The research in the lab is focused on statistical and machine learning techniques applied to the modeling and processing of speech and language. A typical problem in speech and language processing has a very large number of training examples, is sequential, highly structured, and has a unique measure of performance. The lab's goal is to develop rigorous statistical and machine learning algorithms that maximize performance by matching the internal structure of the problem and by optimizing its unique measure of performance.

News

Research

Hide and Speak, Deep Neural Networks for Speech Steganography

Hiding speech inside of speech.

Read more »

People

Faculty

Joseph Keshet
Joseph Keshet
Professor

PhD Students

Felix Kreuk
Speech Generation
Joseph Shrem
Joseph Shrem
Speech Segmentation
Fuchs Tzviya
Fuchs Tzviya
Speech Segmentation
Yael Segal
Yael Segal
Speech Segmentation
Gavi Shalev
Gavi Shalev
XXX

Msc Students

Tamar Fenster
Tamar Fenster
XXX
Gal Lev
Gal Lev
XXX
Roni Chern
Roni Chern
Robustness
Talia Ben-Simon
Talia Ben-Simon
Speech Generation

Alumni

Yossi Adi
Yossi Adi

Publications

2019
December
Hide and Speak: Deep Neural Networks for Speech Steganography.
Felix Kreuk, Yossi Adi, Bhiksha Raj, Rita Singh, and Joseph Keshet.
Preprint.
2018
December
Deceiving end-to-end deep learning malware detectors using adversarial examples.
Felix Kreuk, Assi Barak, Shir Aviv-Reuven, Moran Baruch, Benny Pinkas, and Joseph Keshet.
Workshop on Security in Machine Learning (NIPS).
2018
April
Fooling end-to-end speaker verification with adversarial examples.
Felix Kreuk, Yossi Adi, Moustapha Cisse, and Joseph Keshet.
2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).