Title :
Representation of hidden Markov model for noise adaptive speech recognition
Author :
Lee, L.-M. ; Wang, H.-C.
Author_Institution :
Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan
fDate :
4/13/1995 12:00:00 AM
Abstract :
The state parameters of the hidden Markov model are represented by the autocorrelation coefficients of a context window that can be adaptively transformed to cepstral and delta cepstral coefficients according to the environmental noise. Experimental results show that it can significantly improve the speech recognition rate under noisy environments
Keywords :
Gaussian noise; adaptive signal processing; hidden Markov models; interference suppression; parameter estimation; speech intelligibility; speech recognition; white noise; HMM; autocorrelation coefficients; context window; delta cepstral coefficients; environmental noise; hidden Markov model; noise adaptive speech recognition; noisy environments; speech recognition rate; state parameters;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19950410
