SYSTEM AND METHOD FOR UNIFIED NORMALIZATION IN TEXT-TO-SPEECH AND AUTOMATIC SPEECH RECOGNITION

• US 20160049144A1
• Filed: 08/18/2014
• Published: 02/18/2016
• Est. Priority Date: 08/18/2014
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: CONKIE, Alistair D., GOLIPOUR, Ladan
• Granted Patent: US 10,199,034 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 13/06 Elementary speech units used in speech synthesisers; Concatenation rules
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 2015/025 Phonemes, fenemes or fenones being the recognition units

Abstract

A system, method and computer-readable storage devices are for using a single set of normalization protocols and a single language lexica (or dictionary) for both TTS and ASR. The system receives input (which is either text to be converted to speech or ASR training text), then normalizes the input. The system produces, using the normalized input and a dictionary configured for both automatic speech recognition and text-to-speech processing, output which is either phonemes corresponding to the input or text corresponding to the input for training the ASR system. When the output is phonemes corresponding to the input, the system generates speech by performing prosody generation and unit selection synthesis using the phonemes. When the output is text corresponding to the input, the system trains both an acoustic model and a language model for use in future speech recognition.

Claims

1. A method comprising:

receiving input;

normalizing the input, to yield normalized input;

generating, using the normalized input and a dictionary configured for both automatic speech recognition and text-to-speech processing, output comprising one of phonemes corresponding to the input and text corresponding to the input;

when the output comprises the phonemes corresponding to the input, generating speech by performing prosody generation and unit selection synthesis using the phonemes; and

when the output comprises the text corresponding to the input, training both an acoustic model and a language model for use in future speech recognition.

2. The method of claim 1, wherein the training of the acoustic model and the language model uses the phonemes.

3. The method of claim 2, wherein the acoustic model and the language model are used in generating future speech and recognizing future speech.

4. The method of claim 1, further comprising outputting the speech to a user as part of a dialog system.

5. The method of claim 1, wherein the dictionary comprises syllable boundaries.

6. The method of claim 1, wherein the dictionary comprises contextual rules.

7. The method of claim 6, wherein the output is generated based on the contextual rules.

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;

receiving input;

normalizing the input, to yield normalized input;

generating, using the normalized input and a dictionary configured for both automatic speech recognition and text-to-speech processing, output comprising one of phonemes corresponding to the input and text corresponding to the input;

when the output comprises the phonemes corresponding to the input, generating speech by performing prosody generation and unit selection synthesis using the phonemes; and

when the output comprises the text corresponding to the input, training both an acoustic model and a language model for use in future speech recognition.

9. The system of claim 8, wherein the training of the acoustic model and the language model uses the phonemes.

10. The system of claim 9, wherein the acoustic model and the language model are used in generating future speech and recognizing future speech.

11. The system of claim 8, the computer-readable storage medium having additional instructions stored which, when executed by the processor, cause the processor to perform operations comprising outputting the speech to a user as part of a dialog system.

12. The system of claim 8, wherein the dictionary comprises syllable boundaries.

13. The system of claim 8, wherein the dictionary comprises contextual rules.

14. The system of claim 13, wherein the output is generated based on the contextual rules.

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

receiving input;

normalizing the input, to yield normalized input;

generating, using the normalized input and a dictionary configured for both automatic speech recognition and text-to-speech processing, output comprising one of phonemes corresponding to the input and text corresponding to the input;

when the output comprises the phonemes corresponding to the input, generating speech by performing prosody generation and unit selection synthesis using the phonemes; and

when the output comprises the text corresponding to the input, training both an acoustic model and a language model for use in future speech recognition.

16. The computer-readable storage device of claim 15, wherein the training of the acoustic model and the language model uses the phonemes.

17. The computer-readable storage device of claim 16, wherein the acoustic model and the language model are used in generating future speech and recognizing future speech.

18. The computer-readable storage device of claim 15, having additional instructions stored which, when executed by the computing device, cause the computing device to perform operations comprising outputting the speech to a user as part of a dialog system.

19. The computer-readable storage device of claim 15, wherein the dictionary comprises syllable boundaries.

20. The computer-readable storage device of claim 15, wherein the dictionary comprises contextual rules.