摘要
A method of speech endpoint detection in environments of complicated additive noise is presented. Based on the analysis of noise, an adaptive model of stationary noise is proposed to detect the section where the signal is nonstationary. Then the voice is detected in this section by its harmonic structure, and the accurate endpoint is searched using energy. Compared with the typical algorithms, this algorithm operates reliably in most real noise environments.
A method of speech endpoint detection in environments of complicated additive noise is presented. Based on the analysis of noise, an adaptive model of stationary noise is proposed to detect the section where the signal is nonstationary. Then the voice is detected in this section by its harmonic structure, and the accurate endpoint is searched using energy. Compared with the typical algorithms, this algorithm operates reliably in most real noise environments.
基金
This work was supported by 100 Talents Program of The Chinese Academy of Sciencesby 973 Program (2004CB318106)by the National Natural Science Foundation of China (10574140).
