Improved voice activity detection for speech recognition system

S W Chin; K P Seng; Li-Minn Ang; K H Lim

doi:10.1109/COMPSYM.2010.5685456

Back

Improved voice activity detection for speech recognition system

Conference paper

Peer reviewed

Improved voice activity detection for speech recognition system

S W Chin, K P Seng, Li-Minn Ang and K H Lim

2010 International Computer Symposium (ICS2010), pp.518-523

International Computer Symposium (ICS2010), 2010 (Tainan, Taiwan, 16-Dec-2010–18-Dec-2010)

Institute of Electrical and Electronics Engineers

2010

DOI: https://doi.org/10.1109/COMPSYM.2010.5685456

Files and links (1)

url

https://doi.org/10.1109/COMPSYM.2010.5685456View

Published Version

Abstract

Continuous wavelet transform

Mel frequency cepstral coefficient

Voice activity detection

radial basis function

An improved voice activity detection (VAD) based on the radial basis function neural network (RBF NN) and continuous wavelet transform (CWT) for speech recognition system is presented in the paper. The input speech signal is analyzed in the form of fixed size window by using Mel-frequency cepstral coefficients (MFCC). Within the windowed signal, the proposed RBF-CWT VAD algorithm detects the speech/ non-speech signal using the RBF NN. Once the interchange of speech to non-speech or vice versa occurred, the energy changes of the CWT coefficients are calculated to localize the final coordination of the starting/ending speech points. Instead of classifying the speech signal using the MFCC at the frame-level which easily capture lots of undesired noise encountered by the conventional VAD with the binary classifier, the proposed RBF NN with the aid of CWT analyzes the transformation of the MFCC at the window-level that offers a better compensation to the noisy signal. The simulation results shows an improvement on the precision of the speech detection and the overall ASR rate particularly under the noisy circumstances compared to the conventional VAD with the zero-crossing rate, short-term signal energy and binary classifier.

Details

Title: Improved voice activity detection for speech recognition system
Authors: S W Chin (Author) - University of Nottingham Malaysia Campus
K P Seng (Author) - University of Nottingham Malaysia Campus
Li-Minn Ang (Author) - University of Nottingham Malaysia Campus
K H Lim (Author) - University of Nottingham Malaysia Campus
Publication details: 2010 International Computer Symposium (ICS2010), pp.518-523
Conference details: International Computer Symposium (ICS2010), 2010 (Tainan, Taiwan, 16-Dec-2010–18-Dec-2010)
Publisher: Institute of Electrical and Electronics Engineers
Date published: 2010
DOI: 10.1109/COMPSYM.2010.5685456
ISBN: 9781424476404
Organisation Unit: University of the Sunshine Coast, Queensland; School of Science, Technology and Engineering; Engage Research Lab
Language: English
Record Identifier: 99513901902621
Output Type: Conference paper

Metrics

84 Record Views