Gautham Mysore

Principal Scientist

San Francisco

Gautham is a principal scientist and head of the Audio Research Group at Adobe Research in San Francisco. He is also an Adjunct Professor at Stanford University in the Center for Computer Research in Music and Acoustics (CCRMA). His research involves developing new machine learning and signal processing for a wide variety of real-world audio applications.

He received his Ph.D. (CCRMA), M.A. (CCRMA), and M.S. (Electrical Engineering) from Stanford University. He has previously been a visiting researcher at the Gatsby Computational Neuroscience Unit at the University College London. He has also previously spent time at Microsoft Research and the Department of Electrical Communication Engineering at the lndian Institute of Science.

Please visit his personal website for a complete list of publications.

 

Publications

Audio-Based Music Structure Analysis: Current Trends, Open Challenges, and Applications

Nieto, O., Mysore, G., Wang, C., Smith, J., Schlüter, J., Grill, T., McFee, B., Mysore, G. (Dec. 11, 2020)

Transactions of the International Society for Music Information Retrieval (TISMIR)

A Differentiable Perceptual Audio Metric Learned from Just Noticeable Differences

Manocha, P., Finkelstein, A., Zhang, R., Bryan, N., Mysore, G., Jin, Z. (Oct. 26, 2020)

Interspeech 2020

Controllable Neural Prosody Synthesis

Morrison, M., Jin, Z., Salamon, J., Bryan, N., Mysore, G. (Oct. 26, 2020)

Interspeech 2020

VoiceAssist: Guiding Users to High-Quality Voice Recordings

Seetharaman, P., Mysore, G., Pardo, B., Smaragdis, P., Gomes, C. (May. 4, 2019)

ACM Conference on Human Factors in Computing Systems (CHI)

B-Script: Transcript-based B-roll Video Editing with Recommendations

Huber, B., Shin, H., Russell, B., Wang, O., Mysore, G. (May. 4, 2019)

ACM Conference on Human Factors in Computing Systems (CHI)

Recent Advances in Music Signal Processing

Mueller, M., Pardo, B., Mysore, G., Valimaki, V. (Jan. 10, 2019)

IEEE Signal Processing Magazine

Temporal extensions of Nonnegative Matrix Factorization

Fevotte, C., Smaragdis, P., Mohammadiha, N., Mysore, G. (Aug. 3, 2018)

Book Chapter in Audio Source Separation and Speech Enhancement, Wiley, 2018

LoopMaker: Automatic Creation of Music Loops from Pre-recorded Music

Shi, K., Mysore, G. (Apr. 21, 2018)

ACM Conference on Human Factors in Computing Systems (CHI)

FFTNet: a Real-Time Speaker-Dependent Neural Vocoder

Jin, Z., Finkelstein, A., Mysore, G., Lu, J. (Apr. 15, 2018)

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

Blind Estimation of the Speech Transmission Index for Speech Quality Prediction

Seetharaman, P., Mysore, G., Smaragdis, P., Pardo, B. (Apr. 15, 2018)

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

Crowdsourced Pairwise-comparison for Source Separation Evaluation

Cartwright, M., Pardo, B., Mysore, G. (Apr. 15, 2018)

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

A System for Personalized Music Medley Creation

Shi, K., Mysore, G. (Mar. 11, 2018)

ACM IUI Workshop on Intelligent Music Interfaces for Listening and Creation (MILC)

Dynamic Non-negative Models for Audio Source Separation

Smaragdis, P., Mysore, G., Mohammadiha, N. (Mar. 3, 2018)

Book Chapter in Audio Source Separation, Springer

Re-visiting the Music Segmentation Problem with Crowdsourcing

Wang, C., Mysore, G., Dubnov, S. (Oct. 23, 2017)

International Society of Music Information Retrieval Conference (ISMIR)

AutoDub: Automatic Redubbing for Voiceover Editing

Venkataramani, S., Smaragdis, P., Mysore, G. (Oct. 22, 2017)

ACM Symposium on User Interface Software and Technology (UIST)

VoCo: text-based insertion and replacement in audio narration

Jin, Z., Mysore, G., DiVerdi, S., Lu, J., Finkelstein, A. (Jul. 31, 2017)

ACM Transactions on Graphics (SIGGRAPH)

Eulerian Video Magnification and Analysis

Wadhwa, N., Wu, H., Davis, A., Rubinstein, M., Shih, E., Mysore, G., Chen, J., Buyukozturk, O., Guttag, J., Freeman, W., Durand, F. (Jan. 1, 2017)

Communications of the ACM

Analysis of Prosody Increment Induced by Pitch Accents for Automatic Emphasis Correction

Zhang, Y., Mysore, G., Berthouzoz, F., Hasegawa-Johnson, M. (May. 24, 2016)

Speech Prosody

Structural Segmentation with the Variable Markov Oracle and Boundary Adjustment

Wang, C., Mysore, G. (Mar. 25, 2016)

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

Equalization Matching of Speech Recordings in Real-World Environments

Germain, F., Mysore, G., Fujioka, T. (Mar. 20, 2016)

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

Fast and Easy Crowdsourced Perceptual Audio Evaluation

Cartwright, M., Pardo, B., Mysore, G., Hoffman, M. (Mar. 20, 2016)

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

CUTE: a Concatenative Method for Voice Conversion Using Exemplar-based Unit Selection

Jin, Z., Finkelstein, A., DiVerdi, S., Lu, J., Mysore, G. (Mar. 1, 2016)

The 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Capture-Time Feedback for Recording Scripted Narration

Rubin, S., Berthouzoz, F., Mysore, G., Agrawala, M. (Nov. 8, 2015)

ACM Symposium on User Interface Software and Technology (UIST)

Speaker and Noise Independent Online Single Channel Speech Enhancement

Germain, F., Mysore, G. (Apr. 19, 2015)

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

Speech Dereverberation using a Learned Speech Model

Liang, D., Hoffman, M., Mysore, G. (Apr. 19, 2015)

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

Efficient Manifold Preserving Audio Source Separation using Locality Sensitive Hashing

Kim, M., Smaragdis, P., Mysore, G. (Apr. 19, 2015)

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

Lamello: Passive Acoustic Sensing for Tangible Input Components

Savage, V., Head, A., Hartmann, B., Goldman, D., Mysore, G., Li, W. (Apr. 18, 2015)

ACM Conference on Human Factors in Computing Systems (CHI)

The Visual Microphone: Passive Recovery of Sound from Video

Davis, A., Rubinstein, M., Wadhwa, N., Mysore, G., Durand, F., Freeman, W. (Aug. 12, 2014)

ACM Transactions on Graphics (SIGGRAPH)

Exploiting Long-Term Temporal Dependencies in NMF using Recurrent Neural Networks with Application to Source Separation

Boulanger-Lewandowski, N., Mysore, G., Hoffman, M. (May. 9, 2014)

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

Speech Decoloration based on the Product-of-Filters Model

Liang, D., Ellis, D., Hoffman, M., Mysore, G. (May. 9, 2014)

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

Static and Dynamic Source Separation Using Nonnegative Factorizations: A unified view

Smaragdis, P., Fevotte, C., Mysore, G., Mohammadiha, N., Hoffman, M. (May. 1, 2014)

IEEE Signal Processing Magazine Special Issue on Source Separation and Applications

ISSE: An Interactive Source Separation Editor

Bryan, N., Mysore, G., Wang, G. (Apr. 26, 2014)

ACM Human Factors in Computing Systems (CHI)

A Generative Product-of-Filters Model of Audio

Hoffman, M., Mysore, G. (Apr. 1, 2014)

Proceedings of the 2nd International Conference on Learning Representations (ICLR 2014), April 2014

Source Separation of Polyphonic Music With Interactive User-Feedback on a Piano Roll Display

Bryan, N., Mysore, G., Wang, G. (Nov. 4, 2013)

International Society for Music Information Retrieval Conference (ISMIR)

Combining Modeling of Singing Voice and Background Music for Automatic Separation of Musical Mixtures

Rafii, Z., Germain, F., Sun, D., Mysore, G. (Nov. 4, 2013)

International Society of Music Information Retrieval Conference (ISMIR)

Content-Based Tools for Editing Audio Stories

Rubin, S., Berthouzoz, F., Mysore, G., Li, W., Agrawala, M. (Oct. 1, 2013)

Proceedings of the 26th Annual ACM Symposium on User interface Software and Technology

Speaker and Noise Independent Voice Activity Detection

Germain, F., Sun, D., Mysore, G. (Aug. 25, 2013)

Best Student Paper Award

Interspeech

An Efficient Posterior Regularized Latent Variable Model for Interactive Sound Source Separation

Bryan, N., Mysore, G. (Jun. 16, 2013)

International Conference on Machine Learning (ICML)

Interactive Refinement Of Supervised And Semi-Supervised Sound Source Separation Estimates

Bryan, N., Mysore, G. (May. 1, 2013)

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

Universal Speech Models for Speaker Independent Single Channel Source Separation

Sun, D., Mysore, G. (May. 1, 2013)

ICASSP 2013 – Proceedings of the 38th International Conference on Acoustics, Speech, and Signal Processing, May 2013

Interactive User-feedback for Audio Source Separation

Bryan, N., Mysore, G. (Mar. 19, 2013)

In Proc. IUI 2013 - IEEE International Conference on Automatic Face and Gesture Recognition , March 19 - 22. Presented in the Interactive Machine Learning Workshop, 2013.

UnderScore: Musical Underlays for Audio Stories

Rubin, S., Berthouzoz, F., Mysore, G., Li, W., Agrawala, M. (Oct. 1, 2012)

Proceedings of the 25th annual ACM Symposium on User interface Software and Technology

Language Informed Bandwidth Expansion

Han, J., Mysore, G., Smaragdis, P. (Sep. 23, 2012)

IEEE International Workshop on Machine Learning for Signal Processing

Variational Inference in Non-negative Factorial Hidden Markov Models for Efficient Audio Source Separation

Mysore, G., Sahani, M. (Jun. 26, 2012)

Proceedings of the International Conference on Machine Learning (ICML)

Clustering and Synchronizing Multi-camera Video via Landmark Cross-Correlation

Bryan, N., Smaragdis, P., Mysore, G. (Mar. 25, 2012)

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

Following Musical Sources by Example

Smaragdis, P., Mysore, G. (Mar. 25, 2012)

ICASSP - IEEE International Conference on Acoustics, Speech, and Signal Processing , March 2012

Noise-Robust Dynamic Time Warping Using PLCA Features

King, B., Smaragdis, P., Mysore, G. (Mar. 25, 2012)

ICASSP - IEEE International Conference on Acoustics, Speech, and Signal Processing , March 2012

Following Musical Sources by Example

Smaragdis, P., Mysore, G. (Mar. 25, 2012)

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

A Non-negative Approach to Language Informed Speech Separation

Mysore, G., Smaragdis, P. (Mar. 12, 2012)

LVA/ICA - International Conference on Latent Variable Analysis and Signal Separation, March 2012

Online PLCA for Real-Time Semi-supervised Source Separation

Duan, Z., Mysore, G., Smaragdis, P. (Mar. 12, 2012)

LVA/ICA - International Conference on Latent Variable Analysis and Signal Separation, March 2012

Sound Recognition in Mixtures

Nam, J., Mysore, G., Smaragdis, P. (Mar. 12, 2012)

LVA/ICA - International Conference on Latent Variable Analysis and Signal Separation, March 2012

Audio Imputation Using the Non-negative Hidden Markov Model

Han, J., Mysore, G., Pardo, B. (Mar. 12, 2012)

LVA/ICA - International Conference on Latent Variable Analysis and Signal Separation, March 2012

A Convolutive Spectral Decomposition Approach to the Separation of Feedback from Target Speech

Mysore, G., Smaragdis, P. (Sep. 18, 2011)

MLSP - IEEE International Workshop on Machine Learning for Signal Processing , September 2011

A Non-Negative Approach to Semi-Supervised Separation of Speech from Noise with the Use of Temporal Dynamics

Mysore, G., Smaragdis, P. (May. 22, 2011)

ICASSP - IEEE International Conference on Acoustics, Speech, and Signal Processing , May 2011

Non-negative Hidden Markov Modeling of Audio with Application to Source Separation

Mysore, G., Smaragdis, P., Raj, B. (Sep. 27, 2010)

Best Student Paper Award

LVA/ICA - International Conference on Latent Variable Analysis and Signal Separation, September 2010

Separation by Humming: User Guided Sound Extraction from Monophonic Mixtures

Smaragdis, P., Mysore, G. (Oct. 18, 2009)

WASPAA - IEEE Workshop on Applications of Signal Processing to Audio and Acoustics , October 2009

Multipitch Estimation using Sparse Impulse Distributions and Instrument Specific Priors

Mysore, G., Smaragdis, P. (Jun. 18, 2009)

IMCL - International Conference on Machine Learning (ICML) Workshop on Sparse Methods for Music Audio , June 2009

Probabilistic Factorization of Non-Negative Data with Entropic Co-occurrence Constraints

Smaragdis, P., Shashanka, M., Raj, B., Mysore, G. (Mar. 15, 2009)

ICA - International Conference on Independent Component Analysis and Signal Separation , March 2009

News