System and method of developing a TTS voice

• US 7,996,226 B2
• Filed: 12/15/2009
• Issued: 08/09/2011
• Est. Priority Date: 09/27/2005
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: AT&T Intellectual Property II LP (AT&T, Inc.)
• Inventors: Davis, Steven Lawrence, Fetters, Shane, Schulz, David Eugene, Gustafson, Beverly, Loney, Louise
• Primary Examiner(s): Vo, Huyen X.
• Application Number:
  US12/638,648
• Publication Number:
  US 20100094632A1
• Time in Patent Office: 602 Days
• Field of Search: 704/1, 704/9, 704/10, 704/258, 704/260, 704/261, 704/266, 704/270
• US Class Current: 704/260
• CPC Class Codes: G10L 13/04 Details of speech synthesis systems, e.g. synthesiser structure or memory management

Abstract

Disclosed herein are various aspects of a toolkit used for generating a TTS voice for use in a spoken dialog system. The embodiments in each case may be in the form of the system, a computer-readable medium or a method for generating the TTS voice. An embodiment of the invention relates to a method of tracking progress in developing a text-to-speech (TTS) voice. The method comprises insuring that a corpus of recorded speech contains reading errors and matches an associated written text, creating a tuple for each utterance in the corpus and tracking progress for each utterance utilizing the tuple. Various parameters may be tracked using the tuple but the tuple provides a means for enabling multiple workers to efficiently process a database of utterance in preparation of a TTS voice.

Claims

1. A method of tracking progress in developing a text-to-speech (TTS) voice, the method causing a computing device to perform steps comprising:

checking a corpus of recorded speech for conformity between the corpus and a text;

creating, via a processor of the computing device, a tuple of files for each utterance in the corpus, wherein the tuple is used to track work on each utterance for developing the TTS voice; and

tracking progress of developing the TTS voice with respect to the each utterance using at least the tuple of files created for the each utterance, wherein each tuple comprises automatic speech recognition generated phonemes, pronunciation lists, confidence scores and a progress matrix.

2. The method of claim 1, wherein the progress matrix stores and tracks work performed on the tuple.

3. The method of claim 2, wherein the progress matrix further stores information about which person has performed work on the tuple.

4. The method of claim 3, wherein work-tracking information is stored in the progress matrix such that several people may simultaneously work on the corpus.

5. A non-transitory computer-readable storage medium storing instructions which, when executed by a computing device, cause the computing device to track progress in developing a text-to-speech (TTS) voice, the instructions comprising:

checking a corpus of recorded speech for conformity between the corpus and a text;

creating, via a processor, a tuple of files for each utterance in the corpus, wherein the tuple is used to track work on each utterance for developing the TTS voice; and

tracking progress of developing the TTS voice with respect to the each utterance using at least the tuple of files created for the each utterance, wherein each tuple comprises automatic speech recognition generated phonemes, pronunciation lists, confidence scores and a progress matrix.

6. The non-transitory computer-readable storage medium of claim 5, wherein the progress matrix stores and tracks work performed on the tuple.

7. The non-transitory computer-readable storage medium of claim 6, wherein the progress matrix further stores information about which person has performed work on the tuple.

8. The non-transitory computer-readable storage medium of claim 7, wherein work-tracking information is stored in the progress matrix such that several people may simultaneously work on the corpus.

9. A computing device that tracks progress in developing a text-to-speech (TTS) voice, the computing device comprising:

a processor;

a module controlling the processor to check a corpus of recorded speech for conformity between the corpus and a text;

a module controlling the processor to create a tuple of files for each utterance in the corpus, wherein the tuple is used to track work on each utterance for developing the TTS voice; and

tracking progress of developing TTS voice with respect to the each utterance using at least the tuple of files created for the each utterance, wherein each tuple comprises automatic speech recognition generated phonemes, pronunciation lists, confidence scores and a progress matrix.

10. The computing device of claim 9, wherein the progress matrix stores and tracks work performed on the tuple.

11. The computing device of claim 10, wherein the progress matrix further stores information about which person has performed work on the tuple.

12. The computing device of claim 11, wherein work-tracking information is stored in the progress matrix such that several people may simultaneously work on the corpus.