摘要
为了克服基于传统经验模态分解语音去噪算法在阈值去噪时阈值函数处理不平滑的缺点,对EMD-CIIT(EMD重复间隔阈值)语音去噪方法的阈值函数进行改进,并在Matlab平台搭建的语音识别系统进行仿真实验。实验结果表明,改进阈值函数的EMD-CIIT去噪算法具有较高的识别率及良好的鲁棒性。
The threshold process of speech denoising method based on empirical mode decomposition is not smooth, so the threshold function of EMD-CIIT （EMD clear iterative interval thresholding） speech denoising algorithm is improved. A speech recognition system is built by Matlab simulation platform. The experimental results show that compared with other algorithms, there are higher recognition rate and good robustness in the improved threshold EMIYCIIT algorithm.
出处
《桂林电子科技大学学报》
2016年第1期9-13,共5页
Journal of Guilin University of Electronic Technology
基金
广西自然科学基金(2012GXNSFAA053221)
关键词
语音去噪
EMD
改进阈值
speech denoising
EMD
improved threshold
