JP2016173413A - Information provision system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a user with content associated with guidance voice in linkage with the radiation of the guidance voice.SOLUTION: An information provision system 100 comprises: an acquisition unit 110 for acquiring content Q associated with object sound collected by a sound collection unit 22; a sound radiation unit 28 for radiating, before the acquisition of the content Q by the acquisition unit 110, an acoustic including the acoustic component of the object sound and the acoustic component of previous notice information D for notifying a terminal device 30 of the provision of the content Q; and a delivery unit 120 for collecting the acoustic radiated by the radiation unit 28, and delivering the content Q acquired by the acquisition unit 110 to the terminal device 30 for notifying a user of the provision of the content Q in accordance with the previous notice information D extracted from the acoustic.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a technique for providing information to a user of a terminal device.

  Various techniques for reproducing content such as images and sounds on a mobile terminal have been proposed. For example, Patent Document 1 discloses a technique for distributing content according to the position of a mobile terminal to a mobile terminal registered in advance as a distribution target.

JP 2002-351905 A

  For example, in transportation facilities such as trains and buses, guidance voices that guide the user about information related to getting on and off, transfer, and the like are reproduced as needed. If it is possible to provide the user's mobile terminal with the content of the guidance voice pronunciation, such as a character string or a translated sentence, for example, it is difficult to understand the language of the guidance voice or a hard-of-hearing person who is difficult to hear the guidance voice. It is convenient for users such as foreigners to understand the contents of the guidance voice. In view of the above circumstances, an object of the present invention is to provide a user with content related to guidance voice in conjunction with sound emission of the guidance voice.

  In order to solve the above problems, an information providing system according to the present invention includes an acquisition unit that acquires content related to a target sound collected by a sound collection unit, and the target before the acquisition of the content by the acquisition unit. A sound emitting unit that emits sound including an acoustic component of sound and an acoustic component of notice information for notifying the terminal device of provision of the content, and collecting sound emitted by the sound emitting unit A distribution unit that distributes the content acquired by the acquisition unit to a terminal device that notifies the user of the provision of the content according to the advance notice information extracted from the sound; In the above configuration, the target sound collected by the sound collection unit is emitted from the sound emission unit and listened to by the user of the terminal device, while the content related to the target sound is acquired by the acquisition unit and the distribution unit To the terminal device. That is, the content related to the target sound can be provided to the user in conjunction with the sound emission of the target sound. In addition, when it takes time to acquire the content related to the target sound, the content is provided to the terminal device when it is delayed from the target sound being emitted by the sound emitting unit. There is a problem that it is difficult for a person to grasp the correspondence between the target sound and the content. In the present invention, the acoustic component of the advance notice information for notifying the terminal device of the provision of the content related to the target sound is emitted from the sound emitting unit together with the acoustic component of the target sound before the content generation is completed. There is also an advantage that the user of the terminal device can grasp the correspondence with the content (the content is distributed after the target sound is emitted).

  In a preferred aspect of the present invention, the advance notice information includes identification information of the content, and the distribution unit issues a distribution request specifying the identification information extracted from the sound emitted by the sound emitting unit. When received from the device, the content corresponding to the identification information is distributed to the terminal device. With the above configuration, content corresponding to the identification information is distributed in response to a distribution request from the terminal device, and thus there is an advantage that it is not necessary to register the distribution target terminal device in the distribution unit in advance. In addition, since the identification information included in the advance notice information is specified by the distribution request, there is an advantage that the content corresponding to the target sound can be easily specified even when, for example, a plurality of contents exist as distribution candidates for the terminal device.

  In a preferred aspect of the present invention, the distribution unit sequentially receives the distribution requests transmitted a plurality of times from the terminal device, and content acquisition by the acquisition unit is completed when the distribution request is received. In this case, the content is distributed to the terminal device, but if the acquisition of the content is not completed, the content is not distributed. In the above configuration, the distribution unit sequentially receives distribution requests transmitted from the terminal device a plurality of times, and the content is distributed to the terminal device when acquisition of the content is completed at the time of reception. Therefore, for example, in comparison with a configuration in which a distribution request is transmitted from the terminal device after a lapse of a waiting time for a predetermined time from reception of the advance notice information, the content is actually transferred to the terminal device after the acquisition of the content by the acquisition unit is completed. There is an advantage that the delay until delivery is shortened.

  In a preferred aspect of the present invention, the acquisition unit includes a recognition processing unit that identifies a character string of pronunciation content by speech recognition on the target sound, and the first character string for each of the plurality of first character strings in another language. A selection processing unit that selects a second character string corresponding to a first character string similar to the character string specified by the recognition processing unit from a table in which the second character string translated into Content representing the second character string selected by the part is generated. Therefore, there is an advantage that it is possible to provide the user with content representing an appropriate second character string that does not include misrecognition in speech recognition or mistranslation in machine translation.

  In a preferred aspect of the present invention, the acquisition unit includes a recognition processing unit that specifies a character string of pronunciation content by speech recognition for the target sound, and a translation process that translates the character string specified by the recognition processing unit into another language. A content representing a processing result by the translation processing unit. In the above configuration, content representing the result of translating the character string of the pronunciation content of the target sound into another language is distributed to the terminal device. Therefore, even when the user of the terminal device cannot understand the language of the target sound, there is an advantage that the pronunciation of the target sound can be understood from the content distributed to the terminal device. The content representing the processing result by the translation processing unit includes, for example, content representing a character string after translation by the translation processing unit, and content representing synthesized speech generated by speech synthesis using the translated character string. Illustrated.

  In a preferred aspect of the present invention, the image processing apparatus includes an editing processing unit that edits the character string specified by the recognition processing unit in accordance with an instruction from an instructor, and the translation processing unit is a character after editing by the editing processing unit. Translate the column to another language. In the above configuration, the character string edited by the recognition processing unit according to the instruction from the instructor is translated into another language. Therefore, for example, even when the recognition result by the recognition processing unit includes misrecognition, the translation processing unit can achieve accurate translation by correcting by editing, and the user can be notified of the pronunciation of the target sound accurately. is there.

  The information providing system according to each of the aspects described above is realized by a dedicated electronic circuit or by 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 recording medium is, for example, a non-transitory recording medium, and an optical recording medium (optical disk) such as a CD-ROM is a good example, but a known arbitrary one such as a semiconductor recording medium or a magnetic recording medium This type of recording medium can be included. For example, the program of the present invention can be provided in the form of distribution via a communication network and installed in a computer. The present invention is also specified as an operation method (information providing method) of the information providing system according to each of the above aspects.

It is a lineblock diagram of voice guidance system 1 concerning a 1st embodiment of the present invention. 1 is a configuration diagram of a sound emission system 20. FIG. 3 is a configuration diagram of a signal processing unit 280. FIG. 1 is a configuration diagram of an information management system 10. FIG. 2 is a configuration diagram of a terminal device 30. FIG. 2 is a configuration diagram of a terminal device 30. FIG. It is explanatory drawing of operation | movement of the voice guidance system. It is a figure which shows an example of reproduction | regeneration of the content Q. It is a block diagram of the information management system 10 of 2nd Embodiment. It is a schematic diagram of guidance table TB1 of 2nd Embodiment. It is a block diagram of the voice guidance system 1 which concerns on 3rd Embodiment of this invention. It is a block diagram of the information provision system 100 which concerns on the modification of this invention.

<First Embodiment>
An outline of the voice guidance system 1 of the first embodiment will be described. In the following description, a configuration in which the voice guidance system 1 of the first embodiment is used for voice guidance of public transportation is illustrated.

  FIG. 1 is a configuration diagram of a voice guidance system 1 according to the first embodiment of the present invention. As illustrated in FIG. 1, the voice guidance system 1 of the first embodiment includes an information providing system 100 and a terminal device 30. The information providing system 100 is a computer system that provides various information to the terminal device 30. The terminal device 30 is a portable information processing device such as a mobile phone or a smartphone. In the following description, the user of the terminal device 30 is located at the airport facility C, and the content Q related to the voice for guiding the user (hereinafter referred to as “guidance voice”) is provided to the terminal device 30. Although only one terminal device 30 is illustrated in FIG. 1 for the sake of convenience, in practice, information can be provided from the information providing system 100 to each of the plurality of terminal devices 30.

  As illustrated in FIG. 1, the information providing system 100 according to the first embodiment includes an information management system 10 and a sound emission system 20. The sound emitting system 20 is installed in the airport facility C and used for voice guidance in the airport facility C. Specifically, the sound emission system 20 of the first embodiment emits a guidance voice (target sound) in a specific language (hereinafter referred to as “first language”). The guidance voice is, for example, a sound that represents guidance (for example, boarding guidance, transit guidance, operation information, delay information, etc.) related to an airline operated by an airline company that enters the airport facility C. Further, the sound emission system 20 emits a guidance voice and notifies the terminal apparatus 30 of advance notice information for notifying the terminal apparatus 30 in advance of the provision of the content Q related to the guidance voice. The advance notice information is notified to the terminal device 30 by wireless information communication. The first embodiment exemplifies a case in which notice information is notified from the sound emitting system 20 to the terminal device 30 by acoustic communication using sound (sound wave) as air vibration as a transmission medium in parallel with sound emission of the guidance voice. . That is, the advance notice information is radiated from the sound emitting system 20 as sound together with the guidance voice. In the first embodiment, the identification information D of the content Q related to the guidance voice is generated as the advance notice information.

  On the other hand, the information management system 10 is a computer system that manages information provided to the terminal device 30. The terminal device 30 can communicate with the information management system 10 via a communication network 200 including a mobile communication network and the Internet. The information management system 10 acquires the content Q related to the guidance voice when sound emission of the guidance voice is started. The terminal device 30 transmits a content Q distribution request R including the identification information D notified in advance from the sound emitting system 20 to the information management system 10. The information management system 10 transmits the content Q corresponding to the identification information D specified by the distribution request R received via the communication network 200 to the requesting terminal device 30. The content Q is information related to the guidance voice. In the first embodiment, the terminal device 30 is provided with the content Q indicating the translation obtained by converting the guidance in the first language pronounced by the guidance voice into another language (hereinafter referred to as “second language”). Therefore, a user who can understand the first language grasps the guidance by listening to the guidance voice, and a user who can understand the second language grasps the guidance by referring to the content Q. Specific configurations and functions of the elements of the information providing system 100 outlined above will be described in detail below.

<Sound emission system 20>
FIG. 2 is a configuration diagram of the sound emission system 20. As illustrated in FIG. 2, the sound emission system 20 of the first embodiment includes a sound collection unit 22, a storage unit 21, a communication unit 24, a setting unit 26, and a sound emission unit 28. The sound collecting unit 22 is an acoustic device (microphone) that picks up surrounding sounds, picks up the guidance voice that the guide who is in charge of guiding the airport facility C, and represents the time waveform of the guidance voice. A signal SG is generated. Note that an A / D converter that converts the acoustic signal SG generated by the sound collection unit 22 from analog to digital is not shown for convenience. The storage unit 21 stores a program executed by a CPU (not shown) that controls each element of the sound emission system 20. 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 unit 21. Each function (setting part 26, sound emission part 28) of sound emission system 20 is realized because CPU runs the program memorized by storage part 21.

  The setting unit 26 generates identification information D for identifying the content Q as the advance notice information. The identification information D is a code that can uniquely identify each of the plurality of contents Q. The setting unit 26 generates identification information D of the content Q of the guidance voice every time the guidance voice is generated. The communication unit 24 is a communication device that transmits the identification information D generated by the setting unit 26 and the acoustic signal SG generated by the sound collection unit 22 to the information management system 10 via the communication network 200.

  The sound emitting unit 28 is a unit that emits sound including the acoustic component (acoustic signal SG) of the guidance voice and the acoustic component of the identification information D, and as illustrated in FIG. 2, the signal processing unit 280 and the speaker 286. It comprises. The signal processing unit 280 generates the acoustic signal S1 by combining the identification information D set by the setting unit 26 with the acoustic signal SG. For synthesizing the identification information D with the acoustic signal SG (acoustic watermarking), a known method can be arbitrarily adopted. For example, the method disclosed in International Publication No. 2010/016589 is suitable. Specifically, the signal processing unit 280 includes a modulation processing unit 282 and a mixing processing unit 284, as illustrated in FIG. The modulation processing unit 282 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 20 and collected by the terminal device 30, and voices (eg, guidance voices) and musical sounds that the user listens to in a normal environment. In the range of the frequency band (for example, 18 kHz or more and 20 kHz or less) exceeding the frequency band of the sound (for example, about 16 kHz or less in the audible range). The mixing processing unit 284 in FIG. 3 generates the acoustic signal S1 by superimposing (typically adding) the acoustic signal SG generated by the sound collection unit 22 and the modulation signal SD generated by the modulation processing unit 282. As understood from the above description, the acoustic signal S1 contains the acoustic component (acoustic signal SG) of the guidance voice and the acoustic component (modulation signal SD) including the identification information D of the content Q of the guidance voice. The speaker 286 is an acoustic device that emits sound corresponding to the acoustic signal S 1 supplied from the signal processing unit 280. The D / A converter that converts the acoustic signal S1 from digital to analog is not shown for convenience. In the first embodiment, the sound corresponding to the acoustic signal S1 is emitted from the sound emitting unit 28 (speaker 286) in real time in parallel with the pronunciation of the guidance voice by the guide.

<Information management system 10>
FIG. 4 is a configuration diagram of the information management system 10. As illustrated in FIG. 4, the information management system 10 according to the first embodiment includes an acquisition unit 110, a distribution unit 120, and a storage unit 130. The storage unit 130 stores a program executed by a CPU that controls each element of the information management system 10. 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 unit 130. Each function (acquisition part 110, delivery part 120) of information management system 10 is realized by CPU executing a program memorized by storage part 130. The acquisition unit 110 is a unit that acquires the content Q related to the guidance voice using the acoustic signal SG of the guidance voice supplied from the communication unit 24. As illustrated in FIG. And a processing unit 114. The acquisition unit 110 according to the first embodiment acquires the content Q related to the guidance voice by generating the content Q using the acoustic signal SG of the guidance voice.

  The recognition processing unit 112 identifies a character string L expressing the pronunciation content of the guidance voice by voice recognition with respect to the acoustic signal SG of the guidance voice supplied from the communication unit 24 of the sound emitting system 20. For 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 translation processing unit 114 generates, as the content Q, a character string obtained by converting the character string L specified by the recognition processing unit 112 into another language by machine translation. Specifically, the translation processing unit 114 generates, as the content Q, a character string obtained by converting the character string L expressing the pronunciation content of the guidance voice pronounced in the first language into the second language. A known technique can be arbitrarily employed for the machine translation by the translation processing unit 114. For example, a rule-based machine translation that converts a word order or a word by referring to a result of parsing a character string L and a linguistic rule, or a statistical model that expresses a statistical tendency of a language (translation model and language model) Statistical machine translation that translates the character string L into the second language by using () can be used to translate the character string L. As understood from the above description, the acquisition unit 110 (recognition processing unit 112, translation processing unit 114) of the first embodiment generates a second character string expressing the pronunciation content of the guidance voice pronounced in the first language. The character string converted into the language is acquired as the content Q. The acquisition unit 110 stores the generated content Q and the identification information D received from the sound emission system 20 in the storage unit 130 in association with each other.

  The distribution unit 120 distributes the content Q acquired by the acquisition unit 110 to the terminal device 30. Specifically, when the distribution unit 120 receives the distribution request R of the content Q including the identification information D from the terminal device 30, the distribution unit 120 distributes the content Q corresponding to the identification information D to the requesting terminal device 30. To do.

  As understood from the above description, the sound of the guide voice and the acoustic component of the identification information D are emitted from the sound emitting section 28, triggered by the sound of the guide voice to the sound collection unit 22, while the sound of the guide voice is heard. The signal SG is transmitted to the information management system 10 to generate the content Q. That is, the content Q related to the guidance voice can be distributed to the user of the terminal device 30 in conjunction with the sound emission of the guidance voice. However, while the guidance voice is mixed with the acoustic component of the identification information D after being picked up by the sound pickup unit 22, it is immediately emitted, whereas the content Q is between the sound emission system 20 and the information management system 10. The sound signal SG is transmitted and received through the communication network 200 and processed by the acquisition unit 110 (voice recognition, machine translation), and can be transmitted to the terminal device 30. Therefore, at the time when the guidance voice starts to be emitted, the generation of the content Q of the guidance voice is not yet completed, and the content Q cannot be transmitted to the terminal device 30. That is, in the first embodiment, the sound including the acoustic component of the guidance voice and the acoustic component of the identification information D is emitted by the sound emitting unit 28 before the generation of the content Q is completed.

<Terminal device 30>
FIG. 5 is a configuration diagram of the terminal device 30. As illustrated in FIG. 5, the terminal device 30 includes a sound collection unit 310, an information extraction unit 320, a transmission unit 330, a reception unit 340, a display processing unit 350, an output unit 360, and a storage unit 370. . The storage unit 370 stores a program executed by a CPU that controls each element of the terminal device 30. 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 unit 370. The information extraction unit 320 and the display processing unit 350 are realized by the CPU executing the program stored in the storage unit 370. The sound collection unit 310 is an acoustic device (microphone) that collects ambient sound, and collects sound emitted from the speaker 286 of the sound emission system 20 to generate an acoustic signal S2. The acoustic signal S2 contains the acoustic component of the identification information D. Note that an A / D converter that converts the acoustic signal S2 generated by the sound collection unit 310 from analog to digital is not shown for convenience.

  The information extraction unit 320 extracts the identification information D by demodulating the acoustic signal S2 generated by the sound collection unit 310. Specifically, the information extraction unit 320 emphasizes the band component of the frequency band including the identification information D in the acoustic signal S2, for example, with a band pass filter, and uses the spreading code used for the spread modulation of the identification information D as the coefficient. The identification information D is extracted by passing the matched filter. The transmission unit 330 and the reception unit 340 are communication devices that communicate with the information management system 10 via the communication network 200. The transmission unit 330 transmits the distribution request R of the content Q including the identification information D extracted by the information extraction unit 320 to the information management system 10. The receiving unit 340 receives the content Q distributed from the information management system 10 (distributing unit 120) in response to the distribution request R.

  The output unit 360 outputs various types of information. The output unit 360 of the first embodiment is a display device (for example, a liquid crystal display panel) that displays an image. The display processing unit 350 causes the output unit 360 to display an image. For example, the display processing unit 350 causes the output unit 360 to display the content Q received by the receiving unit 340 from the information management system 10. That is, a character string obtained by translating the guidance voice into another language is displayed as the content Q. In addition, the display processing unit 350 according to the first embodiment notifies the user of the terminal device 30 of the distribution of the content Q corresponding to the guidance voice in advance (that is, the advance notice) prior to the actual distribution of the content Q. . Specifically, the display processing unit 350 causes the output unit 360 to display a message that the content Q related to the guidance voice is to be distributed immediately after the extraction of the identification information D by the information extraction unit 320. For example, as illustrated in FIG. 6, the output unit 360 outputs the message “A message of voice guidance will soon be provided” generated in the second language similar to the content Q together with the identification information D [# 101]. By doing so, the user is notified in advance that the content Q related to the guidance voice listened to by the user is distributed. That is, prior to the distribution of the content Q to the terminal device 30, the user can grasp the distribution of the content Q related to the guidance voice in advance together with listening to the guidance voice.

  FIG. 7 is an explanatory diagram of the overall operation of the voice guidance system 1. The sound collection unit 22 of the sound emission system 20 collects the guidance voice that the guide pronounced in the first language to generate the acoustic signal SG (SA1). The communication unit 24 transmits the acoustic signal SG and the identification information D generated by the sound collection unit 22 to the information management system 10 (SA2). The acquisition unit 110 of the information management system 10 starts generating the content Q related to the guidance voice, triggered by reception of the acoustic signal SG and the identification information D. As shown for convenience in FIG. 7 by hatching, it takes time to generate the content Q of the guidance voice.

  On the other hand, the signal processing unit 280 of the sound emitting unit 28 generates the acoustic signal S1 by combining the identification information D with the acoustic signal SG generated by the sound collecting unit 22 (SA3), and the speaker 286 responds to the acoustic signal S1. Sound is released (SA4). The sound collection unit 310 of the terminal device 30 collects the guidance voice emitted by the speaker 286 and generates an acoustic signal S2. The information extraction unit 320 extracts the guidance voice identification information D by demodulating the acoustic signal S2 generated by the sound collection unit 310 (SA5). As illustrated in FIG. 7, the generation of the content Q may not be completed at the time when the information extraction unit 320 extracts the identification information D. The display processing unit 350 is triggered by the extraction of the identification information D by the information extraction unit 320 (that is, regardless of whether the generation of the content Q has been completed or not), for example, as illustrated in FIG. A message notifying the user that Q is distributed is displayed on the output unit 360 (SA6). Thereby, prior to the actual distribution of the content Q to the terminal device 30, the user can grasp in advance together with listening to the guidance voice that the content Q related to the guidance voice will be delivered soon. .

  When the extraction of the identification information D by the information extraction unit 320 and the notification by the display processing unit 350 are performed, the transmission unit 330 sends the content Q distribution request R including the identification information D extracted by the information extraction unit 320 to the distribution request R. The content Q is transmitted to the information management system 10 a plurality of times until it is actually distributed to the terminal device 30 (SA7, SA9).

  The distribution unit 120 sequentially receives the distribution request R transmitted a plurality of times from the terminal device 30, and determines whether or not the generation of the content Q of the identification information D specified by the distribution request R has been completed. It is determined every time when receiving. Since the generation of the content Q has not yet been completed at the time of receiving the distribution request R in step SA7 in FIG. 7, the distribution unit 120 transmits a non-distributable response to the terminal device 30 (SA8). That is, the content Q is not distributed. On the other hand, the distribution request R in step SA9 in FIG. 7 is received by the distribution unit 120 immediately after the generation of the content Q is completed. When the generation of the content Q is completed at the time of receiving the distribution request R, the distribution unit 120 distributes the content Q generated by the acquisition unit 110 to the requesting terminal device 30 (SA10). The receiving unit 340 of the terminal device 30 receives the content Q distributed from the information management system 10 (SA11), and the display processing unit 350 displays the content Q received by the receiving unit 340 on the output unit 360 (SA12). .

  FIG. 8 is an example of the reproduction of the content Q. FIG. 8 illustrates the content Q generated when the first language (Japanese) guidance voice for guiding the start of boarding the aircraft is emitted. As illustrated in FIG. 8, when the guidance voice in the first language saying that “78 flights to ABC Airlines Paris are just going to board from gate 81” is emitted from the sound emission system 20, the guidance will be given. A character string “Passengers on ABC Airlines flight 78 to Paris are now on boarding at gate 81” obtained by translating the voice into the second language (English) is displayed on the output unit 360 as the content Q.

  As described above, in the first embodiment, the guidance sound collected by the sound collection unit 22 is emitted from the sound emission unit 28 and listened to by the user of the terminal device 30, while the content related to the guidance sound is obtained. Q is generated and distributed from the distribution unit 120 to the terminal device 30. Therefore, the content Q related to the guidance voice can be provided for use of the terminal device 30. In the first embodiment, the content Q is generated by converting the guidance voice pronounced in the first language into the second language. Therefore, a user who can understand the first language can guide the airport facility C by listening to the guidance voice. The user who can understand the second language can grasp the guidance by referring to the content Q.

  By the way, if it takes a certain amount of time to generate the content Q related to the guidance voice, the content Q of the guidance voice is sent to the terminal device 30 when it is greatly delayed from the sound emission of the guidance voice by the sound collection unit 22. Delivered and output. Therefore, in the configuration in which the distribution of the guidance voice content Q is not notified to the user in advance (the above-described display processing unit 350 is omitted, hereinafter referred to as “proportional”), the sound is emitted from the sound emitting unit 28. There may be a problem that it is difficult to grasp the correspondence between the guidance voice and the content Q output from the output unit 360 of the terminal device 30 after sound emission. In the first embodiment, immediately after the acoustic component of the advance notice information (identification information D) for notifying the terminal device 30 of the delivery of the content Q related to the guidance voice is emitted from the sound emitting unit 28 together with the acoustic component of the guidance voice. Since the delivery of the content Q is notified to the user in advance, the user of the terminal device 30 can grasp the correspondence between the guidance voice and the content Q (the content Q is delivered after the guidance voice is emitted). There are also advantages.

  In the first embodiment, the content Q corresponding to the identification information D when the distribution unit 120 receives the distribution request R specifying the identification information D extracted from the sound emitted by the sound emitting unit 28 from the terminal device 30. Is distributed from the distribution unit 120 to the terminal device 30. That is, since the content Q is distributed in response to the distribution request R from the terminal device 30, it is not necessary to register the terminal device 30 in advance as the distribution target of the content Q. Further, since the identification information D is specified by the distribution request R, for example, even when a plurality of contents Q are stored in the storage unit 130 as distribution candidates for the terminal device 30, the contents Q corresponding to the guidance voice listened to by the user There is an advantage that can be easily identified.

  In the first embodiment, the distribution unit 120 sequentially receives the distribution request R transmitted from the terminal device 30 a plurality of times, and when the generation unit 110 completes the generation of the content Q when the distribution request R is received. On the other hand, the content Q is distributed to the terminal device 30, while the content Q is not distributed unless the generation of the content Q is completed. Therefore, for example, in comparison with a configuration in which the distribution request R is transmitted from the terminal device 30 after a lapse of a standby time over a predetermined time (for example, the maximum time required for generating the content Q) from the reception of the identification information D, There is an advantage that a delay from when the generation of the content Q by the acquisition unit 110 is completed until the content Q is actually distributed to the terminal device 30 is shortened.

  In the first embodiment, the character string L of the pronunciation content is identified by voice recognition for the guidance voice, and the result of translating the character string L into another language is generated as the content Q. That is, the content Q representing the result of translating the character string of the pronunciation content of the first language guidance voice into the second language is delivered to the terminal device 30. Therefore, even when the user of the terminal device 30 cannot understand the language of the guidance voice, there is an advantage that the pronunciation content of the guidance voice can be understood by checking the content Q delivered to the terminal device 30.

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. The display processing unit 350 is triggered by the operation of notifying the terminal device 30 of the advance notice information (identification information D) in conjunction with the sound emission of the guidance sound by the sound emission unit 28 and the extraction of the identification information D by the information extraction unit 320. The operation of notifying the user of the delivery of the content Q is the same as in the first embodiment.

  FIG. 9 is a configuration diagram of the information management system 10 of the second embodiment. As illustrated in FIG. 9, the information management system 10 of the second embodiment has a configuration in which the translation processing unit 114 of the first embodiment is replaced with a selection processing unit 118. Further, the storage unit 130 of the second embodiment stores a guide table TB1 in addition to the same information as that of the first embodiment. Since the functions and operations of the recognition processing unit 112 and the distribution unit 120 are the same as those in the first embodiment, detailed description thereof is omitted.

  FIG. 10 is a schematic diagram of the guidance table TB1. As illustrated in FIG. 10, the guide table TB1 includes a plurality of character strings (first character strings) X (first character string) X (representing the pronunciation content of the guidance voice to be pronounced by the guide of the airport facility C. X1, X2, X3,...) And a character string (second character string) Y (Y1, Y2, Y3,...) Obtained by translating the character string X into the second language are associated with each other. Each character string X of the guidance table TB1 is, for example, a sentence recorded in an announcement book that the guide refers to when the guidance voice is pronounced. In FIG. 10, a character string X of various greetings and a character string Y of translations thereof are illustrated.

  The selection processing unit 118 selects the character string Y corresponding to the character string L identified from the acoustic signal SG of the guidance voice by the recognition processing unit 112 from the guidance table TB1. Specifically, the selection processing unit 118 selects one character most similar to the character string L specified by the recognition processing unit 112 among the plurality of character strings X (X1, X2, X3,...) Of the guidance table TB1. A column X is specified, and a character string Y associated with the character string X is selected. For determining the similarity between the character string L and the character string X, a known index such as an edit distance (Levenstein distance) can be arbitrarily adopted. The character string Y selected by the selection processing unit 118 is stored in the storage unit 130 together with the identification information D as the content Q. The subsequent processing is the same as in the first embodiment.

  In the example of FIG. 10, when the character string L “Good morning” is specified, the selection processing unit 118 selects the character string whose edit distance approximates the character string L among the plurality of character strings X in the guidance table TB1. X1 “Good morning” is selected, and the character string Y1 “Good morning” associated with the character string X1 is stored as content Q in the storage unit 130 together with the identification information D.

  Also according to the second embodiment, it is possible to achieve the same effect as the first embodiment. In the second embodiment, a plurality of sets of a first language character string X and a second language character string Y are prepared in advance and correspond to a character string X similar to the character string L specified by speech recognition. The attached character string Y is generated as the content Q. That is, the content Q provided to the user is limited to a character string prepared in advance. Therefore, it is possible to provide an appropriate character string Y to the user even when erroneous recognition occurs in the recognition processing unit 112. In addition, there is an advantage that the possibility of mistranslation can be reduced as compared with the configuration of the first embodiment in which the character string L specified by speech recognition is machine-translated. That is, according to the second embodiment, it is possible to provide the user with the content Q of the proper character string Y that can be surely understood by the user. Moreover, according to the above structure, there exists an advantage that the content Q can be produced | generated easily compared with 1st Embodiment which machine-translates the character string L. FIG. Moreover, according to the above structure, since it is not necessary to mount the translation process part 114 in the information management system 10, the structure and process of the information management system 10 can be simplified.

<Third Embodiment>
The recognition accuracy by the recognition processing unit 112 is practically limited, and erroneous recognition may occur. If the guidance voice is erroneously recognized, there may arise a problem that the content Q that accurately reflects the actual guidance voice content cannot be provided to the user of the terminal device 30. Therefore, in the third embodiment, the misrecognition is corrected by the guider editing the character string L specified by the speech recognition with respect to the guide voice pronounced by the guide as necessary.

  FIG. 11 is a configuration diagram of the voice guidance system 1 of the third embodiment. In the sound emission system 20 of the third embodiment, a display unit 23, an operation unit 25, an edit processing unit 27, and a control unit 29 are added to the configuration of the sound emission system 20 of the first embodiment. The functions of the sound collection unit 22 and the setting unit 26 are the same as those in the first embodiment. In 3rd Embodiment, each function (editing process part 27, control part 29) of the sound emission system 20 is implement | achieved because CPU runs the program memorize | stored in the memory | storage part 21. FIG.

  The display unit 23 is a display device (for example, a liquid crystal display panel) that displays various types of information. The operation unit 25 is an input device that is operated by a guide who generates a guidance voice in order to instruct the sound output system 20. The operation unit 25 according to the third embodiment receives an instruction or the like for reproducing the acoustic signal SG from the guide. The control unit 29 controls writing and reading of the acoustic signal SG with respect to the storage unit 21 in accordance with an instruction from the guide. The control unit 29 according to the third embodiment stores the acoustic signal SG generated by the sound collection unit 22 every time the guide pronounces the guidance voice in the storage unit 21, while the acoustic signal SG according to the operation by the guide. Is read from the storage unit 21 and supplied to the communication unit 24 and the sound emitting unit 28. The communication unit 24 transmits the acoustic signal SG supplied from the control unit 29 to the information management system 10 via the communication network 200.

  As in the first embodiment, the information management system 10 of the third embodiment includes an acquisition unit 110, a distribution unit 120, and a storage unit 130. The function and operation of the distribution unit 120 are the same as in the first embodiment. The recognition processing unit 112 in the acquisition unit 110 specifies the character string L of the guidance voice by voice recognition with respect to the acoustic signal SG received from the communication unit 24 of the sound emission system 20, and uses the character string L via the communication network 200. To the sound emitting system 20.

  The edit processing unit 27 of the sound emission system 20 edits the character string L specified by the recognition processing unit 112 in accordance with an instruction from the guide (instructor) to the operation unit 25. The edit processing unit 27 of the first embodiment displays the character string L on the display unit 23. The guide can instruct to change the character string L by appropriately operating the operation unit 25 while confirming the character string L displayed on the display unit 23. Specifically, if there is a discrepancy between the character string L displayed on the display unit 23 and the pronunciation content of the guidance voice that was pronounced immediately before, the guide will pronounce the guidance voice that was pronounced immediately before. The change of the character string L is instructed so as to match the contents. The edit processing unit 27 generates the character string W by editing the character string L in accordance with an instruction from the user to the operation unit 25. If there is no discrepancy between the character string L and the pronunciation content, the character string L is determined as the edited character string W.

  When the processing by the editing processing unit 27 ends, the guide instructs the completion of editing by operating the operating unit 25 (hereinafter referred to as “editing completion instruction”). In response to the editing completion instruction, the communication unit 24 transmits the character string W edited by the editing processing unit 27 to the information management system 10 together with the identification information D of the content Q of the guidance voice. On the other hand, the control unit 29 reads out the acoustic signal SG stored in the storage unit 21 and supplies it to the sound emitting unit 28 in response to the editing completion instruction. That is, the editing completion instruction can be substantially expressed as an instruction to reproduce the acoustic signal SG.

  The signal processing unit 280 of the sound emitting unit 28 generates the acoustic signal S1 by synthesizing the identification information D with the acoustic signal SG supplied from the control unit 29 by the same method as in the first embodiment. The speaker 286 of the sound emitting unit 28 emits sound corresponding to the acoustic signal S1 supplied from the signal processing unit 280, as in the first embodiment. The operation of the information extraction unit 320 extracting the identification information D from the sound emitted from the sound emission unit 28 and the operation of the display processing unit 350 notifying the user of the delivery of the content Q triggered by the extraction of the identification information D are the first. This is the same as in the first embodiment.

  The translation processing unit 114 of the information management system 10 receives the character string W edited by the editing processing unit 27, and generates the content Q by translating the character string W into another language. The content Q generated by the translation processing unit 114 is stored in the storage unit 130 together with the identification information D transmitted from the sound emission system 20. The operation in which the distribution unit 120 distributes the content Q in response to the distribution request R from the terminal device 30 is the same as that in the first embodiment.

  As understood from the above description, in the third embodiment, triggered by the editing completion instruction, the recorded guidance voice (sound signal S1) is emitted and the content Q related to the guidance voice is generated. Is done. That is, since the guidance voice is emitted after the editing of the character string L is completed, it is possible to reduce the delay from the guidance voice emission to the distribution of the content Q.

  As described above, in the third embodiment, content is obtained by editing the character string L specified by the recognition processing unit 112 in accordance with an instruction from the guide and translating the edited character string W into another language. Q is generated. Therefore, even when the recognition result (character string L) by the recognition processing unit 112 includes misrecognition, by distributing the content Q corresponding to the edited character string W, the pronunciation content of the guidance voice can be accurately transmitted to the user. The effect of being able to be notified is realized.

<Modification>
Each aspect illustrated above can be variously modified. Specific modifications are exemplified below. Two or more modes arbitrarily selected from the following examples can be appropriately combined within a range that does not contradict each other.

(1) In each of the above-described embodiments, the voice guidance related to the flight operated by the airline is exemplified as the scene where the voice guidance system 1 is used. However, the scene where the voice guidance system 1 is used is limited to the above examples. Not. For example, the voice guidance system 1 similar to the above-described embodiments is used for voice guidance of transportation facilities such as trains and buses, and voice guidance of various facilities such as exhibition facilities such as museums and museums, accommodation facilities, and commercial facilities. Is done. It is also possible to use the voice guidance system 1 for providing information (for example, evacuation guidance and status notification) when disasters such as fires and earthquakes occur in various facilities. Further, the sound that is the target of sound collection by the sound collection unit 22 and sound emission by the sound emission unit 28 is not limited to the guidance sound. For example, the above-described embodiments can also be adopted when various sounds such as music are collected by the sound collection unit 22 and emitted from the sound emission unit 28. As understood from the above description, the guidance voices in the above-described forms are examples of sound (target sound) to be reproduced.

(2) In the above-described embodiments, the configuration in which the acquisition unit 110 includes the recognition processing unit 112 and the translation processing unit 114 has been exemplified. However, the positions where the recognition processing unit 112 and the translation processing unit 114 are installed (voice recognition and machine The stage in which translation is performed is not limited to the above examples. For example, it is also possible to install the recognition processing unit 112 and the translation processing unit 114 in the terminal device 30 and distribute the acoustic signal SG transmitted from the sound emitting system 20 from the information management system 10 to the terminal device 30 as the content Q. is there. In the above configuration, the acquisition unit 110 acquires the acoustic signal SG transmitted from the communication unit 24 of the sound emission system 20 as the content Q, associates the content Q with the identification information D, and the distribution unit 120 When the distribution request R of the content Q including the identification information D is received from the terminal device 30, the content Q (acoustic signal SG) corresponding to the identification information D is distributed. The recognition processing unit 112 of the terminal device 30 specifies the character string L of the guidance voice by executing voice recognition on the received content Q, and the translation processing unit 114 of the terminal device 30 specifies the recognition processing unit 112. The translated character string L is translated into the second language to reproduce the content Q.

  In addition, the recognition processing unit 112 and the translation processing unit 114 can be installed in the sound emitting system 20. The communication unit 24 of the sound emission system 20 transmits the character string L generated by the recognition of the acoustic signal SG by the recognition processing unit 112 and the machine translation by the translation processing unit 114 to the information management system 10. The acquisition unit 110 of the information management system 10 acquires the character string L generated by the sound emission system 20 as the content Q. It is also possible to install the recognition processing unit 112 in the sound emitting system 20 and install the translation processing unit 114 in the information management system 10. The terminal device directly from the sound emission system 20 (that is, without intervening the information management system 10) using the character string L generated by the recognition processing unit 112 and the translation processing unit 114 of the sound emission system 20 as the content Q. It is also possible to transmit to 30. For the transmission of the content Q from the sound emitting system 20 to the terminal device 30, short-distance wireless communication (ad hoc communication) using radio waves or infrared rays is suitably used in addition to the acoustic communication exemplified in the above-described embodiments. According to the above configuration, since it is not necessary for the terminal device 30 to execute communication using the communication network 200, for example, even a user who is not subscribed to a communication service using the communication network 200 (for example, a foreign traveler). There is an advantage that the content Q can be used.

  As understood from the above description, the acquisition unit 110 in each of the above-described forms is comprehensively expressed as an element for acquiring the content Q related to the target sound, and its own operation (for example, voice recognition by the recognition processing unit 112). In addition to the element that generates the content Q by machine translation by the translation processing unit 114 and the element that acquires the content Q (for example, the acoustic signal SG and the translated character string) generated by an external device such as the sound emission system 20 Include.

(3) The content Q is not limited to the examples in the above-described embodiments. For example, in each of the above-described forms, the character string obtained by translating the pronunciation content of the guidance voice is generated as the content Q. For example, the content Q representing the synthesized voice generated by the voice synthesis using the translated character string is generated. May be. When the content Q represents sound, a sound emitting device such as a speaker or an earphone that emits the sound is used as the output unit 360. The content Q representing the character string after translation by the translation processing unit 114 and the content Q representing the synthesized speech that pronounces the translated character string are included as content representing the processing result (translation result) by the translation processing unit 114. The In the above description, the configuration including the translation processing unit 114 (for example, the first embodiment) is assumed. Similarly, in the second embodiment, the synthesized speech that pronounces the character string Y selected by the selection processing unit 118 is used. It is possible to generate content Q to represent. The content Q representing the character string Y selected by the selection processing unit 118 and the content Q representing the synthesized speech of the character string Y are comprehensively expressed as the content Q representing the character string Y selected by the selection processing unit 118. .

  Further, the character string L itself specified by voice recognition for the acoustic signal SG of the guidance voice may be generated as the content Q. Also, for example, supplementary items and related information for the pronunciation content of the guidance voice (for example, information whose meaning and content itself do not necessarily match the guidance voice, such as information related to events such as facilities and places to be guided by the guidance voice) The content providing information Q and the link information (for example, URL) indicating the location of the information related to the guidance voice (for example, the content Q exemplified in each of the above-described embodiments) as the content Q from the information providing system 100 to the terminal device 30 A configuration for delivering to the network can also be adopted. The various contents Q exemplified above are comprehensively expressed as information related to the target sound. The relationship that the meaning or content correlates with the guidance voice, such as the content Q representing the pronunciation content of the guidance voice or the character string or voice of the translated sentence, is a typical example of the relationship “related to the target sound”. The relationship of representing the location of the information, such as the content Q representing the link information of the information related to the target sound, can also be included in the relationship related to the target sound.

(4) In each of the above-described embodiments, the configuration in which the content Q is distributed (that is, pull-type distribution) to the terminal device 30 that has transmitted the distribution request R specifying the identification information D is illustrated. Transmission is not mandatory. For example, the content Q can be distributed (ie, push-type distribution) to the terminal device 30 registered in advance in the information management system 10 as a distribution target, triggered by the generation of the content Q. Although the registration method of the terminal device 30 to be distributed is arbitrary, for example, a configuration in which the terminal device 30 located in the airport facility C is registered is preferable. Specifically, the terminal device 30 transmits a registration request triggered by reading a QR code (registered trademark) installed in the airport facility C or receiving a radio signal from a short-range radio in the airport facility C. If the information management system 10 registers the request transmission source terminal device 30 as a distribution target, the distribution target of the content Q can be limited to the terminal device 30 in the airport facility C.

(5) In the above-described embodiments, the identification information D of the content Q of the guidance voice is exemplified as the advance notice information for notifying the terminal device 30 of the provision of the content Q. However, the advance notice information is not limited to the above examples. . For example, the identification information D for identifying the speaker 286 that emits the guidance voice may be used as the advance notice information. In the configuration in which the identification information D of the speaker 286 is used as the advance notice information, when the terminal device 30 that has picked up the guidance voice emitted by the speaker 286 transmits the distribution request R of the content Q including the identification information D, the speaker The content Q representing the latest guidance voice emitted at 286 may be distributed. Further, the notice information may be other than the identification information D. For example, as illustrated in FIG. 6, a message for notifying the user of the delivery of the content Q may be used as the advance notice information. The notice information may be any information that can be recognized by the terminal device 30 as an opportunity for the operation of the terminal device 30 notifying the user of the distribution of the content Q. That is, the advance notice information is comprehensively expressed as information for notifying the terminal device 30 of the provision of the content Q related to the guidance voice.

(6) In the third embodiment, the sound signal SG picked up by the sound pickup unit 22 is stored in the storage unit 21, and the sound signal SG is stored from the storage unit 21 after editing the character string L according to the instruction from the guide. Although supplied to the sound emitting unit 28, it is also possible to emit the guidance voice in real time in parallel with the pronunciation by the guide as in the first embodiment without waiting for the editing of the character string L.

(7) A configuration in which a plurality of contents Q are stored in advance in the storage unit 370 of the terminal device 30 in association with each piece of identification information D may be employed. Each content Q represents a translated sentence (character string Y in the second embodiment) of the guidance voice that is expected to be pronounced by the guide. The information extraction unit 320 of the terminal device 30 identifies the identification information D from the acoustic signal S2 collected by the sound (mixed sound of the guidance voice and the acoustic component of the identification information D) emitted by the sound emission unit 28 of the sound emission system 20. The display processing unit 350 causes the output unit 360 to reproduce the content Q corresponding to the identification information D extracted by the information extracting unit 320 among the plurality of contents Q stored in the storage unit 370. According to the above configuration, since it is not necessary for the terminal device 30 to execute communication using the communication network 200, for example, even a user who is not subscribed to a communication service using the communication network 200 (for example, a foreign traveler) is content. There is an advantage that Q can be used.

(8) In addition to being realized as a single device, the information management system 10 in each of the above embodiments may be realized as a plurality of devices (servers) configured separately from each other. For example, the information management system 10 of each form described above is distributed to a first server including the recognition processing unit 112, a second server including the translation processing unit 114, and a third server including the distribution unit 120, and the first A configuration in which the server, the second server, and the third server communicate with each other via the communication network 200 may be employed.

(9) In each of the above-described embodiments, acoustic communication is used for notification of the identification information D to the terminal device 30, but the communication method for notifying the terminal device 30 of the identification information D is not limited to the above examples. For example, it is also possible to notify the identification information D to the terminal device 30 by wireless communication using infrared rays or electromagnetic waves (for example, short-range wireless communication).

(10) In addition to the configuration in which the character string L (second language) translated by the translation processing unit 114 is distributed to the terminal device 30 as the content Q, the voice that pronounces the character string L (that is, the second language guidance voice) ) Can be emitted from the sound emission unit 28 of the sound emission system 20. For example, as illustrated in FIG. 12, the speech synthesizer 140 is installed in the information management system 10. The voice synthesizer 140 generates an acoustic signal SL of a synthesized voice that is generated by generating the character string L by voice synthesis to which the character string after translation by the translation processing unit 114 is applied. That is, the recognition processing unit 112 and the translation processing unit 114 are used for the generation of the content Q and the generation of the acoustic signal SL. In the above description, the configuration including the translation processing unit 114 (for example, the first embodiment) is illustrated. However, the composition in which the selection processing unit 118 of the second embodiment pronounces the character string Y selected from the guide table TB1. It is also possible for the speech synthesizer 140 to generate the audio signal SL.

  The acoustic signal SL generated by the speech synthesizer 140 is transmitted to the sound emission system 20. The sound emitting unit 28 of the sound emitting system 20 receives the second language guidance voice indicated by the acoustic signal SL received by the communication unit 24 from the information management system 10 after the first language guidance voice indicated by the acoustic signal SG is emitted. Sounds out. In the above configuration, a user who can understand the first language grasps the guidance by listening to the guidance voice in the first language, and a user who can understand the second language gives guidance by listening to the guidance voice in the second language. It is possible to grasp. The user of the terminal device 30 can confirm the guidance by the content Q distributed to the terminal device 30 and can also grasp the guidance by listening to the second language guidance sound emitted from the sound emitting system 20. It is.

  In the configuration in which the speech synthesis unit 140 is installed in the information management system 10, the translation processing unit 114 converts the character string L specified by the recognition processing unit 112 into a plurality of languages (for example, a third language or a fourth language in addition to the second language). Etc.), and the speech synthesizer 140 may generate an acoustic signal SL representing each guidance voice in a plurality of languages and transmit it to the sound emission system 20. The sound emitting unit 28 of the sound emitting system 20 provides guidance in different languages indicated by the plurality of acoustic signals SL received from the information management system 10 by the communication unit 24 after the guidance voice in the first language indicated by the acoustic signal SG is emitted. Sound is emitted sequentially. The number of types of languages translated by the translation processing unit 114 and the order in which the guidance voices (for example, the second language to the fourth language) of each language are emitted are arbitrary.

(11) The configuration for notifying the user of the delivery of the content Q using the notice information (identification information D) can be omitted. For example, the output of the mixed sound of the acoustic component of the guidance voice and the acoustic component of the notice information (identification information D), or the signal processing unit 280 that mixes the modulation signal SD of the identification information D with the acoustic signal SG of the guidance voice is omitted. In addition, the guidance voice collected by the sound collection unit 22 can be emitted from the speaker 286 as it is.

DESCRIPTION OF SYMBOLS 1 ... Voice guidance system, 100 ... Information provision system, 10 ... Information management system, 110 ... Acquisition part, 112 ... Recognition processing part, 114 ... Translation processing part, 118 ... Selection processing part, 120 ... ... Distribution unit 130... Storage unit 140... Speech synthesis unit 20... Sound emission system 21... Storage unit 22. ...... Operating unit, 26 ... setting unit, 27 ... editing processing unit, 28 ... sound emitting unit, 29 ... control unit, 280 ... signal processing unit, 282 ... modulation processing unit, 284 ... mixing processing , 286 …… Speaker, 30 …… Terminal device, 310 …… Sound collecting unit, 320 …… Information extracting unit, 330 …… Sending unit, 340 …… Receiving unit, 350 …… Display processing unit, 360 …… Output Part, 370... Storage part.

Claims (6)

An acquisition unit for acquiring content related to the target sound collected by the sound collection unit;
A sound emission unit that emits sound including the sound component of the target sound and the sound component of the notice information for notifying the terminal device of the provision of the content before the acquisition of the content by the acquisition unit;
The sound acquired by the sound output unit is collected and the content acquired by the acquisition unit is distributed to a terminal device that notifies the user of the provision of the content according to the advance notice information extracted from the sound. A distribution department;
An information providing system comprising: The advance notice information includes identification information of the content,
When the distribution unit receives a distribution request designating the identification information extracted from the sound emitted by the sound emitting unit from the terminal device, the distribution unit distributes content corresponding to the identification information to the terminal device. The information providing system according to claim 1. The distribution unit sequentially receives the distribution request transmitted a plurality of times from the terminal device, and when the acquisition unit completes the acquisition of the content when the distribution request is received, the content is transmitted to the terminal device. 3. The information providing system according to claim 2, wherein distribution of content is not executed unless acquisition of the content is completed. The acquisition unit
A recognition processing unit for identifying a character string of pronunciation content by voice recognition for the target sound;
Corresponding to a first character string similar to the character string specified by the recognition processing unit from a table in which a second character string obtained by translating the first character string into another language is associated with each of the plurality of first character strings. A selection processing unit for selecting a second character string,
The information provision system in any one of Claims 1-3 which produces | generates the content showing the 2nd character string which the said selection process part selected. The acquisition unit
A recognition processing unit for identifying a character string of pronunciation content by voice recognition for the target sound;
A translation processing unit that translates the character string identified by the recognition processing unit into another language,
The information provision system in any one of Claims 1-3 which produces | generates the content showing the process result by the said translation process part. An edit processing unit that edits the character string identified by the recognition processing unit in accordance with an instruction from the instructor;
The information providing system according to claim 5, wherein the translation processing unit translates the character string edited by the editing processing unit into another language.

Images