Hui Lin @UW

About Me

I am a Ph.D. candidate at University of Washington advised by Prof. Jeff Bilmes. I am working in the intersection of machine learning and speech/language processing, with paticular interest in submodular function optimization and its applications. I did several summer internships at Google Research, Microsoft Research, and Microsoft Research Asia. Before joining SSLI lab in September 2006, I got my B.S. and M.S. degrees from Tsinghua University.

Publications

2011

Stefanie Jegelka, Hui Lin, Jeff Bilmes. "On fast approximate submodular minimization", NIPS, 2011

Hui Lin, Jeff Bilmes. "Optimal Selection of Limited Vocabulary Speech Corpora", Proc. Interspeech, Florence, Italy, 2011.(pdf)

Hui Lin, Jeff Bilmes. "Word Alignment via Submodular Maximization over Matroids", The 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT) , 2011.(pdf)

Hui Lin, Jeff Bilmes. "A Class of Submodular Functions for Document Summarization", The 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT) , 2011.(pdf) (slides)

2010

Hui Lin, Jeff Bilmes. "An Application of the Submodular Principal Partition to Training Data Subset Selection", NIPS workshop on Discrete Optimization in Machine Learning , Dec 2010.(pdf)

Shasha Xie, Hui Lin, Yang Liu "Semi-Supervised Extractive Speech Summarization via Co-Training Algorithm", Proc. Annual Conference of the International Speech Communication Association (Interspeech) , Makuhari, Japan, September 2010.(pdf)

Jeff Bilmes, Hui Lin. "Online Adaptive Learning for Speech Recognition Decoding", Proc. Annual Conference of the International Speech Communication Association (Interspeech) , Makuhari, Japan, September 2010.(pdf)

Hui Lin, Jeff Bilmes. "Multi-document Summarization via Budgeted Maximization of Submodular Functions", North American chapter of the Association for Computational Linguistics/Human Language Technology Conference (NAACL/HLT-2010) , Los Angeles, CA, June 2010.(pdf)

2009

Hui Lin, Jeff Bilmes, Shasha Xie. "Graph-based Submodular Selection for Extractive Summarization", in Proc. IEEE Automatic Speech Recognition and Understanding (ASRU), Merano, Italy, December 2009.(pdf)

Hui Lin, Jeff Bilmes, Koby Crammer. " How to Lose Confidence: Probabilistic Linear Machines for Multiclass Classification ", Conference of the International Speech Communication Association (Interspeech) , Brighton U.K., September 2009. (pdf) (demo)

Hui Lin, Jeff Bilmes. "How to Select a Good Training-data Subset for Transcription: Submodular Active Selection for Sequences", Conference of the International Speech Communication Association (Interspeech) , Brighton U.K., September 2009. (pdf)

Hui Lin, Li Deng, Dong Yu, Yifan Gong, Alex Acero, Chin-Hui Lee, "A Study on Multilingual Acoustic Modeling for Large Vocabulary ASR", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , Taipei Taiwan, April 2009. (pdf)

Hui Lin, Alex Stupakov, Jeff Bilmes, "Improving Muliti-lattice Alignment based Spoken Keyword Spotting", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , Taipei Taiwan, April 2009. (pdf)

2008

Hui Lin, Li Deng, Jasha Droppo, Dong Yu, Alex Acero, "Learning Methods in Multilingual Speech Recognition", Neural Information Processing Systems (NIPS) workshop on Speech and Language: Learning-based Methods and Systems , Dec. 2008. (pdf)

Shasha Xie, Yang Liu, Hui Lin, "Evaluating the Effectiveness of Features and Sampling in Extractive Meeting Summarization", IEEE Workshop on Spoken Language Technology (SLT), Goa India, Decemeber 2008. (pdf)

Hui Lin, Alex Stupakov, Jeff Bilmes "Spoken Keyword Spotting via Multi-Lattice Alignment", Proceedings of Interspeech , Brisbane Australia, September 2008. (pdf)

Hui Lin, Jeff Bilmes, "Polyphase Speech Recognition", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Las Vegas, Mar. 2008. (pdf)

2007

Hui Lin, Jeff Bilmes, Dimitra Vergyri, Katrin Kirchhoff, "OOV Detection by Joint Word/Phone Lattice Alignment", IEEE Automatic Speech Recognition and Understanding (ASRU), Kyoto, Japan, Dec. 2007. (pdf)

Hui Lin, Zhijian Ou, "Switching Auxiliary Chains for Speech Recognition", IEEE Signal Processing Letters, Volume 14, Issue 8, Page(s):568-571, Aug. 2007 (pdf)

2006

Hui Lin, Zhijian Ou, "Switching Auxiliary Chains for Speech Recognition based on Dynamic Bayesian Networks", 18th International Conference on Pattern Recognition (ICPR), Hongkong, Aug. 2006. (pdf)

Hui Lin, Zhijian Ou, "Partial-tied-mixture Auxiliary Chain for Speech Recognition based on Dynamic Bayesian Networks", IEEE International Conference on Systems, Man and Cybernetics, Taiwan, 2006. (pdf)

Ye Tian, Jian-lai Zhou, Hui Lin, Hui Jiang, "Tree-based Covariance Modeling for Hidden Markov Models", IEEE Transactions on Audio, Speech and Language Processing, Volume 14, Issue 6, Page(s):2134-2146, Nov. 2006 (pdf)

Hui Lin, Zhijian Ou, Xi Xiao, "Generalized Time-series Active Search with Kullback-Leibler Distance for Audio Fingerprinting", IEEE Signal Processing Letters, Volume 13, Issue 8, Page(s):465-468, Aug. 2006. (pdf)

2005

Hui Lin, Ye Tian, Jian-lai Zhou, Hui Jiang, "Hierarchical Correlation Compensation for Hidden Markov Models", IEEE International Conference of Acoustics, Speech and Signal Processing (ICASSP), Philadelphia, March, 2005. (pdf)

Welcome to Hui's homepage

欢迎来到林晖的主页