Yossi Adi

Yossi is a Research Scientist at Facebook AI Research in Tel Aviv. Prior to joining Facebook, he completed his Ph.D. in Computer Science at Bar-Ilan University. Yossi's research interests focus on developing and analyzing machine learning and deep learning algorithms for speech and language applications.

Research Areas

Yossi's Publications

October 01, 2020

RESEARCH

Voice Separation with an Unknown Number of Multiple Speakers

e present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed.…

Eliya Nachmani, Yossi Adi, Lior Wolf

October 01, 2020

December 04, 2017

RESEARCH

Houdini: Fooling Deep Structured Visual and Speech Recognition Models with Adversarial Examples

Generating adversarial examples is a critical step for evaluating and improving the robustness of learning machines. So far, most existing methods only work for classification and are not designed to alter the true performance measure of the…

Moustapha Cisse, Yossi Adi, Natalia Neverova, Joseph Keshet

December 04, 2017

May 06, 2020

RESEARCH

Phoneme Boundary Detection Using Learnable Segmental Features

Phoneme boundary detection plays an essential first step for a variety of speech processing applications such as speaker diarization, speech science, keyword spotting, etc. In this work we propose a neural architecture coupled with a parameterized structured loss function to learn segmental representations for the task of phoneme boundary detection. We evaluate the proposed method on several datasets.…

Felix Kreuk, Yossi Adi, Yaniv Sheena, Joseph Keshet

May 06, 2020

RESEARCH

Minimal Modifications of Deep Neural Networks using Verification

Deep neural networks (DNNs) are revolutionizing the way complex systems are designed, developed and maintained. As part of the life cycle of DNN-based systems, there is often a need to modify a DNN in subtle ways that affect certain aspects of its behavior, while leaving other aspects of its behavior unchanged (e.g., if a bug is discovered and needs to be fixed, without altering other functionality).…

Yossi Adi, Ben Goldberger, Joseph Keshet, and Guy Katz