DocumentCode :
2998719
Title :
The short-time modified coherence representation and its application for noisy speech recognition
Author :
Mansour, David ; Juang, Biing Hwang
Author_Institution :
AT&T Bell Lab., Murray Hill, NJ, USA
fYear :
1988
fDate :
11-14 Apr 1988
Firstpage :
525
Abstract :
A technique for robust spectral representation of all-pole sequences is proposed. It is shown that the autocorrelation of an all-pole sequence, obtained by passing white noise through an all-pole filter 1/A(z), is an all-pole sequence of the form 1/ A2(z). The short-time modified coherence (SCM) representation, proposed here, is an all-pole modeling of the autocorrelation sequence followed by a spectral shaper. The spectral shaper, essentially a square root operator in the frequency domain, compensates for the inherent spectral distortion introduced by the autocorrelation operation on the autocorrelation sequence of the signal. The properties of the SMC representation, especially its robustness to additive white noise, are analyzed. Initial implementation of the SMC in a speaker-dependent isolated-word recognizer shows a considerable improvement over the standard linear predictive coding (LPC) representation. The SMC recognizer achieved an improvement in recognition accuracy equivalent to an increase in input SNR of approximately 13 dB, as compared to the LPC recognizer
Keywords :
speech recognition; LPC; all-pole filter; all-pole modeling; all-pole sequences; autocorrelation sequence; frequency domain; linear predictive coding; noisy speech recognition; recognition accuracy; short-time modified coherence; speaker-dependent isolated-word recognizer; spectral distortion; spectral representation; spectral shaper; square root operator; white noise; Additive white noise; Autocorrelation; Coherence; Distortion; Filters; Frequency domain analysis; Linear predictive coding; Noise robustness; Sliding mode control; White noise;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1988. ICASSP-88., 1988 International Conference on
Conference_Location :
New York, NY
ISSN :
1520-6149
Type :
conf
DOI :
10.1109/ICASSP.1988.196635
Filename :
196635
Link To Document :
بازگشت