System and method for configuring voice synthesis

• US 8,086,459 B2
• Filed: 10/28/2009
• Issued: 12/27/2011
• Est. Priority Date: 06/05/2002
• Status: Expired due to Fees

• Current Assignee: Interactions, LLC
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Rosen, Kenneth H., Creswell, Carroll W., Farah, Jeffrey J., Bansal, Pradeep K., Syrdal, Ann K.
• Primary Examiner(s): Chawan, Vijay B
• Application Number:
  US12/607,362
• Publication Number:
  US 20100049523A1
• Time in Patent Office: 790 Days
• Field of Search: 704/260, 704/275, 704/223, 704/270, 704/220, 704/267, 704/258, 704/246, 434/236, 715/203, 379/88.16
• US Class Current: 704/270
• 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, via a processor, synthesized speech according to an approach selected based on at least one of a connection characteristic, a spectral difference between an input corresponding to at least one of environmental ambient noise and characteristic spectral properties of an entity, and a bandwidth availability to yield first synthesized speech; and

based on natural language input received from a user indicating an inability to understand the first synthesized speech, playing subsequent synthesized speech according to a different approach from the first synthesized speech.

2. The method of claim 1, wherein the first synthesized speech is further based at least one other parameter associated with at least one of physiological aspects, psychological aspects of perception, and historical data.

3. The method of claim 1, wherein the approach is selected further by matching a listening environment to at least one entity associated with corresponding approach for presenting the synthesized speech.

4. The method of claim 3, wherein the at least one entity comprises at least one of phonemes and phoneme classes.

5. The method of claim 1, wherein the approach is further associated with specifying phonemes for use in playing the synthesized speech.

6. A system for generating speech, the system comprising:

a processor;

a first module that controls the processor to present synthesized speech according to an approach selected based on at least one of a connection characteristic, a spectral difference between an input corresponding to at least one of environmental ambient noise and characteristic spectral properties of an entity, and a bandwidth availability to yield first synthesized speech; and

a second module that controls the processor to present subsequent synthesized speech based on natural language input received from a user indicating an inability to understand the first synthesized speech, the subsequent synthesized speech being presented according to a different approach from the first synthesized speech.

7. The system of claim 6, wherein the first synthesized speech is further based on at least one other parameter associated with at least one of physiological aspects, psychological aspects of perception, and historical data.

8. The system of claim 6, wherein the approach is selected further by matching a listening environment to at least one entity associated with corresponding approach for presenting the first synthesized speech.

9. The system of claim 8, wherein the at least one entity comprises at least one of phonemes and phoneme classes.

10. The system of claim 6, wherein the approach is further associated with specifying phonemes for use in presenting the first synthesized speech.

11. A non-transitory computer-readable medium storing instructions for a computing device, the instructions causing the computing device to perform steps comprising:

playing synthesized speech according to an approach selected based on at least one of a connection characteristic, a spectral difference between an input corresponding to at least one of environmental ambient noise and characteristic spectral properties of an entity, and a bandwidth availability to yield first synthesized speech; and

based on natural language input received from a user indicating an inability to understand the first synthesized speech, playing subsequent synthesized speech according to a different approach from the first synthesized speech.

12. The non-transitory computer-readable medium of claim 11, wherein the first synthesized speech is further based on at least one other parameter associated with at least one of physiological aspects, psychological aspects of perception, and historical data.

13. The non-transitory computer-readable medium of claim 11, wherein the approach is selected further by matching a listening environment to at least one entity associated with corresponding approach for presenting the first synthesized speech.

14. The computer-readable medium of claim 13, wherein the at least one entity comprises at least one of phonemes and phoneme classes.

15. The computer-readable medium of claim 11, wherein the approach is further associated with specifying phonemes for use in presenting the first synthesized speech.