基本信息

郑成诗  男  博士生导师  中国科学院声学研究所
电子邮件: cszheng@mail.ioa.ac.cn
通信地址: 北京市北四环西路21号
邮政编码: 100190

部门/实验室:声学所

研究领域

Statistical-model-based Speech Processing (基于统计特性的语音处理); 
Microphone Array Signal Processing (传声器阵列信号处理);
Machine Learning for Speech and Audio Processing(机器学习语音和音频处理).

招生信息

   
招生专业
081002-信号与信息处理
081001-通信与信息系统
085400-电子信息
招生方向
机器学习
声信号处理
电子与通信工程

教育背景

2004-09--2009-06   中国科学院声学研究所   博士学位
2001-09--2003-06   中国科学技术大学   管理学双学士学位
1999-09--2004-06   中国科学技术大学   学士学位

工作经历

   
工作简历
2020-06~现在, 中国科学院声学研究所, 博士生导师
2018-08~现在, 中国科学院声学研究所, 研究员
2014-11~2015-10,德国埃尔朗根-纽伦堡大学, 访问学者
2014-06~现在, 中国科学院声学研究所, 硕士生导师
2012-01~2018-07,中国科学院声学研究所, 副研究员
2009-07~2011-12,中国科学院声学研究所, 助理研究员
社会兼职
2019-11-01-今,通信学会人工智能技术与应用委员会, 委员
2019-01-01-2022-12-31,中国高科技产业化研究会智能信息处理产业化分会, 理事
2015-11-21-2020-12-31,IEEE, Senior Member
2010-12-31-2015-11-20,IEEE, Member
2010-01-01-今,EURASIP, Member

教授课程

电声原理与应用
信号与系统
声学基础习题课
声学基础

出版信息

   
发表论文
(1) Joint estimation of binaural distance and azimuth by exploiting deep neural networks, J. Acoust. Soc. Am., 2020, 通讯作者
(2) Wideband sparse Bayesian learning for off-grid binaural sound source localization, Signal Processing, 2020, 通讯作者
(3) Speech enhancement using progressive learning-based convolutional recurrent neural network, Applied Acoustics, 2020, 通讯作者
(4) 球谐域类正则化宽带超指向性波束形成算法, Robust broadband regularized superdirective beamforming in the spherical harmonic domain, 声学学报, 2020, 通讯作者
(5) A Supervised Speech Enhancement Approach with Residual Noise Control for Voice Communication, Applied Sciences, 2020, 通讯作者
(6) 球谐域自适应混响抵消与声源定位算法, 声学学报, 2019, 通讯作者
(7) Evaluation of headphone phase equalization on sound reproduction, Applied Acoustics, 2019, 第 2 作者
(8) 室内两步法监督式学习双耳声源距离估计, 声学学报, 2019, 通讯作者
(9) 功率比相关子带划分快速独立向量分析, 信号处理, 2019, 通讯作者
(10) 基于入耳式耳机电阻抗特性的个性化均衡研究, 应用声学, 2019, 第 3 作者
(11) 偏度最大化多通道逆滤波语声去混响研究, 应用声学, 2019, 通讯作者
(12) 双扬声器近场声源重放实验研究, 应用声学, 2019, 第 4 作者
(13) A perceptually motivated LP estimator in noisy and reverberant environments, Speech Communication, 2018, 通讯作者
(14) Guided Spectrogram Filtering for Speech Dereverberation, Applied Acoustics, 2018, 第 1 作者
(15) Statistical Analysis of the Multichannel Wiener Filter Using a Bivariate Normal Distribution for Sample Covariance Matrices, IEEE/ACM Trans. on Audio, Speech, and Lang. Process., 2018, 第 1 作者
(16) Robust Adaptive Beamforming using Noise Reduction Preprocessing-based Fully Automatic Diagonal and Steering Vector Estimation, IEEE ACCESS, 2017, 通讯作者
(17) Analysis of additional stable gain by frequency shifting for acoustic feedback suppression using statistical room acoustics, IEEE Signal Processing Letters, 2016, 第 1 作者
(18) Stereophonic Channel Decorrelation Using a Binaural Masking Model, Applied Acoustics, 2016, 通讯作者
(19) 基于谱优势与非线性变换混合的立体声声学回声消除方法, A stereo acoustic echo cancellation method based on the hybrid of spectral dominance and nonlinear transformation, 电子与信息学报, 2015, 通讯作者
(20) 高压变电站噪声分离算法及其应用, Study and Application of Noise Separation Algorithm in High Voltage Substation, 高电压技术, 2015, 通讯作者
(21) Active headrest with robust performance against head movement, Active headrest with robust performance against head movement, JOURNAL OF LOW FREQUENCY NOISE VIBRATION AND ACTIVE CONTROL, 2015, 通讯作者
(22) Speech quality evaluation of a sparse coding shrinkage noise reduction algorithm with normal hearing and hearing impaired listeners, Speech quality evaluation of a sparse coding shrinkage noise reduction algorithm with normal hearing and hearing impaired listeners, Hearing Research , 2015, 第 3 作者
(23) Equalization of loudspeaker response using balanced model truncation, J. Acoust. Soc. Am., 2015, 通讯作者
(24) A Constrained MMSE LP Residual Estimator for Speech Dereverberation in Noisy Environments, IEEE Signal Processing Letters, 2014, 第 1 作者
(25) On generalized auto-spectral coherence function and its applications to signal detection, IEEE Signal Processing Letters, 2014, 第 1 作者
(26) statistical analysis ofpower-level-difference-based dual-channel post-filter estimator, Applied Acoustics, 2014, 通讯作者
(27) Evaluation of thesparse coding shrinkage noise reduction algorithm in normal hearing and hearingimpaired listeners, Hearing Research, 2014, 第 3 作者
(28) A Statistical Analysis of Two-Channel Post-Filter Estimators in Isotropic Noise Fields, IEEE Transaction on Audio, Speech and Languge Processing, 2013, 第 1 作者
(29) Detection of multiple sinusoids in unknown colored noise using trancated cepstrum thresholding and local signal-to-noise-ratio, Applied Acoustics, 2012, 第 1 作者
(30) On second-order statistics of log-periodogram and cepstral coefficients for processes with mixed spectra, Signal Processing, 2012, 第 1 作者
(31) 基于噪声谱结构特性的谱减法, Spectral subtraction based on the structure of noise power spectral density, 声学学报, 2010, 第 1 作者
(32) Generalized framework for nonparametric coherence function estimation, Electronics Letters, 2010, 第 1 作者
(33) 基于联合语音出现概率的先验信噪比估计算法, A modified a priori SNR estimator based on united speech presence probabilities, 电子与信息学报, 2008, 第 1 作者
(34) On the relationship of non-parametric methods for coherence function estimation, Signal Processing, 2008, 第 1 作者
(35) 自适应平滑周期图语音增强研究, Speech enhancement based on adaptive averaging periodogram, 声学学报, 2007, 第 1 作者

科研活动

   
科研项目
( 1 ) 多传感信息融合语音分离和虚拟声合成研究, 主持, 国家级, 2013-01--2015-12
( 2 ) 基于非线性语音谱分析的单通道语音增强研究, 参与, 国家级, 2014-01--2016-12
( 3 ) 青年创新促进会, 主持, 部委级, 2013-01--2016-12
( 4 ) 超级免提, 主持, 研究所(学校), 2014-01--2014-12
( 5 ) 多点同步激光侦听系统语音重构理论研究及实验研究, 主持, 国家级, 2016-01--2019-12
( 6 ) 特殊路基工程稳定性综合评价研究, 主持, 部委级, 2018-01--2019-12
参与会议
(1)Near-Field Compensated Higher-Order Ambisonics using a Virtual Source Panning Method   AES2018   Tong Wei, Jinqiu Sang, Chengshi Zheng, and Xiaodong Li   2018-10-16
(2)Vibrational Contrast Control for Local Sound Source Rendering on Flat Panel Loudspeakers   AES2018   Ziqing Li, Pingzhan Luo, Chengshi Zheng, and Xiaodong Li   2018-10-16
(3)An Audio Loudness Compression and Compensation Method for Miniature Loudspeaker Playback   AES2017   Ziran Jiang, Jinqiu Sang, Jie Wang, Chengshi Zheng, Fangjie Zhang and Xiaodong Li   2017-10-16
(4)Auditory-Based Smoothing for Equalization of Headphone-to-Eardrum Transfer Function   AES2017   Guangju Li, Ziran Jiang, Jinqiu Sang, Chengshi Zheng, Renhua Peng, and Xiaodong Li   2017-10-16
(5)Analysis of Binaural Features for Supervised Localization in Reverberant Environments   J. Ding, J. Wang, C. Zheng, R. Peng, and X. Li   2016-09-29
(6)Acoustic echo cancellation for asynchronous systems based on resampling adaptive filter coefficients   Y. Cui, J. Wang, C. Zheng, and X. Li   2016-09-29
(7)Statistical analysis and improvement of coherent-to-diffuse power ratio estimators for dereverberation   郑成诗,Andreas Schwarz,李晓东,Walter Kellermann   2016-09-13
(8)Binaural coherent-to-diffuse-ratio estimation for dereverberation using an ITD model   C. Zheng, A. Schwarz, W. Kellermann, and X. Li   2015-08-31
(9)Statistical Analysis of Temporal Coherence Function and Its Application in Howling Detection   C.Zheng, Y. Ke, R. Peng, X. Li, and Y. Zhou   2014-08-20
(10)Delayless method to suppress transient noise using speechproperties and spectral coherence   C. Zheng, S. Wang, R. Peng,and X. Li   2013-10-16
(11)Temporal Coherence-Based Howling Detection for Speech Applications   C. Zheng, H. Liu, R. Peng, X.Li   2012-10-26
(12)Two-Channel Post-Filtering Based on Adaptive Smoothing and Noise Properties   C. Zheng, Y. Zhou, X. Hu, and X. Li   2011-05-22
(13)Speech enhancement based on the structure of noise power spectral density   C. Zheng, Y. Zhou, X. Hu, andX. Li   2010-08-23