METHOD AND SYSTEM FOR PRESELECTION OF SUITABLE UNITS FOR CONCATENATIVE SPEECH

• US 20090094035A1
• Filed: 12/01/2008
• Published: 04/09/2009
• Est. Priority Date: 06/30/2000
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: AT&T Corporation (AT&T, Inc.)
• Inventors: Conkie, Alistair D.
• Granted Patent: US 8,224,645 B2
• Time in Patent Office: Days
• US Class Current: 704/260
• 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 utilizes “triphone contexts” (i.e., triplets comprising a central phoneme and its immediate context) as the basic unit, instead of performing phoneme-by-phoneme synthesis. The method comprises a method of generating a triphone preselection cost database for use in speech synthesis, the method comprising 1) selecting a triphone sequence u₁-u₂-u₃, 2) calculating a preselection cost for each 5-phoneme sequence u_a-u₁-u₂-u₃-u_b, where u₂ is allowed to match any identically labeled phoneme in a database and the units u_a and u_b vary over the entire phoneme universe and 3) storing a group of the selected triphone sequences exhibiting the lowest costs in a triphone preselection cost database.

Claims

1. A method of speech synthesis, the method comprising:

receiving input text;

selecting a plurality of N phoneme units from a triphone unit selection database as candidate phonemes for synthesized speech based on the input text;

if candidate phonemes are available in the triphone unit selection database, applying a cost process to select a set of phonemes from the candidate phonemes;

if no candidate phonemes are available in the triphone unit selection database, applying a single phoneme approach to select phonemes for synthesis; and

synthesizing speech using the set of phonemes from the candidate phonemes and/or the selected phonemes for synthesis from the single phoneme approach.

2. The method of claim 1, wherein the triphone unit selection database is generated by precalculating a list of all phonemes in a phoneme database that can be used in each of a plurality of triphone contexts.

3. The method of claim 1, wherein applying the single phoneme approach to select phonemes for synthesis is performed using a complete set of phonemes of a given type.

4. The method of claim 1, wherein a Viterbi search is applied as the cost process.

5. The method of claim 1, wherein subsequent to the step of receiving input text, the method comprises parsing the received input text to recognizable units.

6. The method of claim 5, wherein parsing the received text into recognizable units further comprises:

applying a text normalization process to parse the received text into known words and convert abbreviations into known words; and

applying a syntactic process to perform a grammatical analysis of the known words and identify their associated parts of speech.

7. A computing device for synthesizing speech from text using a triphone unit selection database, the computing device comprising:

a processor;

a module configured to control the processor to receive input text;

a module configured to control the processor to select a plurality of N phoneme units from the triphone unit selection database as candidate phonemes for synthesized speech based on the input text;

a module configured to control the processor to apply a cost process to select a set of phonemes from the candidate phonemes; and

a module configured to control the processor to synthesize speech using a selected set of phonemes.

8. The computing device of claim 7, wherein a Viterbi search is applied as the cost process.

9. The computing device of claim 7, further comprising a module configured to control the processor to parse received text into recognizable units.

10. The computing device of claim 9, wherein the module configured to control the processor to parse the received text in a recognizable unit further:

apply a text normalization process to parse the received text into known words and convert abbreviations into known words; and

apply a syntactic process to perform a grammatical analysis of the known words and identify their associated parts of speech.

11. A tangible computer-readable medium storing instructions for controlling a computing device to synthesize speech from text using a triphone unit selection database, the instructions comprising:

receiving input text;

selecting a plurality of N phoneme units from a triphone unit selection database as candidate phonemes for synthesized speech based on the input text;

applying a cost process to select a set of phonemes from the candidate phonemes; and

synthesizing speech using the set of phonemes.

13. The tangible computer-readable medium of claim 12, wherein subsequent to the step of receiving the input text the following step is performed:

parsing the received text into recognizable units.

14. The tangible computer-readable medium of claim 13, wherein the parsing comprises the steps of:

applying a text normalization process to parse the received text into known words;

convert abbreviations into known words; and

applying a syntactic process to perform a grammatical analysis of the know words and identify their associated part of speech.

15. A computing device for synthesizing speech, the computing device comprising:

a processor;

a module configured to control the processor to receive input text;

a module configured to control the processor to select a plurality of N phonemes from a triphone unit selection database as candidate phonemes for a synthesized speech based on the input text;

a module configured to control the processor, if candidate phonemes are available in the triphone unit selection database, to apply a cost process to select a set of phonemes from the candidate phonemes;

a module configured to control the processor, if no candidate phonemes are available in the triphone unit selection database, to apply a single phoneme approach to select phonemes for synthesis; and

a module configured to control the processor to synthesize speech using the set of phonemes from the candidate phonemes and/or the selected phonemes for synthesis from the single phoneme approach.

16. The computing device of claim 15, wherein the triphone unit selection database is generated by precalculating a list of all phonemes in a phoneme database that can be used in each of a plurality of triphone contexts.

17. The computing device of claim 15, wherein the module configured to apply a single phoneme approach further applies the single phoneme approach by using a complete set of phonemes of a given type.