Shyam Madhusudhana

Postdoctoral Fellow

Expertise

Passive Acoustics • Automatic Pattern Recognition • Statistical Learning • Signal Processing

My current research involves developing solutions for automatic source separation in continuous ambient audio streams and the development of acoustic deep-learning techniques for unsupervised multi-class classification in the big-data realm, with focus on efficient utilization of modern computing capabilities in achieving real-time performance.

My research interests have been largely multidisciplinary. In the past, I worked as a speech scientist for a leading Automatic Speech Recognition (ASR) solutions provider, before steering my career into bioacoustics and allied disciplines. My Masters thesis offered passive acoustic solutions to monitoring free-ranging blue and fin whales in the Pacific Ocean, and my doctoral research involved development of solutions for the automation of underwater soundscape assessments.

Prior to joining Cornell, I was a research associate with the Centre for Marine Science and Technology (CMST) in Australia, a research associate at the National Institute of Oceanography (NIO) in India , and a postdoctoral research fellow at the Indian Institute of Science Education and Research (IISER-Tirupati), also in India.

I have been actively involved with IEEE’s Oceanic Engineering Society (OES) as an AdCom member and, currently, I serve as the coordinator of Technology Committees. I also referee manuscripts for the Journal of the Acoustical Society of America and, in the past, have refereed for the Australian Acoustical Society as well.

Education

Ph.D., Applied Physics, Curtin University, Australia
M.S., Computer Science, San Diego State University, California
B.E., Computer Science and Engineering, Visvesvaraya Technological University, India

Recent Publications

Bouffaut, L., S. Madhusudhana, V. Labat, A. Boudraa, and H. Klinck (2020). A performance comparison of tonal detectors for low-frequency vocalizations of Antarctic blue whales. The Journal of the Acoustical Society of America 147.
ter Hofstede, H. M., L. B. Symes, S. J. Martinson, T. Robillard, P. Faure, S. Madhusudhana, and R. A. Page (2020). [In Press] Calling songs of katydids (Orthoptera, Tettigoniidae) from Panama. Journal of Orthopteran Research.
Madhusudhana, S., A. Murray, and C. Erbe (2020). [In Press] Automatic detectors for low-frequency vocalizations of Omura’s whales, Balaenoptera omurai: A performance comparison. The Journal of the Acoustical Society of America.
Bouffaut, L., S. Madhusudhana, V. Labat, A. Boudraa, and H. Klinck (2019). Automated blue whale song transcription across variable acoustic contexts. Oceans 2019.
Madhusudhana, S., A. Gavrilov, and C. Erbe (2018). A general purpose automatic detector of broadband transient signals in underwater audio. IEEE 2018 OCEANS:1–6.
Madhusudhana, S. K., B. Chakraborty, and G. Latha (2018). Humpback whale singing activity off the Goan coast in the Eastern Arabian Sea. The International Journal of Animal Sound and its Recording. https://doi.org/10.1080/09524622.2018.1458248
Madhusudhana, S., A. Gavrilov, and C. Erbe (2016). A generic system for the automatic extraction of narrowband signals of biological origin in underwater audio. Proceedings of Meetings on Acoustics 29.
Madhusudhana, S., A. Gavrilov, and C. Erbe (2015). Automatic detection of echolocation clicks based on a Gabor model of their waveform. The Journal of the Acoustical Society of America 137.

Don't miss a thing! Join our email list