Broadcast receiving method, broadcast receiving system, recording medium, and program

• US 7,698,138 B2
• Filed: 12/26/2003
• Issued: 04/13/2010
• Est. Priority Date: 01/15/2003
• Status: Expired due to Fees

• Current Assignee: Sovereign Peak Ventures, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Panasonic Corporation (Panasonic Holdings Corporation)
• Inventors: Hirose, Yoshifumi, Kamai, Takahiro, Yoshida, Hideyuki, Kato, Yumiko
• Primary Examiner(s): Hudspeth; David R
• Assistant Examiner(s): GUERRA-ERAZO, EDGAR X
• Application Number:
  US10/542,409
• Publication Number:
  US 20060259299A1
• Time in Patent Office: 2,300 Days
• Field of Search: 704/270, 704/270.1, 704/275, 704/278, 704/E15.018, 704/E15.019, 704/239, 704/243, 704/257
• US Class Current: 704/257
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04H 60/37 for identifying segments of broadcast information, e.g. scenes or extracting programme ID
• CPC Class Codes: H04H 60/48 for recognising items expressed in broadcast information
• CPC Class Codes: H04N 21/42203 sound input device, e.g. microphone
• CPC Class Codes: H04N 21/432 Content retrieval operation from a local storage medium, e.g. hard-disk details of retrieval of video data and associated meta data in video databases G06F16/739
• CPC Class Codes: H04N 21/4332 by placing content in organized collections, e.g. local EPG data repository interfaces, Database management systems or updating for information retrieval G06F16/23; details of retrieval of video data and associated meta data in video database G06F16/739
• CPC Class Codes: H04N 21/4348 Demultiplexing of additional data and video streams
• CPC Class Codes: H04N 21/435 Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
• CPC Class Codes: H04N 21/4394 involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams arrangements characterised by components specially adapted for monitoring, identification or recognition of audio in broadcast systems H04H60/58
• CPC Class Codes: H04N 21/44224 Monitoring of user activity on external systems, e.g. Internet browsing
• CPC Class Codes: H04N 21/454 Content or additional data filtering, e.g. blocking advertisements
• CPC Class Codes: H04N 21/47214 for content reservation or setting reminders; for requesting event notification, e.g. of sport results or stock market stock exchange data over packet-switching network H04L12/1804; push services over packet-switching network H04L12/1859; notification of incoming messages in packet switching networks H04L51/224
• CPC Class Codes: H04N 21/4722 for requesting additional data associated with the content
• CPC Class Codes: H04N 21/47815 Electronic shopping payment schemes, payment architectures or payment protocols for electronic shopping systems G06Q20/12
• CPC Class Codes: H04N 21/812 involving advertisement data advertising per se G06Q30/02
• CPC Class Codes: H04N 21/8405 represented by keywords
• CPC Class Codes: H04N 5/445 for displaying additional information H04N5/50 takes precedence
• CPC Class Codes: H04N 7/088 the inserted signal being digital

Abstract

A broadcast receiving system includes a broadcast receiving part for receiving a broadcast in which additional information that corresponds to an object appearing in broadcast contents and that contains keyword information for specifying the object is broadcasted simultaneously with the broadcast contents; a recognition vocabulary generating section for generating a recognition vocabulary set in a manner corresponding to the additional information by using a synonym dictionary; a speech recognition section for performing the speech recognition of a voice uttered by a viewing person, and for thereby specifying keyword information corresponding to a recognition vocabulary set when a word recognized as the speech recognition result is contained in the recognition vocabulary set; and a displaying section for displaying additional information corresponding to the specified keyword information.

Claims

1. A broadcast receiving method comprising:

a receiving step of receiving, simultaneously with broadcast contents, additional information containing keyword information for specifying an object that appears in the broadcast contents, and a scene code indicating a scene of the broadcast contents, the additional information and the scene code being broadcasted;

a language model specifying step of specifying, out of language models retained in advance, the language model corresponding to the received scene code when the scene code is received;

a speech recognition step of performing speech recognition of a voice uttered by a viewing person, by using the specified language model;

a specifying step of specifying the keyword information based on the speech recognition result; and

a displaying step of displaying the additional information containing the specified keyword information.

2. The broadcast receiving method according to claim 1, further comprising:

a correcting step of utilizing a synonym dictionary, in which a plurality of words are classified into word classes based on synonymy between the words, thereby correct a frequency of appearance of a predetermined combination of the word classes in an expression form of the specified language model and/or a frequency of appearance of a predetermined word with reference to a predetermined word class in the expression form of the specified language model, based on history information on speech recognition results of already performed speech recognition,

wherein the speech recognition step performs the speech recognition by using the corrected language models.

17. The broadcast receiving method according to claim 1, wherein

the scene code is broadcasted every time the scene has changed,

the receiving step receives the scene code broadcasted every time the scene has changed,

the language model specifying step specifies the language model every time the scene code has received, and

the speech recognition step performs the speech recognition by using the language model specified every time the scene code is received.

3. A broadcast receiving system comprising:

a first apparatus comprising a broadcasting part broadcasting additional information containing keyword information for specifying an object that appears in broadcast contents, and a scene code indicating a scene of the broadcast contents, and

a second apparatus comprising;

a receiving part receiving, simultaneously with the broadcast contents, the additional information and the scene code;

a language model specifying part specifying, out of language models retained in advance, the language model corresponding to the received scene code when the scene code is received;

a speech recognition part performing speech recognition of a voice uttered by a viewing person, by using the specified language model;

a specifying part specifying the keyword information based on the speech recognition result; and

a displaying part displaying the additional information containing the specified keyword information.

4. The broadcast receiving system according to claim 3, wherein

the second apparatus further comprises a correcting part utilizing a synonym dictionary, in which a plurality of words are classified into word classes based on a synonymy between the words, to thereby correct a frequency of appearance of a predetermined combination of the word classes in an expression form of the specified language model and/or a frequency of appearance of a predetermined word with reference to a predetermined word class in the expression form of the specified language model, based on history information on speech recognition results of already performed speech recognition, and

the speech recognition part performs the speech recognition by using the corrected language model.

18. The broadcast receiving system according to claim 3, wherein

the broadcasting part broadcasts the scene code every time the scene has changed,

the receiving part receives the scene code broadcasted every time the scene has changed,

the language model specifying part specifies the language model every time the scene code has received, and

the speech recognition part performs the speech recognition by using the language model specified every time the scene code is received.

5. A first apparatus comprising

a broadcasting part broadcasting additional information containing keyword information for specifying an object that appears in broadcast contents, and a scene code indicating a scene of the broadcast contents, wherein

the additional information and the scene code are, simultaneously with the broadcast contents, received,

a language model corresponding to the received scene code when the scene code is received is, out of the language models retained in advance, specified,

speech recognition of a voice uttered by a viewing person is, by using the corrected specified language model, performed,

the keyword information is specified based on the speech recognition result, and

the additional information containing the specified keyword information is displayed.

6. The first apparatus according to claim 5, wherein

a synonym dictionary, in which a plurality of words are classified into word classes based on a synonymy between the words, is utilized to thereby correct a frequency of appearance of a predetermined combination of the word classes in an expression form of the specified language model and/or a frequency of appearance of a predetermined word with reference to a predetermined word class in the expression form of the specified language model, based on history information on speech recognition results of already performed speech recognition, and

the speech recognition is performed by using the corrected language model.

7. A second apparatus comprising:

a receiving part receiving, simultaneously with broadcast contents, additional information containing keyword information for specifying an object that appears in the broadcast contents, and a scene code indicating a scene of the broadcast contents, the additional information and the scene code being broadcasted;

a language model specifying part specifying, out of language models retained in advance, the language model corresponding to the received scene code when the scene code is received;

a speech recognition part performing speech recognition of a voice uttered by a viewing person, by using the specified language model;

a specifying part specifying the keyword information based on the speech recognition result; and

a displaying part displaying the additional information containing the specified keyword information.

8. The second apparatus according to claim 7, further comprising

a correcting part utilizing a synonym dictionary, in which a plurality of words are classified into word classes based on a synonymy between the words, to thereby correct a frequency of appearance of a predetermined combination of the word classes in an expression form of the specified language model and/or a frequency of appearance of a predetermined word with reference to a predetermined word class in the expression form of the specified language model, based on history information on speech recognition results of already performed speech recognition wherein the speech recognition part performs the speech recognition by using the corrected language model.

9. The second apparatus according to claim 7, wherein the language model is specified by using an ID imparted to the language model in advance.

10. The second apparatus according to claim 7, wherein

the language model is specified by using keyword information for language model specification,

the keyword information for language model specification is imparted also to the language model retained in advance, and

the language model specifying part specifies the language model depending on a degree of agreement of those keywords for language model specification.

11. The second apparatus according to claim 8, wherein

if the correcting part corrects the frequency of appearance of the predetermined word with reference to the predetermined word class in the expression form of the language model, the history information containing a word recognized in the already performed speech recognition, and

the correcting part extracts a word contained in the word class containing the word corresponding to the keyword information,

with respect to a word contained in the history information among the extracted words, the frequency of appearance of the word with reference to the word class in the expression form of the language model is increased, and

with respect to a word not contained in the history information among the extracted words, the frequency of appearance of the word with reference to the word class in the expression form of the language model is decreased.

12. The second apparatus according to claim 8, wherein

if the correcting part corrects the frequency of appearance of the predetermined combination of the word classes in the expression form of the language model, the history information containing a word recognized in the already performed speech recognition,

the correcting part extracts a word class containing the word corresponding to the keyword information,

with respect to the extracted word class, the frequency of appearance of the predetermined combination of the word classes in the expression form of the language model is increased, and

with respect to a word class not extracted, the frequency of appearance of the predetermined combination of the word classes in the expression form of the language model is decreased.

13. The second apparatus according to claim 8 wherein

if the correcting part corrects the frequency of appearance of the predetermined combination of the word classes in the expression form of the language model, the history information containing a word class containing a word recognized in the already performed speech recognition,

the correcting part extracts a word class corresponding to the keyword information,

with respect to the extracted word class, the frequency of appearance of the predetermined combination of the word classes in the expression form of the language model is increased, and

with respect to a word class not extracted, the frequency of appearance of the predetermined combination of the word classes in the expression form of the language model is decreased.

14. The second apparatus according to any one of claims 7-10, further comprising a transmitting part transmitting an instruction corresponding to a predetermined operation to a predetermined transmission destination when the predetermined operation is performed on the displayed additional information.

15. The second apparatus according to claim 14, wherein

the additional information is goods sales information and/or services sales information,

the instruction corresponding to the predetermined operation is a request for brochure or purchase instruction information concerning the goods and/or the service.

16. The second apparatus according to claim 7, wherein the language model retained in advance has been acquired in advance through a network.

19. A speech recognition method comprising:

a receiving step of receiving, simultaneously with broadcast contents, a scene code indicating a scene of the broadcast contents broadcasted;

a language model specifying step of specifying, out of language models retained in advance, the language model corresponding to the received scene code when the scene code is received; and

a speech recognition step of performing speech recognition of a voice uttered by a viewing person, by using the specified language model.

20. A speech recognition apparatus comprising:

a receiving part receiving, simultaneously with broadcast contents, a scene code indicating a scene of the broadcast contents broadcasted;

a language model specifying part specifying, out of language models retained in advance, the language model corresponding to the received scene code when the scene code is received; and

a speech recognition part performing speech recognition of a voice uttered by a viewing person, by using the specified language model.