Some Demos

Contact info:
Siebel Center for Computer Science
201 N. Goodwin Ave.
Urbana, IL, 61801, USA (map)
I’m a professor and associate head in the CS department at the University of Illinois Urbana-Champaign (and an affiliate professor in ECE).  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 novel machine learning approaches for traditional signal processing problems.  I also helped create and manage the CS side of the CS+Music program.

I am fortunate to have been associated with some amazing research labs. I completed my masters, Ph.D. and a postdoc at the Machine Listening Group at the MIT Media Lab under the supervision of Barry Vercoe. I currently work with AWS as an Amazon Scholar, previously I started Adobe Research's audio research, before that I was at MERL, and have spent some time at Interval Research and Starlab. I was 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 an IEEE fellow, was an IEEE Distinguished Lecturer for 2016-2017, and I am the Editor-in-Chief for the ACM/IEEE Transactions on Audio, Speech, and Language Processing. I've previously chaired the IEEE SPS Audio and Acoustic Signal Processing Technical Committee, the IEEE SPS Machine Learning for Signal Processing Technical Committee, the IEEE SPS Data Science Initiative, and I've served in the IEEE SPS Board of Governors.

I’m a descendant of a long music academic lineage dating to the early 1600s. My Erdös number is 4. You can get my academic stats here, and some of my (US) patents here.  If you are curious, here's my CV.
Selected Offerings (complete list here)

Casebeer, J., N. Bryan, and P. Smaragdis. Meta-AF: Meta-Learning for Adaptive Filters.  Under review ACM/IEEE TASLP [Paper] [Video] [Site]

Subramani, K. and P, Smaragdis.  Point Cloud Audio Processing, in proceedings of IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, Mohonk Mountain House, New Paltz, NY, 2021. [PDFBest Paper Award

E. Tzinis, S. Venkataramani, and P. Smaragdis. Usupervised Deep Clustering for Source Separation: Direct Learning from Mixtures Using Spatial Information, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2018, Brighton, UK. [PDF]

Kim, M. and P. Smaragdis. Bitwise Neural Networks for Efficient Single-Channel Source Separation, in Workshop for Audio Signal Processing, NIPS 2017 [PDF]

Venkataramani, S., J. Casebeer, and P. Smaragdis. Adaptive Front-ends for End-to-end Source Separation, in Workshop for Audio Signal Processing, NIPS 2017 [PDF]

Venkataramani, S., Y.C. Sübakan, and P. Smaragdis. 2017. A Neural Network Alternative to Convolutive Audio Models For Source Separation. 2017. In IEEE Workshop on Machine Learning for Signal Processing (MLSP), Tokyo, Japan, September. 2017.[PDF]

Correa Carvalho, R.G., and P. Smaragdis. 2017. Towards End-to-end Polyphonic Music Transcription: Transforming Music Audio Directly to a Score, in IEEE Workshop for Applications of Signal Processing to Audio and Acoustics (WASPAA), New Paltz, NY, USA. October 2017. [PDF]

Huang, P.-S., M. Kim, M. Hasegawa-Johnson, P. Smaragdis. 2015. Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation. In IEEE Transactions of Audio Speech and Language Processing, to appear [PDF] IEEE SPS Best Paper Award

Sübakan, Y.C., J. Traa and P. Smaragdis. 2014. Spectral Learning of Mixture of Hidden Markov Models, in Neural Information Processing Systems (NIPS) 2014. Montreal, Canada. [PDF]

Huang, P-S., M. Kim, M. Hasegawa-Johnson, P. Smaragdis. 2014. Deep Learning for Monaural Speech Separation, in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Florence, Italy. 2014 [PDF]

Smaragdis, P., C. Fevotte, G. Mysore, N. Mohammadiha, M. Hoffman 2014. Static and Dynamic Source Separation Using Nonnegative Factorizations: A unified view, in IEEE Signal Processing Magazine, May 2014 [PDF]

Smaragdis, P. 2013. Keynote slides from WASPAA 2013 [PDF] (includes embedded audio files when opened with Acrobat Reader)

Mohammadiha, N., P. Smaragdis and A. Leijon. 2013 Supervised and Unsupervised Speech Enhancement Using Nonnegative Matrix Factorization, in IEEE Transactions on Audio, Speech and Signal Processing, Volume 21, No. 10, October 2013. [PDF] IEEE Best Paper Award

Smaragdis, P. and M. Kim. 2013. Non-Negative Matrix Factorization for Irregularly-Spaced Transforms, in IEEE Workshop for Applications of Signal Processing in Audio and Acoustics. New Paltz, NY. October 2013. [PDF]

Kim, M. and P. Smaragdis. 2013. Manifold Preserving Hierarchical Topic Models for Quantization and Approximation, in International Conference on Machine Learning, Atlanta, GA. June 2013. [PDF]

M.A. Pathak, B. Raj, S. Rane, P. Smaragdis. 2013. Privacy Preserving Speech Processing [Draft PDF][Final PDF]

Smaragdis, P. 2012. Keynote slides from LVA/ICA 2012 [PDF] [PPT]

Smaragdis, P. 2011. Approximate nearest-subspace representations for sound mixtures. In Proceedings International Conference on Acoustics, Speech and Signal Processing (ICASSP). Prague, Czech Republic, May, 2011 [PDF]

Mysore, G., Smaragdis, and B. Raj. 2010. Non-negative hidden Markov modeling of audio with application to source separation. In 9th international conference on Latent Variable Analysis and Signal Separation (LCA/ICA). St. Malo, France. September, 2010 [PDF] Best paper award

Smaragdis, P. and B. Raj. 2010. The Markov selection model for concurrent speech recognition. In IEEE international workshop on Machine Learning for Signal Processing (MLSP). Kittilä, Finland. August 2010 [PDF]

Smaragdis, P., M. Shashanka, and B. Raj. 2009. A sparse non-parametric approach for single channel separation of known sounds. In in Neural Information Processing Systems. Vancouver, BC, Canada. December 2009. [PDF]

Smaragdis, P. 2009. User guided audio selection from complex sound mixtures. in the 22nd ACM Symposium on User Interface Software and Technology (UIST 09). Victoria, BC, Canada, October 2009. [PDF]

Smaragdis, P. 2009. Dynamic Range Extension using Interleaved Gains, in IEEE Transactions of Audio, Speech and Language Processing, July 2009. [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, P. Smaragdis, 2007. Sparse Overcomplete Latent Variable Decomposition 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]

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., 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]