Performance evaluation of MLPC and MFCC for HMM based noisy speech recognition

Author

Rahman, Mizanur ; Islam, Md Babul

Author_Institution

Dept. of Comput. Sci. & Eng., Islamic Univ., Kushtia, Bangladesh

fYear

2010

fDate

23-25 Dec. 2010

Firstpage

273

Lastpage

276

Abstract

In this paper auditory like features MLPC and MFCC have been used as front-end and their performance has been evaluated on Aurora-2 database for Hidden Markov Model (HMM) based noisy speech recognition. The clean data set is used for training and test set A is used to examine the performance. It has been found that almost the same recognition performance has been obtained both for MLPC and MFCC and the average word accuracy for MLPC and for MFCC is found to be 59.05% and 59.21%, respectively. It has also been observed that the MLPC is more effective than MFCC for noise type subway and exhibition, on the other hand, MFCC is more superior for babble and car noises.

Keywords

hidden Markov models; performance evaluation; speech recognition; Aurora-2 database; MFCC; MLPC; hidden Markov model; noisy speech recognition; performance evaluation; Accuracy; Computational modeling; Hidden Markov models; Mel frequency cepstral coefficient; Noise; Speech; Speech recognition; Bilinear transformation; HMM; MFCC; MLPC; Noisy speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer and Information Technology (ICCIT), 2010 13th International Conference on

Conference_Location

Dhaka

Print_ISBN

978-1-4244-8496-6

Type

conf

DOI

10.1109/ICCITECHN.2010.5723868

Filename

5723868