METHOD OF CONSTRUCTING MODEL OF RECOGNIZING ENGLISH PRONUNCIATION VARIATION

• US 20090157402A1
• Filed: 02/21/2008
• Published: 06/18/2009
• Est. Priority Date: 12/12/2007
• Status: Active Grant

• Current Assignee: Institute For Information Industry
• Original Assignee: Institute For Information Industry
• Inventors: LEE, Kuei-Ming, HSIEH, Chia-Hsin, LIN, Jui-Tang, CHAI, Shen-Yen, HSU, Chin-Shun, HUANG, Chien-Lin, WU, Chung-Hsien
• Granted Patent: US 8,000,964 B2
• Time in Patent Office: Days
• US Class Current: 704/254
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams

Abstract

A method of constructing a model of recognizing English pronunciation variations is used to recognize English pronunciations with different intonations influenced by native languages. The method includes collecting a plurality of sound information corresponding to English expressions; corresponding phonetic alphabets of the native language and English of a region to International Phonetic Alphabets (IPAs), so as to form a plurality of pronunciation models; converting the sound information with the pronunciation models to form a pronunciation variation network of the corresponding English expressions, thereby detecting whether the English expressions have pronunciation variation paths; and finally summarizing the pronunciation variation paths to form a plurality of pronunciation variation rules. Furthermore, the pronunciation variations are represented by phonetics features to infer possible pronunciation variation rules, which are stored to form pronunciation variation models. The construction of the pronunciation variation models enhances applicability of an English recognition system and accuracy of voice recognition.

Claims

1. A method of constructing a model of recognizing English pronunciation variations, for recognizing English pronunciations with intonations influenced by different native languages, the method at least comprising:

providing a plurality of English expressions and at least one phonetic alphabet corresponding to each of the English expressions, and collecting a plurality of corresponding sound information according to the phonetic alphabet of the English expression;

corresponding phonetic alphabets of the native language and English to a plurality of international phonetic alphabets (IPAs), so as to form a plurality of pronunciation models;

converting the sound information of each of the English expressions by using the pronunciation models, and constructing a pronunciation variation network corresponding to the English expression with reference to the phonetic alphabet of the English expression, so as to detect whether the English expression has a pronunciation variation path; and

summarizing the pronunciation variation paths to form a plurality of pronunciation variation rules.

2. The method of constructing a model of recognizing English pronunciation variations as claimed in claim 1, wherein the forming of each of the pronunciation models comprises:

collecting a plurality of phonetic alphabet pronunciations directed to one of the IPAs, and converting each of the phonetic alphabet pronunciations into a corresponding characteristic value;

forming the characteristic values into a value group and calculating a grouping threshold value corresponding to the characteristic values;

calculating a mean value of the value group;

obtaining a first characteristic value from the value group which is away from the mean value by a maximum numerical distance;

calculating a second characteristic value in the value group which is away from the first characteristic value by a maximum numerical distance;

calculating numerical distances between each characteristic value and the first characteristic value and between each characteristic value and the second characteristic value, and forming a value group containing the characteristic values close to the first characteristic value and a value group containing the characteristic values close to the second characteristic value, respectively;

obtaining a within-group distance and a between-group distance of the two value groups, so as to calculate a grouping standard; and

determining whether the grouping standard is higher than the grouping threshold value through comparison, if yes, calculating a mean value of the value group, and if no, obtaining the value groups of the pronunciation model.

3. The method of constructing a model of recognizing English pronunciation variations as claimed in claim 2, wherein the characteristic values of at least one value group of the pronunciation model correspond to the phonetic alphabets of the native language.

4. The method of constructing a model of recognizing English pronunciation variations as claimed in claim 2, wherein the characteristic values of at least one value group of the pronunciation model correspond to the phonetic alphabets of the English.

5. The method of constructing a model of recognizing English pronunciation variations as claimed in claim 2, wherein the phonetic alphabet pronunciation is transformed into the characteristic value by using Fourier Transform equation.

6. The method of constructing a model of recognizing English pronunciation variations as claimed in claim 1, wherein the step of constructing a pronunciation variation network corresponding to the English expression comprises:

setting the phonetic alphabet of the English expression as a reference;

detecting whether an insertion pronunciation variation exits in each pronunciation of the phonetic alphabets;

detecting whether a deletion pronunciation variation exits between each phonetic alphabet and the next phonetic alphabet;

detecting a substitution pronunciation variation corresponding to each phonetic alphabet; and

constructing the pronunciation variation network.

7. The method of constructing a model of recognizing English pronunciation variations as claimed in claim 6, wherein the step of detecting a substitution pronunciation variation corresponding to each phonetic alphabet comprises:

obtaining a pronunciation type in the IPA for each phonetic alphabet; and

using at least one IPA with the same pronunciation type as the substitution pronunciation variation of the phonetic alphabet.

8. The method of constructing a model of recognizing English pronunciation variations as claimed in claim 6, wherein the step of detecting a substitution pronunciation variation corresponding to each phonetic alphabet comprises:

collecting pronunciations of the IPA;

calculating pronunciation probability for each IPA, so as to establish a phone confusion matrix;

obtaining at least one IPA in a pronunciation probability range based on the phonetic alphabet; and

setting the IPA in the pronunciation probability range as the substitution pronunciation variation of the phonetic alphabet.

9. The method of constructing a model of recognizing English pronunciation variations as claimed in claim 1, further comprising a step of analyzing the English expression to obtain an inference rule according to variation of the phonetic alphabet.

10. The method of constructing a model of recognizing English pronunciation variations as claimed in claim 9, further comprising:

corresponding the phonetic alphabets to pronunciation characteristics of linguistics;

analyzing the pronunciation variation network of the English expression, so as to obtain the inference rule; and

determining whether the phonetic alphabets having the same pronunciation characteristic have the same inference rule.

11. A recording medium of constructing a model of recognizing English pronunciation variations, recording computer-readable computer program codes, used for recognizing English pronunciations with different intonations influenced by native languages, the method of constructing a pronunciation variation model comprising:

providing a plurality of English expressions and at least one phonetic alphabet corresponding to each of the English expressions, and collecting a plurality of corresponding sound information according to the phonetic alphabet of the English expression;

corresponding the phonetic alphabets of the native language and English to a plurality of international phonetic alphabets (IPAs), so as to form a plurality of pronunciation models;

converting the sound information of each of the English expressions by using the pronunciation models, and constructing a pronunciation variation network corresponding to the English expression with reference to the phonetic alphabet of the English expression, so as to detect whether the English expression has a pronunciation variation path; and

summarizing the pronunciation variation paths to form a plurality of pronunciation variation rules.

12. The recording medium as claimed in claim 11, wherein the forming of each of the pronunciation models comprises:

collecting a plurality of phonetic alphabet pronunciations directed to one of the IPAs, and converting each of the phonetic alphabet pronunciations into a corresponding characteristic value;

forming the characteristic values into a value group and calculating a grouping threshold value corresponding to the characteristic values;

calculating a mean value of the value group;

obtaining a first characteristic value from the value group which is away from the mean value by a maximum numerical distance;

calculating a second characteristic value in the value group which is away from the first characteristic value by a maximum numerical distance;

calculating numerical distances between each characteristic value and the first characteristic value and between each characteristic value and the second characteristic value, and forming a value group containing the characteristic values close to the first characteristic value and a value group containing the characteristic values close to the second characteristic value, respectively;

obtaining a within-group distance and a between-group distance of the two value groups, so as to calculate a grouping standard; and

determining whether the grouping standard is higher than the grouping threshold value through comparison, if yes, calculating a mean value of the value group, and if no, obtaining the value groups of the pronunciation model.

13. The recording medium as claimed in claim 12, wherein the characteristic values of at least one value group of the pronunciation model correspond to the phonetic alphabets of the native language.

14. The recording medium as claimed in claim 12, wherein the characteristic values of at least one value group of the pronunciation model correspond to the phonetic alphabets of the English.

15. The recording medium as claimed in claim 12, wherein the phonetic alphabet pronunciation is transformed into the characteristic value by using Fourier Transform equation.

16. The recording medium as claimed in claim 11, wherein the step of constructing a pronunciation variation network corresponding to the English expression comprises:

setting the phonetic alphabet of the English expression as a reference;

detecting whether an insertion pronunciation variation exits in each pronunciation of the phonetic alphabets;

detecting whether a deletion pronunciation variation exits between each phonetic alphabet and the next phonetic alphabet;

detecting a substitution pronunciation variation corresponding to each phonetic alphabet; and

constructing the pronunciation variation network.

17. The recording medium as claimed in claim 16, wherein the step of detecting a substitution pronunciation variation corresponding to each phonetic alphabet comprises:

obtaining a pronunciation type in the IPA for each phonetic alphabet; and

using at least one IPA with the same pronunciation type as the substitution pronunciation variation of the phonetic alphabet.

18. The recording medium as claimed in claim 16, wherein the step of detecting a substitution pronunciation variation corresponding to each phonetic alphabet comprises:

collecting pronunciations of the IPA;

calculating pronunciation probability for each IPA, so as to establish a phone confusion matrix;

obtaining at least one IPA in a pronunciation probability range based on the phonetic alphabet; and

setting the IPA in the pronunciation probability range as the substitution pronunciation variation of the phonetic alphabet.

19. The recording medium as claimed in claim 11, further comprising a step of analyzing the English expression to obtain an inference rule according to the variation of the phonetic alphabet.

20. The recording medium as claimed in claim 19, wherein the step of detecting a substitution pronunciation variation corresponding to each phonetic alphabet comprises:

corresponding the phonetic alphabets to pronunciation characteristics of linguistics;

analyzing the pronunciation variation network of the English expression, so as to obtain the inference rule; and

determining whether the phonetic alphabets having the same pronunciation characteristic have the same inference rule.