[1]王水平,唐振民,陈北京,等.复杂环境下语音增强的复平面谱减法[J].南京理工大学学报(自然科学版),2013,37(06):857-862.
 Wang Shuiping,Tang Zhenmin,Chen Beijing,et al.Complex plane spectral subtraction for speech enhancement in complicated environments[J].Journal of Nanjing University of Science and Technology,2013,37(06):857-862.
点击复制

复杂环境下语音增强的复平面谱减法
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
37卷
期数:
2013年06期
页码:
857-862
栏目:
出版日期:
2013-12-31

文章信息/Info

Title:
Complex plane spectral subtraction for speech enhancement in complicated environments
作者:
王水平123唐振民3陈北京12蒋 晔3
南京信息工程大学 1.计算机与软件学院;
2.江苏省网络监控工程中心,江苏 南京 210044;
3.南京理工大学 计算机科学与工程学院,江苏 南京 210094
Author(s):
Wang Shuiping123Tang Zhenmin3Chen Beijing12Jiang Ye3
1.School of Computer and Software;
2.Jiangsu Engineering Center of Network Monitoring,Nanjing University of Information Science and Technology,Nanjing 210044,China;
3.School of Computer Science and Engineering,NUST,Nanjing 210094,China
关键词:
复杂环境 语音增强 复平面 谱减法 增益函数
Keywords:
complicated environments speech enhancement complex plane spectral subtraction gain function
分类号:
TN912.35
摘要:
为了降低复杂环境中存在的各类噪声,消除噪声给语音识别及说话人识别等系统在军事自动指挥及控制领域等的应用中带来的影响,设计了一种新的谱减法。针对传统谱减法在语音增强过程中的原始语音和噪声信号相差为0的错误假设,提出一种基于复平面的、考虑纯净语音与噪声及带噪语音之间相位差信息的改进谱减法,对增益函数进行修正。经过复杂的战场仿真环境测试表明,该方法性能较好,在低信噪比的环境下性能更优。对于输入信噪比为5 dB的带噪语音,经复平面谱减法去噪后,输出信噪比为12.21 dB,比传统谱减法提高了2.1 dB。
Abstract:
To reduce noise in complicated environments and eliminate the inferences of noise on the applications of speech recognition and speaker recognition systems in automatic military command and control fields,a new spectral subtraction is designed.Aiming at the incorrect assumption of the traditional spectral subtraction that the phase difference between the clean speech and noise signals is zero in the speech enhancement process,an improved spectral subtraction is proposed based on complex plane and considering the phase difference among the clean speech,the noise and the noisy speech signals.The gain function is corrected.The results of complicated battlefield simulation experiments show that the method proposed here performs better than the traditional spectral subtraction,especially in low signal noise ratio(SNR)conditions.For the noisy speech with input SNR of 5 dB,the output SNR is more than 12.21 dB after denoised by using the complex plane spectral subtraction,which increases 2.1 dB than the result of the traditional spectral subtraction.

参考文献/References:

[1] 路建伟,丁庆海,朱雪平,等.战场环境下的军事命令识别技术[J].南京理工大学学报,2002,26(4):438-441,445.
Lu Jianwei,Ding Qinghai,Zhu Xueping,et al.The military order recognition technology in battlefield environment[J].Journal of Nanjing University of Science and Technology,2002,26(4):438-441,445.
[2]Loizou P C.Speech enhancement algorithms:A survey:Recent advances in robust speech recognition technology[M].Spain:Bentham Science,2011:60-102.
[3]雷建军,杨震,刘刚,等.噪声鲁棒语音识别研究综述[J].计算机应用研究,2009,26(4):1210-1216.
Lei Jianjun,Yang Zhen,Liu Gang,et al.Review of noise robust speech recognition[J].Application Research of Computers,2009,26(4):1210-1216.
[4]Boll S F.Suppression of acoustic noise in speech using spectral subtraction[J].IEEE Transactions on Acoustics,Speech,and Signal Processing,1979,ASSP-27(2):113-120.
[5]Berouti M,Schwartz R,Makhoul J.Enhancement of speech corrupted by acoustic noise[A].IEEE Interna-tional Conference on ICASSP'79[C].Washington,DC,USA:IEEE,1979:208-211.
[6]何一鸣,张刚兵,钱显毅.基于邻域均值的去椒盐噪声算法[J].南京理工大学学报,2011,35(6):764-767,785.
He Yiming,Zhang Gangbing,Qian Xianyi.Salt and pepper noise removal algorithm based on neighbourhood mean[J].Journal of Nanjing University of Science and Technology,2011,35(6):764-767,785.
[7]Preuss R.A frequency domain noise cancelling prepro-cessor for narrowband speech communications systems[A].IEEE International Conference on ICASSP'79[C].Washington,DC,USA:IEEE,1979:212-215.
[8]Martin R.Noise power spectral density estimation based on optimal smoothing and minimum statistics[J].IEEE Transactions on Speech and Audio Processing,2001,9(5):504-512.
[9]张俊.基于谱减算法语音增强的研究[J].信息技术,2009(3):74-76.
Zhang Jun.Research on speech enhancement based on spectral subtraction method[J].Information Techno-logy,2009(3):74-76.
[10]赵力.语音信号处理[M].2版.北京:机械工业出版社,2009.
[11]Loizou P C.Speech enhancement based on perceptually motivated bayesian estimators of the magnitude spectrum[J].IEEE Transactions on Speech and Audio Processing,2005,13(5):857-869.
[12]蒋晔,唐振民.2011.短语音说话人辨认的研究[J].电子学报,39(4):953-957.
Jiang Ye,Tang Zhenmin.Research on the speaker identification based on short utterance[J].Acta Electronica Sinica,2011,39(4):953-957.
[13]王加永.基于改进谱减法的语音增强研究[J].洛阳理工学院学报(自然科学版),2009,19(2):53-55,72.
Wang Jiayong.Speech enhancement research based on improved spectral subtraction[J].Journal of Luoyang Technology College(Natural Sciences Edition),2009,19(2):53-55,72.
[14]Paliwal K,Wójcicki K,Shannon B.The importance of phase in speech enhancement[J].Speech Communica-tion,2011,53(4):465-494.

备注/Memo

备注/Memo:
收稿日期:2012-09-17 修回日期:2012-11-02
基金项目:国家自然科学基金(61103141); 江苏省自然科学基金(CX2211_0261); 江苏省高等学校大学生实践创新训练计划指导项目(301310300055)
作者简介:王水平(1977-),女,博士生,副教授,主要研究方向:语音信号处理,说话人识别,E-mail:shuipingw@126.com。
引文格式:王水平,唐振民,陈北京,等.复杂环境下语音增强的复平面谱减法[J].南京理工大学学报,2013,37(6):857-862.
投稿网址:http://njlgdxxb.paperonce.org
更新日期/Last Update: 2013-12-31