|
KMID : 1022420110030030091
|
|
Phonetics and Speech Sciences
2011 Volume.3 No. 3 p.91 ~ p.98
|
|
|
Multi-Channel Speech Enhancement Algorithm Using DOA-based Learning Rate Control
|
|
Kim Su-Hwan
Kim Young-Il
Jeong Sang-Bae
Lee Young-Jae
Kim Young-Il
Jeong Sang-Bae
Lee Young-Jae
|
|
|
Abstract
|
|
|
|
In this paper, a multi-channel speech enhancement method using the linearly constrained minimum variance (LCMV) algorithm and a variable learning rate control is proposed. To control the learning rate for adaptive filters of the LCMV algorithm, the direction of arrival (DOA) is measured for each short-time input signal and the likelihood function of the target speech presence is estimated to control the filter learning rate. Using the likelihood measure, the learning rate is increased during the pure noise interval and decreased during the target speech interval. To optimize the parameter of the mapping function between the likelihood value and the corresponding learning rate, an exhaustive search is performed using the Bark"s scale distortion (BSD) as the performance index. Experimental results show that the proposed algorithm outperforms the conventional LCMV with fixed learning rate in the BSD by around 1.5 dB.
|
|
|
KEYWORD
|
|
|
Speeh enhancement, linear constrained minimum variance, direction of arrival, adaptive learning rate control, beamforming
|
|
|
FullTexts / Linksout information
|
|
|
|
|
|
Listed journal information
|
|
|