Speech Endpoint Detection with Low SNR Based on HHTSM
The article presents a detection method on HilbertHuang Transform Spectral Matrix (HHTSM) for improving speech endpoint detection accuracy in low signal-tonoise ratios (SNR). The method analyses signal timefrequency-energy distribution with Hilbert-Huang Transform (HHT), and constructs HHTSM by frames. The frame size is chosen by energy focus character. The speech and noise energy distribution can be distinguished by HHTSM in low SNR. By estimating noise energy distribution, it sets threshold automatically. The result indicates that the method can detect speech endpoint effectively in the negative SNR.
Signal Processing HHTSM HHT Signal Detection Low SNR
LIU Bai-sen Zhang Ye Zhang Wu-lin
dept. of Information Engineering Harbin Institute of Technology Harbin, China dept. of Electronic En dept. of Information Engineering Harbin Institute of Technology Harbin, China Information and Communication Engineering College Harbin Engineering University Harbin, China
国际会议
三峡
英文
1839-1842
2012-05-18(万方平台首次上网日期,不代表论文的发表时间)