DocumentCode :
1613309
Title :
Classification of speaker accent using hybrid DWT-LPC features and K-nearest neighbors in ethnically diverse Malaysian English
Author :
Yusnita, M.A. ; Paulraj, M.P. ; Yaacob, Sazali ; Shahriman, A.B.
Author_Institution :
Fac. of Electr. Eng., Univ. Teknol. MARA, Permatang Pauh, Malaysia
fYear :
2012
Firstpage :
179
Lastpage :
184
Abstract :
Accent is a major cause of variability in automatic speaker-independent speech recognition systems. Under certain circumstances, this event introduces unsatisfactory performance of the systems. In order to circumvent this deficiency, accent analyzer in preceding stage could be a smart solution. This paper proposes a rather new approach of hybrid way to optimize the extraction of accent from speech utterances over other facets using linear predictive coefficients (LPC) derived from discrete wavelet transform (DWT). The constructed features were used to model an accent recognizer, implemented based on K-nearest neighbors. Experimental results showed that the hybrid dyadic-X DWT-LPC features were highly correlated to the Malay, Chinese and Indian accents of Malaysian English speakers through an increase of classification rate of 9.28% over the conventional LPC method.
Keywords :
discrete wavelet transforms; natural language processing; pattern classification; pattern clustering; speaker recognition; Chinese accents; Indian accents; Malay accents; Malaysian English speakers; accent analyzer; accent extraction; accent recognizer; automatic speaker-independent speech recognition systems; discrete wavelet transform; ethnically diverse Malaysian english; hybrid dyadic-X DWT-LPC features; k-nearest neighbors; linear predictive coefficients; speaker accent classification; speech utterances; Approximation methods; Discrete wavelet transforms; Feature extraction; Mel frequency cepstral coefficient; Speech; Speech recognition; Accent Classification; Discrete Wavelet Transform; K-nearest Neighbors; Linear Predictive Coding; Malaysian English;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Applications and Industrial Electronics (ISCAIE), 2012 IEEE Symposium on
Conference_Location :
Kota Kinabalu
Print_ISBN :
978-1-4673-3032-9
Type :
conf
DOI :
10.1109/ISCAIE.2012.6482092
Filename :
6482092
Link To Document :
بازگشت