SYSTEM AND METHOD FOR IMPROVING SYNTHESIZED SPEECH INTERACTIONS OF A SPOKEN DIALOG SYSTEM

• US 20090112596A1
• Filed: 10/30/2007
• Published: 04/30/2009
• Est. Priority Date: 10/30/2007
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: AT&T Labs Incorporated (AT&T, Inc.)
• Inventors: Beutnagel, Mark, Kim, Yeon-Jun, Syrdal, Ann K., Conkie, Alistair D.
• Granted Patent: US 8,566,098 B2
• Time in Patent Office: Days
• US Class Current: 704/260
• 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

Abstract

A system and method are disclosed for synthesizing speech based on a selected speech act. A method includes modifying synthesized speech of a spoken dialogue system, by (1) receiving a user utterance, (2) analyzing the user utterance to determine an appropriate speech act, and (3) generating a response of a type associated with the appropriate speech act, wherein in linguistic variables in the response are selected, based on the appropriate speech act.

Claims

1. A method of modifying synthesized speech of a spoken dialogue system, the method comprising:

receiving a user utterance;

analyzing the user utterance to determine an appropriate speech act; and

generating a response of a type associated with the appropriate speech act, wherein linguistic variables in the response are selected based on the appropriate speech act.

2. The method of claim 1, wherein the linguistic variables are one or more of the group consisting of verbiage, vocabulary, pronunciation, phrasing, pauses, prosody and pitch.

3. The method of claim 1, wherein the appropriate speech act is selected from the group consisting of detail information, general information, “

wh”

questions, yes/no questions, multiple choice questions, greetings, goodbyes, apologies, thanks, requests, directives, repeat, wait, confirmations, disconfirmations, positive exclamations, filled pause, and negative exclamations.

4. The method of claim 1, wherein the generated response is generated using text-to-speech technology.

5. The method of claim 1, wherein the generating step may include

selecting at least one phoneme from a catalogue of a plurality of phonemes, which the catalogue organizes phonemes based on associated speech acts;

and

generating the response based on the selected at least one phoneme.

6. The method of claim 1, wherein the generating step may include:

accessing a catalogue containing a plurality of phrases;

selecting at least one phrase, from the plurality of phrases, associated with the appropriate speech act; and

generating the response based on the selected at least one phrase.

8. The computer readable medium of claim 6 wherein the instructions provide that linguistic variables be one or more of the group consisting of verbiage, vocabulary, pronunciation, phrasing, pauses, prosody and pitch.

9. The computer-readable medium of claim 6 wherein the instructions provide that the appropriate speech act is selected from the group consisting of detail information, general information, “

wh”

questions, yes/no questions, multiple choice questions, greetings, goodbyes, apologies, thanks, requests, directives, repeat, wait, confirmations, disconfirmations, positive exclamations, and negative exclamations.

10. The computer-readable medium of claim 6, wherein the generated response is generated using text-to-speech technology.

11. The computer-readable medium of claim 6, wherein the instructions for the generating step may include:

selecting at least one phoneme from a catalogue of a plurality of phonemes, which the catalogue organizes phonemes based on associated speech acts; and

generating the response based on the selected at least one phoneme.

12. The computer readable medium of claim 6, wherein the instructions for the generating step may include:

accessing a catalogue containing a plurality of phrases;

selecting at least one phrase, from the plurality of phrases, associated with the appropriate speech act; and

generating the response based on the selected at least one phrase.

14. The system of claim 11 wherein the linguistic variables are one or more of the group consisting of verbiage, vocabulary, pronunciation, phrasing, pauses, prosody and pitch.

15. The system of claim 11, wherein the appropriate speech act is selected from the group consisting of detail information, general information, “

wh”

questions, yes/no questions, multiple choice questions, greetings, goodbyes, apologies, thanks, requests, directives, repeat, wait, confirmations, disconfirmations, positive exclamations, and negative exclamations.

16. The system of claim 11, wherein the module configured to generate a response uses text-to-speech technology.

17. The system of claim 11, wherein the module configured to generate may include:

a module configured to select at least one phoneme from a catalogue of a plurality of phonemes, which the catalogue organizes phonemes based on associated speech acts; and

a module configured to generate the response based on the selected at least one phoneme.

18. The system of claim 11, wherein the module configured to generate may include:

a module configured to select at least one phrases from a catalogue of a plurality of phrases, which catalogue organizes phonemes based on associated speech acts; and

a module configured to generate the response based on the selected at least one phrase.

7. A computer-readable medium storing instructions for a computing device to function as a spoken dialogue system, the instructions comprising:

receiving a user utterance;

analyzing the user utterance to determine an appropriate speech act; and

generating a response of a type associated with the appropriate speech act, wherein linguistic variables in the response are selected based on the appropriate speech act.

13. A spoken dialogue system comprising:

a module configured to receive a user utterance;

a module configured to analyze the user utterance to determine an appropriate speech act; and

a module configured to generate a response of a type associated with the appropriate speech act, wherein linguistic variables in the response are selected based on the appropriate speech act.