me

SONGFANG HUANG


IBM T.J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, New York, 10598, U.S.A.
Tel: +1 914 945 1436
Email: s.f.huang @ ed.ac.uk, shuang @ us.ibm.com



    

[ Home | Education | Experience | Publications | Honors/Awards | Professional Experiences | Softwares ]

PUBLICATIONS  

Journal Articles

  1. Songfang Huang and Steve Renals, Hierarchical Bayesian Language Models for Conversational Speech Recognition, accepted by IEEE Transactions on Audio, Speech and Language Processing, 2009.
  2. [ bibtex | show abstract | pdf | IEEE Trans. ASLP ]

Peer-reviewed Conferences/Workshops

  1. Songfang Huang and Steve Renals, Power Law Discounting for N-Gram Language Models, In Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP'10), pages 5178-5181, Dallas, Texas, USA, March 2010. (Best Student Paper Award)
  2. [ bibtex | show abstract | pdf | slides | ICASSP'10 ]

  3. Songfang Huang and Steve Renals, A Parallel Training Algorithm for Hierarchical Pitman-Yor Process Language Models, In Proc. Interspeech'09, pages 2695-2698, Brighton, UK, September 2009.
  4. [ bibtex | show abstract | pdf | poster | INTERSPEECH'09 ]

  5. Songfang Huang and Bowen Zhou, An EM Algorithm for SCFG in Formal Syntax-based Translation, In Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP'09), pages 4813-4816, Taiwan, China, April 2009.
  6. [ bibtex | show abstract | pdf | poster | slides | ICASSP'09 ]

  7. Songfang Huang and Steve Renals, Unsupervised Language Model Adaptation Based on Topic and Role Information in Multiparty Meetings, In Proc. Interspeech'08, pages 833-836, Brisbane, Austrilia, September 2008.
  8. [ bibtex | show abstract | pdf | slides | INTERSPEECH'08 ]
  9. Songfang Huang and Steve Renals, Modeling Topic and Role Information in Meetings using the Hierarchical Dirichlet Process, In A. Popescu-Belis and R. Stiefelhagen, editors, Machine Learning for Multimodal Interaction V, volume 5237 of Lecture Notes in Computer Science, pages 215-225, Springer, 2008.
  10. [ bibtex | show abstract | pdf | slides | video | DOI | MLMI'08 | LNCS'5237 ]
  11. Songfang Huang and Steve Renals, Using Participant Role in Multiparty Meetings as Prior Knowledge for Nonparametric Topic Modeling, In Proc. ICML/UAI/COLT Workshop on Prior Knowledge for Text and Language Processing, pages 21-24, Helsinki, Finland, July 2008.
  12. [ bibtex | show abstract | pdf | poster | proceedings | PTKL'08 ]
  13. Songfang Huang and Steve Renals, Hierarchical Pitman-Yor Language Models for ASR in Meetings, In Proc. IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU'07), pages 124-129, Kyoto, Japan, December 2007.
  14. [ bibtex | show abstract | pdf | poster | ASRU'07 ]
  15. Songfang Huang and Steve Renals, Using Prosodic Features in Language Models for Meetings, In A. Popescu-Belis, S. Renals, and H. Bourlard, editors, Machine Learning for Multimodal Interaction IV, volume 4892 of Lecture Notes in Computer Science, pages 191-202. Springer, 2007.
  16. [ bibtex | show abstract | pdf | slides | video | DOI | MLMI'07 | LNCS'4892 ]

Other Publications (Workshops, Abstracts, etc)

  1. Songfang Huang and Steve Renals, Towards the Application of Hierarchical Bayesian Models on Language Models for Automatic Speech Recognition, the Nonparametric Bayes workshop at ICML'08, Helsinki, Finland, July 2008.
  2. [ bibtex | abstract | pdf | poster | NPBAYES'08 ]
  3. Songfang Huang and Steve Renals, Multimodal Language Models for Multiparty Meetings, In One Day Meeting for Young Speech Researchers, University College London, United Kingdom, April 2007.
  4. [ poster | abstracts | UK Speech ]
  5. Songfang Huang, Hao Wu, Qin Gao, Xihong Wu, and Huisheng Chi, Automatic Recognition and Transcription of Broadcast News, Journal of Technical Acoustics, vol. 24, pages 117-120, 2005. (In Chinese)

Thesises


[ Home | Education | Experience | Publications | Honors/Awards | Professional Experiences | Softwares ]