Yossi Adi

is this you? claim profile

∙ 0 followers

Speech Resynthesis from Discrete Disentangled Self-Supervised Representations

We propose using self-supervised discrete representations for the task o...
04/01/2021 ∙ by Adam Polyak, et al. ∙ 10 ∙ share

read it
Generative Spoken Language Modeling from Raw Audio

Generative spoken language modeling involves learning jointly the acoust...
02/01/2021 ∙ by Kushal Lakhotia, et al. ∙ 11 ∙ share

read it
High Fidelity Speech Regeneration with Application to Speech Enhancement

Speech enhancement has seen great improvement in recent years mainly thr...
01/31/2021 ∙ by Adam Polyak, et al. ∙ 0 ∙ share

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

We present a unified network for voice separation of an unknown number o...
11/04/2020 ∙ by Shlomo E. Chazan, et al. ∙ 0 ∙ share

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

We present a framework that allows to certify the fairness degree of a m...
09/03/2020 ∙ by Shahar Segal, et al. ∙ 27 ∙ share

read it
SAGRNN: Self-Attentive Gated RNN for Binaural Speaker Separation with Interaural Cue Preservation

Most existing deep learning based binaural speaker separation systems fo...
09/02/2020 ∙ by Ke Tan, et al. ∙ 0 ∙ share

read it
Unsupervised Cross-Domain Singing Voice Conversion

We present a wav-to-wav generative model for the task of singing voice c...
08/06/2020 ∙ by Adam Polyak, et al. ∙ 0 ∙ share

read it
Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation

We propose a self-supervised representation learning model for the task ...
07/27/2020 ∙ by Felix Kreuk, et al. ∙ 7 ∙ share

read it
Real Time Speech Enhancement in the Waveform Domain

We present a causal speech enhancement model working on the raw waveform...
06/23/2020 ∙ by Alexandre Défossez, et al. ∙ 0 ∙ share

read it
Voice Separation with an Unknown Number of Multiple Speakers

We present a new method for separating a mixed audio sequence, in which ...
02/29/2020 ∙ by Eliya Nachmani, et al. ∙ 0 ∙ share

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

Generalization bounds which assess the difference between the true risk ...
02/23/2020 ∙ by Yossi Adi, et al. ∙ 0 ∙ share

read it
Phoneme Boundary Detection using Learnable Segmental Features

Phoneme boundary detection plays an essential first step for a variety o...
02/11/2020 ∙ by Felix Kreuk, et al. ∙ 0 ∙ share

read it
Hide and Speak: Deep Neural Networks for Speech Steganography

Steganography is the science of hiding a secret message within an ordina...
02/07/2019 ∙ by Felix Kreuk, et al. ∙ 0 ∙ share

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

Transcribed datasets typically contain speaker identity for each instanc...
12/09/2018 ∙ by Yossi Adi, et al. ∙ 14 ∙ share

read it
Out-of-Distribution Detection using Multiple Semantic Label Representations

Deep Neural Networks are powerful models that attained remarkable result...
08/20/2018 ∙ by Gabi Shalev, et al. ∙ 0 ∙ share

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

Deep Neural Networks have recently gained lots of success after enabling...
02/13/2018 ∙ by Yossi Adi, et al. ∙ 0 ∙ share

read it
Fooling End-to-end Speaker Verification by Adversarial Examples

Automatic speaker verification systems are increasingly used as the prim...
01/10/2018 ∙ by Felix Kreuk, et al. ∙ 0 ∙ share

read it
Houdini: Fooling Deep Structured Prediction Models

Generating adversarial examples is a critical step for evaluating and im...
07/17/2017 ∙ by Moustapha Cisse, et al. ∙ 0 ∙ share

read it
Automatic Measurement of Pre-aspiration

Pre-aspiration is defined as the period of glottal friction occurring in...
04/05/2017 ∙ by Yaniv Sheena, et al. ∙ 0 ∙ share

read it
Learning Similarity Functions for Pronunciation Variations

A significant source of errors in Automatic Speech Recognition (ASR) sys...
03/28/2017 ∙ by Einat Naaman, et al. ∙ 0 ∙ share

read it
Automatic measurement of vowel duration via structured prediction

A key barrier to making phonetic studies scalable and replicable is the ...
10/26/2016 ∙ by Yossi Adi, et al. ∙ 0 ∙ share

read it
Sequence Segmentation Using Joint RNN and Structured Prediction Models

We describe and analyze a simple and effective algorithm for sequence se...
10/25/2016 ∙ by Yossi Adi, et al. ∙ 0 ∙ share

read it
Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks

There is a lot of research interest in encoding variable length sentence...
08/15/2016 ∙ by Yossi Adi, et al. ∙ 0 ∙ share

read it

Yossi Adi

Featured Co-authors

Lior Wolf

Yoav Goldberg

Bhiksha Raj

Gabriel Synnaeve

Ronan Collobert

Yonatan Belinkov

Emmanuel Dupoux

Nicolas Usunier

Wei-Ning Hsu

Anurag Kumar

Tamir Hazan

Speech Resynthesis from Discrete Disentangled Self-Supervised Representations

Generative Spoken Language Modeling from Raw Audio

High Fidelity Speech Regeneration with Application to Speech Enhancement

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

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

SAGRNN: Self-Attentive Gated RNN for Binaural Speaker Separation with Interaural Cue Preservation

Unsupervised Cross-Domain Singing Voice Conversion

Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation

Real Time Speech Enhancement in the Waveform Domain

Voice Separation with an Unknown Number of Multiple Speakers

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

Phoneme Boundary Detection using Learnable Segmental Features

Hide and Speak: Deep Neural Networks for Speech Steganography

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

Out-of-Distribution Detection using Multiple Semantic Label Representations

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

Fooling End-to-end Speaker Verification by Adversarial Examples

Houdini: Fooling Deep Structured Prediction Models

Automatic Measurement of Pre-aspiration

Learning Similarity Functions for Pronunciation Variations

Automatic measurement of vowel duration via structured prediction

Sequence Segmentation Using Joint RNN and Structured Prediction Models

Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks