一种融合相位估计的深度卷积神经网络语音增强方法

doi:10.3969/j.issn.0372-2112.2018.10.008

电子学报 ›› 2018, Vol. 46 ›› Issue (10): 2359-2366.DOI: 10.3969/j.issn.0372-2112.2018.10.008

一种融合相位估计的深度卷积神经网络语音增强方法

袁文浩, 梁春燕, 夏斌, 孙文珠

山东理工大学计算机科学与技术学院, 山东淄博 255000

收稿日期:2017-10-21 修回日期:2018-02-20 出版日期:2018-10-25
- 通讯作者:
- 袁文浩
- 作者简介:
- 梁春燕,女.1986年出生,山东淄博人.2014年毕业于中国科学院声学研究所获博士学位,现为山东理工大学计算机科学与技术学院讲师.主要研究方向为语音信号处理,说话人识别.E-mail:liangchunyan@sdut.edu.cn
- 基金资助:
- 国家自然科学基金 (No.61701286，No.11704229）; 山东省自然科学基金 (No.ZR2015FL003，No.ZR2017MF047，No.ZR2017LA011）

A Deep Convolutional Neural Network Based Speech Enhancement Approach Incorporating Phase Estimation

YUAN Wen-hao, LIANG Chun-yan, XIA Bin, SUN Wen-zhu

College of Computer Science and Technology, Shandong University of Technology, Zibo, Shandong 255000, China

Received:2017-10-21 Revised:2018-02-20 Online:2018-10-25 Published:2018-10-25
- Corresponding author:
- YUAN Wen-hao

摘要/Abstract

摘要： 在时频域的语音增强中，幅度估计和相位估计都是影响语音增强性能的重要因素.为了在基于深度学习的语音增强方法中融合对相位的估计，本文将含噪语音短时傅里叶变换（STFT）的实部和虚部特征作为两个通道输入深度卷积神经网络，通过建立一个同步估计纯净语音STFT的实部和虚部特征的多任务学习模型，实现了对幅度和相位的同步估计.实验结果表明，相比仅考虑幅度估计的方法，本文方法具有更好的噪声抑制能力，在低信噪比条件下，显著提高了语音增强性能.

关键词: 语音增强, 相位估计, 幅度估计, 深度卷积神经网络

Abstract: In the speech enhancement of the time-frequency domain, both the amplitude estimation and the phase estimation are the important factors that affect speech enhancement performance. In order to incorporate the phase estimation into the speech enhancement approaches based on deep learning, the real and imaginary part of the short-time Fourier transform (STFT) of noisy speech are treated as two channels and fed into the deep convolutional neural network (DCNN) in this paper. By establishing a multi-task learning model which simultaneously estimates the real and imaginary part of the STFT of clean speech, the synchronous estimation of the amplitude and phase is achieved. Experimental results show that compared with the approaches only considering the amplitude estimation, the proposed approach has better noise suppression ability, and improves speech enhancement performance significantly under the condition of low SNR.

Key words: speech enhancement, phase estimation, amplitude estimation, deep convolutional neural network

中图分类号:

TN912.3

袁文浩, 梁春燕, 夏斌, 孙文珠. 一种融合相位估计的深度卷积神经网络语音增强方法[J]. 电子学报, 2018, 46(10): 2359-2366.

YUAN Wen-hao, LIANG Chun-yan, XIA Bin, SUN Wen-zhu. A Deep Convolutional Neural Network Based Speech Enhancement Approach Incorporating Phase Estimation[J]. Acta Electronica Sinica, 2018, 46(10): 2359-2366.

参考文献

[1] 刘文举,聂帅,梁山,等.基于深度学习语音分离技术的研究现状与进展[J].自动化学报,2016,42(6):819-833. LIU Wen-Ju,NIE Shuai,LIANG Shan,ZHANG Xue-Liang.Deep learning based speech separation technology and its developments[J].Acta Automatica Sinica,2016,42(6):819-833.(in Chinese)
[2] 孟宪波,鲍长春.基于最小控制GARCH模型的噪声估计算法[J].电子学报,2016,44(3):747-752. MENG Xian-bo,BAO Chang-chun.Noise estimate algorithm based on minima controlled GARCH model[J].Acta Electronica Sinica,2016,44(3):747-752.(in Chinese)
[3] 何玉文,鲍长春,夏丙寅,等.基于AR-HMM在线能量调整的语音增强方法[J].电子学报,2014,42(10):1991-1997. HE Yu-wen,BAO Chang-chun,XIA Bing-yin,et al.Online energy adjustment using AR-HMM for speech enhancement[J].Acta Electronica Sinica,2014,42(10):1991-1997.(in Chinese)
[4] WANG Y,WANG D L.Towards scaling up classification-based speech separation[J].IEEE Transactions on Audio,Speech,and Language Processing,2013,21(7):1381-1390.
[5] WANG Y,NARAYANAN A,WANG D L.On training targets for supervised speech separation[J].IEEE/ACM Transactions on Audio,Speech,and Language Processing,2014,22(12):1849-1858.
[6] XU Y,DU J,DAI L R,et al.An experimental study on speech enhancement based on deep neural networks[J].IEEE Signal Processing Letters,2014,21(1):65-68.
[7] XU Y,DU J,DAI L R,et al.A regression approach to speech enhancement based on deep neural networks[J].IEEE/ACM Transactions on Audio,Speech,and Language Processing,2015,23(1):7-19.
[8] 韩伟,张雄伟,闵刚,等.基于感知掩蔽深度神经网络的单通道语音增强方法[J].自动化学报,2017,43(2):248-258. HAN Wei,ZHANG Xiong-Wei,MIN Gang,et al.A single-channel speech enhancement approach based on perceptual masking deep neural network[J].Acta Automatica Sinica,2017,43(2):248-258.(in Chinese)
[9] PALIWAL K,WÓJCICKI K,SHANNON B.The importance of phase in speech enhancement[J].Speech Communication,2011,53(4):465-494.
[10] WILLIAMSON D S,WANG Y,WANG D L.Complex ratio masking for monaural speech separation[J].IEEE/ACM Transactions on Audio,Speech,and Language Processing,2016,24(3):483-492.
[11] WENINGER F,ERDOGAN H,WATANABE S,et al.Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR[A].Proceedings of International Conference on Latent Variable Analysis and Signal Separation[C].Liberec:Springer International Publishing,2015.91-99.
[12] MAYER F,WILLIAMSON D S,MOWLAEE P,et al.Impact of phase estimation on single-channel speech separation based on time-frequency masking[J].The Journal of the Acoustical Society of America,2017,141(6):4668-4679.
[13] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenet classification with deep convolutional neural networks[A].Proceedings of the International Conference on Neural Information Processing Systems[C].Nevada:Curran Associates Inc,2012.1097-1105.
[14] 柯圣财,赵永威,李弼程,彭天强.基于卷积神经网络和监督核哈希的图像检索方法[J].电子学报,2017,45(1):157-163. KE Sheng-cai,ZHAO Yong-wei,LI Bi-cheng,PENG Tian-qiang.Image retrieval based on convolutional neural network and kernel-based supervised hashing[J].Acta Electronica Sinica,2017,45(1):157-163.(in Chinese)
[15] GAROFOLO J S,LAMEL L F,FISHER W M,et al.TIMIT Acoustic-Phonetic Continuous Speech Corpus[CD].Philadelphia:Linguistic Data Consortium,1993.
[16] HU G."100 Nonspeech Environmental Sounds,2004"[OL]. http://web.cse.ohio-state.edu/pnl/corpus/HuNo-nspeech/HuCorpus.html,2004.
[17] VARGA A,STEENEKEN H J M.Assessment for automatic speech recognition:Ⅱ.NOISEX-92:A database and an experiment to study the effect of additive noise on speech recognition systems[J].Speech Communication,1993,12(3):247-251.
[18] RIX A W,BEERENDS J G,HOLLIER M P,et al.Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs[A].Proceedings of IEEE International Conference on Acoustics,Speech,and Signal Processing[C].Utah:IEEE,2001.749-752.
[19] TAAL C H,HENDRIKS R C,HEUSDENS R,et al.An algorithm for intelligibility prediction of time-frequency weighted noisy speech[J].IEEE Transactions on Audio,Speech,and Language Processing,2011,19(7):2125-2136.
[20] VINCENT E,GRIBONVAL R,FEVOTTE C.Performance measurement in blind audio source separation[J].IEEE Transactions on Audio,Speech,and Language Processing,2006,14(4):1462-1469.
[21] YU D,EVERSOLE A,SELTZER M,et al.An Introduction to Computational Networks and the Computational Network Toolkit[R].Tech.Rep.MSR,Microsoft Research,2014.

一种融合相位估计的深度卷积神经网络语音增强方法

A Deep Convolutional Neural Network Based Speech Enhancement Approach Incorporating Phase Estimation

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	周静, 鲍长春, 张旭. 基于聚焦信号子空间估计导向矢量的干扰声源抑制方法[J]. 电子学报, 2023, 51(1): 76-85.
[2]	张志文, 刘天歌, 聂鹏举. 基于实景数据增强和双路径融合网络的实时街景语义分割算法[J]. 电子学报, 2022, 50(7): 1609-1620.
[3]	欧世峰, 赵艳磊, 宋鹏, 高颖. 基于概率耦合的双直接判决先验信噪比估计算法[J]. 电子学报, 2020, 48(8): 1605-1614.
[4]	袁文浩, 胡少东, 时云龙, 李钊, 梁春燕. 一种用于语音增强的卷积门控循环网络[J]. 电子学报, 2020, 48(7): 1276-1283.
[5]	袁文浩, 娄迎曦, 梁春燕, 夏斌. 利用生成噪声提高语音增强方法的泛化能力[J]. 电子学报, 2019, 47(4): 791-797.
[6]	罗会兰, 张云. 基于深度网络的图像语义分割综述[J]. 电子学报, 2019, 47(10): 2211-2220.
[7]	陈楠, 鲍长春. 基于双耳线索编码原理的语音增强方法[J]. 电子学报, 2019, 47(1): 227-233.
[8]	孟宪波, 鲍长春. 基于最小控制GARCH模型的噪声估计算法[J]. 电子学报, 2016, 44(3): 747-752.
[9]	陈斌, 牛铜, 张连海, 屈丹, 李弼程. 不相关匹配追踪的分段区分性特征变换方法[J]. 电子学报, 2016, 44(12): 2924-2931.
[10]	何玉文, 鲍长春, 夏丙寅. 基于AR-HMM在线能量调整的语音增强方法[J]. 电子学报, 2014, 42(10): 1991-1997.
[11]	梁岩, 鲍长春, 夏丙寅, 何玉文, 周璇, 李娜. 基于高斯混合模型的压缩域语音增强方法[J]. 电子学报, 2012, 40(10): 2031-2038.
[12]	庞蕾;张继贤;范洪冬. 多基线干涉SAR测量技术发展与趋势分析[J]. 电子学报, 2010, 38(9): 2152-2157.
[13]	应娜;赵晓晖;董婧;方昕. 一种谐波正弦语音模型的最佳相位估计算法[J]. 电子学报, 2009, 37(4): 860-863.
[14]	刘建强, 冯大政, 周祎. 基于多信道信号增强的卷积混迭语音信号盲分离的后处理方法[J]. 电子学报, 2007, 35(12): 2389-2393.
[15]	欧世峰;赵晓晖. 基于帧间相关性的最大后验估计语音增强算法[J]. 电子学报, 2007, 35(10): 2007-2013.