改进相位谱补偿的语音增强算法

doi:10.3969/j.issn.1001-2400.2017.03.015

Abstract

Abstract:

The typical phase spectrum compensation method has the negative enhancement performance in a low SNR,so the improved phase spectrum compensation method is proposed for this problem. First, the algorithm compensates the speech spectrum through the phase compensation function obtained by calculating the signal to noise ratio of each frame; second, by the new speech presence probability algorithm to estimate the noise power spectral density; finally, we apply the new phase spectrum and the estimated noise in the wiener filter. Simulation results show that the improved algorithm proposed in this paper can effectively improve the ability of voice systems to remove noise especially in a low SNR.

Key words: phase spectrum compensation, speech presence probability, noise power spectrum, wiener filter, speech enhancement

WANG Dong;JIA Hairong. Speech enhancement using improved phase spectrum compensation[J].Journal of Xidian University, 2017, 44(3): 83-88.

References

［1］张君昌, 刘海鹏, 樊养余. 一种自适应时移与阈值的DCT语音增强算法［J］. 西安电子科技大学学报, 2014, 41(6): 155-159.
ZHANG Junchang,LIU Haipeng,FAN Yanyu. Speech Enhancement Method Using Self-adaptive Time-shift and Threshold Discrete Cosine Transform［J］. Journal of Xidian University, 2014, 41(6): 155-159.
［2］ EPHRAIM Y, MALAH D. Speech Enhancement Using a Minimum-mean Square Error Short-time Spectral Amplitude Estimator［J］. IEEE Transactions on Acoustics, Speech and Signal Processing, 1984, 32(6): 1109-1121.
［3］高银秋, 邓宗元, 杨震. 数字音频产品中基于人耳听觉感知特性的水印嵌入系统设计［J］. 南京邮电大学学报, 2006, 26(5): 56-64.
GAO Yinqiu, DENG Zongyuan, YANG Zhen. Design of Watermark Embedding System for Digital Audio Products Based on HAS［J］. Journal of Nanjing University of Posts and Telecommunications, 2006, 26(5): 56-64.
［4］ PALIWAL K, WJCICKI K, SHANNON B. The Importance of Phase in Speech Enhancement［J］. Speech Communication, 2011, 53(4): 465-494.
［5］ STARK A P, WJCICKI K K, LYONS J G, et al. Noise Driven Short-time Phase Spectrum Compensation Procedure for Speech Enhancement［C］//Proceedings of the Annual Conference of the International Speech Communication Association. Bonn: International Speech Communication Association, 2008: 549-552.
［6］ KRAWCZYK M, GERKMANN T. STFT Phase Reconstruction in Voiced Speech for an Improved Single-channel Speech Enhancement［J］. IEEE/ACM Transactions on Speech and Language Processing,2014, 22(12): 1931-1940.
［7］高永婵, 廖桂生, 朱圣棋. 复合高斯噪声中知识辅助的贝叶斯Rao检测方法［J］. 西安电子科技大学学报, 2013, 40(6): 46-51.
GAO Yongchan, LIAO Guisheng, ZHU Shengqi. Knowledge-aided Bayesian Rao Detection Approach in Compound Gaussian Noise［J］. Journal of Xidian University, 2013, 40(6): 46-51.
［8］ GERKMANN T, HENDRIKS R C. Noise Power Estimation Based on the Probability of Speech Presence［C］//Proceedings of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics. Piscataway: IEEE, 2011: 145-148.
［9］容强,肖汉. 基于MMSE维纳滤波语音增强方法研究与Matlab实现［J］. 计算机应用与软件, 2015, 32(1):153-156.
RONG Qiang, XIAO Han. Study on MMSE Wiener Flitering-based Speech Enhancement Method and MATLAB Implementation［J］. Computer Applications and Software, 2015, 32(1): 153-156.

[1]	MEI Shulin,JIA Hairong,WANG Xiaogang,WU Yifeng. Combination of dynamic features with a new mask to optimize neural network speech enhancement [J]. Journal of Xidian University, 2021, 48(3): 91-98.
[2]	CHANG Xinxu,ZHANG Yang,YANG Lin,KOU Jinqiao,WANG Xin,XU Dongdong. Speech enhancement method based on the multi-head self-attention mechanism [J]. Journal of Xidian University, 2020, 47(1): 104-110.
[3]	YUAN Wenhao,LIANG Chunyan,LOU Yingxi,FANG Chao,WANG Zhiqiang. Speech enhancement method based on the time-frequency smoothing deep neural network [J]. Journal of Xidian University, 2019, 46(4): 130-136.
[4]	JIA Hairong,WANG Weimei,WANG Yan,PEI Junhua. Speech enhancement based on discriminative joint sparse dictionary alternate optimization [J]. Journal of Xidian University, 2019, 46(3): 74-81.
[5]	YUAN Wenhao,LOU Yingxi,LIANG Chunyan,WANG Zhiqiang. Speech enhancement method based on the perceptual joint optimization deep neural network [J]. Journal of Xidian University, 2019, 46(2): 89-94.
[6]	WANG Kangkang;WANG Keyan;LI Yunsong. Text image refocusing by using the convolutional neural network [J]. Journal of Xidian University, 2018, 45(4): 80-85.
[7]	GUO Xin;JIA Hairong;WANG Dong. Speech enhancement using the improved K-SVD algorithm by subspace [J]. Journal of Xidian University, 2016, 43(6): 109-115.
[8]	LI Dawei;YANG Rijie;HAN Jianhui. Study of speech enhancement in the background of ship-radiated noise [J]. Journal of Xidian University, 2016, 43(5): 133-138.
[9]	ZHANG Junchang;LIU Haipeng;FAN Yangyu. Speech enhancement method using self-adaptive time-shift and threshold discrete cosine transform [J]. J4, 2014, 41(6): 155-159+194.
[10]	ZENG Qing-ning;OUYANG Shan. Subband MCRASC-MGSC algorithm for speech enhancement with the mini-typed microphone array [J]. J4, 2010, 37(6): 1011-1016.
[11]	WU Jian-xin;WANG Tong;SUO Zhi-yong. Fast DOA estimation algorithm based on the multistage Wiener filter [J]. J4, 2009, 36(2): 263-268.
[12]	HUANG Lei;WU Shun-jun;ZHANG Lin-rang. A fast super-resolution method for coherent signals [J]. J4, 2006, 33(1): 57-61.
[13]	HUANG Lei;WU Shun-jun;FENG Da-zheng;ZHANG Lin-rang. A low computational complexity ESPRIT method [J]. J4, 2005, 32(4): 570-573.
[14]	HUANG Lei;YUAN Wei-ming;ZHANG Lin-rang;WU Shun-jun. Direction of arrival estimation based on the MSWF [J]. J4, 2004, 31(6): 865-869.

Speech enhancement using improved phase spectrum compensation

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 14

Metrics

Comments

Recommended 10