个人简历

理学博士，北京建筑大学教授、博士生导师；2006年在瑞士联邦工学院（洛桑）获得理学博士学位。曾任职中科院声学研究所研究员/博士生导师，担任声纹识别、语种识别与音乐信号处理方向学术带头人。研究成果在国家相关部门与全国多个省（区/直辖市）推广应用；获得新疆自治区科技进步一等奖1项，中科院科技杰出成就奖1项。

教育经历
2001.05-2006.10 瑞士联邦工学院（洛桑），获理学博士学位
1994.09-1997.07 中科院微电子所微电子专业，获硕士学位
1990.09-1994.07 北京理工大学微电子专业，获学士学位
工作经历
2019.11-目前 北京建筑大学电信学院，教授
2010.10-2019.10 中科院声学所，研究员
2009.10-2010.10 中科院声学所，副研究员
2007.06-2009.08 伦敦大学玛丽皇后学院，高级研究人员
2001.05-2007.05 瑞士联邦工学院（洛桑），助理研究员
2000.10-2001.03 摩托罗拉（中国），软件工程师
1999.10-2000.09 安捷伦软件公司（中国），研究工程师
1997.9-1999.09 中国华大集成电路设计中心，IC设计工程师
科研获奖
2013年 语音自动识别 获新疆自治区科技进步一等奖
2014年 基于海云计算的智能处理系统研究 中科院科技杰出成就奖

研究领域

（1）机器学习
（2）语音及音乐信号处理
（3）建筑声学

近期论文

[1] Music Onset Detection Based on Resonator Time-frequency Image(2008). IEEE Transactions On Audio, Speech And Language Processing, vol. 16, num. 8, 2008, p. 1685-1695 . (SCI，IF=3.531)
[2] A Computationally Efficient Method for Polyphonic Pitch Estimation(2009), EURASIP Journal on Advances in Signal Processing, Volume 2009 , Article ID 729494, 11 pages. (SCI，IF=1.749)
[3] Polyphonic Piano Transcription with a Note-Based Music Language Model(2018), in: Applied Sciences, 8(3),470. （SCI， IF=2.231）
[4] A Two-Stage Approach to Note-Level Transcription of a Specific Piano (2017), in: Applied Sciences, 7(9),901. (SCI，IF=2.231)
[5] Window-Dominant Signal Subspace Methods for Multiple Short-Term Speech Source Localization (2017), in: IEEE/ACM Transactions on Audio, Speech, and Language Processing, 25:4(731 - 744). (SCI，IF=3.531)
[6] Phonotactic language recognition using dynamic pronunciation and language branch discriminative information (2015), in: Speech Communication, 75(50 - 61) (SCI，IF=1.661)
[7] Discriminatively learned network for i-vector based speaker recognition(2018), in: IET Electronics Letters, 54:22(1302-1304) . (SCI，IF=1.343)
[8] Speaker-Phonetic I-Vector Modeling for Text-Dependent Speaker Verification with Random Digit Strings (2019), in: IEICE TRANSACTIONS on Information and Systems, .E102-D:2(346-354) . (SCI，IF=0.576)
[9] Robust speaker recognition using a library of cross-domain variation compensation transforms (2016), in: IET Electronics Letters, 52:4(321-323) . (SCI，IF=1.343)
[10] Cross-domain variation compensation for robust speaker verification (2015), in: IET Electronics Letters, 51:21(1706-1707) . (SCI，IF=1.343)
[11] Feature recovery for noise-robust speaker verification (2015), in: IET Electronics Letters, 51:18(1459-1461) . (SCI，IF=1.343)
[12] Voice biometrics using linear Gaussian model（2014）, in IET Biometrics ,3:1(9-15), 2014 （SCI, IF=2.092）
[13] A General Bayesian Model for Speaker Verification (2016)，in Chinese Journal of Electronics, 25:6,(1045-1051). （SCI, IF=0.945）
[14] PLF Optimization for Target Language Detection (2017)，in Chinese Journal of Electronics, 26:1(118-121). （SCI, IF=0.945）
[15] Speaker Recognition Using Sparse Probabilistic Linear Discriminant Analysis(2013)，in IEICE TRANS. fundmentals of Electronics Communications and Computer Sciences , E96–A:10(1938-1945) . （SCI, IF=0.368）
[16] Automatic Piano Music Transcription Using Audio-Visual Features(2015)，in Chinese Journal of Electronics, 24:3,(596-603). （SCI, IF=0.945）
[17] Modeling prosodic features with probabilistic linear discriminant analysis for speaker verification（2014），in Shengxue Xuebao/Acta Acustica，40:1(28-33). (EI)
[18] Gaussian PLDA for Speaker Verification and Joint Estimation(2014) , in Acta Automatica Sinica, 40(6): 1068-1074. (EI)
[19] Enhanced Voice Activity Detection based on Automatic Segmentation and Event Classification (2014) , in Journal of Computational Information Systems,10:10(4169-4177). (EI)
[20] Language recognition based on SVM 1 vs.1 classification（2013）, in Qinghua Daxue Xuebao/Journal of Tsinghua University,53:6(808:812). (EI)