Speex中语音增强算法的仿真与评估

Simulation and Evaluation on Speech Enhancement Algorithm of Speex

随着VoIP技术在近年来的快速发展,互联网语音通信得到了越来越多的应用,IP电话的语音通信质量成为制约其发展的重要因素,因此应用了许多新技术使其语音质量更符合用户的要求。在VoIP系统中使用语音增强算法,可以消除发送端噪声干扰,提高通话质量。研究的Speex算法中的STSA-MMSE语音增强算法是在计算先验和后验信噪比的基础上估计噪声,再通过计算得出一个增益值,作用于带噪语音,对噪声段进行抑制,对叠加了噪声的语音尽可能分离噪声,最终达到增强语音清晰度,提高语音舒适度的目的。

With the rapid development of VoIP technology in recent years,Internet voice communications applications become more popular.The voice quality of IP phone is an important restrictive factor for its development.Many new technologies have been applied to improving the voice quality and meeting the users needs.In VoIP system,the use of speech enhancement algorithm at the sending end is an effective method to solve noise pollution and improve speech quality.A speech enhancement algorithm in Speex is studied,a minimum-mean square error short-time spectral amplitude estimator based on calculating a priori and a posteriori signal-to-noise ratio is used,and then a gain value that acts on the noisy speech is obtained.The enhanced speech would be clearer and more comfortable by eliminating noise.