Method for generating text script of high efficiency

• US 7,447,625 B2
• Filed: 03/10/2003
• Issued: 11/04/2008
• Est. Priority Date: 09/13/2002
• Status: Active Grant

• Current Assignee: Industrial Technology Research Institute
• Original Assignee: Industrial Technology Research Institute
• Inventors: Huang, Jing-Yi, Kuo, Chih-Chung
• Primary Examiner(s): Dorvil; Richemond
• Assistant Examiner(s): SAINT CYR, LEONARD
• Application Number:
  US10/384,938
• Publication Number:
  US 20040054536A1
• Time in Patent Office: 2,066 Days
• Field of Search: None
• US Class Current: 704/9
• 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

Abstract

This proposal presents performance indices and search criteria for the text script generation in the design of corpus-based TTS systems. Based on our criteria a new search method is presented to solve the text selection problem more systematically and efficiently, unlike previous researches either concentrated on covering rate or on hit rate. By control a weighting factor, the covering rate of unit types can be increased to improve the robustness of the TTS system. Finally, the scalable and controllable design of the multi-stage search can produce various kinds of text scripts ideally suitable for the requirement of various kinds of corpus-based TTS systems.

Claims

1. A method of generation text script of high efficiency, said method comprising:

selecting N₁ sentences with best integrated efficiency from a source corpus comprised by at least a sentence and resulting N₁ sets, wherein each set of said N₁ sets has at least a sentence;

repeating procedures for generating text script of high efficiency until satisfying a termination criterion, said procedures comprising;

deleting the sentences in said N_i sets from said source corpus and resulting in N_i corpora, wherein N_i is equal to or greater than two;

correspondingly selecting M_i+l sentences with best integrated efficiency from each of said N_i corpora and resulting in N_i×

M_i+1 sets, wherein each of the N_i×

M_i+1 sets is generated by placing each of the M_i+1 sentences into a corresponding set of the N_i sets of a previous procedure;

selecting N_i+1 sets with best integrated efficiency from said N_i×

M_i+1 sets;

replacing said N_i sets with said N_i+1 sets when a termination criterion is satisfied and the set with best integrated efficiency among said N_i+1 sets is said text script of high efficiency; and

storing said text script in a memory, and said text script being used as text script for corpus of TTS (text to speech);

wherein i meaning an i^th procedure, i=1, 2, . . . ;

N_i+1 being a number of said selected sets with best integrated efficiency in said i^th procedure;

M_i+1 being a number of said selected sentences with best integrated efficiency from one of the N_i corpora;

M_i and N_i being an integer and greater than or equal to one, j=1, 2, . . . ; and

said integrated efficiency being decided upon an integrated efficiency function that comprising reciprocals of total unit instances of said selected sentence or set of sentences.

2. The method according to claim 1, wherein said integrated efficiency function is combination of a hit-rate efficiency, a covering-rate efficiency, and a weighting factor.

3. The method according to claim 2, wherein said sentences of said source corpus comprises at least a unit instance, said unit instance corresponds to at least a unit type, where said at least a unit type comprises at least a set of unit type.

4. The method according to claim 3, wherein said hit-rate efficiency is the ratio of a hit rate and total unit instances of said N_i sets.

5. The method according to claim 4, wherein said hit rate is the ratio of total unit instances gathered by set of unit types of said N_i sets and total unit instances gathered by said source corpus.

6. The method according to claim 3, wherein said covering-rate is the ratio of a covering rate and said unit instances of said N_i sets.

7. The method according to claim 6, wherein said covering-rate is the ratio of said total unit type of said N_i sets and total unit type of said source corpus.

8. The method according to claim 3, said termination criterion being selected from the group consisting of a set text script size, a set hit rate, a set covering rate, and a set integrated rate, wherein

said text script size is the number of unit instances covered by said set corresponding to said N_i sets respectively;

said set hit rate is the ratio of total unit instances gathered by sets of unit types covered by said unit instances covered by said set corresponding to said N_i sets respectively and total unit instances gathered by said source corpus;

said set covering rate is the ratio of total unit types covered by said set corresponding to said N_i sets respectively and total unit types covered by said source corpus; and

said set integrated rate is combination of said set hit-rate efficiency corresponding to said N_i sets respectively and said covering-rate efficiency corresponding to said N_i sets respectively.

9. The method according to claim 1, said selecting sets are not entirely equal to said former selecting sets when resulting N_i×

M_i+1 sets.

18. The method according to claim 1, said selecting sets are not entirely equal to said former selecting sets when resulting N_i×

M_i+1 sets.

10. A method of scalably generating text script of high efficiency, said method comprising:

selecting N₁ sentences aimed at a unit-class with best N₁ integrated efficiency from a source corpus comprised by at least a sentence and resulting N₁ sets, wherein said source corpus comprising by at least a unit instance corresponding to at least a unit type, said unit-class separated different classes according to said unit types, and each set of said N₁ sets comprised by at least a sentence;

repeating procedures for generating text script of high efficiency until satisfying a termination criterion of unit-class, said procedures comprising;

selecting N₁ sentences with best integrated efficiency from a source corpus comprised by at least a sentence and resulting N₁ sets, wherein each set of said N₁ sets comprised by at least a sentence;

repeating procedures for generating text script of high efficiency until satisfying a termination criterion, said procedures comprising;

deleting the sentences in said N_i sets from said source corpus and resulting in N_i corpora, wherein N_i is equal to or greater than two;

correspondingly selecting M_i+l sentences with best integrated efficiency from each of said N_i corpora and resulting in N_i×

M_i+1 sets, wherein each of the N_i×

M_i+1 sets is generated by placing each of the M_i+1 sentences into a corresponding set of the N_i sets of a previous procedure;

selecting N_i+1 sets with best integrated efficiency from said N_i×

M_i+1 sets;

replacing said N_i sets with said N_i sets when a termination criterion is satisfied and the set with best integrated efficiency among said N_i+1 sets is said text script of high efficiency; and

storing said text script in a memory, and said text script being used as text script for corpus of TTS (text to speech);

wherein i meaning an i^th procedure, i=1, 2, . . . ;

N_i+1 being a number of said selected sets with best integrated efficiency in said i^th procedure;

M_i+1 being a number of said selected sentences with best integrated efficiency from one of the N_i corpora;

M_i and N_i being an integer and greater than or equal to one, j=1, 2, . . . ; and

said integrated efficiency being decided upon an integrated efficiency function that comprising reciprocals of total unit instances of said selected sentence or set of sentences.

11. The method according to claim 10, said unit-class separates different class according to self features and context features of said unit types.

12. The method according to claim 10, wherein said integrated efficiency function is combination of a hit-rate efficiency, a covering-rate efficiency, and a weighting factor.

13. The method according to claim 12, wherein said covering-rate is the ratio of a covering rate and said total unit instances of said N_i×

M_i+1 sets.

14. The method according to claim 13, wherein said covering-rate is the ratio of said total unit types gathered by said unit instances of said N_i×

M_i+1 sets and total unit types gathered by said unit instances of said source corpus.

15. The method according to claim 12, wherein said hit-rate is the ratio of a hit rate and said total unit instances of said N_i×

M_i+1 sets.

16. The method according to claim 15, wherein said hit-rate is the ratio of said total unit types gathered by said unit type of said N_i×

M_i+1 sets and total unit types gathered by said unit instances of said source corpus.

17. The method according to claim 10, said termination criterion being selected from the group consisting of a text script size of unit instance, a hit rate of unit instance, a covering rate of unit type, and an integrated rate, wherein

said text script size of unit instance is the number of unit instances covered by said set corresponding to said N_i sentences respectively;

said hit rate of unit instance is the ratio of total unit instances gathered by sets of unit types covered by said set corresponding to said N_i sentences respectively and total unit instances gathered by said source corpus;

said covering rate of unit type is the ratio of total unit types gathered by unit instances covered by said set corresponding to said N_i sentences respectively and total unit types covered by said unit instances of said source corpus; and

said integrated rate is combination of said set hit-rate efficiency corresponding to said N_i sentences respectively and said covering-rate efficiency corresponding to said N_i sentences respectively.