Title :
Noise model adaptation in model based speech enhancement
Author :
McKinley, Bruce L. ; Whipple, Gary H.
Author_Institution :
Signal Processing Consultants, Fairfax, VA, USA
Abstract :
This paper presents a noise model adaptation algorithm for model based speech enhancement (MBSE). Noise model adaptation is essential for proper operation of MBSE in non-stationary noise environments. The proposed algorithm updates the model to reflect changes in the amplitude, spectral shape and sources of the noise. Noise model codewords are selected for retraining based on a distance measure from noise-only input vectors, and a new centroid is formed based on a moving-average window length which determines the adaptation characteristics. An efficient algorithm for updating the probability structure of the noise model is presented. The adaptation algorithm is evaluated and shown to improve the performance of minimum mean-square error MBSE against actual non-stationary noise environments
Keywords :
hidden Markov models; moving average processes; noise; probability; spectral analysis; speech coding; speech enhancement; speech processing; vector quantisation; adaptation characteristics; centroid; distance measure; minimum mean-square error; model based speech enhancement; moving average adaptation; moving-average window length; noise amplitude; noise model adaptation algorithm; noise model codewords; noise sources; noise spectral shape; noise-only input vectors; nonstationary noise environments; performance; probability structure updating; retraining; vector quantization; Adaptation model; Filters; Hidden Markov models; Noise generators; Noise shaping; Prototypes; Signal processing algorithms; Speech enhancement; Speech processing; Working environment noise;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference on
Conference_Location :
Atlanta, GA
Print_ISBN :
0-7803-3192-3
DOI :
10.1109/ICASSP.1996.543200
