System and method for cloud-based text-to-speech web services

• US 9,009,050 B2
• Filed: 11/30/2010
• Issued: 04/14/2015
• Est. Priority Date: 11/30/2010
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Beutnagel, Mark Charles, Conkie, Alistair D., Kim, Yeon-Jun, Schroeter, Horst Juergen
• Primary Examiner(s): AZAD, ABUL K
• Application Number:
  US12/956,354
• Publication Number:
  US 20120136664A1
• Time in Patent Office: 1,596 Days
• Field of Search: 704/270.1, 704258-269
• US Class Current: 704/260
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 13/04 Details of speech synthesis systems, e.g. synthesiser structure or memory management

Abstract

Disclosed herein are systems, methods, and non-transitory computer-readable storage media for generating speech. One variation of the method is from a server side, and another variation of the method is from a client side. The server side method, as implemented by a network-based automatic speech processing system, includes first receiving, from a network client independent of knowledge of internal operations of the system, a request to generate a text-to-speech voice. The request can include speech samples, transcriptions of the speech samples, and metadata describing the speech samples. The system extracts sound units from the speech samples based on the transcriptions and generates an interactive demonstration of the text-to-speech voice based on the sound units, the transcriptions, and the metadata, wherein the interactive demonstration hides a back end processing implementation from the network client. The system provides access to the interactive demonstration to the network client.

Claims

1. A method comprising:

receiving, at a network-based automatic speech processing system, a request, from a network client independent of information of internal operations of the network-based automatic speech processing system, to generate a text-to-speech voice, the request comprising speech samples, transcriptions of the speech samples, and metadata describing the speech samples;

extracting sound units from the speech samples based on the transcriptions;

generating a demonstration of the text-to-speech voice based only on the sound units, the transcriptions, and the metadata, wherein the text-to-speech voice is language agnostic; and

providing access to the demonstration to the network client.

2. The method of claim 1, further comprising:

receiving an additional request from the network client for the text-to-speech voice; and

providing the text-to-speech voice to the network client.

3. The method of claim 1, wherein the request is received via a web interface.

4. The method of claim 1, wherein the speech samples are required to meet a minimum quality threshold.

5. The method of claim 1, wherein the network-based speech processing system comprises a language analysis module, a database, and an acoustic synthesis module.

6. The method of claim 1, wherein the text-to-speech voice is language agnostic.

7. The method of claim 1, further comprising:

analyzing the speech samples;

determining a coverage hole in the speech samples for a particular purpose; and

suggesting, to the network client, a type of additional speech sample intended to address the coverage hole.

8. The method of claim 7, wherein analyzing, determining, and suggesting is done iteratively until a threshold coverage for the particular purpose is reached.

9. The method of claim 1, further comprising generating a log associated with the demonstration.

10. The method of claim 9, further comprising transmitting the log to the network client.

11. The method of claim 1, further comprising modifying one of the sound units and the demonstration based on an intervention from a human expert.

12. 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;

receiving a request, from a network client independent of information of internal operations of a network-based automatic speech processing system, to generate the text-to-speech voice, the request comprising speech samples, transcriptions of the speech samples, and metadata describing the speech samples;

extracting sound units from the speech samples based on the transcriptions;

generating a demonstration of the text-to-speech voice based only on the sound units, the transcriptions, and the metadata, wherein the text-to-speech voice is language agnostic; and

providing access to the demonstration to the network client.

13. The system of claim 12, the computer-readable storage medium having additional instructions stored which result in operations comprising:

receiving an additional request from the network client for the text-to-speech voice; and

providing the text-to-speech voice to the network client.

14. The system of claim 12, wherein the request is transmitted via a web interface.

15. The system of claim 12, wherein the speech samples meet a minimum quality threshold.

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

receiving, at a network-based automatic speech processing system, a request, from a network client independent of information of internal operations of the network-based automatic speech processing system, to generate a text-to-speech voice, the request comprising speech samples, transcriptions of the speech samples, and metadata describing the speech samples;

extracting sound units from the speech samples based on the transcriptions;

generating a demonstration of the text-to-speech voice based only on the sound units, the transcriptions, and the metadata, wherein the text-to-speech voice is language agnostic; and

providing access to the demonstration to the network client.

17. The computer-readable storage device of claim 16, having additional instructions stored which result in operations comprising:

analyzing the speech samples;

determining a coverage hole in the speech samples for a particular purpose; and

suggesting, to the network client, a type of additional speech sample intended to address the coverage hole.

18. The computer-readable storage device of claim 17, wherein analyzing, determining, and suggesting is done iteratively until a threshold coverage for the particular purpose is reached.

19. The computer-readable storage device of claim 16, having additional instructions stored which result in operations:

generating a log associated with the demonstration.

20. The computer-readable storage device of claim 19, the instructions further comprising:

transmitting the log to the network client.