The Speech Recognition Group

Research Interests

• Large Vocabulary Continuous Speech Recognition (LVCSR).
• Robust speech/speaker recognition under adverse environment.
• Speech understanding.
• Machine learning.
• Neural network theory, application, and parallel implementation.
• Hidden Markov Model.
• Real-time implementation of speech recognition system.
• Text to speech synthesis.
• Articulatory modeling of speech production and synthesis.

Projects

• A Neural Network System for Large-Vocabulary Continuous Speech Recognition in Variable Acoustic Environments
• Text Independent Speaker Recognition Using Telephone Speech

Members

• Dr. James L. Flanagan <jlf@caip.rutgers.edu>
• Mahesh Krishnamoorthy , M.S. Candidate <krishnam@caip.rutgers.edu>
• Krishna Dayanidhi , M.S. Candidate <krsna@caip.rutgers.edu>

Alumni

• Dr. Qiguang Lin , IBM T. J. Watson Research Center <qlin@caip.rutgers.edu>
• Dr. Samir Chennoukh , Philips Research Laboratory, Netherlands <chenoukh@caip.rutgers.edu>
• ChiWei Che , Philips Research Laboratory, Taiwan <cche@caip.rutgers.edu>
• Prabhu Raghavan , Lucent Technology, Bell Labs <prabhura@caip.rutgers.edu>
• Dr. DongSuk Yuk , IBM T. J. Watson Research Center <yuk@caip.rutgers.edu>

Publications

• Robust Speech Recognition Using Neural Networks and Hidden Markov Models
  - Adaptations Using Non-linear Transformations
  DongSuk Yuk
  Ph.D. dissertation, Rutgers University, October 1999
  CAIP Technical Report TR-238, September 1999
• Adaptation To Environment And Speaker Using Maximum Likelihood Neural Networks
  (Nominee of the ESCA best student paper)
  DongSuk Yuk, James Flanagan, Mahesh Krishnamoorthy, Krishna Dayanidhi
  EUROSPEECH, September 1999
• Telephone Speech Recognition Using Neural Networks and Hidden Markov Models
  DongSuk Yuk and James Flanagan
  IEEE International Conference on Acoustics, Speech, and Signal Processing, March 1999
• Speech Recognition in a Reverberant Environment using Matched Filter Array (MFA) Processing and Linguistic-Tree Maximum Likelihood Linear Regression (LT-MLLR) Adaptation
  Prabhu Raghavan, Richard Renomeron, ChiWei Che, DongSuk Yuk, and James Flanagan
  IEEE International Conference on Acoustics, Speech, and Signal Processing, March 1999
• Voiced-Unvoiced Classification for Recognition of Stop Consonants
  Mahesh Krishnamoorthy, DongSuk Yuk, Krishna Dayanidhi, Samir Chennoukh, Daniel J. Sinder, and James L. Flanagan
  Acoustical Society of America, 137th Meeting, March 1999
• A Neural Network System for Robust Large-Vocabulary Continuous Speech Recognition in Variable Acoustic Environments
  DongSuk Yuk, Prabhu Raghavan, Richard Renomeron, James Flanagan
  CAIP Technical Report 234, January 1999
• Speech Recognition in A Reverbrant Environment Using Matched Filter Array Processing And Linguistic-Tree Maximum Likelihood Linear Regression Adaptation
  Prabhu Raghavan, Richard Renomeron, ChiWei Che, Samir Chennoukh, DongSuk Yuk, and James Flanagan
  Acoustical Society of America, 136th Meeting, October 1998
• N-best Breadth Search for Large Vocabulary Continuous Speech Recognition Using A Long Span Language Model
  DongSuk Yuk, ChiWei Che, Prabhu Raghavan, and James Flanagan
  Acoustical Society of America, 136th Meeting, October 1998
• Speaker and Environment Adaptation in Continuous Speech Recognition.
  Prabhu Raghavan, CAIP Technical Report No. TR-227, 1998.
• Robust Speech Recognition Using Maximum Likelihood Neural Networks and Continuous Density Hidden Markov Models
  DongSuk Yuk, ChiWei Che, and James Flanagan
  IEEE Workshop on Speech Recognition and Understanding, December 1997
• Speaker Adaptation in Speech Recognition
  Prabhu Raghavan and ChiWei Che
  134th Acoustical Society of America Meeting, December 1997
• Development of The RU Hub4 System
  ChiWei Che, DongSuk Yuk, Samir Chennoukh, and James Flanagan
  DARPA Speech Recognition Workshop, February 1997
• Selective Use of the Speech Spectrum and Effective Text Confirmation for Robust Speaker Recognition
  Qiguang Lin, Ea-Ee Jan, ChiWei Che, DongSuk Yuk, and James Flanagan
  Fourth International Conference on Spoken Language Processing, October 1996
• Environment-Independent Continuous Speech Recognition Using Neural Networks and Hidden Markov Models
  DongSuk Yuk, ChiWei Che, Limin Jin, and Qiguang Lin
  IEEE International Conference on Acoustics, Speech, and Signal Processing, May 1996
• Robust Distant-Talking Speech Recognition
  Qiguang Lin, ChiWei Che, DongSuk Yuk, Limin Jin, Bert de Vries, John Pearson, and James Flanagan
  IEEE International Conference on Acoustics, Speech, and Signal Processing, May 1996
• An HMM Approach to Text-Prompted Speaker Verification
  ChiWei Che, Qiguang Lin, and DongSuk Yuk
  IEEE International Conference on Acoustics, Speech, and Signal Processing, May 1996
• Development of 1996 RU Speaker Recognition System
  ChiWei Che, DongSuk Yuk, James Flanagan, and Qiguang Lin
  DARPA Speaker Recognition Workshop, March 1996
• Development of CROWNS: CAIP Recognizer Of Words 'N Sentences
  ChiWei Che, Qiguang Lin, and DongSuk Yuk
  DARPA Speech Recognition Workshop, February 1996
• Environment-Independent Continuous Speech Recognition
  DongSuk Yuk, Qiguang Lin, ChiWei Che, Limin Jin, and James Flanagan
  IEEE Automatic Speech Recognition Workshop, December 1995
• A Microphone Array and Neural Network System for Speech Recognition
  Qiguang Lin, ChiWei Che, DongSuk Yuk, and James Flanagan
  15th Annual Speech Research Symposium, June 1995.