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 Yossi Adi

Yossi Adi

Differentiable Model Compression via Pseudo Quantization Noise


Apr 20, 2021
Alexandre Défossez, Yossi Adi, Gabriel Synnaeve

Figure 1 for Differentiable Model Compression via Pseudo Quantization Noise
Figure 2 for Differentiable Model Compression via Pseudo Quantization Noise
Figure 3 for Differentiable Model Compression via Pseudo Quantization Noise
Figure 4 for Differentiable Model Compression via Pseudo Quantization Noise

  Access Paper or Ask Questions

Speech Resynthesis from Discrete Disentangled Self-Supervised Representations


Apr 02, 2021
Adam Polyak, Yossi Adi, Jade Copet, Eugene Kharitonov, Kushal Lakhotia, Wei-Ning Hsu, Abdelrahman Mohamed, Emmanuel Dupoux

Figure 1 for Speech Resynthesis from Discrete Disentangled Self-Supervised Representations
Figure 2 for Speech Resynthesis from Discrete Disentangled Self-Supervised Representations
Figure 3 for Speech Resynthesis from Discrete Disentangled Self-Supervised Representations
Figure 4 for Speech Resynthesis from Discrete Disentangled Self-Supervised Representations

  Access Paper or Ask Questions

Generative Spoken Language Modeling from Raw Audio


Feb 01, 2021
Kushal Lakhotia, Evgeny Kharitonov, Wei-Ning Hsu, Yossi Adi, Adam Polyak, Benjamin Bolte, Tu-Anh Nguyen, Jade Copet, Alexei Baevski, Adelrahman Mohamed, Emmanuel Dupoux

Figure 1 for Generative Spoken Language Modeling from Raw Audio
Figure 2 for Generative Spoken Language Modeling from Raw Audio
Figure 3 for Generative Spoken Language Modeling from Raw Audio
Figure 4 for Generative Spoken Language Modeling from Raw Audio

  Access Paper or Ask Questions

High Fidelity Speech Regeneration with Application to Speech Enhancement


Jan 31, 2021
Adam Polyak, Lior Wolf, Yossi Adi, Ori Kabeli, Yaniv Taigman

Figure 1 for High Fidelity Speech Regeneration with Application to Speech Enhancement
Figure 2 for High Fidelity Speech Regeneration with Application to Speech Enhancement
Figure 3 for High Fidelity Speech Regeneration with Application to Speech Enhancement

  Access Paper or Ask Questions

Single channel voice separation for unknown number of speakers under reverberant and noisy settings


Nov 04, 2020
Shlomo E. Chazan, Lior Wolf, Eliya Nachmani, Yossi Adi

Figure 1 for Single channel voice separation for unknown number of speakers under reverberant and noisy settings
Figure 2 for Single channel voice separation for unknown number of speakers under reverberant and noisy settings
Figure 3 for Single channel voice separation for unknown number of speakers under reverberant and noisy settings
Figure 4 for Single channel voice separation for unknown number of speakers under reverberant and noisy settings

  Access Paper or Ask Questions

Fairness in the Eyes of the Data: Certifying Machine-Learning Models


Sep 03, 2020
Shahar Segal, Yossi Adi, Benny Pinkas, Carsten Baum, Chaya Ganesh, Joseph Keshet

Figure 1 for Fairness in the Eyes of the Data: Certifying Machine-Learning Models
Figure 2 for Fairness in the Eyes of the Data: Certifying Machine-Learning Models
Figure 3 for Fairness in the Eyes of the Data: Certifying Machine-Learning Models
Figure 4 for Fairness in the Eyes of the Data: Certifying Machine-Learning Models

  Access Paper or Ask Questions

Unsupervised Cross-Domain Singing Voice Conversion


Aug 06, 2020
Adam Polyak, Lior Wolf, Yossi Adi, Yaniv Taigman

Figure 1 for Unsupervised Cross-Domain Singing Voice Conversion
Figure 2 for Unsupervised Cross-Domain Singing Voice Conversion
Figure 3 for Unsupervised Cross-Domain Singing Voice Conversion

  Access Paper or Ask Questions

Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation


Aug 06, 2020
Felix Kreuk, Joseph Keshet, Yossi Adi

Figure 1 for Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation
Figure 2 for Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation
Figure 3 for Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation
Figure 4 for Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation
* Interspeech 2020 paper 
  Access Paper or Ask Questions

Real Time Speech Enhancement in the Waveform Domain


Jun 23, 2020
Alexandre Defossez, Gabriel Synnaeve, Yossi Adi

Figure 1 for Real Time Speech Enhancement in the Waveform Domain
Figure 2 for Real Time Speech Enhancement in the Waveform Domain
Figure 3 for Real Time Speech Enhancement in the Waveform Domain
Figure 4 for Real Time Speech Enhancement in the Waveform Domain

  Access Paper or Ask Questions

Voice Separation with an Unknown Number of Multiple Speakers


Feb 29, 2020
Eliya Nachmani, Yossi Adi, Lior Wolf

Figure 1 for Voice Separation with an Unknown Number of Multiple Speakers
Figure 2 for Voice Separation with an Unknown Number of Multiple Speakers
Figure 3 for Voice Separation with an Unknown Number of Multiple Speakers
Figure 4 for Voice Separation with an Unknown Number of Multiple Speakers

  Access Paper or Ask Questions

On the generalization of bayesian deep nets for multi-class classification


Feb 23, 2020
Yossi Adi, Yaniv Nemcovsky, Alex Schwing, Tamir Hazan

Figure 1 for On the generalization of bayesian deep nets for multi-class classification
Figure 2 for On the generalization of bayesian deep nets for multi-class classification
Figure 3 for On the generalization of bayesian deep nets for multi-class classification
Figure 4 for On the generalization of bayesian deep nets for multi-class classification

  Access Paper or Ask Questions

Phoneme Boundary Detection using Learnable Segmental Features


Feb 16, 2020
Felix Kreuk, Yaniv Sheena, Joseph Keshet, Yossi Adi

Figure 1 for Phoneme Boundary Detection using Learnable Segmental Features
Figure 2 for Phoneme Boundary Detection using Learnable Segmental Features
Figure 3 for Phoneme Boundary Detection using Learnable Segmental Features
Figure 4 for Phoneme Boundary Detection using Learnable Segmental Features

  Access Paper or Ask Questions

Hide and Speak: Deep Neural Networks for Speech Steganography


Feb 07, 2019
Felix Kreuk, Yossi Adi, Bhiksha Raj, Rita Singh, Joseph Keshet

Figure 1 for Hide and Speak: Deep Neural Networks for Speech Steganography
Figure 2 for Hide and Speak: Deep Neural Networks for Speech Steganography
Figure 3 for Hide and Speak: Deep Neural Networks for Speech Steganography
Figure 4 for Hide and Speak: Deep Neural Networks for Speech Steganography

  Access Paper or Ask Questions

To Reverse the Gradient or Not: An Empirical Comparison of Adversarial and Multi-task Learning in Speech Recognition


Dec 13, 2018
Yossi Adi, Neil Zeghidour, Ronan Collobert, Nicolas Usunier, Vitaliy Liptchinsky, Gabriel Synnaeve

Figure 1 for To Reverse the Gradient or Not: An Empirical Comparison of Adversarial and Multi-task Learning in Speech Recognition
Figure 2 for To Reverse the Gradient or Not: An Empirical Comparison of Adversarial and Multi-task Learning in Speech Recognition
Figure 3 for To Reverse the Gradient or Not: An Empirical Comparison of Adversarial and Multi-task Learning in Speech Recognition

  Access Paper or Ask Questions

Out-of-Distribution Detection using Multiple Semantic Label Representations


Oct 21, 2018
Gabi Shalev, Yossi Adi, Joseph Keshet

Figure 1 for Out-of-Distribution Detection using Multiple Semantic Label Representations
Figure 2 for Out-of-Distribution Detection using Multiple Semantic Label Representations
Figure 3 for Out-of-Distribution Detection using Multiple Semantic Label Representations
Figure 4 for Out-of-Distribution Detection using Multiple Semantic Label Representations

  Access Paper or Ask Questions

Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring


Jun 11, 2018
Yossi Adi, Carsten Baum, Moustapha Cisse, Benny Pinkas, Joseph Keshet

Figure 1 for Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring
Figure 2 for Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring
Figure 3 for Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring
Figure 4 for Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring

  Access Paper or Ask Questions

Fooling End-to-end Speaker Verification by Adversarial Examples


Feb 16, 2018
Felix Kreuk, Yossi Adi, Moustapha Cisse, Joseph Keshet

Figure 1 for Fooling End-to-end Speaker Verification by Adversarial Examples
Figure 2 for Fooling End-to-end Speaker Verification by Adversarial Examples
Figure 3 for Fooling End-to-end Speaker Verification by Adversarial Examples

  Access Paper or Ask Questions

Houdini: Fooling Deep Structured Prediction Models


Jul 17, 2017
Moustapha Cisse, Yossi Adi, Natalia Neverova, Joseph Keshet

Figure 1 for Houdini: Fooling Deep Structured Prediction Models
Figure 2 for Houdini: Fooling Deep Structured Prediction Models
Figure 3 for Houdini: Fooling Deep Structured Prediction Models
Figure 4 for Houdini: Fooling Deep Structured Prediction Models
* 12 pages, 8 figures, under review 
  Access Paper or Ask Questions

Learning Similarity Functions for Pronunciation Variations


Jun 18, 2017
Einat Naaman, Yossi Adi, Joseph Keshet

Figure 1 for Learning Similarity Functions for Pronunciation Variations
Figure 2 for Learning Similarity Functions for Pronunciation Variations
Figure 3 for Learning Similarity Functions for Pronunciation Variations
Figure 4 for Learning Similarity Functions for Pronunciation Variations

  Access Paper or Ask Questions

Automatic Measurement of Pre-aspiration


Jun 15, 2017
Yaniv Sheena, Míša Hejná, Yossi Adi, Joseph Keshet

Figure 1 for Automatic Measurement of Pre-aspiration
Figure 2 for Automatic Measurement of Pre-aspiration
Figure 3 for Automatic Measurement of Pre-aspiration
Figure 4 for Automatic Measurement of Pre-aspiration

  Access Paper or Ask Questions

Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks


Feb 09, 2017
Yossi Adi, Einat Kermany, Yonatan Belinkov, Ofer Lavi, Yoav Goldberg

Figure 1 for Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks
Figure 2 for Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks
Figure 3 for Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks
Figure 4 for Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks

  Access Paper or Ask Questions

Automatic measurement of vowel duration via structured prediction


Oct 26, 2016
Yossi Adi, Joseph Keshet, Emily Cibelli, Erin Gustafson, Cynthia Clopper, Matthew Goldrick

Figure 1 for Automatic measurement of vowel duration via structured prediction
Figure 2 for Automatic measurement of vowel duration via structured prediction
Figure 3 for Automatic measurement of vowel duration via structured prediction
Figure 4 for Automatic measurement of vowel duration via structured prediction

  Access Paper or Ask Questions

Sequence Segmentation Using Joint RNN and Structured Prediction Models


Oct 25, 2016
Yossi Adi, Joseph Keshet, Emily Cibelli, Matthew Goldrick

Figure 1 for Sequence Segmentation Using Joint RNN and Structured Prediction Models
Figure 2 for Sequence Segmentation Using Joint RNN and Structured Prediction Models
Figure 3 for Sequence Segmentation Using Joint RNN and Structured Prediction Models
Figure 4 for Sequence Segmentation Using Joint RNN and Structured Prediction Models
* under review 
  Access Paper or Ask Questions