摘要
利用自适应KLT提出了一种新的语音去噪方法。自适应KLT的语音去噪算法,不需要白化处理,既可以自适应跟踪KLT阵,又能够有效地协调去噪后信号的音质与可懂度之间的矛盾。在说话人识别阶段采用改进的MCE。实验表明,该混合系统确实能够增强说话人辨认的鲁棒性和识别率。
In this paper,a kind of novel speech de-noising method based on the combination of wavelet de-noising and adapting KLT is proposed.The speech de-noising arithmetic of adapting KLT need not white processing.It is adapted to tract KLT matrix, as well as effectively harmonized the contradiction between signal tone after de-noising and intelligibility.At the recognition stage, Modified MCE is adopted.The experiment is showed that the hybrid system can indeed enhance the robust and the speaker recognition rate of speaker recognition.
出处
《计算机工程与应用》
CSCD
北大核心
2009年第15期194-195,215,共3页
Computer Engineering and Applications
