Blind dereverberation of single channel speech signal based on harmonic structure
Blind dereverberation of single channel speech signal based on harmonic structure
复制标题
基于谐波结构的单通道语音信号盲去混响
DOI：
--
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
M. Miyoshi
中科院分区：
文献类型：
--
作者：
T. Nakatani;M. Miyoshi
本文提出了一种单麦克风语音信号去混响的新方法。对于诸如语音识别的应用，当在记录中使用远距离麦克风时，混响语音会导致严重的问题。当混响时间超过0.5s时，这尤其严重。我们提出了一种方法，它使用的基本频率（F/sub 0/）的目标语音作为主要特征的去混响。该方法首先估计语音信号的F/sub 0/和谐波结构，然后获得去混响算子。该算子基于逆滤波操作将混响信号变换成其直接信号。去混响是在没有房间声学或目标语音的先验知识的情况下实现的。实验结果表明，当混响时间大于0.1s时，从5240个日语单词发音中估计出的去混响算子可以有效地降低混响。
The paper presents a new method for dereverberation of speech signals with a single microphone. For applications such as speech recognition, reverberant speech causes serious problems when a distant microphone is used in recording. This is especially severe when the reverberation time exceeds 0.5 s. We propose a method which uses the fundamental frequency (F/sub 0/) of the target speech as the primary feature for dereverberation. This method initially estimates F/sub 0/ and the harmonic structure of the speech signal and then obtains a dereverberation operator. This operator transforms the reverberant signal to its direct signal based on an inverse filtering operation. Dereverberation is achieved without prior knowledge of either the room acoustics or the target speech. Experimental results show that the dereverberation operator estimated from 5240 Japanese word utterances could effectively reduce the reverberation when the reverberation time is longer than 0.1 s.