Please wait a minute...
Front. Inform. Technol. Electron. Eng.  2014, Vol. 15 Issue (12): 1154-1163    DOI: 10.1631/jzus.C1400085
    
Speech enhancement with a GSC-like structure employing sparse coding
Li-chun Yang, Yun-tao Qian
College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China; Intelligent Control Research Institute, Zhejiang Wanli University, Ningbo 315101, China
Download:   PDF(0KB)
Export: BibTeX | EndNote (RIS)      

Abstract  Speech communication is often influenced by various types of interfering signals. To improve the quality of the desired signal, a generalized sidelobe canceller (GSC), which uses a reference signal to estimate the interfering signal, is attracting attention of researchers. However, the interference suppression of GSC is limited since a little residual desired signal leaks into the reference signal. To overcome this problem, we use sparse coding to suppress the residual desired signal while preserving the reference signal. Sparse coding with the learned dictionary is usually used to reconstruct the desired signal. As the training samples of a desired signal for dictionary learning are not observable in the real environment, the reconstructed desired signal may contain a lot of residual interfering signal. In contrast, the training samples of the interfering signal during the absence of the desired signal for interferer dictionary learning can be achieved through voice activity detection (VAD). Since the reference signal of an interfering signal is coherent to the interferer dictionary, it can be well restructured by sparse coding, while the residual desired signal will be removed. The performance of GSC will be improved since the estimate of the interfering signal with the proposed reference signal is more accurate than ever. Simulation and experiments on a real acoustic environment show that our proposed method is effective in suppressing interfering signals.

Key wordsGeneralized sidelobe canceller      Speech enhancement      Voice activity detection      Dictionary learning      Sparse coding     
Received: 09 March 2014      Published: 05 December 2014
CLC:  TN912.35  
Cite this article:

Li-chun Yang, Yun-tao Qian. Speech enhancement with a GSC-like structure employing sparse coding. Front. Inform. Technol. Electron. Eng., 2014, 15(12): 1154-1163.

URL:

http://www.zjujournals.com/xueshu/fitee/10.1631/jzus.C1400085     OR     http://www.zjujournals.com/xueshu/fitee/Y2014/V15/I12/1154


基于稀疏编码的广义旁瓣抵消器语音增强算法

在广义旁瓣抵消器中,利用阻塞矩阵阻塞目标信号得到参考干扰信号,以便估计干扰信号,因此需尽量降低泄漏进参考干扰信号的目标信号。本文使用稀疏编码方法重构通过阻塞矩阵得到的参考干扰信号,以抑制目标干扰信号的泄漏,从而在较小语音失真情况下实现更有效的语音增强。利用非语音段干扰信号作为样本,训练得到干扰信号字典,用以重构参考干扰信号中的干扰信号,而目标信号由于与干扰信号不相关,可以被抑制。本文算法在传统阻塞矩阵基础上,加入干扰信号稀疏编码,实现了抑制残余目标信号的目的。基于稀疏编码的广义旁瓣抵消器具有如下两个特点:一是利用非随机干扰信号结构相对稳定的特性,利用非语音段学习得到干扰信号字典,该字典与参考干扰信号结构特征相关,从而可用于对参考干扰信号的稀疏重构;二是克服了传统方法中单纯使用阻塞矩阵难以有效避免目标信号泄漏的不足,利用干扰信号字典进行稀疏编码,以抑制泄漏的少量残余目标信号的影响。本文提出的基于稀疏编码的参考干扰信号重构方法,可有效抑制参考干扰信号中的少量泄漏目标信号,利用自适应滤波估计得到较为准确的原始干扰信号,可以在目标语音失真度较小的情况下,实现对干扰信号最大程度的抑制。

关键词: 广义旁瓣抵消器,  语音增强,  语音活动检测,  字典学习,  稀疏编码 
[1] Min Yuan, Bing-xin Yang, Yi-de Ma, Jiu-wen Zhang, Fu-xiang Lu, Tong-feng Zhang. Multi-scale UDCT dictionary learning based highly undersampled MR image reconstruction using patch-based constraint splitting augmented Lagrangian shrinkage algorithm[J]. Front. Inform. Technol. Electron. Eng., 2015, 16(12): 1069-1087.