%0 Journal Article
%T Research on Speech Endpoint Detection Algorithm with Low SNR
%A Jian Wei
%A XiangĄ¯e Sun
%J Open Access Library Journal
%V 4
%N 3
%P 1-8
%@ 2333-9721
%D 2017
%I Open Access Library
%R 10.4236/oalib.1103487
%X <div style="text-align:justify;">
	<span style="line-height:1.5;">The detection of speech endpoint is an important application for speech signal processing. Although there are variance methods, the endpoint canĄ¯t be detected accurately in low SNR (Signal to Noise Ratio). The paper pointes out an endpoint detection algorithm combining two methods together: the one is improved spectral subtraction based on multitaper spectral estimation, and the other is BARK subband variance in frequency domain. Firstly, the noisy speech signal is processed though the improved spectral subtraction based on multitaper spectral estimation. It can achieve the purpose of noise reduction through this step. Then the noisy speech signal is detected using the method of BARK subband variance in frequency domain. Compared with the common endpoint detection algorithm, it is concluded that endpoint detection accuracy by new method can be improved in low SNR.</span> 
</div>
%K Endpoint Detection
%K Multitaper Spectral Estimation
%K Improved Spectral Subtraction
%K BARK Subband Variance
%U http://www.oalib.com/paper/5283953