杜俊，男，生于1982年6月，信号与信息处理博士，中国科学技术大学电子工程与信息科学系特任研究员。IEEE/ISCA/IAPR会员，中文信息学会会员，担任IEEE/ACM Transactions on Audio Speech and Language Processing、Speech Communication、Pattern Recognition Letters、IEEE/CAA Journal of Automatica Sinica、ICDAR、ISCSLP、ICPR、WCSP、《信号处理》等国内外学术期刊和会议的论文评审，在国内外学术期刊和会议上发表学术论文50余篇。曾任ChinaSIP 2014/2015国际会议的分会主席，其中ISCSLP 2006、ISCSLP 2008、INTERSPEECH 2006、INTERSPEECH 2015四次会议的论文均进入最佳论文候选。主要研究领域包括语音增强、语音分离等语音信号处理技术以及噪声鲁棒性语音识别、自然场景下的OCR和面向用户定制的手写识别等多模态交互核心技术。主讲本科生课程《信号统计建模基础》。 

学习工作经历

承担科研项目

• 2014.01-2016.12，主持国家自然科学基金青年项目：

　　基于深度神经网络的噪声鲁棒性语音识别方法研究

• 2013.07-2014.07，主持安徽省科技攻关项目：

　　基于移动互联网的口语翻译关键技术及系统研发　

• 2014.07-2016.07，主持安徽省自然科学基金青年项目：

　　基于深度学习的语音增强技术研究

• 2013.07-2014.07，参与安徽省科技攻关项目：

　　面向家庭服务机器人的人机交互关键技术研究

• 2013.12-2014.12， 参与电子信息产业发展基金：

　　基于自然语音人机交互的信息搜索系统研发和产业化

• 2015.01-2016.12，参与安徽省自然科学基金面上项目：

　　基于深度学习的特定说话人语音增强研究 

　　近五年发表第一作者论文如下： 

1. Jun Du, Jian-Fang Zhai, Jin-Shui Hu, Bo Zhu, Si Wei, and Li-Rong Dai, “Writer adaptive feature extraction based on convolutional neural networks for online handwritten Chinese character recognition,” Accepted by Proc. ICDAR 2015.

2. Jun Du, Yan-Hui Tu, Yong Xu, Li-Rong Dai, and Chin-Hui Lee, “Speech separation of a target speaker based on deep neural networks,” Proc. ICSP, 2014, pp.473-477.

3. Jun Du, “Irrelevant variability normalization via hierarchical deep neural networks for online handwritten Chinese character recognition,” Proc. ICFHR, 2014, pp.303-308.

4. Jun Du, Jin-Shui Hu, Bo Zhu, Si Wei, and Li-Rong Dai, “Writer adaptation using bottleneck features and discriminative linear regression for online handwritten Chinese character recognition,” Proc. ICFHR, 2014, pp.311-316.

5. Jun Du, Jin-Shui Hu, Bo Zhu, Si Wei, and Li-Rong Dai, “A study of designing compact classifiers using deep neural networks for online handwritten Chinese character recognition,” Proc. ICPR, 2014, pp.2950-2955.

6. Jun Du, Qing Wang, Tian Gao, Li-Rong Dai, and Chin-Hui Lee, “Robust speech recognition with speech enhanced deep neural networks,” Proc. INTERSPEECH, 2014, pp.616-620.

7. Jun Du and Qiang Huo, “Synthesized stereo mapping via deep neural networks for noisy speech recognition,” Proc. ICASSP, 2014, pp.1783-1787.

8. Jun Du and Qiang Huo, “An irrelevant variability normalization approach to discriminative training of multi-prototype based classifiers and its applications for online handwritten Chinese character recognition,” Pattern Recognition, Vol. 47, No. 12, pp.3959-3966, 2014.

9. Jun Du and Qiang Huo, “An improved VTS feature compensation using mixture models of distortion and IVN training for noisy speech recognition,” IEEE/ACM Transactions on Audio, Speech and Language Processing, Vol. 22, No. 11, pp.1601-1611, 2014.

10. Jun Du and Qiang Huo, “A VTS-based feature compensation approach to noisy speech recognition using mixture models of distortion,” Proc. ICASSP, 2013, pp.7078-7082.

11. Jun Du and Qiang Huo, “An irrelevant variability normalization based discriminative training approach for online handwritten Chinese character recognition,” Proc. ICDAR, 2013, pp.69-73.

12. Jun Du and Qiang Huo, “A discriminative linear regression approach to adaptation of multi-prototype based classifiers and its applications for Chinese OCR,” Pattern Recognition, Vol. 46, No. 8, pp.2313-2322, 2013.

13. Jun Du and Qiang Huo, Kai Chen, “Designing compact classifiers for rotation-free recognition of large vocabulary online handwritten Chinese characters,” Proc. ICASSP, 2012, pp.1721-1724.

14. Jun Du and Qiang Huo, “A discriminative linear regression approach to OCR adaptation,” Proc. ICPR, 2012, pp.629-632.

15. Jun Du and Qiang Huo, “IVN-based joint training of GMM and HMMs using an improved VTS-Based feature compensation for noisy speech recognition,” Proc. INTERSPEECH, 2012.

16. Jun Du, Qiang Huo, Lei Sun, and Jian Sun, “Snap and translate using Windows Phone,” Proc. ICDAR, 2011, pp.809-813.

17. Jun Du, Yu Hu, and Hui Jiang, “Boosted mixture learning of Gaussian mixture hidden Markov models based on maximum likelihood for speech recognition,” IEEE Trans. on Audio, Speech and Language Processing, Vol. 19, No. 7,, pp.2091-2100, 2011.

18. Jun Du, and Qiang Huo, “A feature compensation approach using high-order vector Taylor series approximation of an explicit distortion model for noisy speech recognition,” IEEE Trans. on Audio, Speech and Language Processing, Vol. 19, No. 8, pp.2285-2293, 2011.

19. Jun Du, Li-Rong Dai, and Ren-Hua Wang, “Cepstral shape normalization (CSN) for robust speech recognition,” Journal of Chinese Information Processing, Vol. 24, No. 2, pp.104-110, 2010.

20. Jun Du, Yu Hu, Li-Rong Dai, and Ren-Hua Wang, “HMM-base pseudo-clean speech synthesis for SPLICE algorithm,” Proc. ICASSP, 2010, pp.4570-4573.

21. Jun Du, Yu Hu, and Hui Jiang, “Boosted mixture learning of Gaussian mixture HMMs for speech recognition,” Proc. INTERSPEECH, 2010, pp.2942-2945.

招生信息：

须具备语音信号与信息处理基础理论知识背景和相关研究经历。本实验室建有面向于大规模语音分析与建模的服务器/GPU硬件平台和软件、语音数据平台。学生在学习和研究过程中，除可根据有关政策获得国家及学校的奖学金外，本实验室还视学生的科研情况，进行一定的科研补助。