Title :
A sequential algorithm for robust parameter estimation and enhancement of noisy speech
Author :
Lee, Byung-Gook ; Lee, Ki Yong ; Ann, Souguil ; Song, Iickho
Author_Institution :
Dept. of Electron. Eng., Seoul Nat. Univ., South Korea
Abstract :
The sequential estimation of robust parameters and enhancement of noisy speech based on the expectation-maximization (EM) algorithm is considered when the excitation source is a mixture of two Gaussian distributions with different variances. Methods of stochastic approximation are used to convert a traditionally iterative algorithm into a sequential one. The proposed algorithm is robust against the observation noise and enhances noisy speech to produce results that are 3~4-dB better than conventional methods
Keywords :
Gaussian distribution; parameter estimation; sequential estimation; speech enhancement; Gaussian distributions; excitation source; expectation-maximisation algorithm; noisy speech; observation noise; robust parameter estimation; sequential algorithm; stochastic approximation; Electronic mail; Gaussian distribution; Gaussian noise; Iterative algorithms; Noise robustness; Parameter estimation; Speech enhancement; Speech processing; Stochastic resonance; White noise;
Conference_Titel :
Circuits and Systems, 1993., ISCAS '93, 1993 IEEE International Symposium on
Conference_Location :
Chicago, IL
Print_ISBN :
0-7803-1281-3
DOI :
10.1109/ISCAS.1993.393703
