System and Method for Configuring Voice Synthesis

• US 20140081642A1
• Filed: 11/26/2013
• Published: 03/20/2014
• Est. Priority Date: 06/05/2002
• Status: Active Grant

• Current Assignee: Interactions, LLC
• Original Assignee: AT&T Intellectual Property II LP (AT&T, Inc.)
• Inventors: Rosen, Kenneth H., Creswell, Carroll W., Farah, Jeffrey J., Bansal, Pradeep K., Syrdal, Ann K.
• Granted Patent: US 9,460,703 B2
• Time in Patent Office: Days
• US Class Current: 704/258
• CPC Class Codes: G10L 13/02 Methods for producing synthetic speech; Speech synthesisers
• CPC Class Codes: G10L 13/033 Voice editing, e.g. manipulating the voice of the synthesiser

Abstract

Systems and methods for providing synthesized speech in a manner that takes into account the environment where the speech is presented. A method embodiment includes, based on a listening environment and at least one other parameter associated with at least one other parameter, selecting an approach from the plurality of approaches for presenting synthesized speech in a listening environment, presenting synthesized speech according to the selected approach and based on natural language input received from a user indicating that an inability to understand the presented synthesized speech, selecting a second approach from the plurality of approaches and presenting subsequent synthesized speech using the second approach.

Claims

1. A method comprising:

playing synthesized speech, wherein the synthesized speech is synthesized using a historical speech template;

receiving from a user an indication of inability to understand the synthesized speech;

receiving an environmental input indicating environmental conditions near the user;

selecting, based on the environmental input, an environmental speech template;

modifying, via a processor, the synthesized speech using the environmental speech template, to yield modified synthesized speech; and

playing the modified synthesized speech.

2. The method of claim 1, further comprising recording the modified synthesized speech in a suggestion database.

3. The method of claim 2, wherein the suggestion database comprises environmental speech templates based on one of a connection type, a bandwidth available, and an abnormal human perception.

4. The method of claim 1, wherein the modified synthesized speech comprises phonemes modified according to the environmental speech template.

5. The method of claim 1, wherein the selecting, based on the environmental input, the environmental speech template further comprises matching the environmental input to a plurality of environmental variables in a matrix.

6. The method of claim 5, wherein a match is identified when a spectral difference between the environmental input and a property of an entity exceeds a threshold.

7. The method of claim 6, wherein the spectral difference is frequency weighted based on human auditory perception.

8. A system comprising:

a processor; and

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

playing synthesized speech, wherein the synthesized speech is synthesized using a historical speech template;

receiving from a user an indication of inability to understand the synthesized speech;

receiving an environmental input indicating environmental conditions near the user;

selecting, based on the environmental input, an environmental speech template;

modifying the synthesized speech using the environmental speech template, to yield modified synthesized speech; and

playing the modified synthesized speech.

9. The system of claim 8, the computer-readable storage medium having additional instructions stored which result in the operations further comprising recording the modified synthesized speech in a suggestion database.

11. The system of claim 8, wherein the modified synthesized speech comprises phonemes modified according to the environmental speech template.

12. The system of claim 8, wherein the selecting, based on the environmental input, the environmental speech template further comprises matching the environmental input to a plurality of environmental variables in a matrix.

13. The system of claim 12, wherein a match is identified when a spectral difference between the environmental input and a property of an entity exceeds a threshold.

14. The method of claim 13, wherein the spectral difference is frequency weighted based on human auditory perception.

10. The system of claim 10, wherein the suggestion database comprises environmental speech templates based on one of a connection type, a bandwidth available, and an abnormal human perception.

15. A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:

playing synthesized speech, wherein the synthesized speech is synthesized using a historical speech template;

receiving from a user an indication of inability to understand the synthesized speech;

receiving an environmental input indicating environmental conditions near the user;

selecting, based on the environmental input, an environmental speech template;

modifying the synthesized speech using the environmental speech template, to yield modified synthesized speech; and

playing the modified synthesized speech.

16. The computer-readable storage device of claim 15, the computer-readable storage medium having additional instructions stored which result in the operations further comprising recording the modified synthesized speech in a suggestion database.

17. The computer-readable storage device of claim 16, wherein the suggestion database comprises environmental speech templates based on one of a connection type, a bandwidth available, and an abnormal human perception.

18. The computer-readable storage device of claim 15, wherein the modified synthesized speech comprises phonemes modified according to the environmental speech template.

19. The computer-readable storage device of claim 15, wherein the selecting, based on the environmental input, the environmental speech template further comprises matching the environmental input to a plurality of environmental variables in a matrix.

20. The computer-readable storage device of claim 19, wherein a match is identified when a spectral difference between the environmental input and a property of an entity exceeds a threshold.