーディオ信号受信装置、オーディオ信号再生装置および音響通信システム |
JP5343758B2 (ja) | 2008-08-21 | 2013-11-13 | ヤマハ株式会社 | 音声再生装置 |
CA2689727A1 (en) * | 2009-02-27 | 2010-08-27 | Research In Motion Limited | Methods and apparatus for use in selectively retrieving and displaying user interface information of a wireless peripheral device |
JP2010284423A (ja) | 2009-06-15 | 2010-12-24 | Toshiba Corp | 医用画像診断装置及び医用画像撮影方法 |
JP2011109629A (ja) * | 2009-11-17 | 2011-06-02 | Toru Tsurubuchi | 自動再生音声ガイドシステム |
EP2362385A1 (en) | 2010-02-26 | 2011-08-31 | Fraunhofer-Gesellschaft zur Förderung der Angewandten Forschung e.V. | Watermark signal provision and watermark embedding |
EP2550652A4 (en) * | 2010-03-25 | 2015-01-21 | Verisign Inc | SYSTEMS AND METHOD FOR PROVIDING ACCESS TO RESOURCES THROUGH IMPROVED AUDIO SIGNALS |
US9183560B2 (en) * | 2010-05-28 | 2015-11-10 | Daniel H. Abelow | Reality alternate |
JP2011255982A (ja) | 2010-06-07 | 2011-12-22 | Hitachi Ltd | エレベーターの情報通知装置 |
US9143881B2 (en) * | 2010-10-25 | 2015-09-22 | At&T Intellectual Property I, L.P. | Providing interactive services to enhance information presentation experiences using wireless technologies |
US9002717B2 (en) * | 2010-12-03 | 2015-04-07 | At&T Intellectual Property I, L.P. | Method and apparatus for audio communication of information |
US20120214416A1 (en) | 2011-02-23 | 2012-08-23 | Jonathan Douglas Kent | Methods and apparatuses for communication between devices |
US9754045B2 (en) * | 2011-04-01 | 2017-09-05 | Harman International (China) Holdings Co., Ltd. | System and method for web text content aggregation and presentation |
KR101563951B1 (ko) * | 2011-04-05 | 2015-10-28 | 야마하 가부시키가이샤 | 정보 제공 시스템, 식별 정보 해결 서버, 및 휴대 단말 장치 |
JP2013005377A (ja) | 2011-06-21 | 2013-01-07 | Yamaha Corp | 携帯端末装置および情報提供システム |
JP2013008109A (ja) | 2011-06-22 | 2013-01-10 | Yamaha Corp | 文書投稿支援システム、携帯端末装置および文書投稿支援プログラム |
JP2013024915A (ja) * | 2011-07-15 | 2013-02-04 | Yamaha Corp | ドングル(dongle)装置および再生システム |
JP2013068657A (ja) | 2011-09-20 | 2013-04-18 | Casio Comput Co Ltd | 画像生成装置、画像生成方法及びそのプログラム、並びに演奏支援装置、演奏支援方法及びプログラム |
JP5953687B2 (ja) | 2011-09-26 | 2016-07-20 | ヤマハ株式会社 | 情報処理装置及びプログラム |
JP5454544B2 (ja) * | 2011-10-12 | 2014-03-26 | 富士ゼロックス株式会社 | 画像処理装置、情報提供システム及びプログラム |
JP5866728B2 (ja) * | 2011-10-14 | 2016-02-17 | サイバーアイ・エンタテインメント株式会社 | 画像認識システムを備えた知識情報処理サーバシステム |
US9053096B2 (en) | 2011-12-01 | 2015-06-09 | Elwha Llc | Language translation based on speaker-related information |
JP2013117688A (ja) | 2011-12-05 | 2013-06-13 | Sony Corp | 音響処理装置、音響処理方法、プログラム、記録媒体、サーバ装置、音響再生装置および音響処理システム |
US9110891B2 (en) * | 2011-12-12 | 2015-08-18 | Google Inc. | Auto-translation for multi user audio and video |
JP2013125047A (ja) | 2011-12-13 | 2013-06-24 | Zenrin Datacom Co Ltd | 情報提供システム、使用言語種別提供端末装置、情報提供装置、情報提供方法、使用言語種別提供プログラムおよび情報提供プログラム |
JP6167542B2 (ja) | 2012-02-07 | 2017-07-26 | ヤマハ株式会社 | 電子装置及びプログラム |
CN102868752A (zh) * | 2012-09-25 | 2013-01-09 | 北京苹果派科技有限公司 | 一种数据传输方法、系统及终端 |
US9305559B2 (en) | 2012-10-15 | 2016-04-05 | Digimarc Corporation | Audio watermark encoding with reversing polarity and pairwise embedding |
US20140120503A1 (en) * | 2012-10-25 | 2014-05-01 | Andrew Nicol | Method, apparatus and system platform of dual language electronic book file generation |
CN203136168U (zh) * | 2012-12-17 | 2013-08-14 | 北京天安信通科技有限责任公司 | 一种基于超声波或声波进行用户识别的无线移动通信终端 |
CN103077165A (zh) * | 2012-12-31 | 2013-05-01 | 威盛电子股份有限公司 | 自然语言对话方法及其系统 |
JP2014138324A (ja) * | 2013-01-17 | 2014-07-28 | Casio Comput Co Ltd | 情報提供システム、サーバシステム、端末装置、情報提供方法及びプログラム |
JP6255946B2 (ja) | 2013-02-21 | 2018-01-10 | ヤマハ株式会社 | 復調装置、音響伝送システム、プログラム及び復調方法 |
KR102108500B1 (ko) * | 2013-02-22 | 2020-05-08 | 삼성전자 주식회사 | 번역 기반 통신 서비스 지원 방법 및 시스템과, 이를 지원하는 단말기 |
US9093064B2 (en) * | 2013-03-11 | 2015-07-28 | The Nielsen Company (Us), Llc | Down-mixing compensation for audio watermarking |
US20140269678A1 (en) * | 2013-03-15 | 2014-09-18 | Evan Patrick McGee | Method for providing an application service, including a managed translation service |
US9635417B2 (en) * | 2013-04-05 | 2017-04-25 | Dolby Laboratories Licensing Corporation | Acquisition, recovery, and matching of unique information from file-based media for automated file detection |
KR101288305B1 (ko) | 2013-05-02 | 2013-08-01 | (주)아이스플럽 | 차량에서의 자동 안내 방송 장치를 활용한 위치 정보 제공 시스템, 모바일 기기, 및 프로그램을 기록한 컴퓨터로 판독 가능한 기록 매체 |
US20150149146A1 (en) * | 2013-11-22 | 2015-05-28 | Jay Abramovitz | Systems for delivery of audio signals to mobile devices |
US9614969B2 (en) * | 2014-05-27 | 2017-04-04 | Microsoft Technology Licensing, Llc | In-call translation |
US20150347399A1 (en) * | 2014-05-27 | 2015-12-03 | Microsoft Technology Licensing, Llc | In-Call Translation |
JP6484958B2 (ja) | 2014-08-26 | 2019-03-20 | ヤマハ株式会社 | 音響処理装置、音響処理方法およびプログラム |
US20160170970A1 (en) * | 2014-12-12 | 2016-06-16 | Microsoft Technology Licensing, Llc | Translation Control |
WO2017112813A1 (en) * | 2015-12-22 | 2017-06-29 | Sri International | Multi-lingual virtual personal assistant |
-
2015
- 2015-04-28 JP JP2015092283A patent/JP5871088B1/ja active Active
- 2015-07-27 CN CN201580040538.8A patent/CN106537496B/zh active Active
- 2015-07-27 AU AU2015297648A patent/AU2015297648B2/en not_active Ceased
- 2015-07-27 KR KR1020177031874A patent/KR20170125415A/ko active Search and Examination
- 2015-07-27 KR KR1020177005255A patent/KR101796429B1/ko active IP Right Grant
- 2015-07-27 US US15/327,753 patent/US10733386B2/en active Active
- 2015-07-27 EP EP15827950.5A patent/EP3176782B8/en active Active
- 2015-07-27 WO PCT/JP2015/071237 patent/WO2016017577A1/ja active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH02190888A (ja) * | 1989-01-20 | 1990-07-26 | Hitachi Ltd | 案内情報再生装置及びそれを用いた案内システム |
JPH11252121A (ja) * | 1998-03-05 | 1999-09-17 | Ntt Data Corp | 位置依存情報提供システム |
JP2002092236A (ja) * | 2000-09-20 | 2002-03-29 | Victor Co Of Japan Ltd | 情報配信システム |
JP2008058953A (ja) * | 2006-07-26 | 2008-03-13 | Nec (China) Co Ltd | 音声透かしをベースとするメディア・プログラムの識別方法及び装置 |
JP2009180893A (ja) * | 2008-01-30 | 2009-08-13 | Dainippon Printing Co Ltd | 音響信号で制御されるコンテンツ再生装置 |
Non-Patent Citations (1)
Title |
---|
See also references of EP3176782A4 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2017201445A (ja) * | 2016-05-02 | 2017-11-09 | 株式会社Co3 | 音声ガイド提供システム |
WO2019044520A1 (ja) * | 2017-08-31 | 2019-03-07 | ヤマハ株式会社 | 情報提供方法および情報提供装置 |
JPWO2019044520A1 (ja) * | 2017-08-31 | 2019-11-07 | ヤマハ株式会社 | 情報提供方法および情報提供装置 |
JP2020053060A (ja) * | 2017-08-31 | 2020-04-02 | ヤマハ株式会社 | 情報提供方法、情報提供装置およびプログラム |
JP7331645B2 (ja) | 2017-08-31 | 2023-08-23 | ヤマハ株式会社 | 情報提供方法および通信システム |
US11790913B2 (en) | 2017-08-31 | 2023-10-17 | Yamaha Corporation | Information providing method, apparatus, and storage medium, that transmit related information to a remote terminal based on identification information received from the remote terminal |
US11211076B2 (en) | 2017-11-28 | 2021-12-28 | Google Llc | Key phrase detection with audio watermarking |
US11727947B2 (en) | 2017-11-28 | 2023-08-15 | Google Llc | Key phrase detection with audio watermarking |
Also Published As
Publication number | Publication date |
---|---|
AU2015297648A1 (en) | 2017-03-16 |
CN106537496B (zh) | 2019-12-20 |
AU2015297648B2 (en) | 2017-07-06 |
KR101796429B1 (ko) | 2017-11-09 |
JP2016075890A (ja) | 2016-05-12 |
EP3176782B8 (en) | 2021-02-24 |
KR20170033429A (ko) | 2017-03-24 |
US20170206195A1 (en) | 2017-07-20 |
CN106537496A (zh) | 2017-03-22 |
JP5871088B1 (ja) | 2016-03-01 |
EP3176782A1 (en) | 2017-06-07 |
KR20170125415A (ko) | 2017-11-14 |
US10733386B2 (en) | 2020-08-04 |
EP3176782B1 (en) | 2020-12-02 |
EP3176782A4 (en) | 2018-03-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5871088B1 (ja) | 端末装置、情報提供システム、情報提供方法およびプログラム | |
JP6170645B1 (ja) | 情報管理システムおよび端末装置 | |
JP5887446B1 (ja) | 情報管理システム、情報管理方法およびプログラム | |
JP6569252B2 (ja) | 情報提供システム、情報提供方法およびプログラム | |
JP6114249B2 (ja) | 情報送信装置および情報送信方法 | |
JP7087745B2 (ja) | 端末装置、情報提供システム、端末装置の動作方法および情報提供方法 | |
JP6569629B2 (ja) | 情報送信装置、情報送信方法およびプログラム | |
JP2017191363A (ja) | 情報生成システムおよび情報提供方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 15827950 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15327753 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
REEP | Request for entry into the european phase |
Ref document number: 2015827950 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2015827950 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 20177005255 Country of ref document: KR Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 2015297648 Country of ref document: AU Date of ref document: 20150727 Kind code of ref document: A |