System and method for configuring voice synthesis

• US 7,624,017 B1
• Filed: 10/26/2007
• Issued: 11/24/2009
• 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., Syrdal, Ann K., Bansal, Pradeep K., Farah, Jeffrey J.
• Primary Examiner(s): Chawan; Vijay B
• Application Number:
  US11/924,682
• Time in Patent Office: 760 Days
• Field of Search: 704/258, 704/260, 704/220, 704/267, 704/235, 704/223, 704/257, 704/275, 704/270, 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 for controlling a spoken dialog system, the method comprising:

based on a listening environment and at least one other parameter associated with at least one of a connection characteristic, a spectral difference, or a bandwidth availability, selecting an approach from a plurality of approaches for presenting synthesized speech in the listening environment;

presenting synthesized speech according to the selected approach; and

based on natural language input received from a user indicating 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.

2. The method of claim 1, wherein the at least one other parameter further comprises at least one of physiological aspects, psychological aspects of perception, and historical data.

3. The method of claim 1, wherein selecting an approach further comprises matching the listening environment to at least one entity associated with an approach for presenting the synthesized speech.

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

5. The method of claim 1, wherein selecting an approach further comprises specifying phonemes for use in presenting the synthesized speech.

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

a suggestion module that receives environmental input associated with a listening environment and generates a first suggestion of an approach for presenting speech in the listening environment;

a historical suggestion module that receives the environmental input and generates a second suggestion for presenting speech in the listening environment based on historical data for presenting speech in the listening environment;

a selection module that receives at least the first and second suggestion and selects the approach for presenting the speech; and

a speech synthesis module that presents speech in the listening environment based at least in part on the selected approach.

7. The system of claim 6, further comprising:

a modification module that receives the selected approach and a separate input and modifies the selected approach based on the input and outputs a modified selection; and

wherein the speech synthesis module receives the modified selection and presents speech in the listening environment based on the modified selection.

8. The system of claim 7, wherein the separate input comprises input from a user.

9. The system of claim 8, wherein the user input requests at least one of the following speech characteristics:

lower, higher, softer, louder, slower, faster, higher pitched, or lower pitched.

10. The system of claim 7, wherein the separate input is an instruction from a user to modify synthesized speech.

11. The system of claim 7, wherein the input to the modification module results in different phonemes being selected for speech synthesis than would be selected based on output from the selection module.

12. A computer-implemented method of synthesized speech, the method comprising:

receiving environmental input and generating a first suggestion for a first approach to present speech in a listening environment;

receiving the environmental input and generating a second suggestion for a second approach to present speech in the listening environment based on historical data associated with presenting speech in the listening environment;

receiving the suggestion of the first approach and the suggestion of the second approach and generating a selection of an approach based on the first suggestion and second suggestion;

receiving separate input regarding how to present the speech;

modifying the selected approach based on the separate input; and

presenting speech in the listening environment based on the modified selected approach.

13. The method of claim 12, wherein the separate input is user input.

14. The method of claim 12, further comprising:

selecting phonemes for presenting the speech based on the modified selected approach.