基于小波变换的自适应多分辨率语音增强算法
AN ADAPTIVE MULTIRESOLUTION SPEECH ENHANCEMENT ALGORITHM BASED ON WAVELET TRANSFORM
-
摘要: 本文提出了一种基于小波变换的自适应多分辨率语音增强算法,它在尺度上和尺度间同时对受噪声污染的语音信号作自适应滤波处理,从而使得对听觉影响最严重的频段上的噪声被有效地滤除掉,滤波后的语音信噪比和主观听觉质量都得到了很大的改善。Abstract: In this paper, an adaptive multiresolution speech enhancement algorithm based on wavelet transform is put forward. It can make adaptive filtering to noise speech both at scales and among scales. So that the noise parts during the frequency intervals which decrease hearing quality mostly are reduced efficiently. Both the SNR and subject hearing quality of denoised speech are high and good.
-
Delopoulous A, Kollias S. Optimal filter banks for signal reconstruction from noisy subband components. IEEE Trans. on SP, 1996, SP-44(2):212-224.[2]Mallat S. A theory for multiresolution signal decomposition: The wavlet representation. IEEE Trans. on PAMI, 1989, PAMI-11(7): 674-691.[3]Mallat S, Liang Hwang Wen. Singularity detection and processing with wavelet. IEEE Trans. on IT, 1992, IT-38(2): 617-643.[4]Qinghua Zhang, Benveniste Albert. Wavlet networks. IEEE Trans. on NN, 1992, NN-3(6): 889-898.[5]Sahiner B, Yagle A E. Image reconstruction from projection under wavelet constraints. IEEE Trans. on SP,1993, SP-41(12): 3579-3583.[6]Gilloire A, Vetterli M. Adaptive filtering in subband. in Proc. IEEE Int. Conf. on ASSP, New York: Apr.,1988, 1572-1575.[7]Zhang J, Walter G G, Lee W N W. Wavelet neural networks for function learning. IEEE Trans. on SP, 1995, SP-43(6): 1489-1496.
计量
- 文章访问数: 2328
- HTML全文浏览量: 60
- PDF下载量: 1198
- 被引次数: 0