GUO Yanmeng  FU Qiang  YAN Yonghong　

(Institute of Acoustics, The Chinese Academy of Sciences  Beijing  100080)

Received Feb. 27, 2006

Revised Apr. 3, 2006

Abstract 　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.

PACS number: 43.70, 43.60