Abstract: In order to improve the robustness of speech endpoint detection in low SNR environments，an improved speech endpoint detection method based on spectral subtraction and adaptive multi-band spectral entropy is proposed.In this method，the additive noise is removed using spectral subtraction at first，and background noise estimate value is updated timely，then improved adaptive multi-band spectral entropy is used to detect the endpoints for the enhanced speech.Experimental results indicate that the proposed method possesses good detection performance.Compared with the traditional method，this method improves the endpoint detection accuracy，and good detection capability in low SNR environments.

Key words: endpoint detection, spectral subtraction, adaptive multi-band spectral entropy

摘要： 为了提高低信噪比下语音端点检测的性能，提出了一种改进的基于谱减法和自适应子带谱熵的语音端点检测方法。该方法先利用谱减法对带噪语音消除加性噪声，及时更新背景噪声估计，再对增强后的语音信号利用改进的自适应子带谱熵进行端点检测。实验结果表明，该方法具有良好的检测性能，相对传统方法提高了端点检测的准确率，在低信噪比环境下仍能比较准确地检测到语音的端点。

关键词: 端点检测, 谱减法, 自适应子带谱熵