Adaptive β-order generalized spectral subtraction for speech enhancement

Authors:
Junfeng Li;Shuichi Sakamoto;Satoshi Hongo;Masato Akagi;Yôiti Suzuki
Affiliations:
Research Institute of Electrical Communication, Tohoku University, 2-1-1 Katahira, Sendai, Japan;Research Institute of Electrical Communication, Tohoku University, 2-1-1 Katahira, Sendai, Japan;Department of Design and Computer Application, Miyagi National College of Technology, 48 Nodayama, Natori, Japan;School of Information Science, JAIST, 1-1 Asahidai, Nomi, Japan;Research Institute of Electrical Communication, Tohoku University, 2-1-1 Katahira, Sendai, Japan
Venue:
Signal Processing
Year:
2008

Citing 3
Cited 3

Assessment for automatic speech recognition II: NOISEX-92: a database and an experiment to study the effect of additive noise on speech recognition systems

Speech Communication - Special issue on speech processing in adverse conditions
Speech Enhancement

Speech Enhancement
Multichannel post-filtering in nonstationary noise environments

IEEE Transactions on Signal Processing

Post-processing for frequency-domain blind source separation in hearing aids

ICICS'09 Proceedings of the 7th international conference on Information, communications and signal processing
Context-adaptive pre-processing scheme for robust speech recognition in fast-varying noise environment

Signal Processing
A complementary low-cost method for broadband noise reduction in hearing aids for medium to high SNR levels

Computers in Biology and Medicine

Quantified Score

Hi-index	0.08

Visualization

Abstract

The performance degradation of speech communication systems in noisy environments inspired increasing research on speech enhancement and noise reduction. As a well-known single-channel noise reduction technique, spectral subtraction (SS) has widely been used for speech enhancement. However, the spectral order @b set in SS is always fixed to some constants, resulting in performance limitation to a certain degree. In this paper, we first analyze the performance of the @b-order generalized spectral subtraction (GSS) in terms of the gain function to highlight its dependence on the value of spectral order @b. A data-driven optimization scheme is then introduced to quantitatively determine the change of @b with the change of the input signal-to-noise ratio (SNR). Based on the analysis results and considering the non-uniform effect of real-world noise on speech signal, we propose an adaptive @b-order GSS in which the spectral order @b is adaptively updated according to the local SNR in each critical band frame by frame as in a sigmoid function. The performance of the proposed adaptive @b-order GSS is finally evaluated objectively by segmental SNR (SEGSNR) and log-spectral distance (LSD), and subjectively by spectrograms and mean opinion score (MOS), using comprehensive experiments in various noise conditions. Experimental results show that the proposed algorithm yields an average SEGSNR increase of 2.99dB and an average LSD reduction of 2.71dB, which are much larger improvement than that obtained with the competing SS algorithms. The superiority of the proposed algorithm is also demonstrated by the highest MOS ratings obtained from the listening tests.