Modified MFCC windowed technique for speaker word recognition

Authors:
I. Patel;Y. S. Rao
Affiliations:
Dr. B. V. Raju Institute of Tech. Narsapur, Medak;Andhra University Visakhapanam, A. P.
Venue:
Proceedings of the International Conference & Workshop on Emerging Trends in Technology
Year:
2011

Citing 5
Cited 0

Experiments with a Nonlinear Spectral Subtractor (NSS), Hidden Markov Models and the projection, for robust speech recognition in cars

Speech Communication - Eurospeech '91
Fundamentals of speech recognition

Fundamentals of speech recognition
Speech recognition in noisy environments: a survey

Speech Communication
Robustness in Automatic Speech Recognition: Fundamentals and Applications

Robustness in Automatic Speech Recognition: Fundamentals and Applications
Influence of background noise and microphone on the performance of the IBM Tangora speech recognition system

ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II

Quantified Score

Hi-index	0.00

Visualization

Abstract

Mel frequency cepstral coefficients (MFCCs) are one of the most popular forms of parameterization of the speech signal in speaker word recognition systems. MFCC's are based on the known variation of the human ear's critical bandwidths. In this paper, we present a way to modifying the windowing technique to improve the extraction of speech features by hamming window and hanning window to a more efficient windowing method called Kaiser Window to minimize the mean square error rather than maximizing error