Deepu Vijayasenan


Associate Professor

Date of Joining at NITK: 

Tuesday, January 1, 2013

Professional Experience: 

2013 Jan – Till date, Assistant Professor, NIT-K, Surathkal
2011 Jan -2012 Dec. Post Doctoral Researcher, Universität des Saarlandes
2003-2006 Research Consultant, Hewlett-Pacard Research Labs, Bangalore.

Contact Details


deepu.senan [at] gmail[dot]com


Land line : +91 – 824 – 247 3511 Mobile: +91 97 393 27 595
Academic Background
Ph.D - Ecole Polytechnique Fédéral de Lausanne (EPFL), Switzerland M.E, Signal Processing, -.Indian Institute of Science, Bangalore.
Areas of Interest

Speech Signal Processing,
Machine Learning.

Supervision of Ph.D

2 Ongoing

Significant Publications
Journal Publications:
  1. Deepu Vijayasenan, Fabio Valente, Herv e Bourlard “Multistream speaker diarization of meetings recordings beyond MFCC and TDOA features” Speech Communication 54(1), 55-67: (2012) 10.1016/j.specom.2011.07.001.
  2. Deepu Vijayasenan F. Valente and Herv e Bourlard “An Information Theoretic Combination of MFCC and TDOA Features for Speaker Diarization” IEEE Transactions on Acoustics, Speech and Language Processing 19(2): 431-438 (2011) 10.1109/TASL.2010.2048603.
  3. Deepu Vijayasenan F. Valente and Herv e Bourlard “An Information Theoretic Approach to Speaker Diarization of Meeting Data” IEEE Transactions on Acoustics, Speech and Language Processing 17(7), 1382-1393:(2009), 10.1109/TASL.2009.2015698.


Conference Publications:
  1. Kalluri, Shareef Babu, Deepu Vijayasenan, and Sriram Ganapathy. "A Deep Neural Network Based End to End Model for Joint Height and Age Estimation from Short Duration Speech." ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2019.

  2. Lakshmi S., Deepu Vijayasenan, Sumam David S., Saraswathy Sreeram and Pooja K S "An Integrated Deep Learning Approach towards Automatic Evaluation of Ki-67 Labeling Index." In TENCON 2019 - 2019 IEEE Region 10 Conference. IEEE, 2019

  3. Prediction of Aesthetic Elements in Karnatic Music: a Machine Learning Approach,  Ragesh Rajan, Ashwin Kalyan and Deepu V., Interspeech 2018, Hyderabad

  4. Frequency Contour Modeling to Synthesize Natural Flute Renditions for Carnatic Music, Pranav Prasad, Anand G, Shashank S, Deepu V., Signal Processing and Communication, SPCOM 2018, Bangalore

  5. Robust features for automatic estimation of physical parameters from speech KS Babu, D Vijayasenan Region 10 Conference, TENCON 2017, Malaysia.

  6. Estimating multiple physical parameters from speech data SB Kalluri, A Vijayakumar, D Vijayasenan, R Singh Machine Learning for Signal Processing (MLSP), 2016,  Italy

  7. A novel approach for Robust Detection of Heart Beats in Multimodal Data using neural networks and boosted trees S Vernekar, D Vijaysenan, R Ranjan Computing in Cardiology Conference (CinC), 2016, 1137-1140  2016, Canada

  8. A novel approach for classification of normal/abnormal phonocardiogram recordings using temporal signal analysis and machine learning S Vernekar, S Nair, D Vijaysenan, R Ranjan Computing in Cardiology Conference (CinC), 2016, 1141-1144, Canada

  9. Study of Wireless Channel Effects on Audio Forensics D Vijayasenan, SB Kalluri, K Sreekanth, A Issac 22nd Annual International Conference on Advanced Computing and  and Communication (ADCOM) 2016

  10. Deepu Vijayasenan and F. Valente, “DiarTk: An Open Source Toolkit for Research in Multistream Speaker Diarization and its Application to Meetings Recordings”, INTERSPEECH 2012, Florence, Italy.

  11. Deepu Vijayasenan and F. Valente “Speaker Diarization of Meetings based on Large TDOA Feature Vectors” Proceedings of ICASSP 2012, Kyoto, Japan.

  12. Deepu Vijayasenan F. Valente and Herve Bourlard “Advances in Fast Multistream Diarization based on the Information Bottleneck Framework” Proceedings of Interpseech 2010 Kyoto, Makuhari,  Japan.

  13. Deepu Vijayasenan F. Valente and Herve Bourlard “Multistream Speaker Diarization Beyond Two Acoustic Streams” Proceedings of ICASSP 2010

  14. Deepu Vijayasenan F. Valente and Herve Bourlard “KL Realignment for Speaker Diarization with Multiple Feature Streams” Proceedings of Interspeech 2009 pp. 1059-1062.

  15. Deepu Vijayasenan F. Valente and Herve Bourlard “Mutual Information based Channel Selection for Speaker Diarization of Meetings Data” ICASSP 2009 pp.4065-4068.


  1. Shekhar Ramachandra Borgaonkar, Prasenjit Dey and Deepu Vijayasenan, “Systems and methods for estimating distances using multi-resolution functions” US Patent: US20090204364.
  2. 2. Dinesh Mandalapu, Sriganesh Madhvanath, Deepu Vijayasenan, Rama Vennelakanti, “Annotation on Media Sheet Indicating Functionality to be Performed in Relation to Image on Media Sheet” US Patent: US20100309527.

Contact us

Dr. T. Laxminidhi,  Professor and Head, 
Department of E&C, NITK, Surathkal
P. O. Srinivasnagar,
Mangalore - 575 025 Karnataka, India.

Connect with us

We're on Social Networks. Follow us & get in touch.