Professional Talks

  1. International Conference on Acoustics, Speech, and Signal Processing (ICASSP), New Orleans, Tutorial Speech: “Deep Natural Language Processing and Learning”, March 2017 
  2. University of Michigan, Ann Arbor, "Deep Discriminative and Variational Manifold Learning", January 2017 (hosted by Prof. Issam El Naqa and Dr. Huan-Hsin Tseng)
  3. Annual Conference of the International Speech Communication Association (INTERSPEECH), San Francisco, Tutorial Speech: “Machine Learning for Speaker Recognition”, September 2016 (with Prof. Man-Wai Mak)
  4. International Workshop on Spatial and Temporal Modeling from Statistical, Machine Learning and Engineering Perspectives (STM), Tokyo, “Neural Network Learning”, July 2016 (hosted by Prof. Tomoko Matsui)
  5. Beijing University of Posts and Telecommunications, Beijing, “Bayesian Nonparametrics for Speech and Language Processing”, July 2016 (hosted by Prof. Zhanyu Ma)
  6. International Workshop on Spatial and Temporal Modeling from Statistical, Machine Learning and Engineering Perspectives (STM), Tokyo, “Bayesian Source Separation”, July 2015 (hosted by Prof. Tomoko Matsui)
  7. Microsoft Research Asia, Suzhou, China, “Bayesian Speech and Language Processing”, June 2015 (hosted by Dr. Mei-Yuh Hwang)
  8. International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Brisbane, Australia, Tutorial Speech: Adaptive Learning for Model-Based Blind Source Separation, April 2015
  9. International Symposium on Chinese Spoken Language Processing (ISCSLP), Singapore, Tutorial Speech: “Unsupervised Speech and Language Processing via Topic Models”, September 2014
  10. Aalborg University, Denmark, “Bayesian Nonparametric Information Processing”, August 2014 (hosted by Prof. Zheng-Hua Tan)
  11. International Workshop on Spatial and Temporal Modeling from Statistical, Machine Learning and Engineering Perspectives (STM), Tokyo, “Bayesian Nonparametric Information Processing”, July 2014 (hosted by Prof. Gareth Peters)
  12. BBN Technologies, Cambridge, MA, “Bayesian Speech and Language Processing”, February 2014 (hosted by Dr. Ivan Bulyko)
  13. Massachusetts Institute of Technology, Cambridge, MA, “Bayesian Speech and Language Processing”, January 2014 (hosted by Prof. James Glass)
  14. Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Kaohsiung, Taiwan, Tutorial Speech: “Machine Learning for Multimedia Sequential Pattern Recognition”, October 2013 (with Prof. Koichi Shinoda)
  15. Annual Conference of the International Speech Communication Association (INTERSPEECH), Lyon, France, Tutorial Speech: “Recent Advances in Large Vocabulary Continuous Speech Recognition”, August 2013 (with Dr. George Saon)
  16. International Workshop on Spatial and Temporal Modeling from Statistical, Machine Learning and Engineering Perspectives, Tokyo, “Bayesian Group Sparse Modeling and Learning”, August 2013 (hosted by Prof. Tomoko Matsui)
  17. IBM T. J. Watson Research Center, Yorktown Heights, NY, “Bayesian Hidden Markov Neural Networks”, February 2013 (hosted by Dr. George Saon)
  18. Mitsubishi Electric Research Laboratories, Cambridge, MA, “Bayesian Group Sparse Learning”, January 2013 (hosted by Dr. Shinji Watanabe)
  19. University of Southern California, Los Angeles, CA, APSIPA Distinguished Lecture: “Bayesian Learning for Speech and Language Processing”, December 2012 (hosted by Prof. Shrikanth S. Narayanan)
  20. The Hong Kong University of Science and Technology, Hong Kong, APSIPA Distinguished Lecture: “Independent Component Analysis and Unsupervised Learning”, July 2012 (hosted by Prof. Pascale Fung)
  21. International Workshop on Statistical Machine Learning (IWSML), Kyoto, APSIPA Distinguished Lecture: “Independent Component Analysis and Unsupervised Learning”, March 2012 (hosted by Prof. Tomoko Matsui)
  22. International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Kyoto, Tutorial Speech: “Bayesian Learning for Speech and Language Processing”, March 2012 (with Dr. Shinji Watanabe)
  23. Microsoft Research Asia, Beijing, “Bayesian Topic Models for Document Representation”, September 2011 (hosted by Dr. Shuming Shi)
  24. Tsinghua University, Beijing, “Bayesian Topic Models for Document Representation”, September 2011 (hosted by Prof. Ji Wu)
  25. Shun Hing Institute of Advanced Engineering, The Chinese University of Hong Kong, Hong Kong, Distinguished Lecture: “Embracing Uncertainty and Sparsity for Speech Recognition”, June 2011 (hosted by Prof. Pak-Chung Ching)
  26. Tokyo Institute of Technology, Tokyo, “Bayesian and Sparse Learning of Acoustic and Language Models”, March 2011 (hosted by Prof. Masashi Sugiyama)
  27. Institute for Infocomm Research, Singapore, “Bayesian and Sparse Learning for Speech Recognition”, January 2011 (hosted by Dr. Haizhou Li)
  28. National University of Singapore, Singapore, “Bayesian and Sparse Learning for Speech Recognition”, January 2011 (hosted by Prof. Wee Sun Lee)
  29. Princeton University, Princeton, NJ, “Topic-Based Language Models for Speech Recognition”, July 2010 (hosted by Prof. David Blei)
  30. Columbia University, New York City, “Machine Learning Methods for Speech Separation and Recognition”, July 2010 (hosted by Prof. Dan Ellis)
  31. IBM T. J. Watson Research Center, Yorktown Heights, NY, “Bayesian Sensing Hidden Markov Models for Speech Recognition”, July 2010 (hosted by Dr. George Saon)
  32. University of Cambridge, Cambridge, UK, “Bayesian Learning Approaches for Speech Recognition”, September 2009 (hosted by Dr. Kai Yu)
  33. Tsukuba University, Tokyo, “Independent Component Analysis for Speech Separation and Recognition”, July 2009 (hosted by Prof. Shoji Makino)
  34. NTT Communication Science Laboratories, Kyoto, “Machine Learning Approaches for Speech Recognition”, July 2009 (hosted by Dr. Shinji Watanabe)
  35. Kyoto University, Kyoto, “Machine Learning Approaches for Speech Recognition”, July 2009 (hosted by Prof. Tatsuya Kawahara)
  36. IBM T. J. Watson Research Center, Yorktown Heights, NY, “Some Statistical Approaches to Robust Speech Recognition”, January 2006 (hosted by Dr. George Saon)
  37. University of Washington, Seattle, WA, “Towards Robust Acoustic and Language Modeling for Speech Recognition”, May 2004 (hosted by Dr. Mei-Yuh Hwang)
  38. Microsoft Research, Redmond, “Towards Robust Acoustic and Language Modeling for Speech Recognition”, May 2004 (hosted by Dr. Alex Acero)
  39. The Chinese University of Hong Kong, Hong Kong, “Online Unsupervised Adaptation and Robust Classification for Speech Recognition”, June 2002 (hosted by Prof. Tan Lee)