DocumentCode :
3391677
Title :
Text-independent pronunciation evaluation based on phone-level Gaussian classifier
Author :
Geng, Jie ; Miao, Zhenjiang
Author_Institution :
Inst. of Inf. Sci., Beijing JiaoTong Univ., Beijing, China
fYear :
2010
fDate :
24-28 Oct. 2010
Firstpage :
557
Lastpage :
560
Abstract :
This paper presents a novel text-independent pronunciation evaluation method. The method aims at testing the mandarin Putonghua pronunciation proficiency of the dialectal speakers from every area of China. In the proposed method, 5 pronunciation proficiency levels are assigned for each phone; accordingly, 5 Single Gaussian classifiers are created to represent the 5 levels for a phone. 4 phone-level features are described and used in the classifiers. In the testing step, phone-level output probabilities are combined to get the sentence-level likelihood.
Keywords :
pattern classification; speech processing; text analysis; dialectal speakers; phone level Gaussian classifier; pronunciation proficiency; text independent pronunciation evaluation; Correlation; Equations; Feature extraction; Humans; Support vector machine classification; Testing; Training; Gaussian classifier; dialectal speech; phone-level features; pronunciation evaluation; text-independent;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing (ICSP), 2010 IEEE 10th International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-5897-4
Type :
conf
DOI :
10.1109/ICOSP.2010.5655117
Filename :
5655117
Link To Document :
بازگشت