清華大學(xué)

歐智堅 博士 副研究員

電話：+86-10-62796193

傳真：+86-10-62770317

電子郵箱： ozj AT tsinghua.edu.cn

個人主頁：http://oa.ee.tsinghua.edu.cn/~ouzhijian/index.htm

研究領(lǐng)域

語音信號與信息處理（語音識別與理解，聲源分離，說話人識別，自然語言處理等）

機(jī)器智能（特別是概率圖模型理論及應(yīng)用）。

獎勵與榮譽

2012年，清華大學(xué)第五屆青年教師教學(xué)大賽一等獎。

2010年，清華大學(xué)優(yōu)秀班（級）主任一等獎。

2004年，特定內(nèi)容音頻識別系統(tǒng)(集成語音關(guān)鍵詞識別、說話人識別、音頻指紋)通過國家計算機(jī)網(wǎng)絡(luò)與信息安全管理中心的評測。

2003年，贏得2003年度國家863語音識別評測－音節(jié)識別任務(wù)。

2002年，獲清華大學(xué)電子系博士生學(xué)術(shù)論壇最佳論文獎。

學(xué)術(shù)成果精選期刊論文

[1] Hui Lin, Zhijian Ou. Switching Auxiliary Chains for Speech Recognition. IEEE Signal Processing Letters, 2007, 14(8): 568~571.

[2] Xianyu Zhao, Zhijian Ou. Closely Coupled Processing and Model-Based Compensation for Microphone Speech Recognition. IEEE Transactions on Audio, Speech and Language Processing, 2007, 15(3): 1114~1122.

[3] Hui Lin, Zhijian Ou, Xi Xiao. Generalized Time-series Active Search with Kullback-Leibler Distance for Audio Fingerprinting. IEEE Signal Processing Letters, 2006, 13(8): 464~468.

[4] Jun Luo, Zhijian Ou. Efficient keyword spotting system for information retrieval. Journal on Communication (in Chinese), 2006, 27(2): 113~118.

[5] Xianyu Zhao, Zhijian Ou, Zuoying Wang. Using Vector Taylor Series with Noise Clustering for Speech Recognition in Non-stationary Noisy Environments. High Technology Letters, 2006, 12(1): 18~23.

[6] Xianyu Zhao, Zhijian Ou, Zuoying Wang. Using Word-Graph in Unsupervised Vector Taylor Series Algorithm for Robust Speech Recognition. High Technology Letters (in Chinese), 2004, 14: 17~22.

[7] Jun Luo, Zhijian Ou, Zuoying Wang. Eigenvoice-based MAP fast adaptation in correlation subspaces. Journal of Tsinghua University (in Chinese), 2004, 44(6): 829~832.

精選會議論文

[1] Zhijian Ou, Yang Zhang. Probabilistic acoustic tube: a probabilistic generative model of speech for speech analysis/synthesis. International Conference on Artificial Intelligence and Statistics (AISTATS), La Palma, Spain, 2012,4.

[2] Zhijian Ou, Kan Deng. Combining eigenvoice speaker modeling and VTS-based environment compensation for robust speech recognition. ICASSP, Kyoto, Japan, 2012,3.

[3] Nan Ding, Zhijian Ou. Variational nonparametric Bayesian hidden Markov model. In: Proc. ICASSP, Dallas, USA, 2010,3.

[4] Zhijian Ou, Jun Luo. Latent correlation analysis of HMM parameters for speech recognition. In: Proc. ICASSP, Hawaii, USA, 2007,4.

[5] Zhijian Ou, Zuoying Wang. Discriminative combination of multiple linear predictions for speech recognition. In: Proc. ICSLP, Jeju, Korea, 2004,10.