Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Rif A. Saurous

Rif A. Saurous

tfp.mcmc: Modern Markov Chain Monte Carlo Tools Built for Modern Hardware


Feb 04, 2020
Junpeng Lao, Christopher Suter, Ian Langmore, Cyril Chimisov, Ashish Saxena, Pavel Sountsov, Dave Moore, Rif A. Saurous, Matthew D. Hoffman, Joshua V. Dillon

* Based on extended abstract submitted to PROBPROG 2020 
  Access Paper or Ask Questions

Coincidence, Categorization, and Consolidation: Learning to Recognize Sounds with Minimal Supervision


Nov 14, 2019
Aren Jansen, Daniel P. W. Ellis, Shawn Hershey, R. Channing Moore, Manoj Plakal, Ashok C. Popat, Rif A. Saurous

Figure 1 for Coincidence, Categorization, and Consolidation: Learning to Recognize Sounds with Minimal Supervision
Figure 2 for Coincidence, Categorization, and Consolidation: Learning to Recognize Sounds with Minimal Supervision
Figure 3 for Coincidence, Categorization, and Consolidation: Learning to Recognize Sounds with Minimal Supervision
Figure 4 for Coincidence, Categorization, and Consolidation: Learning to Recognize Sounds with Minimal Supervision
* This extended version of a ICASSP 2020 submission under same title has an added figure and additional discussion for easier consumption 
  Access Paper or Ask Questions

Automatically Batching Control-Intensive Programs for Modern Accelerators


Oct 23, 2019
Alexey Radul, Brian Patton, Dougal Maclaurin, Matthew D. Hoffman, Rif A. Saurous

Figure 1 for Automatically Batching Control-Intensive Programs for Modern Accelerators
Figure 2 for Automatically Batching Control-Intensive Programs for Modern Accelerators
Figure 3 for Automatically Batching Control-Intensive Programs for Modern Accelerators
Figure 4 for Automatically Batching Control-Intensive Programs for Modern Accelerators
* 10 pages; under review for Systems and Machine Learning 2020 
  Access Paper or Ask Questions

Simple, Distributed, and Accelerated Probabilistic Programming


Nov 29, 2018
Dustin Tran, Matthew Hoffman, Dave Moore, Christopher Suter, Srinivas Vasudevan, Alexey Radul, Matthew Johnson, Rif A. Saurous

Figure 1 for Simple, Distributed, and Accelerated Probabilistic Programming
Figure 2 for Simple, Distributed, and Accelerated Probabilistic Programming
Figure 3 for Simple, Distributed, and Accelerated Probabilistic Programming
Figure 4 for Simple, Distributed, and Accelerated Probabilistic Programming
* Appears in Neural Information Processing Systems, 2018. Code available at http://bit.ly/2JpFipt 
  Access Paper or Ask Questions

VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking


Oct 27, 2018
Quan Wang, Hannah Muckenhirn, Kevin Wilson, Prashant Sridhar, Zelin Wu, John Hershey, Rif A. Saurous, Ron J. Weiss, Ye Jia, Ignacio Lopez Moreno

Figure 1 for VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking
Figure 2 for VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking
Figure 3 for VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking
Figure 4 for VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking
* To be submitted to ICASSP 2019 
  Access Paper or Ask Questions

Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron


Mar 24, 2018
RJ Skerry-Ryan, Eric Battenberg, Ying Xiao, Yuxuan Wang, Daisy Stanton, Joel Shor, Ron J. Weiss, Rob Clark, Rif A. Saurous

Figure 1 for Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron
Figure 2 for Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron
Figure 3 for Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron
Figure 4 for Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron

  Access Paper or Ask Questions

Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis


Mar 23, 2018
Yuxuan Wang, Daisy Stanton, Yu Zhang, RJ Skerry-Ryan, Eric Battenberg, Joel Shor, Ying Xiao, Fei Ren, Ye Jia, Rif A. Saurous

Figure 1 for Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
Figure 2 for Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
Figure 3 for Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
Figure 4 for Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis

  Access Paper or Ask Questions

On Using Backpropagation for Speech Texture Generation and Voice Conversion


Mar 08, 2018
Jan Chorowski, Ron J. Weiss, Rif A. Saurous, Samy Bengio

Figure 1 for On Using Backpropagation for Speech Texture Generation and Voice Conversion
Figure 2 for On Using Backpropagation for Speech Texture Generation and Voice Conversion
Figure 3 for On Using Backpropagation for Speech Texture Generation and Voice Conversion
Figure 4 for On Using Backpropagation for Speech Texture Generation and Voice Conversion
* Accepted to ICASSP 2018 
  Access Paper or Ask Questions

Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions


Feb 16, 2018
Jonathan Shen, Ruoming Pang, Ron J. Weiss, Mike Schuster, Navdeep Jaitly, Zongheng Yang, Zhifeng Chen, Yu Zhang, Yuxuan Wang, RJ Skerry-Ryan, Rif A. Saurous, Yannis Agiomyrgiannakis, Yonghui Wu

Figure 1 for Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
Figure 2 for Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
Figure 3 for Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
Figure 4 for Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
* Accepted to ICASSP 2018 
  Access Paper or Ask Questions

Fixing a Broken ELBO


Feb 13, 2018
Alexander A. Alemi, Ben Poole, Ian Fischer, Joshua V. Dillon, Rif A. Saurous, Kevin Murphy

Figure 1 for Fixing a Broken ELBO
Figure 2 for Fixing a Broken ELBO
Figure 3 for Fixing a Broken ELBO
Figure 4 for Fixing a Broken ELBO
* 21 pages, 9 figures 
  Access Paper or Ask Questions

Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks


Dec 08, 2017
Shankar Krishnan, Ying Xiao, Rif A. Saurous

Figure 1 for Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks
Figure 2 for Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks
Figure 3 for Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks
Figure 4 for Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks

  Access Paper or Ask Questions

TensorFlow Distributions


Nov 28, 2017
Joshua V. Dillon, Ian Langmore, Dustin Tran, Eugene Brevdo, Srinivas Vasudevan, Dave Moore, Brian Patton, Alex Alemi, Matt Hoffman, Rif A. Saurous

Figure 1 for TensorFlow Distributions
Figure 2 for TensorFlow Distributions
Figure 3 for TensorFlow Distributions

  Access Paper or Ask Questions

Unsupervised Learning of Semantic Audio Representations


Nov 06, 2017
Aren Jansen, Manoj Plakal, Ratheet Pandya, Daniel P. W. Ellis, Shawn Hershey, Jiayang Liu, R. Channing Moore, Rif A. Saurous

Figure 1 for Unsupervised Learning of Semantic Audio Representations
Figure 2 for Unsupervised Learning of Semantic Audio Representations
Figure 3 for Unsupervised Learning of Semantic Audio Representations
* Submitted to ICASSP 2018 
  Access Paper or Ask Questions

Uncovering Latent Style Factors for Expressive Speech Synthesis


Nov 01, 2017
Yuxuan Wang, RJ Skerry-Ryan, Ying Xiao, Daisy Stanton, Joel Shor, Eric Battenberg, Rob Clark, Rif A. Saurous

Figure 1 for Uncovering Latent Style Factors for Expressive Speech Synthesis
Figure 2 for Uncovering Latent Style Factors for Expressive Speech Synthesis
Figure 3 for Uncovering Latent Style Factors for Expressive Speech Synthesis
* Submitted to NIPS ML4Audio workshop and ICASSP 
  Access Paper or Ask Questions

Tacotron: Towards End-to-End Speech Synthesis


Apr 06, 2017
Yuxuan Wang, RJ Skerry-Ryan, Daisy Stanton, Yonghui Wu, Ron J. Weiss, Navdeep Jaitly, Zongheng Yang, Ying Xiao, Zhifeng Chen, Samy Bengio, Quoc Le, Yannis Agiomyrgiannakis, Rob Clark, Rif A. Saurous

Figure 1 for Tacotron: Towards End-to-End Speech Synthesis
Figure 2 for Tacotron: Towards End-to-End Speech Synthesis
Figure 3 for Tacotron: Towards End-to-End Speech Synthesis
Figure 4 for Tacotron: Towards End-to-End Speech Synthesis
* Submitted to Interspeech 2017. v2 changed paper title to be consistent with our conference submission (no content change other than typo fixes) 
  Access Paper or Ask Questions

Deep Probabilistic Programming


Mar 07, 2017
Dustin Tran, Matthew D. Hoffman, Rif A. Saurous, Eugene Brevdo, Kevin Murphy, David M. Blei

Figure 1 for Deep Probabilistic Programming
Figure 2 for Deep Probabilistic Programming
Figure 3 for Deep Probabilistic Programming
Figure 4 for Deep Probabilistic Programming
* Appears in International Conference on Learning Representations, 2017. A companion webpage for this paper is available at http://edwardlib.org/iclr2017 
  Access Paper or Ask Questions

Scalable Learning of Non-Decomposable Objectives


Mar 01, 2017
Elad ET. Eban, Mariano Schain, Alan Mackey, Ariel Gordon, Rif A. Saurous, Gal Elidan

Figure 1 for Scalable Learning of Non-Decomposable Objectives
Figure 2 for Scalable Learning of Non-Decomposable Objectives
Figure 3 for Scalable Learning of Non-Decomposable Objectives

  Access Paper or Ask Questions

CNN Architectures for Large-Scale Audio Classification


Jan 10, 2017
Shawn Hershey, Sourish Chaudhuri, Daniel P. W. Ellis, Jort F. Gemmeke, Aren Jansen, R. Channing Moore, Manoj Plakal, Devin Platt, Rif A. Saurous, Bryan Seybold, Malcolm Slaney, Ron J. Weiss, Kevin Wilson

Figure 1 for CNN Architectures for Large-Scale Audio Classification
Figure 2 for CNN Architectures for Large-Scale Audio Classification
Figure 3 for CNN Architectures for Large-Scale Audio Classification
Figure 4 for CNN Architectures for Large-Scale Audio Classification
* Accepted for publication at ICASSP 2017 Changes: Added definitions of mAP, AUC, and d-prime. Updated mAP/AUC/d-prime numbers for Audio Set based on changes of latest Audio Set revision. Changed wording to fit 4 page limit with new additions 
  Access Paper or Ask Questions

AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech


Nov 28, 2016
Brian Patton, Yannis Agiomyrgiannakis, Michael Terry, Kevin Wilson, Rif A. Saurous, D. Sculley

Figure 1 for AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech
Figure 2 for AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech
Figure 3 for AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech
Figure 4 for AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech
* 4 pages, 2 figures, 2 tables, NIPS 2016 End-to-end Learning for Speech and Audio Processing Workshop 
  Access Paper or Ask Questions

Trainable Frontend For Robust and Far-Field Keyword Spotting


Jul 19, 2016
Yuxuan Wang, Pascal Getreuer, Thad Hughes, Richard F. Lyon, Rif A. Saurous

Figure 1 for Trainable Frontend For Robust and Far-Field Keyword Spotting
Figure 2 for Trainable Frontend For Robust and Far-Field Keyword Spotting
Figure 3 for Trainable Frontend For Robust and Far-Field Keyword Spotting
Figure 4 for Trainable Frontend For Robust and Far-Field Keyword Spotting

  Access Paper or Ask Questions