Conference Pubs

2017

  • Zhe Gan, Chuang Gan, Xiaodong He, Yunchen Pu, Kenneth Tran, Jianfeng Gao, Lawrence Carin, Li Deng. Semantic Compositional Networks for Visual Captioning, CVPR (spotlight), 2017.
  • Chuang Gan, Zhe Gan, Xiaodong He,  Jianfeng Gao, Li Deng. StyleNet: Generating Attractive Visual Captions with Styles. CVPR (poster), 2017.
  • A Celikyilmaz, L Deng, L Li, C Wang. Scaffolding Networks for Teaching and Learning to Comprehend. arXiv:1702.08653, 2017.
  • Y Liu, J Chen, L Deng.  Li Deng. An Unsupervised Learning Method Exploiting Sequential Output Statistics, arXiv:1702.07817
  • C. Wang, Y Wang, PS Huang, A Mohamed, D Zhou, L Deng. Sequence Modeling via Segmentations, arXiv:1702.07463, 2017.
  • Zhe Gan, P. D. Singh, Ameet Joshi, Xiaodong He, Jianshu Chen, Jianfeng Gao, Li Deng. CHARACTER-LEVEL DEEP CONFLATION FOR BUSINESS DATA ANALYTICS, Proc. IEEE-ICASSP, March 2017, New Orleans.
  •  Xuesong Yang, Yun-Nung Chen, Dilek Hakkani-Tür, Paul Crook, Xiujun Li, Jianfeng Gao, Li Deng. END-TO-END JOINT LEARNING OF NATURAL LANGUAGE UNDERSTANDING AND DIALOGUE MANAGER, Proc. IEEE-ICASSP, March 2017, New Orleans.

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

2003

2002

2001

2000

1998

1997

1996

1995

  • J. Sun and L. Deng. “Annotation and use of speech production corpus for building language-universal speech recognizers”, Proceedings of the 2nd International Symposium on Chinese Spoken Language Processing (ISCSLP), Beijing, October 2000, Vol. 3, pp. 31-34.
  • J. Sun, R. Tongneri and L. Deng. “A robust speech understanding system using conceptual relational grammar,” Proceedings of the International Conference on Spoken Language Processing,October 2000, Vol. 2, pp. 879-882.
  • S. Dusan and L. Deng. “Acoustic-to-articulatory inversion using dynamical and phonological constraints” Proceedings of the 5th Speech Production Workshop: MODELS AND DATA, Kloster Seeon, Germany, May 1-4, 2000, pp. 237-240.
  • M. Naito, L. Deng, and Y. Sagisaka. “Speaker adaptation methods using vocal tract parameters,” (in Japanese) Proceedings of the 1998 Spring Meeting of the Acoustical Society of Japan, Yokohama, Japan, March 17-19, 1998, pp. 55-56.
  • M. Naito, L. Deng, and Y. Sagisaka. “A study on speaker clustering methods using vocal tract parameters,” (in Japanese) Proceedings of Japan Institute of Electronics, Information, and Communication Engineers (IEICE), Yokosuka, Japan, December 1997, Vol. 97, No. 441, pp. 35-40.
  • L. Deng (invited). “A dynamic, feature-based approach to speech modeling and recognition,”Proceedings of the 1997 IEEE Workshop on Automatic Speech Recognition and Understanding, Santa Barbara, CA, December 14-17, 1997, pp. 107-114.
  • X. Shen, L. Deng, and A. Yasmin. “H-infinity filtering for speech enhancement,” Proceedings of the International Conference on Spoken Language Processing, Philadelphia, PA, October 3-6, 1996, pp. 873-876.
  • L. Deng, X. Shen, and D. Jamieson. “Simulation of disordered speech using a frequency-domain vocal tract model,” Proceedings of the International Conference on Spoken Language Processing, Philadelphia, PA, October 3-6, 1996, pp. 768-771.
  • D. Jamieson, L. Deng, M. Price, V. Parsa, and J. Till. “Interactions of speech disorders with speech coders: Effects on speech intelligibility,” Proceedings of the International Conference on Spoken Language Processing, Philadelphia, PA, October 3-6, 1996, pp. 737-740.
  • G. Ramsay and L. Deng. “Optimal filtering and smoothing for speech recognition using a stochastic target model,” Proceedings of the International Conference on Spoken Language Processing, Philadelphia, PA, October 3-6, 1996, pp. 1113-1116.
  • L. Deng, G. Ramsay, and D. Sun. (invited). “Production models as a structural basis for automatic speech recognition,” Proceedings of the Fourth European Speech Production Workshop, Autrans, France, May 24-27, 1996, pp. 69–80.
  • L. Deng. “Finite-state automata derived from overlapping articulatory features: A novel phonological construct for speech recognition,” Proceedings of the Workshop on Computational Phonology in Speech Technology, (published by Association for Computational Linguistics), Santa Cruz, CA, June 28, 1996. pp. 37-45.
  • L. Deng and H. Sheikhzadeh. “Temporal and rate aspects of speech encoding in the auditory system: Simulation results on TIMIT data using a layered neural network interfaced with a cochlear model,” Proceedings of European Speech Communication Association Tutorial and Research Workshop on the Auditory Basis of Speech Recognition, July 15 – 19, 1996, Keele University, United Kingdom, pp. 75-78.
  • C. Rathinavelu and L. Deng. “HMM-based speech recognition using state-dependent, discriminatively derived transforms on Mel-warped DFT features”, Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol.1, Atlanta, Georgia, May 7-10, 1996, pp. 9–12.
  • L. Deng, G. Ramsay, and H. Sameti. “From modeling surface phenomena to modeling mechanisms: Towards a faithful model of the speech process aiming at speech recognition,” Proceedings of the 1995 IEEE Workshop on Automatic Speech Recognition, December 10-13, 1995, Snowbird, Utah, pp. 183-184.
  • G. Ramsay and L. Deng. “Maximum-likelihood estimation for articulatory speech recognition using a stochastic target model,” Proceedings of the 1995 European Conference on Speech Communication and Technology, Spain, September 18-21, 1995, pp. 1401-1404.
  • G. Ramsay and L. Deng. “Modal analysis of acoustic wave propagation in the vocal tract using a finite-difference method,” Proceedings of the XII International Congress of Phonetic Sciences, Stockholm, Sweden, August 13-19, 1995, Vol 2, pp. 338-341.
  • G. Ramsay and L. Deng. “Articulatory synthesis using a stochastic target model of speech production,” Proceedings of the XII International Congress of Phonetic Sciences, Stockholm, Sweden, August 13-19, 1995, Vol 2, pp. 478-481.
  • L. Deng, J. Wu, and H. Sameti. “Improved speech modeling and recognition using multi-dimensional articulatory states as primitive speech units,” Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Detroit, MI, May 8-12, 1995, pp. 385-388.
  • D. Sun and L. Deng. “Analysis of acoustic-phonetic variations in fluent speech using TIMIT,”Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Detroit, MI, May 8-12, 1995, pp. 201-204.
  • C. Rathinavelu and L. Deng. “Use of generalized dynamic feature parameters for speech recognition: Maximum likelihood and minimum classification error approaches,” Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Detroit, MI, May 8-12, 1995, pp. 373-376.
  • S. Shen and L. Deng. “Discrete H-infinity filtering design with application to speech enhance ment,”Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Detroit, MI, May 8-12, 1995, pp. 1504-1507.
  • H. Sheikhzadeh, R. Brennan, L. Deng, and H. Sameti, “Real-time implementation of HMM-based MMSE algorithm for speech enhancement in hearing aid applications,” Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, 1995 ,
  • D. Sun and L. Deng. “Nonstationary-state hidden Markov model with state-dependent time warping: Application to speech recognition,” Proceedings of the 1994 International Conference on Spoken Language Processing, Vol. 1, Yokohama, Japan, September, 18-22, 1994. pp. 243–246,
  • L. Deng and H. Sameti. “Speech recognition using dynamically defined speech units,” Proceedings of the 1994 International Conference on Spoken Language Processing, Vol. 4, pp. 2167-2170, Yokohama, Japan, September, 18-22, 1994.
  • H. Sheikhzadeh and L. Deng. “Interval statistics from a cochlear model in response to speech sounds,” Journal of the Acoustical Society of America, Vol. 95, No. 6, June 1994 (Abstract), pp. 2842. (The 127th Meeting of the Acoustical Society of America, June 4-8, 1994, Cambridge, MA.)
  • L. Deng and I. Kheirallah. “Stability analysis on finite-difference solution of a basilar-membrane vibration model with application to acoustic signal processing,” Journal of the Acoustical Society of America, Vol. 95, No. 6, June 1994 (Abstract), pp. 2840. (The 127th Meeting of the Acoustical Society of America, June 4-8, 1994, Cambridge, MA.)
  • L. Deng and H. Sameti. “Articulatory phonology and speech recognition: A study on use of dynamically defined speech primitives,” Journal of the Acoustical Society of America, Vol. 95, No. 6, June 1994 (Abstract), pp. 2870. (The 127th Meeting of the Acoustical Society of America, June 4-8, 1994, Cambridge, MA.)
  • G. Ramsay and L. Deng. “A stochastic framework for articulatory speech recognition,” Journal of the Acoustical Society of America, Vol. 95, No. 6, June 1994 (Abstract), pp. 2871. (The 127th Meeting of the Acoustical Society of America, June 4-8, 1994, Cambridge, MA.)
  • K. Hassanein, L. Deng and M. Elmasry. “A neural predictive hidden Markov model for speaker recognition,” Proceedings of the Workshop on Automatic Speaker Recognition, Identification and Verification, Martigny, Switzerland, April, 1994, pp. 115-118.
  • L. Deng and M. Aksmanovic. “HMMs with mixtures of trended functions for automatic speech recognition,” IEEE International Conference on Speech, Image Processing and Neural Networks, April 13-15, 1994, HongKong, pp. 702-705.
  • L. Deng. “A theory on optimal construction of dynamic features for hidden Markov modeling of speech,” IEEE International Conference on Speech, Image Processing and Neural Networks, April 13-15, 1994, HongKong, pp. 351-354.
  • L. Deng and D. Sun. “Phonetic classification and recognition using HMM representation of overlapping articulatory features for all classes of English sounds,” Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Adelaide, Australia, April 19-22, 1994, Vol. 1, pp. 45-48.
  • K. Hassanein, L. Deng and M. Elmasry. “Vowel classification using a neural predictive HMM: A discriminative training approach,” Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Adelaide, Australia, April 19-22, 1994, Vol 2, pp. 665-668.
  • H. Sameti, H. Sheikhzadeh, L. Deng and R. Brennan. “Comparative performance of spectral subtraction and HMM-based speech enhancement strategies with application to hearing aid design.” Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Adelaide, Australia, April 19-22, 1994, Vol. 1, pp. 13-16.
  • L. Deng. “A computational model of phonology-phonetics integration for automatic speech recognition,” Proceedings of the 1993 IEEE Workshop on Automatic Speech Recognition, December 12-15, 1993, Snowbird, Utah, pp. 83–84.
  • K. Hassanein, L. Deng and M. Elmasry. “A neural predictive hidden Markov model for speech and speaker recognition,” Proceedings of the Fifth International Conference on MicroelectronicsDecember 14-16, 1993, Dhahran, Saudi Arabia, pp. 108-111.
  • L. Deng and D. Sun. “Speech recognition using the atomic speech units constructed from overlapping articulatory features,” Proceedings of the 1993 European Conference on Speech Communication and Technology, September 21-23, 1993, Berlin, Germany, Vol. III, pp. 1635–1638.
  • D. Zhang, L. Deng, and M. Elmasry. “Pipelined neural network architecture for speech recognition,”Proceedings of the 1993 World Congress on Neural Networks, July 11-15, 1993, Portland, Oregon, Vol. III, pp. 55-58.
  • L. Deng. “Design of a feature-based speech recognizer aiming at integration of auditory processing, signal modeling, and phonological structure of speech.” (invited) Journal of the Acoustical Society of America, Vol. 93, No.4, Pt. 2, pp. 2318, April, 1993.
  • K. Hassanein, L. Deng, and M. Elmasry. “Maximal mutual information training of a neural predictive HMM speech recognition system,” Proceedings of the 1992 IEEE Workshop on Neural Networks for Signal Processing, August 31–September 2, 1992, Copenhagen, Denmark, pp. 164-173.
  • K. Erler and L. Deng. “HMM representation of quantized articulatory features for recognition of highly confusible words,” Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, San Francisco, CA., March, 1992, pp.545-548.
  • L. Deng. “Speech modeling and recognition using a time series model containing trend functions with Markov modulated parameters,” Proceedings of the 1991 IEEE Workshop on Automatic Speech Recognition, Arden House, New York, December, 1991, pp. 24-26.
  • L. Deng and K. Erler. “Microstructural speech units and their HMM representation for discrete utterance speech recognition,” Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Toronto, Ontario, Canada, May, 1991, pp. 193–196. P. Seitz, V. Gupta, M. Lennig, P. Kenny, L. Deng, D. O’Shaughnessy, and P. Mermelstein. “Phonological rule set complexity as a factor in the performance of a very large vocabulary word recognition system,” Journal of the Acoustical Society of America, 87(1), May, 1990, S108 (Abstract).
  • L. Deng, V. Gupta, M. Lennig, P. Kenny, and P. Mermelstein. “Acoustic recognition component of an 86,000-word speech recognizer,” Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Albuquerque, New Mexico, 1990, pp. 741–744.
  • L. Deng, P. Kenny, M. Lennig, V. Gupta and P. Mermelstein. “A locus model of coarticulation in a hidden-Markov-model-based speech recognizer,” Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Glascow, Scotland, 1989, pp. 97-100.
  • L. Deng, P. Kenny, M. Lennig, V. Gupta and P. Mermelstein. “Large vocabulary word recognition based on phonetic representation by hidden Markov models”, Proceedings of the Canadian Conference on Electrical and Computer Engineering, Vancouver, Canada, November 1988, pp. 131-134.
  • L. Deng, M. Lennig, and P. Mermelstein. “Modeling acoustic-phonetic detail in a hidden-Markov-model-based large vocabulary speech recognizer,” Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, New York, New York, Vol. 1, April 1988, pp. 509–512.
Advertisements