Method and system for preselection of suitable units for concatenative speech

• US 20040093213A1
• Filed: 11/05/2003
• Published: 05/13/2004
• 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 7,124,083 B2
• Time in Patent Office: Days
• 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 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 triphone preselection cost database for use in speech synthesis, the database generated according to a 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.

2. The triphone preselection cost database of claim 1, wherein storing the group of selected sequences comprises:

a) determining a plurality of N least cost database units for the particular 5-phoneme context;

b) performing the union of the N least cost units for all combinations of u_a and u_b;

c) storing the union created in step

     4) in a triphone preselection cost database; and

d) repeating steps

     1)-3) for each possible triphone sequence.

3. The triphone preselection cost database of claim 1, the method for generating the database further comprising generating a key to index each triphone in the database.

4. The triphone preselection cost database of claim 2, wherein a plurality of fifty least costs sequences for any possible 5-phone context are stored.

5. The triphone preselection cost database of claim 1, wherein the preselection cost is the target cost or an element of the target cost.

6. A computer-readable medium storing a triphone preselection cost database for use in speech synthesis, the database generated according to a 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.

7. The computer-readable medium of claim 6, wherein storing the group of selected sequences comprises:

a) determining a plurality of N least cost database units for the particular 5-phoneme context;

b) performing the union of the N least cost units for all combinations of u_a and u_b;

c) storing the union created in step

     4) in a triphone preselection cost database; and

d) repeating steps

     1)-3) for each possible triphone sequence.

8. The computer-readable medium of claim 7, the method for generating the database further comprising generating a key to index each triphone in the database.

9. The computer-readable medium of claim 7, wherein a plurality of fifty least costs sequences for any possible 5-phone context are stored.

10. The computer-readable medium of claim 7, wherein the preselection cost is the target cost or an element of the target cost.

11. 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.

12. The method of generating a triphone preselection cost database of claim 11, wherein storing the group of selected sequences comprises:

a) determining a plurality of N least cost database units for the particular 5-phoneme context;

b) performing the union of the N least cost units for all combinations of u_a and u_b;

c) storing the union created in step

     4) in a triphone preselection cost database; and

d) repeating steps

     1)-3) for each possible triphone sequence.

13. The method of generating a triphone preselection cost database of claim 11, the method for generating the database further comprising generating a key to index each triphone in the database.

14. The method of generating a triphone preselection cost database of claim 12, wherein a plurality of fifty least costs sequences for any possible 5-phone context are stored.

15. The method of generating a triphone preselection cost database of claim 11, wherein the preselection cost is the target cost or an element of the target cost.