Speech enhancement based on bionic wavelet transform of subband spectrum entropy

doi:10.11772/j.issn.1001-9081.2015.03.868

Abstract

Abstract:

Front end noise processing has a direct impact upon the accuracy and stability of the speech recognition. According to the fact that the signal separated by wavelet denoising algorithm isn't its optimal estimation, a novel Bionic Wavelet Transform (BWT) de-noising algorithm based on subband spectrum entropy was proposed. To achieve the purpose of speech enhancement, the subband spectrum entropy, which has a good accuracy of the endpoint detection, was taken full advantage to distinguish the parts of speech and noise, to real-timely update the threshold of BWT, and to precisely determine the noise signal wavelet coefficients. The experimental results indicate that the Signal-to-Noise Ratio (SNR) of the proposed algorithm is 8% higher than the Wiener filter algorithm. The proposed method has significant enhancement effect on speech signal in noisy environments.

Key words: speech enhancement, subband spectrum entropy, Bionic Wavelet Transform (BWT), denoising, threshold

摘要：

前端噪声处理直接关系着语音识别的准确性和稳定性,针对小波去噪算法所分离出的信号不是原始信号的最佳估计,提出一种基于子带谱熵的仿生小波变换(BWT)去噪算法。充分利用子带谱熵端点检测的精确性,区分含噪语音部分和噪声部分,实时更新仿生小波变换中的阈值,精确地区分出噪声信号小波系数,达到语音增强目的。实验结果表明,提出的基于子带谱熵的仿生小波语音增强方法与维纳滤波方法相比,信噪比(SNR)平均提高约8%,所提方法对噪声环境下语音信号有显著的增强效果。

关键词: 语音增强, 子带谱熵, 仿生小波变换, 去噪, 阈值

CLC Number:

TN912.3

LIU Yan, NI Wanshun. Speech enhancement based on bionic wavelet transform of subband spectrum entropy[J]. Journal of Computer Applications, 2015, 35(3): 868-871.

刘艳, 倪万顺. 基于子带谱熵的仿生小波语音增强[J]. 计算机应用, 2015, 35(3): 868-871.

References

[1] LI F. Based on wavelet transform speech recognition of research and application[D]. Guilin: Guilin University of Technology, 2011.(李法强. 基于小波变换的语音识别的研究和应用[D].桂林:桂林理工大学,2011.)
[2] DAI Y, ZHANG J. Reduction of 1/f noise in semiconductor devices based on wavelet transform and Wiener filter[J]. Acta Physica Sinica, 2011,60(11):185-190.(代煜,张建勋. 基于小波变换和维纳滤波的半导体器件1/f噪声滤波[J].物理学报,2011,60(11):185-190.)
[3] GENG Y, ZHANG D. Survey of adaptive filtering algorithms[J]. Information and Electroic Engineering, 2008,6(4):315-320.(耿妍,张端金. 自适应滤波算法综述[J].信息与电子工程, 2008,6(4):315-320.)
[4] ZHANG T, HE L, HUANG H, et al. Speech endpoint detection based on critical band and energy entropy[J]. Journal of Computer Applications, 2013,33(1):175-178.(张婷,何凌,黄华,等.基于临界频带及能量熵的语音端点检测[J].计算机应用,2013,33(1):175-178.)
[5] DONOHO D L, JOHNSTONE I M. Adapting to unknown smoothness via wavelet shrinkage[J]. Journal of the American Statistical Association, 1995, 90(432):1200-1224.
[6] REN Y, ZHANG X, JIA H. New threshold function of wavelet packet speech enhancement algorithm[J]. Application Research of Computers, 2013,30(1):114-116.(任永梅,张雪英,贾海荣. 一种新阈值函数的小波包语音增强算法[J].计算机应用研究,2013,30(1):114-116.)
[7] YAO J, ZHANG Y T. Bionic wavelet transform: a new time-frequency method based on all auditory model[J]. IEEE Transactions on Biomedical Engineering, 2001,48(8):856-863.
[8] SHEN J-L, HUNG J-W, LEE L-S. Robust entropy-based endpoint detection for speech recognition in noisy environments[EB/OL].[2014-08-12]. http://wenku.baidu.com/view/e676ae0979563c1ec 5da71d5.html.
[9] LI Y, WANG T, CUI H, et al. Voice activity detection in non-stationary noise[EB/OL].[2014-09-01]. http://ieeexplore.ieee.org/xpl/login.jsp?tp=&arnumber=4281886&url=http%3A%2F%2Fieeexplore.ieee.org%2Fstamp%2Fstamp.jsp%3Ftp%3D%26arnumber%3D4281886.
[10] WU B, WANG K. Robust endpoint detection algorithm based on the adaptive band-partitioning spectral entropy in adverse environments[J]. IEEE Transactions on Speech and Audio Processing, 2005,13(5):762-775.
[11] LI R, HU C, YU J. Research of speech endpoint detection based on spectral entropy algorithm[J]. Journal of Wuhan University of Technology, 2013,35(7):134-139.(李荣荣,胡昌奎,余娟.基于谱熵的语音端点检测算法改进研究[J].武汉理工大学学报.2013,35(7):134-139.)
[12] YANG X, FAN X. Speech enhancement based on bionic wavelet transform and adaptive threshold functions[J]. Control and Decision, 2006,21(9):1033-1036.(杨玺,樊晓平.基于仿生小波变换和自适应阈值的语音增强方法[J].控制与决策,2006,21(9):1033-1036.)
[13] CHEN X, WANG Y, LIU L. Deep study on wavelet threshold method for image noise removing[J]. Laser and Infrared, 2012,42(1):3-5.(陈小曦,王延杰,刘恋. 小波阈值去噪法的深入研究[J].激光与红外,2012,42(1):3-5.)

[1]	LIU Xiaoguang, JIN Shaokang, WEI Zihui, LIANG Tie, WANG Hongrui, LIU Xiuling. Real-time fall detection method based on threshold and extremely randomized tree [J]. Journal of Computer Applications, 2021, 41(9): 2761-2766.
[2]	ZHANG Yuanjun, ZHANG Xihuang. Dynamic network representation learning model based on graph convolutional network and long short-term memory network [J]. Journal of Computer Applications, 2021, 41(7): 1857-1864.
[3]	JING Beibei, GUO Jia, WANG Liqing, CHEN Jing, DING Hongwei. Image double blind denoising algorithm combining with denoising convolutional neural network and conditional generative adversarial net [J]. Journal of Computer Applications, 2021, 41(6): 1767-1774.
[4]	JIA Heming, LI Yao, JIANG Zichao, SUN Kangjian. Multi-threshold segmentation of forest fire images based on modified symbiotic organisms search algorithm [J]. Journal of Computer Applications, 2021, 41(5): 1465-1470.
[5]	ZHUO Yuxin, HAN Suya, ZHANG Yufeng, LI Zhiyao, DONG Yifeng. Automatic segmentation method of microwave ablation region based on Nakagami parameters images of ultrasonic harmonic envelope [J]. Journal of Computer Applications, 2021, 41(10): 3089-3096.
[6]	LUO Jun, CHEN Lifei. Sentiment classification of incomplete data based on bidirectional encoder representations from transformers [J]. Journal of Computer Applications, 2021, 41(1): 139-144.
[7]	LONG Chao, ZENG Qingning, LUO Ying. Small-array speech enhancement based on noise cancellation and beamforming [J]. Journal of Computer Applications, 2020, 40(8): 2386-2391.
[8]	WANG Sipeng, DU Changping, YE Zhixian, SONG Guanghua, ZHENG Yao. Soft fault detection for flapping wing micro aerial vehicle based on multistep neural network observer [J]. Journal of Computer Applications, 2020, 40(8): 2449-2454.
[9]	HU Xueying, GUO Hairu, ZHU Rong. Image super-resolution reconstruction based on hybrid deep convolutional network [J]. Journal of Computer Applications, 2020, 40(7): 2069-2076.
[10]	CAO Jianfang, ZHAO Aidi, ZHANG Zibang. Application of convolutional neural network with threshold optimization in image annotation [J]. Journal of Computer Applications, 2020, 40(6): 1587-1592.
[11]	ZHANG Haoran, WANG Xueyuan, LI Xiaoxia. Low SNR denoising algorithm based on adaptive voice activity detection and minimum mean-square error log-spectral amplitude estimation [J]. Journal of Computer Applications, 2020, 40(6): 1763-1768.
[12]	WU Qinghe, WU Haifeng, SHEN Yong, ZENG Yu. Speech enhancement using multi-microphone state space model under industrial noise environment [J]. Journal of Computer Applications, 2020, 40(5): 1476-1482.
[13]	WANG Zhongfeng, XU Zhiyuan, SONG Chunhe, ZHANG Hongyu, CAI Yingkai. Gradient-based deep network pruning algorithm [J]. Journal of Computer Applications, 2020, 40(5): 1253-1259.
[14]	LI Jing, JING Xu, YANG Huijun. Blockchain electronic counting scheme based on practical Byzantine fault tolerance algorithm [J]. Journal of Computer Applications, 2020, 40(4): 954-960.
[15]	ZHU Zhe, XU Shaohua. Denoising autoencoder deep convolution process neural network and its application in time-varying signal classification [J]. Journal of Computer Applications, 2020, 40(3): 698-703.