SYNTHESIS-BASED PRE-SELECTION OF SUITABLE UNITS FOR CONCATENATIVE SPEECH

• US 20070282608A1
• Filed: 05/15/2007
• Published: 12/06/2007
• Est. Priority Date: 07/05/2000
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: AT&T Corporation (AT&T, Inc.)
• Inventors: CONKIE, ALISTAIR
• Granted Patent: US 7,565,291 B2
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: G10L 13/07 Concatenation rules

Abstract

A system and computer-readable medium synthesize speech from text using a triphone unit selection database. The instructions on the computer-readable medium control a computing device to perform the steps: receiving input text, selecting a plurality of N phoneme units from the 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 selected set of phonemes.

Claims

1. A system for synthesizing speech, the system comprising:

a module configured to select at least one phoneme unit from a triphone unit selection database as at least one candidate phoneme to use in synthesizing speech;

a module configured to select a set of phonemes from the at least one candidate phoneme; and

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

2. The system of claim 1, wherein a Viterbi search is applied in a cost process associated with selecting the set of phonemes.

3. The system of claim 1, further comprising:

a module configured to parse received input text into recognizable units that are used to synthesize speech.

4. The system of claim 3, wherein the module configured to parse the received input text further:

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

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

5. A method for synthesizing speech, the method comprising:

selecting at least one phoneme unit from a triphone unit selecting database as a candidate phoneme to use in synthesizing speech;

selecting a set of phonemes from the at least one candidate phonemel abd

synthesizing speech using the selected set of phonemes.

6. The method of claim 5, wherein a Viterbi search is applied as the cost process associated with selecting the set of phonemes.

7. The method of claim 5, further comprising:

parsing the received input text into recognizable units that are used to synthesize speech.

8. The method of claim 7, wherein the step of parsing the received input text 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 part of speech.

9. A tangible computer-readable medium storing a computer program for controlling a computing device to synthesize speech, the instructions comprising:

selecting a set of phonemes from the at least one candidate phoneme; and

synthesizing speech using the selected set of phonemes.

10. The computer-readable medium of claim 9, wherein a Viterbi search is applied as the cost process associating with selecting the set of phonemes.

11. The computer-readable medium of claim 9, wherein the instructions further comprises:

parsing the received text into recognizable units that are used to synthesize speech.

12. The computer-readable medium of claim 11, wherein step of parsing the received input text 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 part of speech.