Paris Smaragdis
I’m a graduate of the Media Lab and currently a senior research scientist at Adobe Systems. I did my masters, Ph.D. and a postdoc at the Machine Listening Group at MIT under the supervision of Barry Vercoe. My primary research interests revolve around making machines that can listen. I’ve done plenty of work on signal processing, machine learning and statistics as they relate to artificial perception, and in particular computational audition. I also love working on anything related to audio! The bulk of my work on audio is on source separation, and various machine learning approaches to traditional signal processing problems.
I am fortunate to have been associated with some amazing research labs. I used to work at MERL, and also spent some time at Interval Research and Starlab. Currently I’m also a visiting scientist at MIT’s McGovern Institute for Brain Research. In 2006 I was selected by MIT’s Technology Review as one of the year’s top young technology innovators. I’m a descendant of a long musical lineage dating to the early 1600s. My Erdös number is 5.
Selected Recent Publications (complete list here)
Smaragdis, P. 2009. Dynamic Range Extension using Interleaved Gains, in IEEE Transactions of Audio, Speech and Language Processing, to appear [PDF]
Smaragdis, P. 2009. Relative Pitch Tracking of Multiple Arbitrary Sounds. In Journal of the Acoustical Society of America, Volume 125, Issue 5, pp. 3406-3413 (May 2009) [PDF]
Shashanka, M.V., B. Raj and P. Smaragdis, 2008. Probabilistic Latent Variable Models as Non-Negative Factorizations. In special issue on Advances in Non-negative Matrix and Tensor Factorization, Computational Intelligence and Neuroscience Journal. May 2008. [PDF]
Smaragdis, P, B. Raj, and M.V. Shashanka, 2008. Sparse and shift-invariant feature extraction from non-negative data. In proceedings IEEE International Conference on Audio and Speech Signal Processing, Las Vegas, Nevada, USA. April 2008 Paper: [PDF]
Shashanka, M.V., B. Raj, P. Smaragdis, 2007. Sparse Overcomplete Latent Variable Decoposition of Counts Data. In Neural Information Processing Systems (NIPS), Vancouver, BC, Canada. December 2007. Paper: [PDF], technical supplement: [PDF]
Smaragdis, P. and M.V. Shashanka, 2007. A Framework for Secure Speech Recognition. In IEEE Transactions on Audio, Speech and Language Processing. May 2007. Paper: [PDF]
Shashanka, M.V., B. Raj, P. Smaragdis, 2007. Sparse Overcomplete Decomposition for Single Channel Speaker Separation. In proceedings IEEE International Conference on Audio and Speech Signal Processing, Honolulu, Hawaii, USA. 15-20 April 2007 Paper: [PDF]
Smaragdis, P. 2007. Convolutive Speech Bases and their Application to Speech Separation. In IEEE Transactions of Speech and Audio Processing. January 2007. Paper: [PDF]
Smaragdis, P. and P. Boufounos, 2007. Position and Trajectory Learning for Microphone Arrays, In IEEE Transactions on Speech and Audio Processing. January 2007. [PDF]
Smaragdis, P., B. Raj, and M.V. Shashanka, 2006, A probabilistic latent variable model for acoustic modeling, Advances in models for acoustic processing workshop, NIPS 2006. Paper: [PDF], Presentation: [PPT]
Smaragdis, P. Component based techniques for monophonic speech separation and recognition, in "Blind Speech Separation", S. Makino, T-W.Lee and H. Sawada (eds.) Blind Speech Separation, Springer. [Book Link]
