Share This Author
Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring
- Yossi Adi, Carsten Baum, Moustapha Cissé, Benny Pinkas, Joseph Keshet
- Computer ScienceUSENIX Security Symposium
- 13 February 2018
This work presents an approach for watermarking Deep Neural Networks in a black-box way, and shows experimentally that such a watermark has no noticeable impact on the primary task that the model is designed for.
Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks
- Yossi Adi, Einat Kermany, Yonatan Belinkov, Ofer Lavi, Yoav Goldberg
- Computer ScienceICLR
- 15 August 2016
This work proposes a framework that facilitates better understanding of the encoded representations of sentence vectors and demonstrates the potential contribution of the approach by analyzing different sentence representation mechanisms.
Real Time Speech Enhancement in the Waveform Domain
Empirical evidence shows that the proposed causal speech enhancement model, based on an encoder-decoder architecture with skip-connections, is capable of removing various kinds of background noise including stationary and non-stationary noises, as well as room reverb.
Houdini: Fooling Deep Structured Prediction Models
This work introduces a novel flexible approach named Houdini for generating adversarial examples specifically tailored for the final performance measure of the task considered, be it combinatorial and non-decomposable.
Fooling End-To-End Speaker Verification With Adversarial Examples
- Felix Kreuk, Yossi Adi, Moustapha Cissé, Joseph Keshet
- Computer ScienceIEEE International Conference on Acoustics…
- 10 January 2018
This paper presents white-box attacks on a deep end-to-end network that was either trained on YOHO or NTIMIT, and shows that one can significantly decrease the accuracy of a target system even when the adversarial examples are generated with different system potentially using different features.
Voice Separation with an Unknown Number of Multiple Speakers
A new method is presented for separating a mixed audio sequence, in which multiple voices speak simultaneously, that greatly outperforms the current state of the art, which, as it is shown, is not competitive for more than two speakers.
On Generative Spoken Language Modeling from Raw Audio
- Kushal Lakhotia, Evgeny Kharitonov, Emmanuel Dupoux
- Computer ScienceTransactions of the Association for Computational…
- 1 February 2021
Generative Spoken Language Modeling is introduced, the task of learning the acoustic and linguistic characteristics of a language from raw audio and a set of metrics to automatically evaluate the learned representations atoustic and linguistic levels for both encoding and generation.
Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation
The proposed model is a convolutional neural network that operates directly on the raw waveform that is optimized to identify spectral changes in the signal using the Noise-Contrastive Estimation principle and reaches state-of-the-art performance on both data sets.
Minimal Modifications of Deep Neural Networks using Verification
This work uses recent advances in DNN verification and proposes a technique for modifying a DNN according to certain requirements, in a way that is provably minimal, does not require any retraining, and is thus less likely to affect other aspects of the DNN’s behavior.
Speech Resynthesis from Discrete Disentangled Self-Supervised Representations
To generate disentangled representation, low-bitrate representations are extracted for speech content, prosodic information, and speaker identity to synthesize speech in a controllable manner using self-supervised discrete representations.