Tabulating triphone sequences by 5-phoneme contexts for speech synthesis

• US 8,566,099 B2
• Filed: 07/16/2012
• Issued: 10/22/2013
• Est. Priority Date: 06/30/2000
• Status: Expired due to Fees

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: AT&T Intellectual Property II LP (AT&T, Inc.)
• Inventors: Conkie, Alistair D.
• Primary Examiner(s): Lerner, Martin
• Application Number:
  US13/550,074
• Publication Number:
  US 20130013312A1
• Time in Patent Office: 463 Days
• Field of Search: 704/258, 704/260, 704/263, 704/266, 704/267
• US Class Current: 704/258
• CPC Class Codes: G10L 13/07 Concatenation rules
• CPC Class Codes: G10L 2015/022 Demisyllables, biphones or triphones being the recognition units

Abstract

A system and method for improving the response time of text-to-speech synthesis using triphone contexts. The method includes identifying a set of triphone sequences, tabulating the set of triphone sequences using a plurality of contexts, where each context specific triphone sequence of the plurality of context specific triphone sequences has a top N triphone units made of the triphone units having lowest target costs when each triphone unit is individually combined into a 5-phoneme combination. Input texts having one of the contexts are received, and one of the context specific triphone sequences is selected based on the context. Input text is then synthesized using the context specific triphone sequence.

Claims

1. A method comprising:

identifying a set of triphone sequences;

tabulating, via a processor, the set of triphone sequences using a plurality of contexts, to yield a plurality of context specific triphone sequences, each context specific triphone sequence of the plurality of context specific triphone sequences having a top N triphone units comprising those triphone units having lower target costs when each triphone unit is individually combined into a 5-phoneme combination;

receiving an input text having one of the plurality of contexts;

selecting one of the context specific triphone sequences based on the one context; and

synthesizing the input text using the one context specific triphone sequence.

2. The method of claim 1, wherein the lowest target costs are calculated using a Viterbi search.

3. The method of claim 1, further comprising after receiving the input text and prior to selecting the one context specific triphone sequence, parsing the input text into recognizable units.

4. The method of claim 3, wherein parsing the input text further comprises:

applying a text normalization process to parse the input text into known words and converting abbreviations into known words;

applying a syntactic process to perform a grammatical analysis of the known words; and

identifying parts of speech in the known words based on the syntactic process.

5. The method of claim 1, wherein the set of triphone sequences is stored in a database.

6. The method of claim 1, wherein synthesizing the input text further comprises usage of a prosody determination device.

7. 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;

identifying a set of triphone sequences;

tabulating the set of triphone sequences using a plurality of contexts, to yield a plurality of context specific triphone sequences, each context specific triphone sequence of the plurality of context specific triphone sequences having a top N triphone units comprising those triphone units having lower target costs when each triphone unit is individually combined into a 5-phoneme combination;

receiving an input text having one of the plurality of contexts;

selecting one of the context specific triphone sequences based on the one context; and

synthesizing the input text using the one context specific triphone sequence.

8. The system of claim 7, wherein the lowest target costs are calculated using a Viterbi search.

9. The system of claim 7, the computer-readable storage medium having additional instructions stored which result in the operations further comprising after receiving the input text and prior to selecting the context specific triphone sequence, parsing the input text into recognizable units.

10. The system of claim 9, wherein parsing the input text further comprises:

applying a text normalization process to parse the input text into known words and converting abbreviations into known words;

applying a syntactic process to perform a grammatical analysis of the known words; and

identifying parts of speech in the known words based on the syntactic process.

11. The system of claim 7, wherein the set of triphone sequences is stored in a database.

12. The system of claim 7, wherein synthesizing the input text further comprises usage of a prosody determination device.

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

identifying a set of triphone sequences;

tabulating the set of triphone sequences using a plurality of contexts, to yield a plurality of context specific triphone sequences, each context specific triphone sequence of the plurality of context specific triphone sequences having a top N triphone units comprising those triphone units having lower target costs when each triphone unit is individually combined into a 5-phoneme combination;

receiving an input text having one of the plurality of contexts;

selecting one of the context specific triphone sequences based on the one context; and

synthesizing the input text using the one context specific triphone sequence.

14. The computer-readable storage device of claim 13, wherein the lowest target costs are calculated using a Viterbi search.

15. The computer-readable storage device of claim 13, the computer-readable storage device having additional instructions stored which result in the operations further comprising after receiving the input text and prior to selecting the context specific triphone sequence, parsing the input text into recognizable units.

16. The computer-readable storage device of claim 15, wherein parsing the input text further comprises:

applying a text normalization process to parse the input text into known words and converting abbreviations into known words;

applying a syntactic process to perform a grammatical analysis of the known words; and

identifying parts of speech in the known words based on the syntactic process.

17. The computer-readable storage device of claim 13, wherein the set of triphone sequences is stored in a database.

18. The computer-readable storage device of claim 13, wherein synthesizing the input text further comprises usage of a prosody determination device.