WO2014199602A1 - 話者識別方法、話者識別装置及び情報管理方法 - Google Patents
話者識別方法、話者識別装置及び情報管理方法 Download PDFInfo
- Publication number
- WO2014199602A1 WO2014199602A1 PCT/JP2014/002992 JP2014002992W WO2014199602A1 WO 2014199602 A1 WO2014199602 A1 WO 2014199602A1 JP 2014002992 W JP2014002992 W JP 2014002992W WO 2014199602 A1 WO2014199602 A1 WO 2014199602A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- speaker
- information
- content
- voice information
- database
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 133
- 238000007726 management method Methods 0.000 title claims description 72
- 238000004891 communication Methods 0.000 description 117
- 238000010586 diagram Methods 0.000 description 33
- 230000006870 function Effects 0.000 description 13
- 230000005236 sound signal Effects 0.000 description 8
- 239000000284 extract Substances 0.000 description 6
- 238000001514 detection method Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000003825 pressing Methods 0.000 description 3
- 239000002537 cosmetic Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 238000010187 selection method Methods 0.000 description 2
- 235000019640 taste Nutrition 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
- 230000005540 biological transmission Effects 0.000 description 1
- 238000009430 construction management Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000008685 targeting Effects 0.000 description 1
Images
Classifications
-
- 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
- G10L17/00—Speaker identification or verification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/41—Structure of client; Structure of client peripherals
- H04N21/422—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS]
- H04N21/42203—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS] sound input device, e.g. microphone
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/441—Acquiring end-user identification, e.g. using personal code sent by the remote control or by inserting a card
- H04N21/4415—Acquiring end-user identification, e.g. using personal code sent by the remote control or by inserting a card using biometric characteristics of the user, e.g. by voice recognition or fingerprint scanning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/4508—Management of client data or end-user data
- H04N21/4532—Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, preferences
Definitions
- the present invention relates to a speaker identification method for identifying a speaker, a speaker identification device, and an information management method.
- viewing content is estimated by estimating the viewer's age, sex and relationship between viewers based on temperature distribution information and voice information, and further considering the degree of matching to a place or a time zone or the like.
- the method of choice is disclosed. Thereby, it is realized to provide viewing content adapted to the viewer and the place.
- voice data of a plurality of specific speakers are registered together with speaker identification information that can identify the speakers, and the similarity between the registered voice data and the input voice data is calculated. And performing speech recognition are described.
- the present invention has been made to solve the above-mentioned problems, and it is an object of the present invention to provide a speaker identification method, a speaker identification device and an information management method capable of easily registering voice information in a database easily. It is
- a speaker identification method is a speaker identification method for identifying a speaker who is in the vicinity of a device that displays content, comprising the steps of: acquiring voice information of the speaker Determining whether the speaker corresponding to the voice information matches the speaker corresponding to the registered voice information stored in association with the content information related to the content in the database; If it is determined that the corresponding speaker matches the speaker corresponding to the registered voice information stored in the database, the content information on the content displayed on the device at the time of obtaining the voice information is Acquiring, storing the acquired content information in association with the registered voice information, and corresponding to the acquired voice information If the speaker is determined not to match the speaker corresponding to the registered voice information stored in the database, including the steps of: storing in the database the acquired voice information as the registered voice information.
- the age and gender of the viewer are estimated based on the temperature distribution information and the voice information.
- Patent Document 1 it is assumed that there is a viewer (speaker) under the assumption that the temperature of an adult male is the lowest and the temperature of an infant is the highest and the temperature of an adult woman is the temperature intermediate between an adult man and an infant.
- Age and gender are identified by examining the temperature at the location where
- the viewer (speaker) can be classified into only three categories of "adult male", “adult female” and “infant” and the viewer in more detail. It does not disclose about the method of specifying the age etc. of (speaker).
- Patent Document 1 discloses a method of estimating the age and gender of a viewer (speaker) by analyzing the spectrum and speech of a voice signal.
- this method can be classified only into rough categories such as "adult male”, “adult female” and “infant” as in the method using the temperature described above.
- the viewing content providing system described in Patent Document 1 can roughly classify viewers (speakers). That is, for example, even if a certain audience (speaker) is identified in the category of "adult male", the tastes and preferences of adult males vary, and services specific to each audience (speaker) are provided. It is difficult.
- voice data and speaker identification information are initially registered, and the similarity between the registered voice data and input voice data is calculated to perform voice recognition. There is.
- a speaker identification method is a speaker identification method for identifying a speaker who is in the vicinity of a device that displays content, comprising the steps of: acquiring voice information of the speaker Determining whether the speaker corresponding to the voice information matches the speaker corresponding to the registered voice information stored in association with the content information related to the content in the database; If it is determined that the corresponding speaker matches the speaker corresponding to the registered voice information stored in the database, the content information on the content displayed on the device at the time of obtaining the voice information is Acquiring, storing the acquired content information in association with the registered voice information, and corresponding to the acquired voice information If the speaker is determined not to match the speaker corresponding to the registered voice information stored in the database, including the steps of: storing in the database the acquired voice information as the registered voice information.
- the speaker's database can be constructed and updated without performing troublesome setting operations for the speaker. Further, since only the voice information and the content information are managed in association with each other, only the necessary database can be constructed without accumulating useless information, and the data amount of the database can be reduced.
- the content information includes the name of the content and a person's name associated with the content.
- the name of the content and the person's name associated with the content are stored in association with the registered voice information, so that the content viewed by the speaker can be managed.
- a plurality of contents associated with the registered voice information are classified into a plurality of genres, and a ratio of contents classified into each genre among the plurality of contents is calculated for each of the plurality of genres.
- the method further includes the step of storing the ratio of the content calculated for each of the plurality of genres in the database in association with the registered voice information.
- the database associates and stores content information and a service provided to a speaker who viewed the content corresponding to the content information, and the speaker corresponding to the acquired voice information Is determined to match the speaker corresponding to the registered voice information stored in the database, the content information stored in association with the registered voice information is identified, and the identified content information is identified
- the method further includes the steps of identifying an associated service and providing the identified service to the speaker.
- the speaker can confirm the available services.
- the method further comprises the step of storing in the database.
- the speaker since the service selected by the speaker from among the displayed at least one service candidate is provided to the speaker, the speaker can select a desired service. Also, since the provided service is stored in the database in association with the registered voice information, the service provided to the speaker can be managed.
- the service includes a service that distributes content to be displayed on the device, or a service that distributes an advertisement to be displayed on the device.
- the speaker with a service for distributing the content to be displayed on the device or a service for distributing the advertisement to be displayed on the device.
- a speaker identification device is a speaker identification device for identifying a speaker, and includes a display unit for displaying content and voice information of a speaker who is around the speaker identification device.
- a speaker corresponding to the voice information acquired by the voice acquisition unit a database for storing a voice acquisition unit to be acquired, registered voice information as registered voice information, and content information related to content in association with each other;
- a determination unit which determines whether or not the speaker matches the speaker corresponding to the registered voice information stored in association with the content information in the database; and the speaker corresponding to the voice information acquired by the determination unit If it is determined that the speaker matches the speaker corresponding to the registered voice information stored in the database, it is displayed on the display unit when the voice information is acquired.
- a database updating unit that acquires content information related to the content and stores the acquired content information in association with the registered voice information; and a speaker corresponding to the voice information acquired by the determination unit is stored in the database
- a database storage unit that stores voice information acquired by the voice acquisition unit as registered voice information in the database when it is determined that the voice information does not match the speaker corresponding to the stored registered voice information.
- the speaker's database can be constructed and updated without performing troublesome setting operations for the speaker. Further, since only the voice information and the content information are managed in association with each other, only the necessary database can be constructed without accumulating useless information, and the data amount of the database can be reduced.
- An information management method is an information management method in a speaker identification system for identifying a speaker who is in the vicinity of a device displaying content, the method including the step of receiving voice information of the speaker Determining whether a speaker corresponding to the received voice information matches a speaker corresponding to registered voice information stored in association with content information related to content in the database; If it is determined that the speaker corresponding to the voice information matches the speaker corresponding to the registered voice information stored in the database, the content displayed on the device when the voice information is acquired Acquiring content information related to the content information, and storing the received content information in association with the registered voice information; If it is determined that the speaker corresponding to the received voice information does not match the speaker corresponding to the registered voice information stored in the database, the received voice information is registered in the database as registered voice information. And storing.
- the database can be constructed and updated without performing troublesome setting operations for the speaker. Further, since only the voice information and the content information are managed in association with each other, only the necessary database can be constructed without accumulating useless information, and the data amount of the database can be reduced.
- FIG. 1 is a diagram showing an entire configuration of a speaker identification system according to a first embodiment of the present invention.
- the configuration shown in FIG. 1 is an example, and the speaker identification system may have a configuration other than the configuration shown in FIG. Also, the speaker identification system may lack some of the configurations shown in FIG.
- the speaker identification system includes a server device 100 and a speaker identification device 110.
- the speaker identification device 110 is, for example, a content viewing device such as a television or a personal computer installed in each home. As shown in FIG. 1, the server device 100 and the speaker identification device 110 installed in each home are communicably connected to each other via the network 120.
- one speaker identification device 110 may be connected to the server device 100, and a plurality of speaker identification devices 110 may be connected to the server device 100. Also, a plurality of speaker identification devices 110 may be arranged in each home. Also, the network 120 is, for example, the Internet.
- the place where the server apparatus 100 is disposed is not particularly limited.
- the server apparatus 100 may be disposed at a data center that handles big data, or may be disposed at each home.
- the data center is owned by a company that manages and operates the data center. Further, each configuration of the server apparatus 100 may be integrated in one apparatus or may be arranged in different apparatuses.
- the server apparatus 100 includes a control unit 101, a communication unit 102, a program information database (DB) 103, a service information database (DB) 104, and a family database (DB) 105.
- the program information DB 103 and the service information DB 104 are a common database (DB) common to all homes.
- the family database (DB) 105 is an individual database (DB) constructed for each home.
- the control unit 101 is a component that performs various controls related to the server device 100, and is not particularly limited.
- the control unit 101 includes, for example, a CPU (central processing unit).
- the communication unit 102 is a component for connecting to the network 120, and is not particularly limited. The connection to the network 120 does not matter.
- the program information database 103 and the service information database 104 which are common databases are databases referred to by all the speaker identification devices 110.
- the program information database 103 and the service information database 104 are recording devices capable of storing a large amount of information.
- the program information database 103 and the service information database 104 may be stored in the same device, or may be stored in separate devices.
- the program information database 103 stores, for example, program information (program name, broadcast time, genre, performers, etc.) related to a television program.
- the server apparatus 100 may acquire program information on a television program from an external server apparatus.
- Television programs are provided by terrestrial digital broadcast waves or satellite broadcast waves.
- the content that the user (speaker) views and listens to is not limited to a television program, but may be content acquired via the Internet.
- the service information database 104 stores information on services to be provided to the speaker.
- the family database 105 and the family database 106 which are individual databases are constructed separately for each home.
- the family database 105 is referenced only from the speaker identification device 110 corresponding to each database.
- the family database 105 is a recording device capable of accumulating a large amount of information as the common database.
- the family database 105 corresponds to the speaker identification device 110 in the home A shown in FIG. 1
- the family database 106 corresponds to the speaker identification device 110 in the home B shown in FIG.
- Each family database may be stored in the same device or may be stored in separate devices.
- the speaker identification device 110 includes a control unit 111, a communication unit 112, a voice acquisition unit 113, and a display unit 114. Note that these configurations may be incorporated as part of the configuration of the content viewing device, or may be included in an apparatus connected to the outside of the content viewing device.
- the speaker identification device 110 may have any of the above-described configurations, and may be, for example, a television for home use, a PC (personal computer), a smartphone, a tablet computer, a mobile phone, or the like. Also, the speaker identification device 110 may be a dedicated device for performing a speaker identification system.
- control unit 111 and the communication unit 112 have the same configuration as the control unit 101 and the communication unit 102 of the server apparatus 100, and thus the description thereof will be omitted.
- the voice acquisition unit 113 is a voice recording device provided with a microphone.
- the display unit 114 is a device having a display function by a monitor or the like.
- FIG. 1 illustrates a speaker identification system described below by the speaker identification device 110 and the server device 100
- the present invention is not limited to this.
- part or all of the configuration of the server apparatus 100 may be included in the speaker identification device 110, or the speaker identification system may be configured with only the speaker identification device 110.
- FIG. 2 is a block diagram showing the configuration of the speaker identification system in the first embodiment.
- the speaker identification system includes a voice acquisition unit 201, a viewing content information acquisition unit 202, and a database management unit 203.
- the speech acquisition unit 201 acquires speech information in a format that can be analyzed for speaker identification.
- the voice information in a format that can be analyzed may be a sound including the voice of one speaker.
- the voice acquisition unit 201 may remove noise from the voice information if the voice information includes noise other than human voice. Further, the timing of acquiring the audio information and the time length of the acquired audio information are not particularly limited.
- the voice acquisition unit 201 may always obtain voice information or may obtain voice information at preset time intervals. Further, the voice acquisition unit 201 may obtain voice information only when a person is producing a voice.
- the voice acquisition unit 201 automatically detects a voice section, and as a result of analyzing the obtained voice information, outputs voice information that can be identified to the database management unit 203.
- the viewing content information acquisition unit 202 acquires viewing content information on the content that the speaker is viewing at the timing when the voice acquisition unit 201 acquires the voice information.
- the viewing content information includes, for example, the genre of the content, the broadcast time, the cast, the viewing time, and the like.
- the viewing content information may include other information that can be acquired from the content providing source or the content viewing device.
- the viewing content information acquisition unit 202 outputs the acquired viewing content information to the database management unit 203.
- the database management unit 203 constructs and manages the family database 105 using the voice information acquired by the voice acquisition unit 201 and the viewing content information acquired by the viewing content information acquisition unit 202.
- the family database 105 associates and stores registered voice information, which is voice information acquired in the past, and a history of viewing content information of a speaker corresponding to the registered voice information.
- the registered voice information is registered as a WAV format file.
- the registered voice information may not necessarily be a WAV format file.
- the registered voice information may be voice-compressed data such as MPEG format or AIFF format.
- the registered voice information is automatically encoded, for example, into a compressed file and stored in the family database 105.
- the database management unit 203 may store the viewing content information acquired by the viewing content information acquisition unit 202 as it is in the family database 105, or the viewing content information acquired by the viewing content information acquisition unit 202 may be stored in the internal memory. After being accumulated, analyzed and classified, the analyzed and classified viewing content information may be accumulated in the family database 105. The information accumulated in the family database 105 will be described later.
- the database management unit 203 determines whether the speaker corresponding to the voice information acquired by the voice acquisition unit 201 matches the speaker corresponding to the registered voice information stored in the family database 105 in association with the viewing content information. To judge. When it is determined that the speaker corresponding to the acquired voice information matches the speaker corresponding to the registered voice information stored in the family database 105, the database management unit 203 displays the display unit when the voice information is acquired. Viewing content information on the content displayed in 114 is acquired, and the acquired viewing content information is stored in association with the registered voice information. When it is determined that the database management unit 203 does not match the speaker corresponding to the acquired voice information with the speaker corresponding to the registered voice information stored in the family database 105, the database management unit 203 is acquired by the voice acquisition unit 201. Voice information is stored in the family database 105 as registered voice information.
- FIG. 3 is a flowchart showing the operation of the speaker identification system in the first embodiment of the present invention.
- the family database update method by the speaker identification system according to the first embodiment will be described with reference to FIG. Note that the processing of the flowchart is continuously performed, and the processing of the flowchart is repeated at the time of voice acquisition.
- the speech acquisition unit 201 acquires speech information of a speaker (step S1).
- step S2 based on the result of analyzing (not shown) the acquired voice information, the database management unit 203 matches the acquired voice information with the registered voice information accumulated in the family database 105 in the past? It is determined whether or not it is (step S2). Here, if it is determined that the acquired voice information matches the registered voice information, the process proceeds to step S3. If it is determined that the acquired voice information does not match the registered voice information, the process proceeds to step S5. move on. When the present speaker identification system is used for the first time, there is no family DB, so the process proceeds to step S5.
- the method of comparing the acquired voice information and the registered voice information is not particularly limited.
- the database management unit 203 obtains a speaker model from the obtained voice information, and determines the obtained speaker model by comparing the obtained speaker model with the speaker model of the registered voice information.
- the speaker model is information required to identify a speaker, which is calculated from characteristics unique to an individual such as frequency characteristics of acquired voice information.
- the database management unit 203 may create a speaker model by calculating a normal distribution from frequency characteristics.
- the speaker model may be any information for specifying a speaker, and may be other characteristics that can be acquired from voice information or other information that can be calculated from them.
- the database management unit 203 determines whether the acquired voice information matches the registered voice information stored in the family database 105 in the past, thereby to speak the story corresponding to the acquired voice information. It can be determined whether or not the speaker matches the speaker corresponding to the registered voice information stored in the family database 105 in association with the viewing content information.
- the viewing content information acquisition unit 202 views the viewing content information related to the content currently being viewed by the speaker by the speaker identification device 110. Are acquired from the program information database 103 (step S3).
- the database management unit 203 stores the viewing content information acquired by the viewing content information acquisition unit 202 in association with the registered voice information stored in the family database 105 (step S4). This rebuilds the family database.
- the database management unit 203 stores the newly acquired viewing content information in addition to the viewing content already stored.
- the database management unit 203 registers (stores) the acquired voice information in the family database 105 as registered voice information. (Step S5). At this time, the database management unit 203 may store a speaker model created from the acquired voice information as registered voice information.
- the above process is repeated at regular intervals, and updating of the family database 105 is repeated, whereby a database with high accuracy is constructed.
- FIG. 4 is a sequence diagram showing an example of the operation of the speaker identification system according to Embodiment 1 of the present invention.
- the voice acquisition unit of the speaker identification device 110 speaks.
- the step 113 detects that there is an utterance and acquires voice information of the speaker (step S11).
- control unit 111 analyzes the voice information acquired by the voice acquisition unit 113 (not shown), and the communication unit 112 transmits the voice information analyzed by the control unit 111 to the server device 100.
- the voice analysis process may be performed by the control unit 111 of the speaker identification device 110 or may be performed by the control unit 101 of the server device 100.
- the communication unit 102 of the server device 100 receives the voice information transmitted by the speaker identification device 110.
- the control unit 101 of the server device 100 registers the received voice information in the family database using the voice information received by the communication unit 102 and the family database 105 corresponding to the home A of the server device 100.
- the voice information is compared (step S13).
- the control unit 101 determines whether the received voice information matches the registered voice information in the family database. Thus, it can be determined whether the speaker whose speech has been detected is a speaker whose voice information has already been registered.
- the method of determining whether the received voice information matches the registered voice information is the same as the method described in step S2 of FIG.
- each family database is managed in association with a device ID for identifying the speaker identification device 110, and This can be determined by adding the device ID. That is, the family database is provided for each device ID for identifying the speaker identification device 110, the speaker identification device 110 adds the device ID to the voice information and transmits it, and the server device 100 receives the device Read the family database corresponding to the ID.
- the family database may be provided for each viewer ID for identifying a viewer, and the speaker identification device 110 may add the viewer ID to the voice information and transmit it, and the server apparatus 100 May read out a family database corresponding to the received viewer ID.
- the control unit 101 may compare the acquired voice information with all registered voice information of a plurality of family databases.
- control unit 101 causes the viewer (speaker) in the home A to view when the voice information is acquired.
- Viewing content information related to the content (program) being acquired is acquired from the program information database 103 in the server apparatus 100 (step S14).
- the method by which the control unit 101 of the server apparatus 100 identifies the program being viewed by the viewer (speaker) is not limited.
- the control unit 101 may sequentially request the speaker identification device 110 to transmit program identification information capable of identifying a viewed program such as a channel number.
- the speaker identification device 110 may transmit program identification information such as a viewing channel together with the voice information, and the control unit 101 selects viewing content information corresponding to the received program identification information as a program information database. You may acquire from 103.
- control unit 101 builds and updates the family database 105 for each viewer (speaker) based on the acquired viewing content information (step S15).
- FIG. 5 is a diagram showing an example of a data structure of a family database according to Embodiment 1 of the present invention.
- the control unit 101 selects the content that was being viewed when the voice information was acquired.
- Viewing content information such as genre, main performers and broadcast time is stored in a family database, and the family database is updated.
- each registration voice information stored in the WAV format is associated with view content information including a broadcast start date and time of a content viewed by a speaker corresponding to the registration voice information, a program name and a cast.
- the family database may manage the registered voice information in association with the viewing content information on the content viewed by the speaker as it is.
- the viewing content information may include the name of the content and the name of a person associated with the content, and may not include the broadcast date and time.
- FIG. 6 is a diagram showing another example of the data structure of the family database in the first embodiment of the present invention.
- the result of analysis of the content viewed by the speaker corresponding to the registered voice information in the past is associated with each registered voice information stored in the WAV format as the viewed content information and managed.
- the control unit 101 calculates and manages the ratio of the genre, the performers, and the viewing time zone in the content that the speaker has viewed in the past.
- the control unit 101 classifies the plurality of contents associated with the registered voice information into a plurality of genres, calculates the ratio of the contents classified into each genre among the plurality of contents for each of the plurality of genres, The ratio of content calculated for each genre may be associated with registered voice information and stored in the family database.
- control unit 101 extracts performers associated with each of a plurality of contents associated with the registered voice information, counts the number of extracted performers of each performer, and is associated with the registered voice information.
- the ratio of the number of extractions of each performer to the number of all contents may be calculated, and the ratio of the number of extractions of performer calculated for each performer may be stored in the family database in association with the registered voice information.
- control unit 101 classifies the plurality of contents associated with the registered voice information into a plurality of viewing time zones, and the contents classified into each viewing time zone among the plurality of contents for each of a plurality of viewing time zones
- the ratio of content calculated for each of a plurality of viewing time zones may be associated with registered voice information and stored in the family database.
- the viewing time zones are classified into, for example, four time zones: morning, noon, night and late night.
- control unit 101 extracts text information from the voice information, and based on the extracted text information
- the speaker may be determined by analyzing the contents of the statement.
- the control unit 101 may also determine the speaker by comparing the acquired viewing content information with the viewing content information stored in the family database.
- the control unit 101 does not update the family database at that time, and stores the acquired voice information in the internal memory. You may accumulate. Then, the control unit 101 newly creates, as registered voice information, voice information determined to be the same person among a plurality of voice information stored in the memory, for example, every week, and stores it in the family database. (Registration) may be performed.
- the communication unit 102 may transmit the updated information of the constructed family database to the speaker identification device 110 (step S16).
- the communication unit 112 of the speaker identification device 110 receives the update information of the family database transmitted by the server device 100.
- the display unit 114 of the speaker identification device 110 may display the updated content of the family database based on the received updated information of the family database (step S17).
- the display unit 114 may display part or all of the updated family database.
- the processes of step S16 and step S17 are not essential processes.
- FIG. 7 is a diagram showing an example of the updated content of the family database displayed on the speaker identification device
- FIG. 8 is a diagram showing another example of the updated content of the family database displayed on the speaker identification device is there.
- the display unit 114 may display only the viewing content information corresponding to the user to which the viewing content information has been added. Further, as shown in FIG. 7, the display unit 114 may display the viewing content information as it is. In addition, as shown in FIG. 8, the display unit 114 may display, as viewing content information, a result of analysis of the content that the speaker corresponding to the registered voice information has viewed in the past. In the example illustrated in FIG. 8, the display unit 114 displays the genre, the performers, and the ratio of the viewing time zone in the content that the speaker viewed in the past.
- the timing for displaying the updated content of the family database may be the timing when the family database 105 (106) is updated, or may be timing when the user has instructed to display the updated content of the family database.
- the user can grasp the acquired viewing content information.
- the speaker identification device 110 can further improve the accuracy of the family database by having a function of correcting the erroneous information by some operation when there is an error in the information stored in the family database. it can.
- the speaker identification device 110 may perform the processing of step S13 and step S15 of FIG.
- the speaker identification device 110 may include a family database 105.
- FIG. 9 is a sequence diagram showing another example of the operation of the speaker identification system in the first embodiment of the present invention.
- step S21 the voice acquisition unit 113 of the speaker identification device 110 detects that there is an utterance and obtains voice information of the speaker (step S21).
- the process of step S21 is the same as the process of step S11 of FIG. 4.
- control unit 111 uses the voice information acquired by the voice acquisition unit 113 and the family database 105 corresponding to the home A of the speaker identification device 110 to register the acquired voice information in the family database.
- the information is compared (step S22).
- the process of step S22 is the same as the process of step S13 of FIG.
- the communication unit 112 requests the server device 100 to view content information (step S23).
- control unit 101 of the server device 100 selects viewing content information on the content (program) that the viewer (speaker) in the home A is watching at the time when the voice information is acquired, in the server device 100. It acquires from the information database 103 (step S24).
- the process of step S24 is the same as the process of step S14 of FIG.
- the communication unit 102 transmits the acquired viewing content information to the speaker identification device 110 (step S25).
- the communication unit 112 of the speaker identification device 110 receives the viewing content information transmitted by the server device 100.
- control unit 111 constructs and updates the family database 105 for each viewer (speaker) based on the received viewing content information (step S26).
- the process of step S26 is the same as the process of step S15 of FIG.
- step S27 the display unit 114 of the speaker identification device 110 may display the updated contents of the family database (step S27).
- the process of step S27 is the same as the process of step S17 of FIG.
- the family database can be constructed and updated without performing troublesome setting operations for the user.
- only the audio information and the viewing content information are associated with each other and managed, only the necessary database can be constructed without accumulating unnecessary information, and the data amount of the database can be reduced.
- the optimum content can be provided to the user who is watching or the optimum content without acquiring useless information such as the user's age and the user's gender. It can be recommended.
- personal information such as the user's name, age, and gender is not acquired, the user can use the speaker identification system with confidence.
- the database management unit 203 acquires Although voice information is registered in the family database, the present invention is not particularly limited thereto.
- the database management unit 203 acquires voice information of the speaker continuously during a predetermined time (period), and it is determined that the voice information acquired in step S2 does not match the registered voice information of the family database.
- the number of times may be counted, and the process of step S5 may be performed only when the counted number exceeds a predetermined number. This makes it possible to suppress an increase in data and noise that does not need to be acquired in the family database.
- control unit 101 may delete the registered voice information from the family database when the voice information matching the registered voice information is not acquired for a predetermined period or more. Thereby, even if voice information of a person other than a family member is registered in the family database, it can be automatically deleted.
- FIG. 10 is a block diagram showing a configuration of a speaker identification system according to Embodiment 2 of the present invention.
- the speaker identification system includes a voice acquisition unit 201, a viewing content information acquisition unit 202, a database management unit 203, and a service providing unit 204.
- FIG. 10 the same components as those of the speaker identification system shown in FIG.
- the configurations of the voice acquisition unit 201 and the viewing content information acquisition unit 202 are the same as in the first embodiment, and thus the description thereof is omitted.
- the database management unit 203 constructs a family database based on the acquired voice information and the viewing content information. Furthermore, in the second embodiment, the database management unit 203 outputs the voice information and the viewing content information stored in the family database to the service providing unit 204. In addition, the database management unit 203 acquires information on a service provided to the user from the service providing unit 204 described later, and stores the information in association with the registered voice information. In addition, the database management unit 203 may manage a database that stores information related to service candidates to be provided in association with television content.
- the service providing unit 204 provides a service suitable for the preference of the viewer (speaker) when a predetermined service providing condition is satisfied, based on the acquired voice information and the viewing content information.
- the service is a service for recommending content such as viewable television programs or a service for distributing advertisements.
- the service providing unit 204 may provide other services that can be analogized from the viewing content information.
- the service is provided to the display unit 114 at the serviceable timing. Also, when a service is presented, a plurality of available service candidates may be presented and selected by the viewer (speaker).
- the candidate for the service to be provided may be acquired from a database managed by the database management unit 203.
- the service database (not shown) associates and stores viewing content information and a service provided to a speaker who has viewed content corresponding to the viewing content information.
- the viewing content information stored in the service database is, for example, the name of the content.
- the service providing unit 204 is stored in association with the registered voice information.
- the present content information is identified, the service associated with the identified content information is identified, and the identified service is provided to the speaker.
- the service providing unit 204 determines whether there is at least one service that can be provided and that it is a predetermined service providing timing. Then, when it is determined that there is a service that can be provided, and it is determined that it is a predetermined service provision timing, the service providing unit 204 displays the candidate of at least one service that can be provided on the speaker identification device 110 Let
- the service providing unit 204 provides the speaker with a service selected by the speaker from among the displayed at least one service candidate.
- the database management unit 203 stores the provided service in the family database in association with the registered voice information.
- the service includes a service for distributing content to be displayed on the speaker identification device 110 or a service for distributing an advertisement to be displayed on the speaker identification device 110.
- FIG. 11 is a flowchart showing the operation of the speaker identification system in the second embodiment of the present invention.
- a service providing method by the speaker identification system according to the second embodiment will be described with reference to FIG. Note that the processing of the flowchart is continuously performed, and the processing of the flowchart is repeated at the time of voice acquisition.
- step S31 and step S32 in FIG. 11 are the same as the processes in step S1 and step S2 in FIG. Further, when it is determined that the voice information acquired in step S32 does not match the registered voice information, the process of step S33 of registering the acquired voice information in the family database is the same as the process of step S5 of FIG. Therefore, the explanation is omitted.
- the viewing content information acquisition unit 202 When it is determined that the acquired voice information matches the registered voice information of the family database (YES in step S32), the viewing content information acquisition unit 202 relates to the content currently being viewed by the speaker by the speaker identification device 110. Viewing content information is acquired from the program information database 103 (step S34). The process of step S34 is the same as the process of step S3 of FIG.
- the service providing unit 204 acquires at least one service candidate to be provided from the database management unit 203 (step S35).
- the at least one service candidate to be provided is, for example, at least one service associated with the viewing content information corresponding to the registered voice information that matches the acquired voice information. That is, at this point in time, at least one service candidate to be acquired is associated with the viewing content information, and therefore, is narrowed down to one that matches the preference of the viewer (speaker).
- the service providing unit 204 determines whether the service providing condition is satisfied (step S36). If it is determined that the service providing condition is satisfied, the process proceeds to step S34. If it is determined that the service providing condition is not satisfied, the process proceeds to step S40.
- the service providing condition is a determination as to whether or not there is a service that can be provided, and a determination as to whether it is time to provide a predetermined service. The determination as to whether or not there is a service that can be provided is whether or not at least one service candidate has been acquired in step S35. For example, depending on the content being viewed, there is a possibility that service candidates are not associated. In that case, the process proceeds to step S40.
- the determination as to whether or not it is the timing to provide the service may be, for example, the provision of the service such as the timing when the power of the speaker identification device 110 is turned on or the timing when the content being watched Is the timing that does not disturb the viewing of the content. If it is the timing to inhibit viewing of the content, the process proceeds to step S40.
- the timing of service provision may be intentionally selected by the viewer (speaker) or may be automatically determined by the speaker identification system.
- the service providing unit 204 displays at least one service candidate on the display unit 114 in a selectable state (step S37).
- the display method may be displayed so as not to disturb viewing of the currently displayed content, or may be switched from the currently displayed content to display service candidates. A display example of service candidates will be described later.
- the service providing unit 204 provides the selected service (step S38).
- the process may proceed to step S40.
- the database management unit 203 associates the information on the selected service with the registered voice information and adds it to the family database (step S39).
- step S40 the database management unit 203 stores the viewing content information acquired by the viewing content information acquisition unit 202 in association with the registered voice information stored in the family database (step S40). This rebuilds the family database.
- the process of step S40 is the same as the process of step S4 in FIG.
- FIG. 12 is a sequence diagram showing an example of the operation of the speaker identification system in the second embodiment of the present invention.
- the description of the same processing as the speaker identification system in the first embodiment shown in FIG. 4 is omitted.
- the processes in steps S51 to S54 in FIG. 12 are the same as the processes in steps S11 to S14 in FIG.
- the voice information of the viewer (speaker) in home A in FIG. 1 is matched with the voice information of the existing speaker in family database 105 by comparing it with the registered voice information in family database 105. Then, the case where it is determined will be described.
- the control unit 101 of the server device 100 acquires at least one service candidate to be provided from the service information database 104 based on the viewing content information in the family database 105 (step S55).
- the method of acquiring the provided service candidate will be described.
- FIG. 13 is a diagram showing an example of a data structure of a family database according to Embodiment 2 of the present invention. As shown in FIG. 13, in the family database 105 according to the second embodiment, viewing voice information and a history of services (service selection history) selected in the past by the speaker are associated with registered voice information. It has been accumulated.
- FIG. 14 is a diagram showing an example of a data structure of a service information database according to Embodiment 2 of the present invention.
- candidates for the provided service are stored in association with the name of the content.
- one service candidate is not necessarily associated with one content name, and a plurality of service candidates may be associated with one content name.
- the control unit 101 compares the content name included in the viewing content information associated with the registered voice information “0001. wav” with the content name in the service information database 104.
- the control unit 101 searches the content name in the service information database 104 for a content name that matches the content name included in the viewing content information associated with the registered voice information “0001. wav”.
- the control unit 101 acquires, from the service information database 104, a candidate for a provided service corresponding to the matching content name.
- candidates for services content provision or advertisement provision
- the method of acquiring service candidates is not limited to this.
- the cast and the provided service candidate may be managed in association with each other.
- candidates for a service providing content or providing an advertisement related to a performer interested in the speaker are selected.
- FIG. 15 is a diagram showing another example of the data structure of the service information database according to the second embodiment of the present invention.
- candidates for provided services are stored in association with the genre of content. .
- the control unit 101 specifies the genre of the content most viewed in the past by using the viewing content information associated with the registered voice information determined to be identical to the acquired voice information, and the service From the genres in the information database 104, a genre that matches the specified genre is searched. If there is a matched genre, the control unit 101 acquires, from the service information database 104, a candidate for provided service corresponding to the matched genre. As a result, candidates for services (providing content or providing advertisements) related to the genre of the content of interest to the speaker are selected.
- the voice information is not acquired, if there is information of a service that can be provided based on the viewing content information in the family database 105, the provided service candidate in the service information database 104 may be updated.
- the communication unit 102 of the server apparatus 100 transmits service information indicating at least one acquired service candidate to the television serving as the speaker identification device 110 (step S56).
- the communication unit 112 of the speaker identification device 110 receives the service information transmitted by the server device 100.
- the control unit 111 of the speaker identification device 110 determines whether it is the timing at which service can be provided, and when it is determined that the timing is at which the service can be provided, the display unit 114 of the speaker identification device 110 Displays the service candidate (step S57).
- the display unit 114 displays, for example, the current viewing position of the viewer (speaker), such as the timing immediately after the television is turned on, the timing when the program guide is displayed, or the timing immediately after some operation on the television is performed. Display candidate services at timings that are not concentrated on content and are likely to be appropriate for selecting a service or changing the content being viewed.
- control unit 101 of the server apparatus 100 may determine whether it is a serviceable timing, or whether the control unit 111 of the speaker identification device 110 may be a serviceable timing. You may decide Then, the input receiving unit (not shown) of the speaker identification device 110 receives the selection of one service by the viewer (speaker) from among the displayed at least one service candidate.
- FIG. 16 is a diagram showing an example of a selection screen for selecting service candidates in the second embodiment of the present invention.
- the display unit 114 displays the acquired available service (advertisement delivery) candidate.
- FIG. 16 illustrates an example in which a plurality of advertisements are displayed in association with the color of the button on the remote control.
- the viewer can select the desired service (delivery of advertisement) by pressing the button of the remote control corresponding to the desired service (delivery of advertisement).
- a desired operation may be performed by selecting a service from the service display portion, and a viewer (speaker) who views the service voluntarily performs those operations. May be
- FIG. 17 is a diagram showing another example of the selection screen for selecting service candidates in the second embodiment of the present invention.
- the display unit 114 displays the acquired available service (reproduction of content) candidates.
- FIG. 17 shows an example in which content (program) recommended to a viewer (speaker) is displayed, for example.
- the viewer (speaker) can select the desired service (reproduction of content) by pressing the button of the remote control corresponding to the desired service (reproduction of content).
- the control unit 111 of the speaker identification device 110 provides the selected service (step S58). That is, the control unit 111 causes the display unit 114 to display the selected service. For example, if the selected service is a content for reproducing program content, the control unit 111 reproduces the selected content. If the content to be reproduced is stored in the speaker identification device 110, the control unit 111 reads and reproduces the stored content. In addition, if the content to be reproduced is not stored in the speaker identification device 110 but is stored in the server device 100, the control unit 111 acquires the content from the server device 100 and reproduces the acquired content. Do. In addition, if the selected service is a service that delivers an advertisement, the control unit 111 causes the web page of the selected advertisement to be displayed via the network.
- the selected service is a service that delivers an advertisement
- the communication unit 112 transmits service selection information on the selected service to the server device 100 (step S59).
- the service selection information includes, for example, the date and time when the content was reproduced, the name of the reproduced content, and the performer of the reproduced content.
- the communication unit 102 of the server device 100 receives the service selection information transmitted by the speaker identification device 110.
- control unit 101 of the server device 100 updates the family database 105 based on the acquired viewing content information and the received service selection information (step S60).
- the control unit 101 updates the viewing content information in association with the registered voice information, and also updates the service selection information selected by the viewer (speaker).
- the control unit 101 updates the service selection history in association with the registered voice information.
- the communication unit 102 may transmit the updated information of the constructed family database to the speaker identification device 110 (step S61).
- the communication unit 112 of the speaker identification device 110 receives the update information of the family database transmitted by the server device 100.
- the display unit 114 of the speaker identification device 110 may display the updated content of the family database based on the received updated information of the family database (step S62).
- the display unit 114 may display part or all of the updated family database.
- the processes of step S61 and step S62 are not essential processes.
- the family database can be constructed without requiring the user to perform troublesome setting operations.
- Providing a more optimal service to the speaker since information on the preference of the speaker corresponding to the registered voice information can be stored by selecting the optimal service from among at least one service candidate. Can.
- WO 01/089216 discloses an advertisement distribution method and an advertisement distribution apparatus for transmitting advertisement data to a receiver of each registered viewer.
- the conventional advertisement distribution apparatus receives, on the transmission side, data characterizing the audience from each registered viewer, receives data characterizing the audience targeting the advertisement data, associates it with the advertisement data, and is registered.
- the advertisement data to be transmitted to the receiver of the viewer based on the degree of matching between the data characterizing the viewer layer of the viewer and the data characterizing the audience targeted by the advertisement
- the advertisement data assigned to the viewer is transmitted to the receiver of the viewer for each of the registered viewers selected from among the above and assigned to the viewer.
- advertisement data distribution is controlled based on the degree of agreement between data characterizing the audience targeted by the advertisement and data characterizing only the already registered viewer. Ru. Therefore, when the contents of registration change, for example, the family configuration of the viewer changes, it is necessary to voluntarily change the registration contents. In addition, there is a problem that it is not possible to receive an appropriate advertisement because it is impossible to judge the degree of coincidence with the data characterizing the audience targeted by the advertisement if the data characterizing the audience demographic of the audience is forgotten. doing.
- a speaker identification method is a speaker identification method for identifying a speaker, which includes the steps of acquiring voice information of the speaker, and a speaker corresponding to the acquired voice information. Determining whether the database corresponds to the speaker corresponding to the registered voice information stored in association with the speaker information on the speaker in the database; and the speaker corresponding to the acquired voice information is the database Accepting the input of the speaker information by the speaker when it is determined that the speaker does not match the speaker corresponding to the registered voice information stored in the database; and the database including the acquired voice information as registered voice information And storing the received speaker information in the database in association with the registered voice information.
- the voice information of the speaker is acquired to identify the speaker, and when a new speaker not registered in the database is identified, the user is prompted to register the speaker information to be associated with the new speaker in the database.
- the registered speaker information is registered in the database. Therefore, a new speaker can be registered in the database without performing troublesome setting operations for the speaker.
- the step of distributing the content according to the speaker information since the content corresponding to the speaker information is distributed, it is possible to provide the speaker with appropriate content.
- the speaker information includes at least one of the speaker's age and the speaker's gender.
- content can be provided according to at least one of the speaker's age and gender.
- a speaker identification device is a speaker identification device for identifying a speaker, and a voice acquisition unit for obtaining voice information of a speaker who is around the speaker identification device;
- a database for storing registered voice information, which is voice information, and speaker information on a speaker in association with each other, and a speaker corresponding to the voice information acquired by the
- a determination unit which determines whether or not the speaker corresponds to the registered voice information stored in association with the personal information, and the speaker corresponding to the acquired voice information is stored in the database
- the database includes the input reception unit for receiving the input of the speaker information by the speaker, and the acquired voice information as registered voice information.
- the voice information of the speaker is acquired to identify the speaker, and when a new speaker not registered in the database is identified, the user is prompted to register the speaker information to be associated with the new speaker in the database.
- the registered speaker information is registered in the database. Therefore, a new speaker can be registered in the database without performing troublesome setting operations for the speaker.
- An information management method is an information management method in a speaker identification system for identifying a speaker, comprising the steps of: receiving voice information of the speaker; and corresponding to the received voice information Determining whether the target speaker matches the speaker corresponding to the registered voice information stored in the database in association with the speaker information related to the speaker, and the speech corresponding to the received voice information Sending input prompting information prompting the speaker to input speaker information if it is determined that the speaker does not match the speaker corresponding to the registered voice information stored in the database; Receiving the speaker information input by the speaker according to the input promotion information; storing the received voice information as registered voice information in the database; It has been the talker information in association with the registered voice information; and a step of storing in the database.
- the voice information of the speaker is acquired to identify the speaker, and when a new speaker not registered in the database is identified, the user is prompted to register the speaker information to be associated with the new speaker in the database.
- the registered speaker information is registered in the database. Therefore, a new speaker can be registered in the database without performing troublesome setting operations for the speaker.
- a content providing system for providing appropriate content in accordance with viewer information on a viewer
- various types of content are provided according to the viewer in front of a television (hereinafter also referred to as a terminal device). It shows about the content provision system implemented via communication lines, such as the internet.
- FIG. 18 is a diagram showing an overall configuration of a content providing system according to Embodiment 3 of the present invention.
- the content providing system 400 includes a voice acquisition unit 401, a speaker identification unit 402, a viewer configuration management unit 403, an information input unit 404, a content distribution control unit 405, a content distribution unit 406, and a display unit 407. Equipped with
- the voice acquisition unit 401 obtains a voice signal (voice information) of a viewer (speaker).
- the speaker identifying unit 402 identifies the speaker from the voice information acquired by the voice acquiring unit 401.
- the speaker identifying unit 402 determines whether the speaker corresponding to the acquired voice information matches the speaker corresponding to the registered voice information stored in the database in association with the speaker information on the speaker. Do.
- the speaker information includes, for example, at least one of the speaker's age and the speaker's gender.
- the viewer configuration management unit 403 manages viewer configuration information using the identification information acquired from the speaker identification unit 402, and when it is determined to be a new viewer, prompts the user to input information related to the new viewer. It receives input information and manages the viewer configuration.
- the information input unit 404 receives an input of information from the viewer. When it is determined that the speaker corresponding to the acquired voice information does not match the speaker corresponding to the registered voice information stored in the database, the information input unit 404 accepts the input of the speaker information by the speaker .
- the viewer configuration management unit 403 stores the acquired voice information as registered voice information in the database, and stores the received speaker information in the database in association with the registered voice information.
- the content delivery control unit 405 controls delivery of content according to the viewer composition information managed by the viewer configuration management unit 403.
- the content distribution unit 406 is controlled by the content distribution control unit 405, and distributes content according to the viewer configuration information.
- the content distribution unit 406 distributes content according to the speaker information.
- the display unit 407 prompts input of information on the viewer and displays the distributed content.
- the content providing system 400 does not necessarily have to include all of these configurations, and some configurations may be missing.
- the content providing system 400 can be divided into, for example, a terminal device on the viewer side and a server device for distributing content.
- a microphone disposed in a television as an example of a terminal device
- a central processing unit CPU
- ROM read only memory
- various communication ICs Integrated Circuits
- each unit of the server device is realized by hardware such as a CPU configuring a computer, a ROM storing a control program, and an IC for various communications.
- FIG. 19 is a block diagram showing a configuration of a content providing system according to Embodiment 3 of the present invention.
- the content providing system 500 in FIG. 19 shows an example of the configuration of the content providing system 400 in FIG.
- the content providing system 500 and the content providing system 400 are the same system, but are represented by different codes for convenience.
- the content providing system 500 shown in FIG. 19 includes a server device 510 and a terminal device 520.
- the server device 510 includes a server communication unit 511, a speaker identification unit 512, a viewer configuration management unit 513, an advertisement distribution control unit 514, a viewer configuration DB (Data Base) 515, and a distribution advertisement DB (Data Base) 516. .
- the place where the server device 510 is disposed is not particularly limited.
- the server device 510 may be disposed at a data center that handles big data, or may be disposed at each home.
- the data center is owned by a company that manages and operates the data center.
- each configuration of the server device 510 may be integrated in one device or may be arranged in different devices.
- the terminal device 520 includes a terminal communication unit 521, a voice acquisition unit 522, an information input unit 523, and a display unit 524.
- the terminal device 520 may be any device having these configurations.
- the terminal device 520 is configured of, for example, a television in a home, a PC (personal computer), a display connected to the PC, or the like. Further, the terminal device 520 may be configured by a mobile terminal such as a mobile phone, a smartphone, or a tablet terminal.
- the terminal device 520 may not necessarily include each component inside the terminal device 520. For example, only the voice acquisition unit 522 may be attached to the outside of the terminal device 520.
- the content providing system 500 may include a plurality of terminal devices 520, and each terminal device 520 may be connected to the server device 510.
- the server communication unit 511 receives line data via the communication line 530, which is various public lines such as the Internet. Then, the server communication unit 511 extracts the viewer voice signal transmitted by the terminal device 520 from the received line data, and outputs it to the speaker identification unit 512. Further, the server communication unit 511 extracts the viewer tag data transmitted by the terminal device 520 from the received line data, and outputs the viewer tag data to the viewer configuration management unit 513. Also, server communication unit 511 outputs the registration promotion signal and advertisement data generated when a new speaker is detected as line data to communication line 530, and registers the registration promotion signal and advertisement data through communication line 530. Transmit to terminal 520.
- the speaker identifying unit 512 acquires the viewer voice signal output by the server communication unit 511 to identify the speaker, and outputs the speaker identification result to the viewer configuration managing unit 513.
- the speaker identifying unit 512 compares the acquired viewer voice signal with the registered voice signal registered in the viewer configuration DB 515 to identify a speaker. At this time, the speaker identification unit 512 detects a new speaker when the acquired viewer voice signal and the registered voice signal registered in the viewer configuration DB 515 do not match.
- the viewer configuration management unit 513 When the new speaker is detected by the speaker identification unit 512, the viewer configuration management unit 513 outputs a registration promotion signal to the server communication unit 511. That is, when the speaker identified by the speaker identification unit 512 is not registered in the viewer configuration stored in the viewer configuration DB 515, the viewer configuration management unit 513 promotes registration to the server communication unit 511. Output a signal. Also, the viewer configuration management unit 513 acquires the viewer tag data input by the viewer from the server communication unit 511, manages tag information associated with the viewer configuration, and outputs the viewer configuration information.
- the advertisement distribution control unit 514 selects an advertisement to be distributed to the terminal side from the distribution advertisement DB 516 based on the viewer configuration information, and outputs the selected advertisement to the server communication unit 511.
- the viewer configuration DB 515 is a database for storing viewer configuration information managed by the viewer configuration management unit 513.
- the viewer configuration DB is created for each terminal device, and is managed by the IP address or ID corresponding to each terminal device.
- the distribution advertisement DB 516 is a database for storing advertisement data distributed and managed by the advertisement distribution control unit 514.
- the terminal communication unit 521 receives line data via the communication line 530, which is various public lines such as the Internet.
- the terminal communication unit 521 receives the advertisement data and the registration promotion signal transmitted by the server device 510, and outputs the received advertisement data and the registration promotion signal to the display unit 524. Also, the terminal communication unit 521 outputs the viewer voice signal acquired by the voice acquisition unit 522 to the communication line 530, and outputs the viewer tag data input by the information input unit 523 to the communication line 530.
- the audio acquisition unit 522 acquires a viewer audio signal and outputs the audio signal to the terminal communication unit 521.
- the information input unit 523 receives the input of the viewer tag data associated with the new viewer when the registration promotion screen by the registration promotion signal is displayed on the display unit 524, and the input viewer tag data is transmitted to the terminal communication unit Output to 521.
- the display unit 524 displays a screen prompting input of the viewer tag data when the registration promotion signal is received. In addition, the display unit 524 displays the received distribution advertisement data.
- each device does not necessarily have to have all the configurations described above, and some configurations may be missing.
- each device may have a configuration having another function.
- FIG. 20 is a sequence diagram showing an example of the operation of the content providing system 500 according to the third embodiment of the present invention. Note that FIG. 20 shows a case where a new viewer is detected in the terminal device 520.
- step S71 the audio acquisition unit 522 of the terminal device 520 acquires the audio signal of the viewer of the terminal device 520 (step S71). Note that the process of step S71 corresponds to the process performed by the voice acquisition unit 401 of the content providing system 400 in FIG.
- the terminal communication unit 521 of the terminal device 520 transmits the acquired viewer voice signal to the server device 510 through the communication line 530 (step S72).
- the terminal communication unit 521 may transmit other information related to the terminal device 520, such as an ID or an IP address for specifying the user of the terminal device 520, together with the viewer voice signal.
- the server communication unit 511 of the server device 510 receives the viewer voice signal transmitted by the terminal device 520.
- the speaker identifying unit 512 of the server device 510 receives the viewer voice signal transmitted from the terminal device 520 via the communication line 530, and the viewer configuration DB 515 corresponding to the terminal device 520 that has obtained the viewer voice signal.
- the extraction of the viewer configuration DB 515 corresponding to the terminal device 520 may be performed based on information that can specify a storage location such as an IP address sent from the terminal device 520.
- the process of step S73 corresponds to the process of the speaker identification unit 402 of the content providing system 400 in FIG.
- the speaker identifying unit 512 detects a new speaker not registered in the viewer configuration DB 515 (step S74). That is, when there is a registered voice signal matching the received viewer voice signal among the registered voice signals registered in the viewer configuration DB 515, the speaker identifying unit 512 speaks the speech corresponding to the viewer voice signal. It is determined that the speaker is the speaker corresponding to the registered voice signal. On the other hand, when the registered voice signal matching the received viewer voice signal does not exist among the registered voice signals registered in the viewer configuration DB 515, the speaker identifying unit 512 speaks the speech corresponding to the viewer voice signal. It is determined that the speaker is a new speaker not registered in the viewer configuration DB 515. Thereby, a new speaker is detected.
- the server communication unit 511 of the server device 510 transmits a registration promotion signal for prompting the terminal device 520 to register in the database of tag information associated with the new speaker via the communication line 530 (step S75).
- the terminal communication unit 521 of the terminal device 520 receives the registration promotion signal transmitted via the communication line 530.
- the detection of a new speaker may be conditional on the sound signal of the new speaker being continuously detected for a predetermined period (several days) or the like. This makes it possible to avoid false identification of a temporary visitor's voice or the like as the voice of a fixed viewer such as a family.
- the display unit 524 displays a registration prompting screen for promoting entry of tag information in association with the new speaker (step S76).
- the process of step S76 corresponds to the process of the display unit 407 of the content providing system 400 in FIG.
- the registration prompting screen may be displayed at a position that does not interfere with viewing of the content, such as an end of a display screen on which content such as a program is displayed.
- the registration promotion screen may be displayed at a timing that does not hinder the viewing of the content, such as when the terminal device 520 is powered on / off.
- the information input unit 523 receives an input of new speaker information including a viewer voice signal and information on a viewer (viewer tag data) associated with the viewer voice signal (step S77).
- the new speaker inputs new speaker information in accordance with the display on the registration promotion screen.
- the process of step S77 corresponds to the process of the information input unit 404 of the content providing system 400 in FIG.
- FIG. 21 is a view showing an example of a display screen for inputting a speaker's voice signal at the time of new speaker registration
- FIG. 22 is for inputting a speaker's age and gender at the time of new speaker registration
- FIG. 23 is a view showing an example of the display screen of FIG. 23, and FIG. 23 is a view showing an example of the display screen for inputting the nickname of the speaker at the time of new speaker registration.
- the speech acquisition unit 522 first acquires a speech signal.
- a voice level meter for surely recording the voice of the user, a vocabulary for uttering, etc. are displayed, and a new talk is made by a simple operation such as operation of the determination button on the remote control. Acquire the voice signal of the person.
- the information input unit 523 receives an input of tag data to be associated with the speaker.
- the tag data includes the new speaker's nickname, age and gender.
- the input of the age and gender is accepted by a simple remote control operation. The user moves to the respective input fields of age and gender, selects the corresponding item displayed on the child screen, and presses the enter button to complete the input.
- the user inputs his / her nickname using a ten key. After the input of the nickname is completed, the input to the tag data is completed by moving to the completion button and pressing the determination button.
- the terminal communication unit 521 transmits the viewer tag data and the viewer voice signal of the new speaker to the server device 510 via the communication line 530 (step S78).
- the server communication unit 511 of the server device 510 receives the viewer tag data and the viewer voice signal transmitted by the terminal device 520.
- the viewer configuration management unit 513 of the server device 510 updates the viewer configuration DB 515 by storing the viewer tag data and the viewer voice signal received by the server communication unit 511 in the viewer configuration DB 515.
- the process of step S79 corresponds to the process of the viewer configuration management unit 403 of the content providing system 400 in FIG.
- FIG. 24 is a view showing an example of the data configuration of the viewer configuration DB 515. As shown in FIG. As shown in FIG. 24, in the viewer configuration DB 515, the age, sex, and the obtained viewer voice signal are associated with each nickname representing the viewer.
- the database constructed in the viewer configuration DB 515 is not limited to this example.
- the advertisement distribution control unit 514 of the server device 510 selects, from the distribution advertisement DB 516, advertisement data according to the information on the viewer stored in the viewer configuration DB 515 (step S80).
- the selection method of the advertisement is not particularly limited.
- the distribution advertisement DB 516 stores advertisement data to be distributed in association with age and gender. For example, a male in his 40's is associated with an advertisement for a car, a female in his 30's is associated with an advertisement for cosmetics, and the advertisement distribution control unit 514 determines the age and gender of the user. Choose the best ad according to The process of step S80 corresponds to the process of the content distribution control unit 405 of the content providing system 400 in FIG.
- the distribution advertisement DB 516 may store the advertisement data in association with only the age, or may store the advertisement data in association with only the gender. In addition, the distribution advertisement DB 516 may store advertisement data in association with information on viewers other than age and gender. When the address of the viewer is stored in the viewer configuration DB 515, the distribution advertisement DB 516 stores advertisement data in association with the address, and the advertisement distribution control unit 514 determines the store closest to the address of the viewer. Advertisement data may be selected.
- the server communication unit 511 transmits the advertisement data selected by the advertisement distribution control unit 514 to the terminal device 520 via the communication line 530 (step S81).
- the terminal communication unit 521 of the terminal device 520 receives the advertisement data transmitted by the server device 510.
- step S82 the display unit 524 of the terminal device 520 displays the advertisement data distributed from the server device 510 (step S82).
- the process of step S82 corresponds to the process of the content distribution unit 406 of the content providing system 400 in FIG.
- FIG. 25 is a flowchart showing an example of the operation of the server device 510 according to Embodiment 3 of the present invention.
- the server apparatus 510 starts the operation shown in FIG. 25 when the power switch or a function (not shown in FIG. 19) associated with the power switch is turned on, and the function associated with the power switch or the power switch You may exit when it is turned off.
- step S 91 the server communication unit 511 of the server device 510 receives line data from the communication line 530. At this time, the server communication unit 511 acquires the viewer voice signal transmitted by the terminal device 520.
- the speaker identifying unit 512 identifies a speaker corresponding to the acquired viewer voice signal.
- the speaker identifying unit 512 identifies the speaker by collating the received viewer voice signal with the viewer configuration DB 515 for each terminal device.
- the speaker identifying unit 512 uses the speaker identification result to determine whether a new speaker has been detected. If the received viewer voice signal is not registered in the viewer configuration DB 515, the speaker identifying unit 512 determines that a new speaker has been detected, and the received viewer voice signal is registered in the viewer configuration DB 515. Then, it is determined that a new speaker has not been detected. Note that the detection of a new speaker may be a condition that the speaker does not exist in the viewer configuration DB 515 for a predetermined period (several days). This makes it possible to prevent the temporary voice of the visitor from being erroneously identified as the voice of a stationary viewer such as a family.
- step S93 if it is determined that a new speaker has been detected (YES in step S93), the process proceeds to step S94 to register a new speaker. On the other hand, if it is determined that a new speaker has not been detected (NO in step S93), the process proceeds to step S97.
- step S94 the viewer configuration management unit 513 creates a registration promotion signal for registering information related to a new speaker in the viewer configuration DB 515 and outputs it to the server communication unit 511, and the server communication unit 511 promotes registration. Send a signal.
- step S95 the viewer configuration management unit 513 determines whether or not the server communication unit 511 receives the viewer tag data and the viewer voice signal of the new speaker.
- the viewer tag data and the viewer voice signal are not transmitted from the terminal device 520 even though the registration promotion signal is transmitted, that is, the viewer tag data and the viewer voice signal are not received by the server device 510. If it is determined (NO in step S95), the process returns to step S94 in order to continuously promote registration.
- step S95 when the viewer tag data and the viewer voice signal are transmitted from the terminal device 520, that is, when it is determined that the viewer tag data and the viewer voice signal are received (YES in step S95), the process of step S96. Go to
- the viewer configuration management unit 513 updates the viewer configuration DB 515 for each terminal device. Specifically, the viewer configuration management unit 513 updates the viewer configuration DB 515 using the viewer tag data input by the information input unit 523 and the viewer voice signal acquired by the voice acquisition unit 522. . As shown in FIG. 24, the viewer configuration DB 515 is updated by storing age, gender and a viewer voice signal in association with each other for each new speaker's nickname. The viewer configuration management unit 513 stores the viewer tag data and the viewer voice signal received by the server communication unit 511 in the viewer configuration DB 515.
- the viewer voice signal acquired anew is received by the terminal device 520 that receives the registration promotion signal, and the received viewer voice signal is stored in the viewer configuration DB 515, but the present invention
- the server device 510 receives only the viewer tag data and stores the received viewer tag data in the viewer configuration DB 515 in association with the received viewer voice data. You may
- step S97 the advertisement distribution control unit 514 selects, from the distribution advertisement DB 516, advertisement data corresponding to the information on the viewer (identified speaker or new speaker) stored in the viewer configuration DB 515. . Specifically, the advertisement distribution control unit 514 extracts advertisement data corresponding to the age and gender of the identified speaker or new speaker in the viewer configuration DB 515 from the distribution advertisement DB 516, and transmits the extracted advertisement data to the server communication Output to the part 511.
- step S98 the server communication unit 511 transmits the advertisement data selected by the advertisement distribution control unit 514 to the terminal device 520 via the communication line 530.
- FIG. 26 is a flowchart showing an example of the operation of the terminal device 520 according to Embodiment 3 of the present invention.
- the terminal device 520 starts, for example, the operation shown in FIG. 26 when the power switch or a function (not shown in FIG. 19) associated with the power switch is turned on, and the function associated with the power switch or power switch is You may exit when it is turned off.
- the terminal device 520 is a television, there is a function of displaying a broadcast program (content) as a basic function of the television, but in the description of the content providing system, a detailed description of the display of the content is omitted.
- a broadcast program content
- step S111 the voice acquisition unit 522 obtains a viewer voice signal representing a voice uttered by a viewer who is in the vicinity of the terminal device 520.
- the voice acquisition unit 522 outputs the acquired viewer voice signal to the terminal communication unit 521.
- step S112 the terminal communication unit 521 transmits the viewer voice signal acquired by the voice acquisition unit 522 to the server device 510 via the communication line 530.
- the terminal communication unit 521 outputs the viewer voice signal to the communication line 530 as line data.
- step S113 the terminal communication unit 521 determines whether a registration promotion signal transmitted by the server device 510 has been received. If it is determined that the registration promotion signal has been received (YES in step S113), the process proceeds to step S114. The terminal communication unit 521 outputs the received registration promotion signal to the display unit 524. On the other hand, when it is determined that the registration promotion signal is not received (NO in step S113), the process proceeds to step S117.
- step S114 the display unit 524 displays a registration prompting screen for prompting input of information on a new speaker.
- the information input unit 523 receives an input of the viewer speech signal of the new speaker and the viewer tag data associated with the viewer speech signal of the new speaker.
- step S115 the terminal communication unit 521 determines whether or not the input of the viewer voice signal of the new speaker and the viewer tag data associated with the viewer voice signal of the new speaker is completed. . If it is determined that the input is not completed (NO in step S115), the process returns to step S114, and the display unit 524 continues to display the registration promotion screen. If it is determined that the input has been completed (YES in step S115), the process proceeds to step S116.
- step S116 the terminal communication unit 521 causes the viewer voice signal of the new speaker and the viewer voice signal input by the information input unit 523 such as a remote control according to the registration prompting screen displayed on the display unit 524.
- the viewer tag data (here, the age, gender, and the nickname) associated with the user ID are transmitted to the server device 510.
- step S117 the terminal communication unit 521 receives the advertisement data transmitted by the server device 510.
- step S118 the display unit 524 displays the advertisement data received by the terminal communication unit 521.
- a voice uttered by the viewer is acquired from the terminal device to identify the speaker, and when the same unknown speaker is identified for a certain period, viewing the speaker using the terminal device As a new member of the Then, registration of the speaker information to be associated with the new speaker in the database is prompted, and the input speaker information is registered in the database.
- a database for storing information on each member of the family holding the terminal device.
- a content providing system for delivering an appropriate advertisement according to a viewer.
- the system in the present embodiment is described as a content providing system for providing content, it may be a viewer configuration DB construction management system for constructing a database.
- the content delivery control unit 405 and the content delivery unit 406 are not essential components.
- the advertisement distribution control unit 514 and the distribution advertisement DB 516 are not essential components.
- the process after step S80 in the flowchart of FIG. 20 is not an essential process.
- the process after step S97 in the flowchart of FIG. 25 is not an essential process.
- the process after step S117 in the flowchart of FIG. 26 is not an essential process.
- Embodiment 4 The content providing system according to the fourth embodiment of the present invention will be described below. In the fourth embodiment, the description of the same configuration as that of the third embodiment will be omitted. Also, the technology of the fourth embodiment can be combined with the technology described in the third embodiment.
- the voice signal acquired by the terminal device is transmitted to the server device, and the identification of the speaker and the management of the information related to the speaker are performed in the server device.
- the device identifies the speaker and manages information on the speaker, and only information on the speaker is transmitted from the terminal device to the server device.
- the content providing system according to the fourth embodiment can reduce the amount of data to be transmitted, and can cope with a low-capacity communication line.
- FIG. 27 is a block diagram showing an example of a configuration of a content providing system according to Embodiment 4 of the present invention.
- the same components as in FIG. 19 are assigned the same reference numerals and descriptions thereof will be omitted.
- the content providing system 800 shown in FIG. 27 includes a server device 550 and a terminal device 560.
- the server device 550 includes a server communication unit 551, an advertisement delivery control unit 554, and a delivery advertisement DB (Data Base) 516.
- the terminal device 560 includes a speaker identification unit 512, a terminal communication unit 561, a viewer configuration management unit 562, a viewer configuration DB (Data Base) 515, a voice acquisition unit 522, an information input unit 523, and a display unit 524.
- a speaker identification unit 512 a terminal communication unit 561, a viewer configuration management unit 562, a viewer configuration DB (Data Base) 515, a voice acquisition unit 522, an information input unit 523, and a display unit 524.
- the server communication unit 551 receives line data via the communication line 530, which is various public lines such as the Internet. Then, the server communication unit 551 extracts the viewer configuration information transmitted by the terminal device 560 from the received line data, and outputs the viewer configuration information to the advertisement distribution control unit 514. Further, the server communication unit 551 outputs the advertisement data to the communication line 530 as line data, and transmits the advertisement data to the terminal device 520 via the communication line 530.
- the advertisement distribution control unit 554 selects advertisement data from the distribution advertisement DB 516 based on the viewer configuration information received by the server communication unit 551, and outputs the selected advertisement data to the server communication unit 551.
- the terminal communication unit 561 receives line data via the communication line 530, which is various public lines such as the Internet.
- the terminal communication unit 561 receives the advertisement data transmitted by the server device 550, and outputs the received advertisement data to the display unit 524.
- the terminal communication unit 561 converts the viewer configuration information output by the viewer configuration management unit 562 into line data, and outputs the line data to the communication line 530.
- the viewer configuration management unit 562 transmits a registration promotion signal to the display unit 524. Also, the viewer configuration management unit 562 acquires the viewer voice signal and the viewer tag data input by the viewer using the information input unit 523, and updates the information of the viewer configuration DB 515. Also, the viewer configuration management unit 562 outputs the viewer configuration information of the viewer configuration DB 515 to the terminal communication unit 561.
- FIG. 28 is a sequence diagram showing an example of the operation of the content providing system 800 according to the fourth embodiment of the present invention.
- FIG. 28 shows the case where a new viewer is detected in the terminal device 560.
- the audio acquisition unit 522 of the terminal device 560 acquires the audio signal of the viewer of the terminal device 560 (step S121). Note that the process of step S121 corresponds to the process performed by the voice acquisition unit 401 of the content providing system 400 in FIG.
- the voice acquisition unit 522 outputs the acquired viewer voice signal to the speaker identification unit 512.
- the speaker identifying unit 512 identifies the speaker using the viewer voice signal acquired by the voice acquiring unit 522 and the viewer configuration DB 515 storing the information on the viewer of the terminal device 560 (step S122).
- the process of step S122 corresponds to the process of the speaker identification unit 402 of the content providing system 400 in FIG.
- the viewer configuration DB 515 stores only the viewer configuration information of the viewer using the terminal device 560.
- the viewer configuration information is information in which a nickname, an age, a gender, and an audio signal are associated as shown in FIG.
- the speaker identifying unit 512 detects a new speaker not registered in the viewer configuration DB 515 (step S123). That is, when there is a registered voice signal matching the received viewer voice signal among the registered voice signals registered in the viewer configuration DB 515, the speaker identifying unit 512 speaks the speech corresponding to the viewer voice signal. It is determined that the speaker is the speaker corresponding to the registered voice signal. On the other hand, when the registered voice signal matching the received viewer voice signal does not exist among the registered voice signals registered in the viewer configuration DB 515, the speaker identifying unit 512 speaks the speech corresponding to the viewer voice signal. It is determined that the speaker is a new speaker not registered in the viewer configuration DB 515. Thereby, a new speaker is detected.
- the viewer configuration management unit 562 urges the display unit 524 to register the tag information associated with the new speaker in the database. Instruct to display the registration promotion screen of.
- the detection of a new speaker may be conditional on the sound signal of the new speaker being continuously detected for a predetermined period (several days) or the like. This makes it possible to avoid false identification of a temporary visitor's voice or the like as the voice of a fixed viewer such as a family.
- the display unit 524 displays a registration promotion screen for promoting input of tag information associated with the new speaker (step S124).
- the process of step S124 corresponds to the process of the display unit 407 of the content providing system 400 in FIG.
- the registration prompting screen may be displayed at a position that does not interfere with viewing of the content, such as an end of a display screen on which content such as a program is displayed. Also, the registration prompting screen may be displayed at a timing that does not hinder the viewing of the content, such as when the terminal device 560 is powered on / off.
- the information input unit 523 receives an input of new speaker information including a viewer voice signal and information on a viewer (viewer tag data) associated with the viewer voice signal (step S125).
- the new speaker inputs new speaker information in accordance with the display on the registration promotion screen.
- the process of step S125 corresponds to the process of the information input unit 404 of the content providing system 400 in FIG.
- the registration prompting screen displayed on the display unit 524 of the terminal device 560 at the time of inputting new speaker information is as already described in the third embodiment using FIGS. Therefore, the detailed description is omitted.
- the viewer configuration management unit 562 stores the viewer tag data and the viewer voice signal of the new speaker in the viewer configuration DB 515, thereby, as in the first embodiment, the viewer configuration The DB 515 is updated (step S126).
- the data configuration of the viewer configuration DB 515 is as shown in FIG.
- the process of step S126 corresponds to the process of the viewer configuration management unit 403 of the content providing system 400 in FIG.
- the terminal communication unit 561 transmits the viewer configuration information of the speaker identified by the speaker identification unit 512 or the new speaker to the server device 550 via the communication line 530 (step S127).
- the viewer configuration information transmitted to the server device 550 may be all or part of a plurality of pieces of information associated with the audio signal. That is, the viewer configuration information may be information including at least one of age and gender and capable of specifying an advertisement to be provided to the speaker.
- terminal communication unit 561 transmits, to server apparatus 550, viewer configuration information including the age and sex of the speaker identified by speaker identification unit 512 or the new speaker.
- the server communication unit 551 of the server device 550 receives the viewer configuration information transmitted by the terminal device 560.
- the advertisement distribution control unit 554 of the server device 550 selects advertisement data to be distributed to the terminal device 560 from the distribution advertisement DB 516 based on the received viewer configuration information (step S128).
- the selection method of the advertisement is not particularly limited.
- the distribution advertisement DB 516 stores advertisement data to be distributed in association with age and gender. For example, a male in his 40's is associated with an advertisement for a car, a female in his 30's is associated with an advertisement for cosmetics, and the advertisement distribution control unit 514 determines the age and gender of the user. Choose the best ad according to The process of step S128 corresponds to the process of the content distribution control unit 405 of the content providing system 400 in FIG.
- the server communication unit 551 transmits the advertisement data selected by the advertisement distribution control unit 514 to the terminal device 560 via the communication line 530 (step S129).
- the terminal communication unit 561 of the terminal device 560 receives the advertisement data transmitted by the server device 550.
- step S130 the display unit 524 of the terminal device 560 displays the advertisement data distributed from the server device 550 (step S130).
- the process of step S130 corresponds to the process of the content distribution unit 406 of the content providing system 400 in FIG.
- FIG. 29 is a flowchart showing an example of the operation of the server apparatus 550 according to Embodiment 4 of the present invention.
- the server apparatus 550 starts the operation shown in FIG. 29 when the power switch or the function associated with the power switch is turned on, and ends when the function associated with the power switch or the power switch is turned off. May be
- step S141 the server communication unit 551 of the server device 550 receives line data from the communication line 530. At this time, the server communication unit 551 acquires the viewer configuration information transmitted by the terminal device 560 and outputs the viewer configuration information to the advertisement distribution control unit 554.
- step S142 the advertisement distribution control unit 554 selects advertisement data from the distribution advertisement DB 516 based on the viewer tag data indicating the age and gender included in the acquired viewer configuration information, and the selected advertisement data Are output to the server communication unit 551.
- step S143 the server communication unit 551 transmits the advertisement data selected by the advertisement distribution control unit 514 to the terminal device 560 via the communication line 530.
- FIG. 30 is a flowchart showing an example of the operation of the terminal device 560 according to Embodiment 4 of the present invention.
- the terminal device 560 starts the operation shown in FIG. 30, for example, when the power switch or the function related to the power switch is turned on, and ends when the function related to the power switch or the power switch is turned off. May be
- step S151 the voice acquisition unit 522 obtains a viewer voice signal representing a voice uttered by a viewer who is around the terminal device 520.
- the voice acquisition unit 522 outputs the acquired viewer voice signal to the speaker identification unit 512.
- the speaker identifying unit 512 identifies a speaker corresponding to the acquired viewer voice signal.
- the speaker identifying unit 512 identifies the speaker by collating the acquired viewer voice signal with the viewer configuration DB 515.
- step S153 the speaker identifying unit 512 uses the speaker identification result to determine whether a new speaker has been detected. If the received viewer voice signal is not registered in the viewer configuration DB 515, the speaker identifying unit 512 determines that a new speaker has been detected, and the received viewer voice signal is registered in the viewer configuration DB 515. Then, it is determined that a new speaker has not been detected. Note that the detection of a new speaker may be a condition that the speaker does not exist in the viewer configuration DB 515 for a predetermined period (several days). This makes it possible to prevent the temporary voice of the visitor from being erroneously identified as the voice of a stationary viewer such as a family.
- step S153 if it is determined that a new speaker has been detected (YES in step S153), the process proceeds to step S154. On the other hand, when it is determined that a new speaker is not detected (NO in step S153), the process proceeds to step S157.
- step S154 the display unit 524 displays a registration prompting screen for prompting input of information on a new speaker.
- the information input unit 523 receives an input of the viewer speech signal of the new speaker and the viewer tag data associated with the viewer speech signal of the new speaker.
- step S155 the viewer configuration management unit 562 determines whether or not the input of the viewer voice signal of the new speaker and the viewer tag data associated with the viewer voice signal of the new speaker is completed. If it is determined that the input has not been completed (NO in step S155), the process returns to step S154, and the display unit 524 continues to display the registration promotion screen. If it is determined that the input has been completed (YES in step S155), the process proceeds to step S156.
- the viewer configuration management unit 562 updates the viewer configuration DB 515. Specifically, the viewer configuration management unit 562 updates the viewer configuration DB 515 using the viewer tag data input by the information input unit 523 and the viewer voice signal acquired by the voice acquisition unit 522. . As shown in FIG. 24, the viewer configuration DB 515 is updated by storing age, gender and a viewer voice signal in association with each other for each new speaker's nickname.
- step S 157 the viewer configuration management unit 562 outputs the viewer configuration information to the terminal communication unit 561, and the terminal communication unit 561 transmits the viewer configuration information to the server device 550 via the communication line 530. Send.
- step S158 the terminal communication unit 561 receives the advertisement data transmitted by the server device 550.
- step S159 the display unit 524 displays the advertisement data received by the terminal communication unit 561.
- the identification of the speaker and the management of the information on the speaker are performed in the terminal device by the above operation, only the information on the speaker necessary to select the advertisement data is selected as the data transmitted from the terminal device. Can be reduced to less data. As a result, even when the communication line has a low capacity, it is possible to provide a content providing system that delivers an advertisement appropriate for the viewer.
- the viewer configuration DB may not only associate the nickname, the age, the gender, and the voice signal with one another, but may further associate information indicating family relationships.
- the information indicating the family relationship is information indicating whether the viewer is, for example, a father, a mother or a child.
- the distribution advertisement DB may store the family configuration and the advertisement data in association with each other, and the content distribution control unit 405 acquires information indicating the family configuration of the viewer and corresponds to the acquired family configuration. Advertisement data to be selected may be selected from the distribution advertisement DB.
- the information indicating the family structure is, for example, information indicating that the family of the viewer is composed of a father, a mother and a child.
- advertisement data can be distributed according to the family configuration in the home.
- the viewer configuration DB not only associates the nickname, the age, the gender, and the voice signal with one another, but further associates the information indicating the family relationship with the information on the program viewed by the viewer.
- the information indicating the family relationship is information indicating whether the viewer is, for example, a father, a mother or a child.
- the information on a program is, for example, information indicating a program name, a channel number, a broadcast date and time, and a cast of a television program viewed on a terminal device.
- the content distribution control unit 405 acquires information indicating the family configuration of the viewer, acquires information on programs of other viewers having the same family configuration as the acquired family configuration, and the other viewers view The selected program may be provided to the identified speaker.
- the advertisement data is provided to the terminal device, but the present invention is not particularly limited to this, and program data may be provided to the terminal device.
- the speaker identification method, the speaker identification device, and the information management method according to the present invention can construct and update the database without performing troublesome setting operations for the speaker, and the speech existing in the vicinity of the device displaying the content It is useful as a speaker identification method for identifying a person, a speaker identification device, and an information management method.
- a new speaker can be registered in the database without performing troublesome setting operations for the speaker, and the speaker is identified. It is useful as a speaker identification method, a speaker identification device, and an information management method.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
Description
特許文献1に記載の視聴コンテンツ提供システムでは、温度分布情報及び音声情報に基づき視聴者(話者)の年齢及び性別を推定している。
(各装置の構成)
図1は、本発明の実施の形態1に係る話者識別システムの全体構成を示す図である。なお、図1に記載の構成は一例であり、話者識別システムは、図1に示されている構成以外の構成を備えていてもよい。また、話者識別システムは、図1に示されている構成の一部の構成が欠けていてもよい。
図2は、本実施の形態1における話者識別システムの構成を示すブロック図である。
図3は、本発明の実施の形態1における話者識別システムの動作を示すフローチャートである。
図4は、本発明の実施の形態1における話者識別システムの動作の一例を示すシーケンス図である。
(話者識別システムの構成)
図10は、本発明の実施の形態2における話者識別システムの構成を示すブロック図である。
図11は、本発明の実施の形態2における話者識別システムの動作を示すフローチャートである。
図12は、本発明の実施の形態2における話者識別システムの動作の一例を示すシーケンス図である。
従来、テレビなどの表示装置の前にいる視聴者を特徴付けるデータを取得して、適切な広告を配信する方法が提案されている(例えば、国際公開第01/089216号参照)。
まず、本実施の形態におけるコンテンツ提供システムの各構成について説明する。
次に、コンテンツ提供システム500の動作について説明する。なお、各装置(端末装置520及びサーバ装置510)の詳細な動作に関しては後述する。ここでは、コンテンツ提供システム500全体の大まかな動作及び処理の流れを説明する。
次に、本実施の形態3におけるコンテンツ提供システム500のサーバ装置510の動作について説明する。
次に、本実施の形態3におけるコンテンツ提供システム500の端末装置520の動作について説明する。
以下、本発明の実施の形態4におけるコンテンツ提供システムを説明する。なお、本実施の形態4において、実施の形態3と同様の構成については説明を省略する。また、実施の形態4の技術は、実施の形態3に記載の技術と組み合わせることも可能である。
図27は、本発明の実施の形態4に係るコンテンツ提供システムの構成の一例を示すブロック図である。図27において、図19と同じ構成要素については、同一の符号を付し、説明を省略する。
次に、コンテンツ提供システム800の動作について説明する。なお、各装置(端末装置560及びサーバ装置550)の詳細な動作に関しては後述する。ここでは、コンテンツ提供システム800全体の大まかな動作及び処理の流れを説明する。
次に、本実施の形態4におけるコンテンツ提供システム800のサーバ装置550の動作について説明する。
次に、本実施の形態4におけるコンテンツ提供システム800の端末装置560の動作について説明する。
Claims (9)
- コンテンツを表示する機器の周辺にいる話者を識別する話者識別方法であって、
前記話者の音声情報を取得するステップと、
前記取得された音声情報に対応する話者が、データベースにコンテンツに関するコンテンツ情報と関連付けて記憶されている登録音声情報に対応する話者と一致するか否かを判断するステップと、
前記取得された音声情報に対応する話者が前記データベースに記憶されている前記登録音声情報に対応する話者と一致すると判断された場合、前記音声情報を取得した時点において前記機器に表示されている前記コンテンツに関するコンテンツ情報を取得し、前記取得されたコンテンツ情報を前記登録音声情報に関連付けて記憶するステップと、
前記取得された音声情報に対応する話者が前記データベースに記憶されている前記登録音声情報に対応する話者と一致しないと判断された場合、前記取得された音声情報を登録音声情報として前記データベースに記憶するステップと、
を含む話者識別方法。 - 前記コンテンツ情報は、前記コンテンツの名称と、前記コンテンツに関連する人物名とを含む、
請求項1記載の話者識別方法。 - 前記登録音声情報に関連付けられている複数のコンテンツを複数のジャンルに分類し、前記複数のジャンル毎に前記複数のコンテンツのうちの各ジャンルに分類されたコンテンツの割合を算出し、前記複数のジャンル毎に算出された前記コンテンツの割合を前記登録音声情報に関連付けて前記データベースに記憶するステップをさらに含む、
請求項1又は2記載の話者識別方法。 - 前記データベースは、コンテンツ情報と、前記コンテンツ情報に対応するコンテンツを視聴した話者に提供されるサービスとを関連付けて記憶し、
前記取得された前記音声情報に対応する話者が前記データベースに記憶されている前記登録音声情報に対応する話者と一致すると判断された場合、前記登録音声情報に関連付けられて記憶されている前記コンテンツ情報を特定し、特定した前記コンテンツ情報に関連付けられているサービスを特定し、特定した前記サービスを前記話者に提供するステップをさらに含む、
請求項1~3のいずれかに記載の話者識別方法。 - 提供可能な少なくとも1つのサービスが存在し、かつ予め決められているサービス提供タイミングであるか否かを判断するステップと、
提供可能なサービスが存在し、かつ予め決められているサービス提供タイミングであると判断された場合、提供可能な前記少なくとも1つのサービスの候補を前記機器に表示するステップとをさらに含む、
請求項4記載の話者識別方法。 - 表示された前記少なくとも1つのサービスの候補の中から前記話者によって選択されたサービスを前記話者に提供するステップと、
提供された前記サービスを前記登録音声情報に関連付けて前記データベースに記憶するステップとをさらに含む、
請求項5記載の話者識別方法。 - 前記サービスは、前記機器に表示するコンテンツを配信するサービス、又は前記機器に表示する広告を配信するサービスを含む、
請求項4~6のいずれかに記載の話者識別方法。 - 話者を識別する話者識別装置であって、
コンテンツを表示する表示部と、
前記話者識別装置の周辺にいる話者の音声情報を取得する音声取得部と、
登録された音声情報である登録音声情報と、コンテンツに関するコンテンツ情報とを関連付けて記憶するデータベースと、
前記音声取得部によって取得された前記音声情報に対応する話者が、前記データベースにコンテンツ情報と関連付けて記憶されている登録音声情報に対応する話者と一致するか否かを判断する判断部と、
前記判断部によって前記取得された音声情報に対応する話者が前記データベースに記憶されている前記登録音声情報に対応する話者と一致すると判断された場合、前記音声情報を取得した時点において前記表示部に表示されている前記コンテンツに関するコンテンツ情報を取得し、前記取得されたコンテンツ情報を前記登録音声情報に関連付けて記憶するデータベース更新部と、
前記判断部によって前記取得された音声情報に対応する話者が前記データベースに記憶されている前記登録音声情報に対応する話者と一致しないと判断された場合、前記音声取得部によって取得された音声情報を登録音声情報として前記データベースに記憶するデータベース記憶部と、
を備える話者識別装置。 - コンテンツを表示する機器の周辺にいる話者を識別する話者識別システムにおける情報管理方法であって、
前記話者の音声情報を受信するステップと、
前記受信された音声情報に対応する話者が、データベースにコンテンツに関するコンテンツ情報と関連付けて記憶されている登録音声情報に対応する話者と一致するか否かを判断するステップと、
前記受信された音声情報に対応する話者が前記データベースに記憶されている前記登録音声情報に対応する話者と一致すると判断された場合、前記音声情報を取得した時点において前記機器に表示されている前記コンテンツに関するコンテンツ情報を取得し、前記受信されたコンテンツ情報を前記登録音声情報に関連付けて記憶するステップと、
前記受信された音声情報に対応する話者が前記データベースに記憶されている前記登録音声情報に対応する話者と一致しないと判断された場合、前記受信された音声情報を登録音声情報として前記データベースに記憶するステップと、
を含む情報管理方法。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2015522527A JP6348903B2 (ja) | 2013-06-10 | 2014-06-05 | 話者識別方法、話者識別装置及び情報管理方法 |
US14/419,056 US9911421B2 (en) | 2013-06-10 | 2014-06-05 | Speaker identification method, speaker identification apparatus, and information management method |
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2013-121713 | 2013-06-10 | ||
JP2013-121715 | 2013-06-10 | ||
JP2013121715 | 2013-06-10 | ||
JP2013121713 | 2013-06-10 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2014199602A1 true WO2014199602A1 (ja) | 2014-12-18 |
Family
ID=52021919
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2014/002992 WO2014199602A1 (ja) | 2013-06-10 | 2014-06-05 | 話者識別方法、話者識別装置及び情報管理方法 |
Country Status (3)
Country | Link |
---|---|
US (1) | US9911421B2 (ja) |
JP (1) | JP6348903B2 (ja) |
WO (1) | WO2014199602A1 (ja) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2020009206A (ja) * | 2018-07-09 | 2020-01-16 | ユニ・チャーム株式会社 | 動画提供装置、ユーザ端末、動画提供方法及び動画提供プログラム |
KR20200101934A (ko) * | 2017-12-27 | 2020-08-28 | 로비 가이드스, 인크. | 음성 데이터 및 미디어 소비 데이터에 기초하여 사용자들을 식별하기 위한 시스템들 및 방법들 |
JP2021002884A (ja) * | 2015-03-30 | 2021-01-07 | ロヴィ ガイズ, インコーポレイテッド | メディアアセットの部分を識別し記憶するためのシステムおよび方法 |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6721298B2 (ja) * | 2014-07-16 | 2020-07-15 | パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカPanasonic Intellectual Property Corporation of America | 音声情報制御方法及び端末装置 |
US10613826B2 (en) * | 2014-12-25 | 2020-04-07 | Maxell, Ltd. | Head-mounted display system and operating method for head-mounted display device |
CN105049882B (zh) * | 2015-08-28 | 2019-02-22 | 北京奇艺世纪科技有限公司 | 一种视频推荐方法及装置 |
EP3698358A1 (en) * | 2017-10-18 | 2020-08-26 | Soapbox Labs Ltd. | Methods and systems for processing audio signals containing speech data |
US11270071B2 (en) | 2017-12-28 | 2022-03-08 | Comcast Cable Communications, Llc | Language-based content recommendations using closed captions |
US11145299B2 (en) | 2018-04-19 | 2021-10-12 | X Development Llc | Managing voice interface devices |
JP7027280B2 (ja) * | 2018-08-10 | 2022-03-01 | 本田技研工業株式会社 | 個人識別装置および個人識別方法 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006324809A (ja) * | 2005-05-17 | 2006-11-30 | Sony Corp | 情報処理装置,情報処理方法,およびコンピュータプログラム |
US20110106744A1 (en) * | 2009-04-16 | 2011-05-05 | Ralf Becker | Content recommendation device, content recommendation system, content recommendation method, program, and integrated circuit |
EP2469843A1 (en) * | 2010-12-27 | 2012-06-27 | Kabushiki Kaisha Toshiba | System and method for recommending programs |
Family Cites Families (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5897616A (en) * | 1997-06-11 | 1999-04-27 | International Business Machines Corporation | Apparatus and methods for speaker verification/identification/classification employing non-acoustic and/or acoustic models and databases |
JP3865924B2 (ja) | 1998-03-26 | 2007-01-10 | 松下電器産業株式会社 | 音声認識装置 |
US7831930B2 (en) * | 2001-11-20 | 2010-11-09 | Universal Electronics Inc. | System and method for displaying a user interface for a remote control application |
JP2000322088A (ja) * | 1999-05-14 | 2000-11-24 | Hitachi Ltd | 音声認識マイクおよび音声認識システムならびに音声認識方法 |
WO2001089216A1 (fr) | 2000-05-15 | 2001-11-22 | Dentsu Inc. | Procede et appareil permettant de commander la transmission de publicite |
DE60120062T2 (de) * | 2000-09-19 | 2006-11-16 | Thomson Licensing | Sprachsteuerung von elektronischen Geräten |
JP2002366166A (ja) * | 2001-06-11 | 2002-12-20 | Pioneer Electronic Corp | コンテンツ提供システム及び方法、並びにそのためのコンピュータプログラム |
US7519534B2 (en) * | 2002-10-31 | 2009-04-14 | Agiletv Corporation | Speech controlled access to content on a presentation medium |
KR20050023941A (ko) * | 2003-09-03 | 2005-03-10 | 삼성전자주식회사 | 음성 인식 및 화자 인식을 통한 개별화된 서비스를제공하는 a/v 장치 및 그 방법 |
WO2005069171A1 (ja) * | 2004-01-14 | 2005-07-28 | Nec Corporation | 文書対応付け装置、および文書対応付け方法 |
JP4311322B2 (ja) | 2004-09-28 | 2009-08-12 | ソニー株式会社 | 視聴コンテンツ提供システム及び視聴コンテンツ提供方法 |
US20070280436A1 (en) * | 2006-04-14 | 2007-12-06 | Anthony Rajakumar | Method and System to Seed a Voice Database |
JP2009296346A (ja) * | 2008-06-05 | 2009-12-17 | Sony Corp | 番組推薦装置、番組推薦方法及び番組推薦プログラム |
JP5172973B2 (ja) * | 2009-01-30 | 2013-03-27 | 三菱電機株式会社 | 音声認識装置 |
US20110099596A1 (en) * | 2009-10-26 | 2011-04-28 | Ure Michael J | System and method for interactive communication with a media device user such as a television viewer |
US20110106536A1 (en) * | 2009-10-29 | 2011-05-05 | Rovi Technologies Corporation | Systems and methods for simulating dialog between a user and media equipment device |
US8682667B2 (en) * | 2010-02-25 | 2014-03-25 | Apple Inc. | User profiling for selecting user specific voice input processing information |
JP2011223573A (ja) | 2010-03-26 | 2011-11-04 | Sharp Corp | 表示装置、テレビジョン受像機、表示装置の制御方法、制御プログラム、および制御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 |
US8484219B2 (en) * | 2010-09-21 | 2013-07-09 | Sony Computer Entertainment America Llc | Developing a knowledge base associated with a user that facilitates evolution of an intelligent user interface |
US9262612B2 (en) * | 2011-03-21 | 2016-02-16 | Apple Inc. | Device access using voice authentication |
CN102781075B (zh) * | 2011-05-12 | 2016-08-24 | 中兴通讯股份有限公司 | 一种降低移动终端通话功耗的方法及移动终端 |
US9092415B2 (en) * | 2012-09-25 | 2015-07-28 | Rovi Guides, Inc. | Systems and methods for automatic program recommendations based on user interactions |
-
2014
- 2014-06-05 WO PCT/JP2014/002992 patent/WO2014199602A1/ja active Application Filing
- 2014-06-05 JP JP2015522527A patent/JP6348903B2/ja active Active
- 2014-06-05 US US14/419,056 patent/US9911421B2/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006324809A (ja) * | 2005-05-17 | 2006-11-30 | Sony Corp | 情報処理装置,情報処理方法,およびコンピュータプログラム |
US20110106744A1 (en) * | 2009-04-16 | 2011-05-05 | Ralf Becker | Content recommendation device, content recommendation system, content recommendation method, program, and integrated circuit |
EP2469843A1 (en) * | 2010-12-27 | 2012-06-27 | Kabushiki Kaisha Toshiba | System and method for recommending programs |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2021002884A (ja) * | 2015-03-30 | 2021-01-07 | ロヴィ ガイズ, インコーポレイテッド | メディアアセットの部分を識別し記憶するためのシステムおよび方法 |
JP7153699B2 (ja) | 2015-03-30 | 2022-10-14 | ロヴィ ガイズ, インコーポレイテッド | メディアアセットの部分を識別し記憶するためのシステムおよび方法 |
US11563999B2 (en) | 2015-03-30 | 2023-01-24 | Rovi Guides, Inc. | Systems and methods for identifying and storing a portion of a media asset |
JP7423719B2 (ja) | 2015-03-30 | 2024-01-29 | ロヴィ ガイズ, インコーポレイテッド | メディアアセットの部分を識別し記憶するためのシステムおよび方法 |
KR20200101934A (ko) * | 2017-12-27 | 2020-08-28 | 로비 가이드스, 인크. | 음성 데이터 및 미디어 소비 데이터에 기초하여 사용자들을 식별하기 위한 시스템들 및 방법들 |
KR102451348B1 (ko) | 2017-12-27 | 2022-10-06 | 로비 가이드스, 인크. | 음성 데이터 및 미디어 소비 데이터에 기초하여 사용자들을 식별하기 위한 시스템들 및 방법들 |
US11798565B2 (en) | 2017-12-27 | 2023-10-24 | Rovi Guides, Inc. | Systems and methods for identifying users based on voice data and media consumption data |
JP2020009206A (ja) * | 2018-07-09 | 2020-01-16 | ユニ・チャーム株式会社 | 動画提供装置、ユーザ端末、動画提供方法及び動画提供プログラム |
Also Published As
Publication number | Publication date |
---|---|
JPWO2014199602A1 (ja) | 2017-02-23 |
JP6348903B2 (ja) | 2018-06-27 |
US20150194155A1 (en) | 2015-07-09 |
US9911421B2 (en) | 2018-03-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2014199602A1 (ja) | 話者識別方法、話者識別装置及び情報管理方法 | |
US8340974B2 (en) | Device, system and method for providing targeted advertisements and content based on user speech data | |
US9270918B2 (en) | Method of recommending broadcasting contents and recommending apparatus therefor | |
JP5482206B2 (ja) | 情報処理装置、情報処理方法およびプログラム | |
JP4538756B2 (ja) | 情報処理装置、情報処理端末、情報処理方法、およびプログラム | |
US20220286750A1 (en) | Reminders of media content referenced in other media content | |
JP2009140051A (ja) | 情報処理装置、情報処理システム、推薦装置、情報処理方法および記憶媒体 | |
JPWO2008081664A1 (ja) | 広告配信システム、広告配信サーバ、広告配信方法、プログラム及び記録媒体 | |
KR101495297B1 (ko) | 스마트 티비 기반의 상황 인지를 통한 사용자 이력 분석 제공 시스템, 장치, 방법 및 컴퓨터 판독 가능한 기록 매체 | |
JP2003250146A (ja) | 番組選択支援情報提供サービスシステムとサーバ装置および端末装置ならびに番組選択支援情報提供方法とプログラムおよび記録媒体 | |
US11687585B2 (en) | Systems and methods for identifying a media asset from an ambiguous audio indicator | |
TW201319981A (zh) | 電視廣告產品資訊顯示系統、方法及其記錄媒體 | |
JP2011223571A (ja) | 情報処理装置、情報処理システム及びプログラム | |
KR20160136555A (ko) | 멀티모달 정보를 이용하여 사용자의 정보를 획득하는 셋톱박스, 셋톱박스로부터 획득한 사용자의 정보를 관리하는 관리 서버, 그리고 이를 이용한 방법 및 컴퓨터 판독 가능한 기록 매체 | |
JP2010171713A (ja) | 広告入出力装置、広告入出力方法、広告入出力プログラム、コンピュータ読取可能な記録媒体、及び録画再生装置 | |
KR102135076B1 (ko) | 인공지능 스피커를 이용한 감성 기반의 사용자 맞춤형 뉴스 추천 시스템 | |
TW201322740A (zh) | 數位化電視廣告產品資訊顯示系統、方法及其記錄媒體 | |
JP2003006511A (ja) | 商品情報提供システム | |
JP2013141050A (ja) | コンテンツ推薦サーバ、コンテンツ表示端末、およびコンテンツ推薦システム | |
JP2020167669A (ja) | 映像と音声を上映するための映像音声管理装置および上映システム | |
JP2002135221A (ja) | 情報受信装置および方法、情報送信装置および方法、情報送受信システムおよび方法、並びに記録媒体 | |
WO2019069831A1 (ja) | 映像と音声を上映するための映像音声管理装置および上映システム | |
CN115866339A (zh) | 电视节目推荐方法、装置、智能设备及可读存储介质 | |
CN111788563A (zh) | 信息处理装置、信息处理方法及程序 | |
JP2019216355A (ja) | 情報処理装置、情報処理方法、及び情報処理プログラム |
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: 14811641 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2015522527 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14419056 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 14811641 Country of ref document: EP Kind code of ref document: A1 |