张卫强 - 清华大学 - 电子工程系

个人简介

张卫强，男，博士，副研究员。2009年清华大学获博士学位，2009年至今清华大学电子工程系任教，2017年斯坦福大学访问学者。目前主要研究方向为语音识别与分析（包括语音识别、关键词检索、语种识别、声纹识别、情感识别等）、音频识别与分析（包括音频检索、音频事件检测、音频场景识别等）、音乐与声学信号处理，机器学习等。以负责人身份承担自然科学基金重点项目、国家重点研发课题等多个项目。发表学术论文200余篇；获国家发明专利30余项。获教育部科技进步一等奖，获得NIST等多项语音比赛冠军。教育背景 2005.9-2009.1 清华大学电子工程系博士学位 2002.9-2005.3 北京理工大学电子工程系硕士学位 1998.9-2002.7 中国石油大学应用物理系学士学位工作经历 2014.12至今清华大学电子工程系副研究员 2016.11-2017.11 斯坦福大学CCRMA访问学者 2010.12-2014.12 清华大学电子工程系助理研究员 2009.12-010.12 清华大学电子工程系校内博士后奖励荣誉部级科技进步三等奖,2017,12,2017-12-29 科技奥运先进集体奖,2008,10,2008-10-01 教育部科技进步一等奖,2007,1,2007-01-25

研究领域

语音识别与分析音频识别与分析音乐与声学信号处理

近期论文

查看导师新发文章（温馨提示：请注意重名现象，建议点开原文通过作者单位确认）

期刊论文 H. Zhang, N. Si, Y. Chen, X. Yang, D. Qu, and W.-Q. Zhang, “Improving speech translation by cross-modal multi-grained contrastive learning,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, pp. 1075–1086, 2023. doi: 10.1109/TASLP.2023.3244521. J. Yao, X. Chen, X.-L. Zhang, W.-Q. Zhang, and K. Yang, “Symmetric saliency-based adversarial attack to speaker identification,” IEEE Signal Processing Letters, vol. 30, 2023. doi: 10.1109/LSP.2023.3236509. C. Wu, F. Wu, T. Qi, W.-Q. Zhang, X. Xie, and Y. Huang, “Removing AI’s sentiment manipulation of personalized news delivery,” Humanities & Social Sciences Communications, vol. 9, no. 459, 2022. doi: 10.1057/s41599-022-01473-1. J. Zhao and W.-Q. Zhang, “Improving automatic speech recognition performance for low-resource languages with self-supervised models,” IEEE Journal of Selected Topics in Signal Processing, 2022, doi: 10.1109/JSTSP.2022.3184480. Z. Zhao and W.-Q. Zhang, “End-to-end keyword search system based on attention mechanism and energy scorer for low resource languages,” Neural Networks, vol. 139, pp. 326-334, Jul. 2021. doi: 10.1016/j.neunet.2021.04.002. C. Lu, Y. Liu, W.-Q. Zhang and S. Zhang, “Tightness of a new and enhanced semidefinite relaxation for MIMO detection,” SIAM Journal on Optimization, vol. 29, no. 1, pp. 719-742, Jan. 2019. J. Kang, W.-Q. Zhang, W.-W. Liu, J. Liu, and M. T. Johnson, “Lattice based transcription loss for end-to-end speech recognition,” Journal of Signal Processing Systems, vol. 90, no. 7, pp. 1013-1023, Sept. 2018. C. Lu, Z. Deng, W.-Q. Zhang, and S.-C. Fang, “Argument division based branch-and-bound algorithm for unit-modulus constrained complex quadratic programming,” Journal of Global Optimization, vol. 70, no. 1, pp. 171-187, Jan. 2018. X.-K. Yang, L. He, D. Qu, and W.-Q. Zhang, “Semi-supervised minimum redundancy maximum relevance feature selection for audio classification,” Multimedia Tools and Applications, vol. 77, no. 1, pp. 713-739, Jan. 2018. X. Yang, D. Qu, W.-L. Zhang, and W.-Q. Zhang, “An adapted data selection for deep learning-based audio segmentation in multi-genre broadcast channel,” Digital Signal Processing, vol. 81, pp. 8-15, Oct. 2018. W.-W. Liu, M. Cai, W.-Q. Zhang, J. Liu, and M. T. Johnson, “Discriminative boosting algorithm for diversified front-end phonotactic language recognition,” Journal of Signal Processing Systems, vol. 82, no. 2, pp. 229-239, Feb. 2016. Z.-Y. Li, W.-Q. Zhang, and J. Liu, “Multi-resolution time frequency feature and complementary combination for short utterance speaker recognition,” Multimedia Tools and Applications, vol. 74, no. 74, pp. 937-953, Feb. 2015. W.-Q. Zhang, W.-W. Liu, Z.-Y. Li, Y.-Z. Shi, and J. Liu, “Spoken language recognition based on gap-weighted subsequence kernels,” Speech Communication, vol. 60, pp. 1-12, May 2014. Y.-Z. Shi, W.-Q. Zhang, J. Liu, and M. Johnson, “Efficient one-pass decoding with NNLM for speech recognition,” IEEE Signal Processing Letters, vol. 21, no. 4, pp. 377-381, Apr. 2014. W.-L. Zhang, D. Qu, W.-Q. Zhang, and B.-C. Li. “Rapid speaker adaptation using compressive sensing,” Speech Communication, vol. 55, no. 10, pp. 950-963, Nov.-Dec. 2013. W.-L. Zhang, W.-Q. Zhang, B.-C. Li, D. Qu, and M. T. Johnson, “Bayesian speaker adaptation based on a new hierarchical probabilistic model,” IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 7, pp. 2002-2015, Sept. 2012. W.-Q. Zhang, L. He, Y. Deng, J. Liu, and M. Johnson, “Time-frequency cepstral feature and constrained heteroscedastic linear discriminant analysis for language recognition,” IEEE Transactions on Audio, Speech and Language Processing, vol. 19, no. 2, pp. 266-272, Feb. 2011. W.-Q. Zhang and J. Liu, “An equalized heteroscedastic linear discriminant analysis algorithm,” IEEE Signal Processing Letters, vol. 15, pp. 585-588, 2008. R. Tao, W.-Q. Zhang, and E.-Q. Chen, “Two-stage method for joint time delay and Doppler shift estimation,” IET Radar, Sonar & Navigation, vol. 2, no. 1, pp. 71-77, Feb. 2008. R. Tao, B. Deng, W.-Q. Zhang, and Y. Wang, “Sampling and sampling rate conversion of band limited signals in the fractional Fourier transform domain,” IEEE Transactions on Signal Processing, vol. 56, no. 1, pp. 158-171, Jan. 2008. 会议论文 J. Zhao, H. Wang, J. Li, S. Chai, G. Wang, G. Chen, and W.-Q. Zhang, “The THUEE system description for the IARPA OpenASR21 Challenge,” in Proc. Interspeech, Songdo ConvensiA, Korea, Sept. 2022. doi: 10.21437/Interspeech.2022-269. J. Zhao, G. Shi, G.-B. Wang, and W.-Q. Zhang, “Automatic speech recognition for low-resource languages: the THUEE systems for the IARPA OpenASR20 evaluation,” in Proc. ASRU, Cartagena, Colombia, Dec. 2021, pp. 335–341. doi: 10.1109/ASRU51503.2021.9688260. L. Xue, K. Song, D. Wu, X. Tan, N. L. Zhang, T. Qin, W.-Q. Zhang, and T.-Y. Liu, “DeepRapper: Neural rap generation with rhyme and rhythm modeling,” in Proc. ACL, Bangkok, Thailand, Aug. 2021, pp. 69-81. doi: 10.18653/v1/2021.acl-long.6. G. Chen, S. Chai, G. Wang, J. Du, W.-Q. Zhang, C. Weng, D. Su, D. Povey, J. Trmal, J. Zhang, M. Jin, S. Khudanpur, S. Watanabe, S. Zhao, W. Zou, X. Li, X. Yao, Y. Wang, Y. Wang, Z. You, and Z. Yan, “GigaSpeech: An evolving, multi-domain ASR corpus with 10,000 hours of transcribed audio,” in Proc. Interspeech, Brno, Czechia, Aug. 2021, pp. 3670-3674. doi: 10.21437/Interspeech.2021-1965. J. Zhao, Z. Lv, A. Han, G. Wang, G. Shi, J. Kang, J. Yan, P. Hu, S. Huang, and W.-Q. Zhang, “The TNT team system descriptions of Cantonese and Mongolian for IARPA OpenASR20,” in Proc. Interspeech, Brno, Czechia, Aug. 2021, pp. 4344-4348. doi: 10.21437/Interspeech.2021-1063. H. Yu, J. Zhao, S. Yang, Z. Wu, Y. Nie, and W.-Q. Zhang, “Language recognition based on unsupervised pretrained models,” in Proc. Interspeech, Brno, Czechia, Aug. 2021, pp. 3271-3275. doi: 10.21437/Interspeech.2021-807. Y. Yan, X. Tan, B. Li, G. Zhang, T. Qin, S. Zhao, Y. Shen, W.-Q. Zhang, and T.-Y. Liu, “Adaptive text to speech for spontaneous style,” in Proc. Interspeech, Brno, Czechia, Aug. 2021, pp. 4668-4672. doi: 10.21437/Interspeech.2021-584. K. He, Y. Shen, W.-Q. Zhang, and J. Liu, “Staged training strategy and multi-activation for audio tagging with noisy and sparse multi-label data,” in Proc. ICASSP, Barcelona, Spain, May 4-8, 2020, pp. 631-635. J. Xie, R. Yan, S. Xiao, L. Peng, M. T. Johnson, and W.-Q. Zhang, “Dynamic temporal residual learning for speech recognition,” in Proc. ICASSP, Barcelona, Spain, May 4-8, 2020, pp. 7709-7713. Z. Zhao and W.-Q. Zhang, “End-to-end keyword search based on attention and energy scorer for low resource languages,” in Proc. Interspeech, Shanghai, China, Oct. 25-29, 2020, pp. 2587-2591. R. Li et al., “THUEE system for NIST SRE19 CTS challenge,” in Proc. Interspeech, Shanghai, China, Oct. 25-29, 2020, pp. 2232-2236. Z. Li, L. He, J. Li, L. Wang, and W.-Q. Zhang, “Towards discriminative representations and unbiased predictions: Class-specific angular softmax for speech emotion recognition,” in Proc. Interspeech, Graz, Austria, Sept. 15-19, 2019, pp. 1696-1700. K. He, Y. Shen, and W.-Q. Zhang, “Hierarchical pooling structure for weakly labeled sound event detection,” in Proc. Interspeech, Graz, Austria, Sept. 15-19, 2019, pp. 3624-3628. H. Yang and W.-Q. Zhang, “Music genre classification using duplicated convolutional layers in neural networks,” in Proc. Interspeech, Graz, Austria, Sept. 15-19, 2019, pp. 3382-3386. Y. Shen, K. He, and W.-Q. Zhang, “Learning how to listen: A temporal-frequential attention model for sound event detection,” in Proc. Interspeech, Graz, Austria, Sept. 15-19, 2019, pp. 2563-2567. J. Kang, W.-Q. Zhang, and J. Liu, “Gated convolutional networks based hybrid acoustic models for low resource speech recognition,” in Proc. ASRU, Okinawa, Japan, Dec. 16-20, 2017, pp. 157-164. Z.-Q. Lv, J. Kang, W.-Q. Zhang, and J. Liu, “An LSTM-CTC based verification system for proxy-word based OOV keyword search,” in Proc. ICASSP, New Orleans, USA, Mar. 5-9, 2017, pp. 5655-5659. Y. Tian, L. He, M. Cai, W.-Q. Zhang, and J. Liu, “Deep neural networks based speaker modeling at different levels of phonetic granularity,” in Proc. ICASSP, New Orleans, USA, Mar. 5-9, 2017, pp. 5440-5444. X.-K. Yang, D. Qu, W.-L. Zhang, and W.-Q. Zhang, “The NDSC transcription system for the 2016 multi-genre broadcast challenge,” in Proc. SLT, San Diego, USA, Dec. 13-16, 2016, pp. 273-278. Z.-Q. Lv, M. Cai, W.-Q. Zhang, and J. Liu, “A novel discriminative score calibration method for keyword search,” in Proc. Interspeech, San Francisco, USA, Sept. 8-12, 2016, pp. 745-749. Y. Tian, M. Cai, H. Liang, W.-Q. Zhang, and J. Liu, “Improving deep neural networks based speaker verification using unlabeled data,” in Proc. Interspeech, San Francisco, USA, Sept. 8-12, 2016, pp. 1863-1867. Z.-Q. Lv, M. Cai, C. Lu, J. Kang, L.-K. Hui, W.-Q. Zhang, and J. Liu, “Improved system fusion for keyword search,” in Proc. ASRU, Scottsdale, USA, Dec. 13-17, 2015, pp. 231-236. M. Cai, Z.-Q. Lv, B.-L. Song, Y.-Z. Shi, W.-L. Wu, C. Lu, W.-Q. Zhang, and J. Liu, “The THUEE system for the OpenKWS14 keyword search evaluation,” in Proc. ICASSP, Brisbane, Australia, Apr. 19-24, 2015, pp. 4734-4738. J. Kang, C. Lu, M. Cai, W.-Q. Zhang, and J. Liu, “Neuron sparseness versus connection sparseness in deep neural network for large vocabulary speech recognition,” in Proc. ICASSP, Brisbane, Australia, Apr. 19-24, 2015, pp. 4954-4958. Y.-Z. Shi, W.-Q. Zhang, M. Cai, and J. Liu, “Variance regularization of RNNLM for speech recognition,” in Proc. ICASSP, Florence, Italy, May 4-9, 2014, pp. 4931-4935. W.-W. Liu, W.-Q. Zhang, Y.-Z. Shi, A. Ji, J. Xu, and J. Liu, “Improved phonotactic language recognition based on RNN feature reconstruction,” in Proc. ICASSP, Florence, Italy, May 4-9, 2014, pp. 5359-5363. W.-W. Liu, W.-Q. Zhang, and J. Liu, “Phonotactic language identification based on time-gap-weighted lattice kernels,” in Proc. Interspeech, Singapore, Sept. 14-18, 2014, pp. 3022-3026. W.-L. Zhang, D. Qu, W.-Q. Zhang, and B.-C. Li, “Speaker adaptation based on sparse and low-rank eigenphone matrix estimation,” in Proc. Interspeech, Singapore, Sept. 14-18, 2014, pp. 2792-2796. Y.-Z. Shi, W.-Q. Zhang, M. Cai, and J. Liu, “Temporal kernel neural network language model,” in Proc. ICASSP, Vancouver, Canada, May 26-31, 2013, pp. 8247-8251. W.-Q. Zhang, Z.-Y. Li, W. Liu, and J. Liu, “THU-EE system fusion for the NIST 2012 speaker recognition evaluation,” in Proc. Interspeech Lyon, France, Aug. 25-29, 2013, pp. 2474-2478. W. Liu, W.-Q. Zhang, Zhang, Z.-Y. Li, and J. Liu. “Parallel absolute-relative feature based phonotactic language recognition,” in Proc. Interspeech, Lyon, France, Aug. 25-29, 2013, pp. 59-63. W.-L. Zhang, W.-Q. Zhang, and B.-C. Li, “Compact acoustic modeling based on acoustic manifold using a mixture of factor analyzers,” in ASRU, Olomouc, Czech Republic, Dec. 8-12, 2013, pp. 37-42. Z.-Y. Li, W.-Q. Zhang, L. He, and J. Liu, “Complementary combination in i-vector level for language recognition,” in Proc. Odyssey, Singapore, Jun. 25-28, 2012, pp. 334-337. Y.-Z. Shi, W.-Q. Zhang, and J. Liu, “Robust audio fingerprinting based on local spectral luminance maxima scheme,” in Proc. Interspeech, Florence, Italy, Aug. 27-31, 2011, pp. 2485-2488. W.-L. Zhang, W.-Q. Zhang, and B.-C. Li, “Speaker adaptation based on speaker-dependent eigenphone estimation,” in Proc. ASRU, Hawaii, USA, Dec. 11-15, 2011, pp. 48-52. W.-Q. Zhang, Y. Deng, L. He, and J. Liu, “Variant time-frequency cepstral features for speaker recognition,” in Proc. Interspeech, Makuhari, Japan, Sept. 26-30, 2010, pp. 2122-2125. S. Meng, W.-Q. Zhang, and J. Liu, “Combining Chinese spoken term detection systems via side-information conditioned linear logistic regression,” in Proc. Interspeech, Makuhari, Japan, Sept. 26-30, 2010, pp. 685-688. J. Yang, J. Liu, and W.-Q. Zhang, “A fast query by humming system based on notes,” in Proc. Interspeech, Makuhari, Japan, Sept. 26-30, 2010, pp. 2898-2901. W.-Q. Zhang, Y. Shan, and J. Liu, “Multiple background models for speaker verification,” in Proc. Odyssey, Brno, Czech Republic, Jun. 28-Jul. 1, 2010, pp. 47-51. W.-Q. Zhang and J. Liu, “Two-stage method for specific audio retrieval,” in Proc. ICASSP, Hawaii, USA, Apr. 15-20, 2007, pp. IV-85-88.

学术兼职

2021年全国人机语音通信学术会议程序委员会主席中国计算机学会语音对话与听觉专委会委员中国人工智能学会人工智能与安全专委会委员中国图象图形学学会视频图像与安全专委会委员 IEEE高级会员 ISCA会员 ACM会员 APSIPA会员