Umesh S


PhD  University of Rhode Island, USA, 1993

M.E.  Madras Institute of Technology, Chennai, 1989

B.E.  Birla Institute of Technology & Science, Pilani, 1987

044-2257 4461

  • Automatic Speech Recognition.
  • Speaker Normalization & Adaptation.
  • Self Supervised Learning.
  • Deep Learning and Machine Learning.
  • Speaker Recognition & Diarisation.

  • AICTE Career Award for Young Teachers 1997.
  • Alexander von Humboldt Research Fellowship 2004.

    Current Courses

  • Introduction to Digital Signal Processing

    Previous Courses

  • Networks & Systems (Fall 2009, Fall 2010, Fall 2013, Fall 2014).
  • Signals & Systems (Spring 2018, Spring 2021).
  • Analog & Digital Signal Processing (Spring 2010, Spring 2011, Spring 2012, Spring 2014, Spring 2015, Spring 2019, Spring 2020).
  • Digital Signal Processing (MTech) (Fall 2019, Fall 2020).
  • Speech Signal Processing (Fall 2011, Fall 2012, Fall 2018).
  • Advanced Topics in Signal Processing (Spring 2013).


  • S V Bharath Kumar and S Umesh [2008]: Non-Uniform Speaker Normalization Using Affine Transformation,To Appear in Journal of the Acoustical Society of America, Vol 124, No 3, Sep 2008.
  • R Sinha and S Umesh [2008]: A Shift based Approach to Speaker Normalization using Non-Linear Frequency-Scaling Model, ISCA Transactions on Speech Communication, Vol 50,No 3, pp 191-202, Mar 2008.
  • S Umesh and R Sinha [2007]: A Study of Filter-Bank Smoothing in MFCC Features for Recognition of Children Speech, IEEE Transactions on Audio, Speech and Language Processing, Volume 15, Issue 8, Nov 2007 Page(s): 2418 2430.
  • S Umesh, L Cohen and D Nelson [2007]: Fluctuations in Speech, Fluctuations and Noise Letters, 1 Vol 7, No 3, Sep 2007, pp 215224.
  • S Umesh, L Cohen and D Nelson [2002]: The Speech Scale, Acoustics Research Letters Online of the Journal of Acoustical Society of America, Vol 3, Issue 3, pp 83-88, July 2002.
  • S Umesh, L Cohen and D Nelson [2002]: Frequency Warping and the Mel-scale, IEEE Signal Processing Letters, vol 9, no 3, pp 104-107, March 2002.
  • S Umesh, L Cohen, N Marinovic, and D J Nelson [1999]: Scale-Transform in Speech Analysis, IEEE Transactions on Speech and Audio Processing, vol 7, no 1, pp 40-45, Jan 1999.
  • S Umesh and D W Tufts [1996]:Estimation of Parameters of Multiple Exponentially Damped Sinusoids using Fast Maximum Likelihood Estimation with Application to NMR Spectroscopy Data,IEEE Trans Signal Processing, vol 44, no 9, pp 2245-2259, Sept 1996.
  • D W Tufts, H Ge, and S Umesh [1993]: Fast Maximum Likelihood Estimation of Signal Parameters using the Shape of the Compressed Likelihood Function, IEEE Journal of Oceanic Engg, Vol 18, no 4, pp 388-400, Oct 1993.

Conference Proceedings

  • D R Sanand and S Umesh [2008]: Study of Jacobian Compensation Using Linear Transformation of Conventional MFCC for VTLN, To Appear in Interspeech-2008, Brisbane, Sep 2008.
  • D R Sanand, V Balaji, R Sandhya Rani and S Umesh [2008]: Use of Spectral Center of Gravity for Generating Speaker Invariant Features for Automatic Speech Recognition, To Appear in Interspeech-2008, Brisbane, Sep 2008.
  • P T Akhil, S P Rath, S Umesh and D R Sanand [2008]: A Computationally Efficient Approach to Warp Factor Estimation in VTLN Using EM Algoirthm and Sufficient Statistics'', To Appear in Interspeech-2008, Brisbane, Sep 2008.
  • D R Sanand, D Dinesh Kumar and S Umesh [2007]: Linear Transformation Approach to VTLN Using Dynamic Frequency Warping,'' Proc of International Conference on Spoken Language Processing (Interspeech 2007), Antwerp, Belgium, August 27-31, 2007.
  • S Umesh, L Cohen and D Nelson [2007]: Fluctuations in speech,'' Proc of Conference on Noise and Fluctuations in Biological, Biophysical, and Biomedical Systems, Florence, Italy, May 2007.
  • S Umesh, D Rama Sanand, G Praveen [2007]: Speaker-Invariant Features for Automatic Speech Recognition,'' Proc. of International Joint Conferences on Artificial Intelligence, (IJCAI-07), pp 1738-1743, Jan 2007.
  • S V Bharath, S Umesh and R Sinha [2006]: Study of Non-Linear Frequency Warping Functions for Speaker Normalization,'' To Appear in Proc of IEEE International Conf on Acoustic, Speech and Signal Processing, (ICASSP Toulouse), April 2006.
  • J Loof and H Ney and S Umesh [2006]: VTLN Warping Factor Estimation Using Accumulation of Sufficient Statistics,'' To Appear in Proc of IEEE International Conf. on Acoustic, Speech and Signal Processing, (ICASSP Toulouse), April 2006.
  • S Umesh, A Zolnay and H Ney [2005]: Implementing Frequency-Warping and VTLN Through Linear Transformation of Conventional MFCC,'' Proc of InterSpeech 2005, (Lisbon, Portugal), Sep'2005.
  • S Umesh, L Cohen and D Nelson [2005]: The Speech Scale and Spectral Transformation,'' Proc of SPIE Conference on Wavelet Applications in Signal & Image Proc, July'2005.
  • S V Bharath and S Umesh [2004]: Non-uniform speaker normalization using frequency-dependent scaling function,'' Proc IEEE International Conference on Signal Processing and Communications, (Bangalore), December 2004.

Books Authored

  • Ajit K Chaturvedi, Srinivasan Umesh, Adrish Banerjee, Kameswari Chebrolu, Joseph John, Ayyangar R Harish (Editors): Proceedings of the Thirteenth National Conference on Communications, I I T Kanpur, 26-28 January 2007 ;ISBN Number: 978-81-904444-0-8.

  • Faculty, Dept of Electrical Engineering, IIT-Kanpur (June 1996 - July 2009)
  • (First as Assistant Professor and finally as Professor).
  • Visiting Researcher, Computer Science VI, RWTH-Aachen, Germany (May 2004 - June 2005)
  • (on Alexander von Humboldt Research Fellowship).
  • Visiting Researcher, Machine Intelligence Laboratory-Cambridge University Engg Dept, UK (June 2003 - April 2004).
  • Visiting Researcher, AT&T Laboratories-Research, USA (May-Dec 1999).
  • Visiting Research Faculty, City Univ of New York, USA (Summer 1997, Summer 1998, Summer 2002).
  • Post-Doctoral Fellow, City Univ of New York, USA (1994-1996).
  • Post-Doctoral Fellow, Univ of Rhode Island, USA (1993-1994).

© 2023-All rights reserved.DEPARTMENT OF Electrical Engineering || Website Credits