Dr. CK Raut

Research Interests

• Large Vocabulary Continuous Speech Recognition (LVCSR)
• Machine Learning and Pattern Recognition
• Discriminative Training
• Bayesian Learning and Inference
• Acoustic Modelling and Model Adaptation
• Robust Speech Recognition in Noisy Environment
• Signal (Audio, Video, Image) Processing

Research Project

• Robust Automatic Transcription of Speech (RATS), Defense Advanced Research Projects Agency [DARPA-BAA-10-34]


• Autonomous Global Integrated Language Exploitation (AGILE) (DARPA Global Autonomous Language Exploitation (GALE) funded project)

Theses

• PhD Thesis:
  Discriminative Adaptive Training and Bayesian Inference for Speech Recognition,
  University of Cambridge, 2009.
  Supervised by: Dr. Mark Gales


• Masters Thesis:
  Robust speech recognition with additive noise and long reverberation,
  The University of Tokyo, 2006.
  Supervised by: Prof. Shigeki Sagayama

Talks/Presentations

• C. K. Raut
  Adaptation and Adaptive Training: A Discriminative and Bayesian Approach,
  A Talk to BBN Technologies, August 2009. [ slides ]
• C. K. Raut, K. Yu and M. J. F. Gales,
  Instantaneous Unsupervised Adaptation using Discriminative Mapping Transforms,
  Young Speech Researchers Meeting (UK Speech), 2008. [ programme | slides ]
• C. K. Raut, K. Yu and M. J. F. Gales,
  Bayesian Discriminative Adaptation for Speech Recognition,
  Young Speech Researchers Meeting (organised by UK Speech), 2007. [ programme/abstract | slides ]

Selected Publications

You can also try: google scholar | microsoft academic search

• C. K. Raut and M. J. F. Gales,
  Bayesian Discriminative Adaptation for Speech Recognition,
  in Proc. ICASSP, Apr 2009.
• C. K. Raut, K. Yu., and M. J. F. Gales,
  Adaptive Training using Discriminative Mapping Transforms,
  in Proc. Interspeech, Sep 2008.
• M. J. F. Gales, F. Diehl, C. K. Raut, M. Tomalin, P. C. Woodland and K. Yu.,
  Development of a Phonetic System for Large Vocabulary Arabic Speech Recognition,
  in Proc. IEEE ASRU, Dec 2007.
• C. K. Raut, T. Nishimoto, and S. Sagayama,
  Model Adaptation for Long Convolutional Distortion by Maximum Likelihood State Filtering Approach,
  in Proc. ICASSP, May 2006.
• C. K. Raut, T. Nishimoto, and S. Sagayama,
  Maximum Likelihood Based General Joint Adaptation for Noise and Long Reverberation,
  in Proc. ASJ conf., Mar 2006.
• C. K. Raut, T. Nishimoto, and S. Sagayama,
  Maximum Likelihood Based HMM State Filtering Approach to Model Adaptation for Long Reverberation,
  in Proc. IEEE ASRU, Nov 2005.
• C. K. Raut, T. Nishimoto, and S. Sagayama,
  Maximum Likelihood Based Compensation of HMM Parameters for Channel Distortion,
  in Proc. ASJ Conf., Sep 2005.
• C. K. Raut, T. Nishimoto, and S. Sagayama,
  Model Adaptation by State Splitting of HMM for Long Reverberation,
  in Proc. Interspeech, Sep 2005.
• C. K. Raut, T. Nishimoto, and S. Sagayama,
  Model Convolution by State Splitting of HMM for Robust Speech Recognition in presence of Convolutional Noise,
  in Proc. ASJ Conf., Mar 2005.


• C. K. Raut, T. Nishimoto, and S. Sagayama,
  Model Adaptation for Reverberant Speech by HMM State Splitting and Convolution of Mixtures,
  in Technical Report of Institute of Electronics, Information and Communication Engineers (IEICE), SP2004-151, Jan. 2005, pp. 37-42.
• C. K. Raut, T. Nishimoto, and S. Sagayama,
  Model Composition by Lagrange Polynomial Approximation for Robust Speech Recognition in Noisy Environment,
  in Proc. ICSLP, Oct 2004.
• C. K. Raut, T. Nishimoto, and S. Sagayama,
  Noise-Driven Temporal Trajectory Filtering of Spectral Parameters forRobust Speech Recognition,
  in Proc. ASJ Conf., Sep 2004.
• C. K. Raut, H. Yamamoto, T. Nishimoto, and S. Sagayama,
  Polynomial-Approximation-Based Model Adaptation for Noisy Speech Recognition,
  in Proc. ASJ Conf., Mar 2004.

Teaching

• M.Phil. in Computer Speech, Text and Internet Technology - Speech Processing II Practical (2007 Lent), University of Cambridge.

Professional Activities

• IEEE Transactions on Audio, Speech and Language Processing, reviewer.
• IEEE Signal Processing Letters, reviewer.
• Pattern Recognition (Elsevier), The Journal of the Pattern Recognition Society, reviewer.
• European Signal Processing Conference (EUSIPCO), reviewer.
• Science Explorer (monthly), executive editor, 2003.
• Technology, The Journal of Nepal Engineers' Students' Society, editor, 2001.

• International Speech Communication Association (ISCA)
• Nepal Engineers' Association (NEA)

Funding

• DARPA GALE supported Autonomous Global Integrated Language Exploitation (AGILE) Research Studentship, Cambridge University Engineering Department (2006-2009).
• International Information Science Foundation, Grant no 2004.2.2.846 (2004).
• Ministry of Education, Culture, Sports, Science and Technology, Government of Japan, Monbukagakusho Research Studentship (2003-2006).

Contact Information