Kernel Fitting for Speech Detection and Enhancement

摘要：

A kernel fitting algorithm is proposed for speech denoising to improve the precision of voice activity detection (VAD) and the performance of speech enhancement, of some popular algorithms. In the algorithm, a noisy speech frame is filtered by kernel fitting, and then its power spectral density is estimated and weighted by a gain factor constructed from frame energy and zero-crossing rate, so that a speech signal is obviously discriminated from a nonspeech one. By incorporation of the VAD outputs and the noise effect into the kernel fitting process, a speech frame is enhanced with better performance than the spectra subtraction algorithm. Experiments are taken on a real life speech signal plus simulated noises, and the results show the potentiality of the proposed algorithms in speech detection and enhancement.

关键词： Speech detection speech enhancement kernel fitting cepstral coefficients power spectral density spectra subtraction

作者: Benyong Liu Jing Zhang Xiang Liao

作者单位: Institute of Intelligent Information Processing / College of Computer Science and Information Techno Key Lab of Audio-Visual Material Examination Guizhou Public Security Department Guiyang 550001, Chin

会议类型: 国际会议

会议名称: 2010 IEEE 10th International Conference on Signal Processing(第十届信号处理国际会议 ICSP 2010)

会议地点: 北京

会议语种:英文

页码: 534-537

在线出版日期: 2010-08-24（万方平台首次上网日期，不代表论文的发表时间）