System for identifying and adapting a TV-user profile by means of speech technology

• US 6,415,257 B1
• Filed: 08/26/1999
• Issued: 07/02/2002
• Est. Priority Date: 08/26/1999
• Status: Expired due to Term

• Current Assignee: Sovereign Peak Ventures, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Matsushita Electric Industrial Company Limited (Panasonic Holdings Corporation)
• Inventors: Junqua, Jean-claude, Kuhn, Roland, Davis, Tony, Zhao, Yi, Li, Weiying
• Primary Examiner(s): Dorvil, Richemond
• Application Number:
  US09/383,797
• Time in Patent Office: 1,041 Days
• Field of Search: 704/275, 704/270, 704/272, 704/251, 704/257, 704/255, 704/200, 704/274, 704/273, 704/256, 704/231
• US Class Current: 704/275
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: H04N 21/42203 sound input device, e.g. microphone
• 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 21/4415 using biometric characteristics of the user, e.g. by voice recognition or fingerprint scanning cryptography using biological data H04L9/3231; authentication in networks using biometric H04L63/0861
• CPC Class Codes: H04N 21/4532 involving end-user characteristics, e.g. viewer profile, preferences monitoring of user activities for profile generation for accessing a video database G06F16/739; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/4667 Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
• CPC Class Codes: H04N 21/47 End-user applications
• CPC Class Codes: H04N 21/482 End-user interface for program selection broadcast systems using EPGs H04H60/72

Abstract

Speech input supplied by the user is evaluated by the speaker verification/identification module, and based on the evaluation, parameters are retrieved from a user profile database. These parameters adapt the speech models of the speech recognizer and also supply the natural language parser with customized dialog grammars. The user'"'"'s speech is then interpreted by the speech recognizer and natural language parser to determine the meaning of the user'"'"'s spoken input in order to control the television tuner. The parser works in conjunction with a command module that mediates the dialog with the user, providing on-screen prompts or synthesized speech queries to elicit further input from the user when needed. The system integrates with an electronic program guide, so that the natural language parser is made aware of what programs are available when conducting the synthetic dialog with the user.

Claims

1. A control system for audio/video equipment comprising:

speaker verification/identification module for ascertaining the identity of a system user based on the user'"'"'s speech;

a user profile database that stores user-specific data based on the identity of a system user and retrieves said data in response to operation of said speaker verification/identification module;

said user profile database being further configured to store at least one user preference information selected from the group consisting of preferred channels, blocked channels and combinations thereof;

a speech recognizer and language parser system for extracting a semantic representation of spoken information provided by the user;

a command module coupled to said speech recognizer and language parser system for providing control signals to said audio/video equipment based on said extracted semantic representation;

said command module being further responsive to said user preference information in providing said control signals; and

wherein at least one of said speech recognizer and language parser system and said command module uses said user-specific data.

2. The control system of claim 1 wherein said speaker verification/identification module associates a user-defined utterance with each system user and detects the occurrence of said utterance in ascertaining the identity of a system user.

3. The control system of claim 1 wherein said speaker verification/identification module associates speaker speech parameters with each system user and detects the occurrence of said speech parameters in ascertaining the identity of a system user.

4. The control system of claim 1 wherein said speaker verification/identification module associates a reduced dimensionality vector with each system user and detects the occurrence of said reduced dimensionality vector in ascertaining the identity of a system user.

5. The control system of claim 4 wherein said reduced dimensionality vector is an Eigenvector.

6. The control system of claim 1 wherein said user profile database stores user-specific data representing adapted speech models that are supplied to said speech recognizer.

7. The control system of claim 1 wherein said user profile database stores user-specific data representing customized dialog grammars that are supplied to said language parser.

8. The control system of claim 1 wherein said user profile database stores user-specific data representing preferred program channels.

9. The control system of claim 1 wherein said user profile database stores user-specific data representing blocked program channels.

10. The control system of claim 1 wherein said user profile database stores user-specific data representing usage log data for a particular user.

11. The control system of claim 1 further comprising program guide data store for storing data extracted from an electronic program guide about available program content.

12. The control system of claim 11 wherein said parser accesses said program guide data store to assist in ascertaining said semantic representation.

13. A control system for audio/video equipment comprising:

a speaker verification/identification module for ascertaining the identity of a system user based on the user'"'"'s speaking of a predefined utterance;

a user profile database that stores user-specific data based on the identity of a system user and retrieves said data in response to operation of said speaker verification/identification module;

said user profile database being further configured to store at least one user preference information selected from the group consisting of preferred channels, blocked channels and combinations thereof;

a command module for providing control signals to said audio/video equipment based on interaction with said user;

said command module being further responsive to said user preference information in providing said control signals; and

wherein said command module uses said user-specific data.

14. The control system of claim 13 wherein said predefined utterance is a predefined wakeup command.

15. The control system of claim 13 wherein said predefined utterance is a predefined word.

16. The control system of claim 13 wherein said predefined utterance is the word:

please.

17. A control system for audio/video equipment comprising:

a speaker verification/identification module for ascertaining the identity of a system user based on the user'"'"'s speech;

a user profile data store containing user-specific data based on the identity of a system user and retrieving said data in response to operation of said speaker verification/identification module;

said user profile database being further configured to store at least one user preference information selected from the group consisting of preferred channels, blocked channels and combinations thereof;

a command module coupled to said speech verification module for providing control signals to said audio/video equipment based on the identity of said system user; and

said command module being further responsive to said user preference information in providing said control signals.

18. The control system of claim 17 wherein said command module blocks predefined content from being accessed by said system user.

19. The control system of claim 17 wherein said command module admits access to predefined content by said system user.

20. The control system of claim 17 wherein said command module implements a parental control system whereby access to selected content is controlled.

21. The control system of claim 17 wherein said speaker verification/identification module associates a user-defined utterance with each system user and detects the occurrence of said utterance in ascertaining the identity of a system user.

22. The control system of claim 17 wherein said speaker verification/identification module associates speaker speech parameters with each system user and detects the occurrence of said speech parameters in ascertaining the identity of a system user.

23. The control system of claim 22 wherein said verification/identification module associates speaker speech parameters with each system user from a first utterance at enrollment time and detects the occurrence of said speech parameters from a second utterance different from said first utterance.

24. The control system of claim 17 wherein said speaker verification/identification module associates a reduced dimensionality vector with each system user and detects the occurrence of said reduced dimensionality vector in ascertaining the identity of a system user.

25. The control system of claim 24 wherein said reduced dimensionality vector is an Eigenvector.

26. The control system of claim 17 wherein said user profile database stores user-specific data representing preferred program content.

27. The control system of claim 17 wherein said user profile database stores user-specific data representing blocked program content.

28. The control system of claim 17 wherein said user profile database stores user-specific data representing usage log data for a particular user.

29. A method for controlling the operation of audio/video equipment comprising the steps of:

processing input speech from an equipment user to ascertain the user'"'"'s identity; and

maintaining a data store of user preference information selected from the group consisting of preferred channels, blocked channels and combinations thereof;

using said ascertained user'"'"'s identity to retrieve said preference information; and

controlling the operation of said equipment based on said preference information.

30. The method of claim 29 wherein said step of processing input speech is performed by comparing said input speech with previously stored information about the user'"'"' speech characteristics.

31. The method of claim 29 wherein said step of processing input speech is performed by comparing information extracted from said input speech with stored information about the user'"'"' speech characteristics.

32. The method of claim 29 further comprising storing profile information based on the identity of an equipment user and using said profile information in controlling the operation of said equipment.

33. The method of claim 29 further comprising providing an eigenspace corresponding to a plurality of training speakers and using said eigenspace in ascertaining said user'"'"'s identity.

34. The method of claim 29 further comprising performing speech recognition upon said input speech to extract command information from said speech and using said command information to further control the operation of said equipment.

35. The method of claim 29 further comprising performing speech recognition and language parsing upon said input speech to extract semantic information from said speech and using said semantic information to further control the operation of said equipment.

36. The method of claim 29 further comprising impeding said user'"'"'s control of said equipment based on said ascertained identity.

37. The method of claim 29 further comprising storing profile information based on the identity of an equipment user and impeding said user'"'"'s control of said equipment based on said ascertained identity and on said stored profile information.

38. The method of claim 29 further comprising:

storing profile information based on the identity of an equipment user, said profile information identifying at least one predetermined program selection; and

blocking said equipment from accessing said at least one predetermined program selection based on said ascertained identity.