Voice Activity Detection in MTF-Based Power Envelope Restoration
Voice Activity Detection in MTF-Based Power Envelope Restoration
复制标题
DOI：
10.21437/interspeech.2011-667
复制
发表时间：
2012-05
期刊：
影响因子：
--
通讯作者：
M. Unoki;Xugang Lu;Rico Petrick;Shota Morita;M. Akagi;R. Hoffmann
中科院分区：
文献类型：
--
作者：
M. Unoki;Xugang Lu;Rico Petrick;Shota Morita;M. Akagi;R. Hoffmann
本文报告了混响环境中传统的语音活动检测（VAD）方法的比较评估。传统的和标准（G.729）的方法进行了讨论。一般来说，这些方法在清洁条件下工作良好，但它们的性能受到混响的严重影响。初步的比较评估表明，由于混响适度增加了误拒绝率（FRR），误接受率（FAR）显着增加。因此，我们开发了一种方法，使用MTF的功率包络恢复，以提高在混响环境中的VAD的鲁棒性。该方法基于调制传递函数的概念，能够盲恢复混响语音的功率包络。该方法由一个MTF为基础的恢复方法作为前端和一个传统的VAD方法作为最终的决定。实验结果表明，该方法是上级优于传统方法的鲁棒性和提供准确的VAD（降低FAR和FRR）在混响环境中。
This paper reports comparative evaluations of conventional voice activity detection (VAD) methods in reverberant environments. Both conventional and standard (G.729) methods are discussed. In general, these methods work well under clean conditions, but their performance is drastically affected by reverberation. Preliminary comparative evaluations showed that the false acceptance rate (FAR) is significantly increased due to the false rejection rate (FRR) being moderately increased by reverberation. We therefore developed a method using MTFbased power envelope restoration to improve the robustness of VAD in reverberant environments. This restoration method can blindly restore the power envelope of reverberant speech based on the MTF concept. The proposed method consists of an MTFbased restoration method as the front end and a conventional VAD method as the final decision. Experimental results demonstrated that the proposed method is superior to conventional methods with regard to robustness and providing accurate VAD (reducing both FAR and FRR) in reverberant environments.