Publications

 


Papers


  1. François G. Germain,, Gautham J. Mysore, “Speaker and Noise Independent Online Single Channel Speech Enhancement”, to appear in the Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Brisbane, Australia. April 2015


  1. Dawen Liang, Matthew D. Hoffman, Gautham J. Mysore, “Speech Dereverberation using a Learned Speech Model”, to appear in the Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Brisbane, Australia. April 2015


  1. Minje Kim, Paris Smaragdis, Gautham J. Mysore, “Efficient Manifold Preserving Audio Source Separation using Locality Sensitive Hashing”, to appear in the Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Brisbane, Australia. April 2015


  1. Valkyrie Savage, Andrew Head, Björn Hartmann, Dan Goldman, Gautham J. Mysore, Wilmot Li, “Lamello: Passive Acoustic Sensing for Tangible Input Components”, to appear in the Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI), Seoul, Korea. April 2015


  1. Gautham J. Mysore, “Can We Automatically Transform Speech Recorded on Common Consumer Devices in Real-World Environments into Professional Production Quality Speech? - A Dataset, Insights, and Challenges”, to appear in the IEEE Signal Processing Letters

     WEBPAGE    DATASET


  1. Abe Davis, Michael Rubinstein, Neal Wadhwa, Gautham J. Mysore, Frédo Durand, William T. Freeman, “The Visual Microphone: Passive Recovery of Sound from Video”, in the Proceedings of SIGGRAPH, August 2014

     Extensive Press Coverage

     WEBPAGE    VIDEO


  1. François G. Germain, Gautham J. Mysore, “Stopping Criteria for Non-negative Matrix Factorization Based Supervised and Semi-Supervised Source Separation”, in the IEEE Signal Processing Letters, Vol. 21, No. 9, October 2014


  1. Nicolas Boulanger-Lewandowski, Gautham J. Mysore, Matthew Hoffman, “Exploiting Long-Term Temporal Dependencies in NMF using Recurrent Neural Networks with Application to Source Separation”, in the Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Florence, Italy. May 2014


  1. Dawen Liang, Daniel P. W. Ellis, Matthew Hoffman, Gautham J. Mysore, “Speech Decoloration based on the Product-of-Filters Model”, in the Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Florence, Italy. May 2014


  1. Paris Smaragdis, Cédric Févotte, Gautham J. Mysore, Nasser Mohammadiha, Matthew Hoffman, “Static and Dynamic Source Separation Using Nonnegative Factorizations: A unified view” in the IEEE Signal Processing Magazine Special Issue on Source Separation and Applications, May 2014


  1. Dawen Liang, Matthew Hoffman, Gautham J. Mysore, “A Generative Product of Filter Model of Audio”, in the Proceedings of the International Conference on Learning Representations (ICLR), Banff, Canada. April 2014

     CODE


  1. Nicholas J. Bryan, Gautham J. Mysore, Ge Wang, “ISSE: An Interactive Source Separation Editor”, in the Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI), Toronto, Canada. April 2014

     WEBPAGE    DEMO VIDEO    ADOBE MAX VIDEO    DEMOS    CODE    SISEC


  1. Nicholas J. Bryan, Gautham J. Mysore, Ge Wang, “Source Separation of Polyphonic Music with Interactive User-Feedback on a Piano Roll Display, in the Proceedings of the International Society of Music Information Retrieval Conference (ISMIR), Curitaba, Brazil. November 2013


  1. Zafar Rafii, François G. Germain, Dennis L. Sun, Gautham J. Mysore, “Combining Modeling of Singing Voice and Background Music for Automatic Separation of Musical Mixtures”, in the Proceedings of the International Society of Music Information Retrieval Conference (ISMIR), Curitaba, Brazil. November 2013


  1. Steve Rubin, Floraine Berthouzoz, Gautham J. Mysore, Wilmot Li, Maneesh Agrawala, “Content-Based Tools for Editing Audio Stories”, in the Proceedings of the ACM Symposium on User Interface Software and Technology (UIST), St. Andrews, Scotland. October 2013

     WEBPAGE    VIDEO    CODE    WEB APP    AUDIO RESULTS


  1. François G. Germain, Dennis L. Sun, Gautham J. Mysore, ”Speaker and Noise Independent Voice Activity Detection”, in the Proceedings of Interspeech, Lyon, France. August 2013

     Best Student Paper Award


  1. Nicholas J. Bryan, Gautham J. Mysore, “An Efficient Posterior Regularized Latent Variable Model for Interactive Source Separation”, in the Proceedings of the International Conference on Machine Learning (ICML), Atlanta, GA. June 2013

    AES Student Design Competition Gold Award

     WEBPAGE    DEMO VIDEO    ADOBE MAX VIDEO    DEMOS    CODE    SISEC


  1. Dennis L. Sun, Gautham J. Mysore, “Universal Speech Models for Speaker Independent Single Channel Source Separation”, in the Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vancouver, Canada. May 2013


  1. Nicholas J. Bryan, Gautham J. Mysore, ”Interactive Refinement of Supervised and Semi-supervised Sound Source Separation Estimates”, in the Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vancouver, Canada. May 2013

     WEBPAGE    SOUND EXAMPLES    CODE


  1. Steve Rubin, Floraine Berthouzoz, Gautham J. Mysore, Wilmot Li, Maneesh Agrawala, “UnderScore: Musical Underlays for Audio Stories”, in the Proceedings of the ACM Symposium on User Interface Software and Technology (UIST), Cambridge, MA. October 2012

     WEBPAGE    VIDEO    CODE


  1. Jinyu Han, Gautham J. Mysore, Bryan Pardo, “Language Informed Bandwidth Expansion”, in the Proceedings of the IEEE International Workshop on Machine Learning for Signal Processing (MLSP), Santander, Spain. September 2012

     SOUND EXAMPLES


  1. Zhiyao Duan, Gautham J. Mysore, Paris Smaragdis, “Speech Enhancement by Online Non-negative Spectrogram Decomposition in Non-stationary Noise Environments”, in the Proceedings of Interspeech, Portland, OR. September 2012

     SOUND EXAMPLES    NOISE DATA SET  


  1. Gautham J. Mysore, Maneesh Sahani, “Variational Inference in Non-negative Factorial Hidden Markov Models for Efficient Audio Source Separation”, in the Proceedings of the International Conference on Machine Learning (ICML), Edinburgh, Scotland. June 2012


  1. Paris Smaragdis, Gautham J. Mysore, “Following Musical Sources by Example”, in the Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Kyoto, Japan. March 2012

     Invited Paper


  1. Nicholas J. Bryan, Paris Smaragdis, Gautham J. Mysore, “Clustering and Synchronizing Multi-camera Video via Landmark Cross-correlation”, in the Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Kyoto, Japan. March 2012

     ADOBE MAX VIDEO


  1. Brian King, Paris Smaragdis, Gautham J. Mysore, “Noise-Robust Dynamic Time Warping Using PLCA Features”, in the Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Kyoto, Japan. March 2012

     ADOBE MAX VIDEO


  1. Gautham J. Mysore, Paris Smaragdis, “A Non-negative Approach to Language Informed Speech Separation”, in the Proceedings of the International Conference on Latent Variable Analysis and Signal Separation (LVA / ICA), Tel-Aviv, Israel. March 2012

     WEBPAGE    SOUND EXAMPLES


  1. Jinyu Han, Gautham J. Mysore, Bryan Pardo, “Audio Imputation Using the Non-negative Hidden Markov Model”, in the Proceedings of the International Conference on Latent Variable Analysis and Signal Separation (LVA / ICA), Tel-Aviv, Israel. March 2012

     WEBPAGE


  1. Juhan Nam, Gautham J. Mysore, Paris Smaragdis, “Sound Recognition in Mixtures”, in the Proceedings of the International Conference on Latent Variable Analysis and Signal Separation (LVA / ICA), Tel-Aviv, Israel. March 2012

   

  1. Zhiyao Duan, Gautham J. Mysore, Paris Smaragdis, “Online PLCA for Real-Time Semi-supervised Source Separation”, in the Proceedings of the International Conference on Latent Variable Analysis and Signal Separation (LVA / ICA), Tel-Aviv, Israel. March 2012

     NOISE DATA SET 


  1. Gautham J. Mysore, Paris Smaragdis, “A Convolutive Spectral Decomposition Approach to the Separation of Feedback from Target Speech”. In the Proceedings of the IEEE International Workshop on Machine Learning for Signal Processing (MLSP), Beijing, China. September 2011


  1. Gautham J. Mysore, Paris Smaragdis, “A Non-negative Approach to Semi-supervised Separation of Speech from Noise with the use of Temporal Dynamics”, in the Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Prague, Czech Republic. May 2011


  1. Gautham J. Mysore, Paris Smaragdis, Bhiksha Raj, “Non-negative Hidden Markov Modeling of Audio with Application to Source Separation”, in the Proceedings of the International Conference on Latent Variable Analysis and Signal Separation (LVA / ICA), St. Malo, France. September 2010

     Best Student Paper Award

     WEBPAGE    SOUND EXAMPLES


  1. Juhan Nam, Gautham J. Mysore, Joachim Ganseman, Kyogu Lee, Jonathan S. Abel, “A Super-Resolution Spectrogram Using Coupled PLCA”, in the Proceedings of Interspeech 2010, Makuhari, Japan. September 2010

     WEBPAGE    CODE


  1. Joachim Ganseman, Paul Scheunders, Gautham J. Mysore, Jonathan S. Abel, “Evaluation of a Score-Informed Source Separation System”, in the Proceedings of the International Society of Music Information Retrieval Conference (ISMIR), Utrecht, Netherlands. August 2010

     WEBPAGE


  1. Joachim Ganseman, Paul Scheunders, Gautham J. Mysore, Jonathan S. Abel “Source Separation by Score Synthesis”, in the Proceedings of the International Computer Music Conference (ICMC), New York, NY. June 2010

     WEBPAGE

   

  1. Paris Smaragdis, Gautham J. Mysore, “Separation by Humming”: User Guided Sound Extraction from Monophonic Mixtures” in the Proceedings of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), New Paltz, NY. October 2009

     WEBPAGE  VIDEO

  1. Gautham J. Mysore, Paris Smaragdis, “Relative Pitch Estimation of Multiple Instruments” in the Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Taipei, Taiwan. April 2009

     WEBPAGE

  1. Paris Smaragdis, Madhusudana Shashanka, Bhiksha Raj, Gautham J. Mysore, “Probabilistic Factorization of Non-Negative Data with Entropic Co-occurrence Constraints” in the Proceedings of the 8th International Conference on Independent Component Analysis and Signal Separation (ICA), Paraty, Brazil. March 2009

  2. Gautham J. Mysore, Ryan J. Cassidy, Julius O. Smith III, “Singer-Dependent Falsetto Detection for Live Vocal Processing Based on Support Vector Classification” in the Proceedings of the IEEE Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA. Oct. 2006

  3. Juan-Pablo Cáceres, Gautham J. Mysore, Jeffrey Treviño, “SCUBA: The Self-Contained Unified Bass Augmenter” in the Proceedings of the International Conference on New Interfaces for Musical Expression (NIME), Vancouver, Canada. May 2005




Abstracts / Extended Abstracts



  1. Nicholas J. Bryan, Gautham J. Mysore, Ge Wang, ”ISSE: An Interactive Source Separation Editor”, in the Neural Information Processing Systems (NIPS) Workshop on Machine Learning Open Source Software, Lake Tahoe, NV. December 2013

     WEBPAGE


  1. Minje Kim, Gautham J. Mysore, Paris Smaragdis, “Probabilistic Latent Component Sharing for the Separation of Non-Orthogonally Overlapping Sources”, in the Speech and Audio in the Northeast Workshop (SANE), Cambridge, MA. October 2013


  1. Nicholas J. Bryan, Gautham J. Mysore, ”Interactive User-Feedback for Sound Source Separation”, in the International Conference on Intelligent User Interfaces (IUI) Workshop on Interactive Machine Learning, Santa Monica, CA. March 2013

     WEBPAGE


  1. Gautham J. Mysore, “A Block Sparsity Approach to Multiple Dictionary Learning for Audio Modeling”, in the International Conference on Machine Learning (ICML) Workshop on Sparsity, Dictionaries, and Projections in Machine Learning and Signal Processing, Edinburgh, Scotland. June 2012


  1. Paris Smaragdis, Gautham J. Mysore, “Sound Separation by Humming”, in the Meeting of the Acoustical Society of America, Cancun, Mexico, November 2010


  1. Gautham J. Mysore, Paris Smaragdis, “Multipitch Estimation using Sparse Impulse Distributions and Instrument Specific Priors” in the International Conference on Machine Learning (ICML) Workshop on Sparse Methods for Music Audio, Montreal, Quebec. June 2009


  1. Ryan J. Cassidy, Gautham J. Mysore, “Automatic Detection of Head Voice in Sung Musical Signals via Machine Learning Classification of Time‐Varying Partial Intensities”, in the Meeting of the Acoustical Society of America, Honolulu, Hawaii, December 2006




Ph.D. Thesis


  1. Gautham J. Mysore, “A Non-negative Framework for Joint Modeling of Spectral Structure and Temporal Dynamics in Sound Mixtures”, Stanford University. June 2010

     Advisor: Julius O. Smith III

     Reading Committee: Paris Smaragdis, Malcolm Slaney, Robert Tibshirani 

     WEBPAGE




Patents - Issued



  1. Paris Smaragdis, Gautham J. Mysore, “User-Guided Audio Selection from Complex Sound Mixtures” - U.S Patent #8954175 issued in February 2015


  1. Nicholas J. Bryan, Paris Smaragdis, Gautham J. Mysore, “Clustering and Synchronizing Content” - U.S Patent #8924345 issued in December 2014


  1. Gautham J. Mysore, Paris Smaragdis, “Language Informed Source Separation” - U.S Patent #8843364 issued in September 2014


  1. Gautham J. Mysore, Paris Smaragdis, “Semi-supervised Source Separation using Non-negative Techniques” - U.S Patent #8812322 issued in August 2014


  1. Gautham J. Mysore, Paris Smaragdis, Brian King, “Noise Robust Template Matching” - U.S Patent #8775167 issued in July 2014


  1. Paris Smaragdis, Gautham J. Mysore, “System and Method for Acoustic Echo Cancellation using Spectral Decomposition ” - U.S. Patent #8724798 issued in May 2014


  1. Gautham J. Mysore, Paris Smaragdis, “Non-negative Hidden Markov Modeling of Signals” - U.S. Patent #8554553 issued in October 2013


  1. Paris Smaragdis, Gautham J. Mysore, “Method and Apparatus for Relative Pitch Tracking of Multiple Arbitrary Sounds ” - U.S. Patent #8380331 issued in February 2013



Patents - Pending



  1. François G. Germain, Gautham J. Mysore, “Acoustic Matching and Splicing of Sound Tracks” - U.S. patent filed in 2015


  1. Dawen Liang, Matthew D. Hoffman, Gautham J. Mysore, “Dereverberation Using a Learned Speech Model” - U.S. Patent filed in 2015


  1. François G. Germain, Gautham J. Mysore, “Performance Metric Based Stopping Criteria for Iterative Algorithms” - U.S. patent filed in 2014


  1. Nicolas Boulanger-Lewandowski, Gautham J. Mysore, Matthew Hoffman, “Non-negative Matrix Factorization Regularized by Recurrent Neural Networks for Audio Processing” - U.S. patent filed in 2014


  1. Minje Kim, Gautham J. Mysore, Paris Smaragdis, “Multichannel Sound Source Identification and Localization” - U.S. Patent filed in 2013


  1. Minje Kim, Paris Smaragdis, Gautham J. Mysore, “Pattern Matching of Sound Data using Hashing” - U.S. Patent filed in 2013


  1. Minje Kim, Paris Smaragdis, Gautham J. Mysore, “Irregular Pattern Identification using Landmark based Convolution” - U.S. Patent filed in 2013


  1. Dawen Liang, Matthew D. Hoffman, Gautham J. Mysore, “Sound Processing using a Product-of-Filters Model” - U.S. Patent filed in 2013


  1. Gautham J. Mysore, Paris Smaragdis, “Variable Sound Decomposition Masks” - U.S. Patent filed in 2013


  1. Dennis L. Sun, Gautham J. Mysore, “Joint Sound Model Generation Techniques” - U.S. Patent filed in 2013


  1. Dennis L. Sun, Gautham J. Mysore, “General Sound Decomposition Models” - U.S. Patent filed in 2013


  1. Nicholas J. Bryan, Gautham J. Mysore, “Sound Decomposition Techniques and User Interfaces” - U.S. Patent filed in 2013


  1. Brian King, Gautham J. Mysore, Paris Smaragdis, “Sound Feature Priority Alignment” - U.S. Patent filed in 2012


  1. Brian King, Gautham J. Mysore, Paris Smaragdis, “Sound Alignment Using Timing Information” - U.S. Patent filed in 2012


  1. Brian King, Gautham J. Mysore, Paris Smaragdis, “Sound Alignment User Interface” - U.S. Patent filed in 2012


  1. Brian King, Gautham J. Mysore, Paris Smaragdis, “Time Interval Sound Alignment” - U.S. Patent filed in 2012


  1. Brian King, Gautham J. Mysore, Paris Smaragdis, “Intelligent Speech Rate Modification” - U.S. Patent filed in 2012


  1. Gautham J. Mysore, Paris Smaragdis, Juhan Nam, “Sound Mixture Recognition” - U.S. Patent filed in 2012


  1. Gautham J. Mysore, Paris Smaragdis, Brian King, “Following Musical Sources by Example” - U.S. Patent filed in 2012


  1. Gautham J. Mysore, Paris Smaragdis, Zhiyao Duan, “Online Source Separation” - U.S. Patent filed in 2011



Home Page