DocumentCode :
2390836
Title :
Mel-scaled Discrete Wavelet Transform and dynamic features for the Persian phoneme recognition
Author :
Tavanaei, Amirhossein ; Manzuri, Mohammad T. ; Sameti, Hossein
Author_Institution :
Dept. of Comput., Sharif Univ. of Technol., Tehran, Iran
fYear :
2011
fDate :
15-16 June 2011
Firstpage :
138
Lastpage :
140
Abstract :
In this paper we use a feature vector consisting of the Mel Frequency Discrete Wavelet Coefficients to recognize spoken phonemes in the Persian language. The purpose of using wavelet in feature extraction is to benefit from its multi resolution analysis and localization property in time and frequency domains. The MFDWCs are obtained by applying the Discrete Wavelet Transform (DWT) to the Mel-scaled log filter bank energies of a speech frame. Feature vectors are used for the HMM-based phoneme recognition on a portion of the FarsDat Persian language database consisting of 35 hour recorded data for training and 15 hour for testing. We evaluate the performance of new features for clean speech and noisy speech and compare it with the Mel Frequency Cepstral Coefficients (MFCC). Experiments on a phone recognition task based on the MFDWC give better result than recognizers based on the MFCC features for both white noise and clean speech cases.
Keywords :
feature extraction; hidden Markov models; natural language processing; speech recognition; wavelet transforms; white noise; FarsDat Persian language database; HMM based phoneme recognition; Persian phoneme recognition; clean speech; feature extraction; feature vector; mel scaled discrete wavelet transform; mel scaled log filter bank energies; speech frame; white noise; Discrete wavelet transforms; Feature extraction; Mel frequency cepstral coefficient; Speech; Speech recognition; MFCC; mel-scaled wavelet transform; phoneme recognition; wavelet transform;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Artificial Intelligence and Signal Processing (AISP), 2011 International Symposium on
Conference_Location :
Tehran
Print_ISBN :
978-1-4244-9833-8
Type :
conf
DOI :
10.1109/AISP.2011.5960989
Filename :
5960989
Link To Document :
بازگشت