个人信息Personal Information
副教授
教师拼音名称：dujun
电子邮箱：
联系方式：(+86)-0551-63603303
- [2008] Jun Du, Qiang Huo, and Yu Hu, “Evaluation of a feature compensation approach using high-order vector Taylor series approximation of an explicit distortion model on Aurora2, Aurora3, and Aurora4 tasks,”, Proc ISCSLP, 2008, pp81-84 Best student paper candidate.
- [2007] Jun Du, Peng Liu, Hui Jiang, Frank Soong, and Ren-Hua Wang, “A new minimum divergence approach to discriminative training,”, Proc ICASSP, 2007, pp677-680.
- [2007] Jun Du, Peng Liu, Frank Soong, Jian-Lai Zhou, and Ren-Hua Wang, “Performance of discriminative HMM training in noise,”, International Journal of the Association for Computational Linguistics and Chinese Language Processing IJCLCLP, Vol 12, No 3, pp291-302, 2007 .
- [2006] Bo Liu, Li-Rong Dai, Ren-Hua Wang, Jun Du, and Jin-Yu Li, “Double Gaussian GMM based feature normalization and its application in speech recognition,”, Acta Automatica Sinica, Vol 32, No 4 , pp519-525, 2006.
- [2006] Jun Du, Peng Liu, Frank Soong, Jian-Lai Zhou, Ren-Hua Wang, "Noisy speech recognition performance of discriminative HMMs", Chinese Spoken Language Processing Springer, Berlin, Heidelberg, 2006 358-369.
- [2006] Zhi-Jie Yan, Peng Liu, Jun Du, Frank Soong, and Ren-Hua Wang, “Training discriminative HMM by optimal allocation of Gaussian kernels,”, Proc ISCSLP, 2006, pp289-298.
- [2006] Jun Du, Peng Liu, Frank Soong, Jian-Lai Zhou, and Ren-Hua Wang, “Minimum divergence based discriminative training,”, Proc INTERSPEECH, 2006, pp2410-2413 Best student paper candidate.
- [2006] Jun Du, Peng Liu, Frank Soong, Jian-Lai Zhou, and Ren-Hua Wang, “Noisy speech recognition performance of discriminative HMMs,”, Proc ISCSLP, 2006, pp358-369 Best student paper candidate.
- [2005] Jun Du, Yu Hu, and Ren-Hua Wang, “An optimized algorithm of feature normalization in robust speech recognition,”, Technical Acoustics, Vol 24, pp 196-200, 2005 .
- 杜俊.Joint training of DNNs by incorporating an explicit dereverberation structure for distant speech recognition.EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING,2016,
- 杜俊,杜俊.A Regression Approach to Single-Channel Speech Separation Via High-Resolution Deep Neural Networks.IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,2016,24(8):1424-1437.
- 杜俊,杜俊.An irrelevant variability normalization approach to discriminative training of multi-prototype based classifiers and its applications for online handwritten Chinese character recognition.PATTERN RECOGNITION,2014,47(12):3959-3966.
- 杜俊,杜俊.A discriminative linear regression approach to adaptation of multi-prototype based classifiers and its applications for Chinese OCR.PATTERN RECOGNITION,2013,46(8):2313-2322.