System and method for data-driven socially customized models for language generation

• US 9,412,358 B2
• Filed: 05/13/2014
• Issued: 08/09/2016
• Est. Priority Date: 05/13/2014
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Stoyanchev, Svetlana, Mishra, Taniya, Conkie, Alistair D.
• Primary Examiner(s): Hudspeth, David
• Assistant Examiner(s): PATEL, SHREYANS A
• Application Number:
  US14/275,938
• Publication Number:
  US 20150332665A1
• Time in Patent Office: 819 Days
• US Class Current: 1/1
• CPC Class Codes: G10L 13/027 Concept to speech synthesisers; Generation of natural phrases from machine-based concepts generation of parameters for speech synthesis out of text G10L13/08
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/07 to the speaker
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces

Abstract

Systems, methods, and computer-readable storage devices for generating speech using a presentation style specific to a user, and in particular the user'"'"'s social group. Systems configured according to this disclosure can then use the resulting, personalized, text and/or speech in a spoken dialogue or presentation system to communicate with the user. For example, a system practicing the disclosed method can receive speech from a user, identify the user, and respond to the received speech by applying a personalized natural language generation model. The personalized natural language generation model provides communications which can be specific to the identified user.

Claims

1. A method comprising:

receiving speech from a user as part of a dialog between the user and a dialog system;

identifying, via a processor configured to perform speech analysis, an identity of the user using characteristics of the speech, to yield a user identification;

generating a personalized natural language generation model based on a stylistic analysis and the user identification, wherein the stylistic analysis is performed on a literary narrative, and wherein the stylistic analysis identifies connections between a personality independent quotation lattice, personality independent attributes, personality dependent attributes, and speakers within the literary narrative; and

applying the personalized natural language generation model while performing, as part of the dialog, one of automatic speech recognition and natural language generation.

2. The method of claim 1, wherein stylistic analysis further comprises:

identifying the speakers in the literary narrative, to yield identified speakers;

attributing quoted utterances in the literary narrative to the identified speakers, to yield a quotation lattice;

identifying the personality independent attributes and the personality dependent attributes of the quoted utterances within the quotation lattice; and

organizing the quotation lattice based on the personality independent attributes, to yield a personality independent quotation lattice.

3. The method of claim 1, wherein the stylistic analysis further comprises identifying a lexical difference between quotations associated with distinct demographics of the speakers.

4. The method of claim 1, wherein the stylistic analysis further comprises identifying a semantic difference between quotations associated with distinct demographics of the speakers.

5. The method of claim 1, wherein the stylistic analysis comprises identifying both a lexical difference and a semantic difference between quotations associated with distinct demographics of the speakers.

6. The method of claim 1, wherein the user identification comprises demographic data of the user.

7. The method of claim 1, wherein the identifying of the user from the speech further comprises performing a prosody analysis of the speech.

8. The method of claim 1, wherein the identifying of the user from the speech further requires the speech to comprise user log-in information.

9. The method of claim 1, wherein the dialog system does not use templates when using the personalized natural language generation model.

10. A system comprising:

a processor configured to perform speech analysis; and

a computer-readable storage medium having instructions stored which, when executed by the processor, case the processor to perform operations comprising;

receiving speech from a user as part of a dialog between the user and a dialog system;

identifying an identity of the user using characteristics of the speech, to yield a user identification;

generating a personalized natural language generation model based on a stylistic analysis and the user identification, wherein the stylistic analysis is performed on a literary narrative, and wherein the stylistic analysis identifies connections between a personality independent quotation lattice, personality independent attributes, personality dependent attributes, and speakers within the literary narrative; and

applying the personalized natural language generation model while performing, as part of the dialog, one of automatic speech recognition and natural language generation.

11. The system of claim 10, wherein stylistic analysis further comprises:

identifying the speakers in the literary narrative, to yield identified speakers;

attributing quoted utterances in the literary narrative to the identified speakers, to yield a quotation lattice;

identifying the personality independent attributes and the personality dependent attributes of the quoted utterances within the quotation lattice; and

organizing the quotation lattice based on the personality independent attributes, to yield a personality independent quotation lattice; and

organizing the personality independent quotation lattice based on a stylistic analysis of the personality independent quotation lattice.

12. The system of claim 10, wherein the stylistic analysis further comprises identifying a lexical difference between quotations associated with distinct demographics of the speakers.

13. The system of claim 10, wherein the stylistic analysis further comprises identifying a semantic difference between quotations associated with distinct demographics of the speakers.

14. The system of claim 10, wherein the stylistic analysis further comprises identifying both a lexica difference and a semantic difference between quotations associated with distinct demographics of the speakers.

15. The system of claim 10, wherein the user identification comprises demographic data of the user.

16. The system of claim 10, wherein the identifying of the user from the speech further comprises performing a prosody analysis of the speech.

17. The system of claim 10, wherein the identifying of the user from the speech requires the speech to comprise user log-in information.

18. The system of claim 10, wherein the dialog system does not use templates when using the personalized natural language generation model.

19. A computer-readable storage device having instructions stored which, when executed by a computing device configured to perform speech analysis, case the computing device to perform operations comprising:

receiving speech from a user as part of a dialog between the user and a dialog system;

identifying, via a processor, the user from the speech, to yield a user identification; and

applying a personalized natural language generation model while performing, as part of the dialog, one of automatic speech recognition and natural language generation, wherein the personalized natural language generation model comprises a personality independent quotation lattice organized using a stylistic analysis of the personality independent quotation lattice, personality independent attributes, personality dependent attributes, and speakers identified within a literary narrative,

wherein organizing the personality independent quotation lattice using the stylistic analysis of the personality independent quotation lattice, the personality independent attributes, the personality dependent attributes, and the speakers identified within a literary narrative comprises;

identifying the speakers in the literary narrative, to yield identified speakers;

attributing quoted utterances in the literary narrative to the identified speakers, to yield a quotation lattice;

identifying the personality independent attributes and the personality dependent attributes of the quoted utterances within the quotation lattice; and

organizing the quotation lattice based on the personality independent attributes, to yield a personality independent quotation lattice; and

organizing the personality independent quotation lattice based on a stylistic analysis of the personality independent quotation lattice, to yield the personalized natural language generation model.

20. The computer-readable storage device of claim 19, wherein the stylistic analysis further comprises identifying both a lexica difference and a semantic difference between quotations associated with distinct demographics of the speakers.