DocumentCode :
2854432
Title :
Including detailed information feature in MFCC for large vocabulary contious speech recornition
Author :
Jia, Lei ; Xu, Bo
Author_Institution :
National Laboratory Of Pattern Recognition, Chinese Academy of Science, Beijing, China 100080
Volume :
1
fYear :
2002
fDate :
13-17 May 2002
Abstract :
This paper focuses on the inclusion of more detailed linguistically relevant speech information in the Mel-Frequency Cepstral Coefficients(MFCC) feature extraction process in order to improve the recognition accuracy of LVCSR. Detailed linguistically relevant speech information feature is extracted to reflect the change of energy spectrum in each mel-frequency bank(MFB). A normalized positive weighting vector is used to combine the log channel energy feature of the standard MFCC with the new detailed information features to form one energy feature for each MFB. The optimal weighting vector can be obtained by the Heteroscedastic Discriminant Analysis (HDA) before feature extraction. Experiments on two test sets show that the new feature extraction method is superior in performance to the standard MFCC and 10% relative error reduction for LVCSR is witnessed in the test set with standard accent speakers.
Keywords :
Data communication; Feature extraction; Laboratories; Mel frequency cepstral coefficient; Multiplexing; Speech; Training;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing (ICASSP), 2002 IEEE International Conference on
Conference_Location :
Orlando, FL, USA
ISSN :
1520-6149
Print_ISBN :
0-7803-7402-9
Type :
conf
DOI :
10.1109/ICASSP.2002.5743840
Filename :
5743840
Link To Document :
بازگشت