Click here for see the full list of upcoming events.
Thursday, Aug 06, 2015
Real-world Audio Source Separation
This meeting is hosted/sponsored by IEEE SPS Chapter
Dr. Gautham J. Mysore
Senior Research Scientist, Adobe Research
AMD Commons C-6/7/8, 991 Stewart Dr., Sunnyvale, CA (map or Google Maps)
6:30pm: Networking/Light Dinner
Free. Donation accepted for food.
Audio source separation algorithms aim to take a recording of a mixture of sound sources as an input and provide the separated sources as outputs. This is useful for a number of applications such as denoising in the presence of complex noises, processing individual instruments in a mixture, automatic karaoke, extracting dialogue from old films to provide a higher quality soundtrack, and upmixing mono recordings to multi-channel recordings. Algorithmically, this is an ill-posed and challenging problem. However, by making use of easily available high level information, generic training data, and user interaction, we can greatly constrain the problem. In this talk, I will discuss a number of techniques that use such constraints with the goal of performing real-world audio source separation.
Gautham J. Mysore is a senior research scientist at Adobe Research and a consulting assistant professor at the Center for Computer Research in Music and Acoustics (CCRMA) at Stanford University. His research involves developing new signal processing and machine learning algorithms for a wide variety of real-world audio applications. He received an M.A. and Ph.D. from CCRMA in 2005 and 2010 respectively, and an M.S. from the electrical engineering department at Stanford in 2008. He has previously been a visiting researcher at the Gatsby Computational Neuroscience Unit at the University College London, and has previously spent time at Microsoft Research and the department of Electrical Communication Engineering at the Indian Institute of Science. He is currently a member of the IEEE Technical Committee on Audio and Acoustic Signal Processing and a vice chair of the AES Technical Committee on Semantic Audio Analysis.
Link to the open source interactive source separation editor:
"Universal Speech Models for Speaker Independent Single Channel Source Separation"
Dennis Sun, Gautham J. Mysore, ICASSP 2013
"Source Separation by Score Synthesis"
Joachim Ganseman, Paul Scheunders, Gautham J. Mysore, Jonathan S. Abel, ICMC 2010
"'Separation by Humming': User Guided Extraction from Monophonic Mixtures"
Paris Smaragdis, Gautham J. Mysore, WASPAA 2009
"An Efficient Posterior Regularized Latent Variable Model for Interactive Source Separation"
Nicholas J. Bryan, Gautham J. Mysore, ICML 2013
"Sound Recognition in Mixtures"
Juhan Nam, Gautham J. Mysore, Paris Smaragdis, LVA/ICA 2012
"Noise-Robust Dynamic Time Warping Using PLCA Features"
Brian King, Paris Smaragdis, Gautham J. Mysore, ICASSP 2012
Links to all of Gautham Mysore's papers including the above.
* from-left: Radhakrishna Giduthuri, Gautham Mysore
Subscribe to future announcements: link