Yossi Adi
Yossi Adi
Research scientist at Facebook AI Research
Adresse e-mail validée de fb.com - Page d'accueil
Citée par
Citée par
Fine-grained analysis of sentence embeddings using auxiliary prediction tasks
Y Adi, E Kermany, Y Belinkov, O Lavi, Y Goldberg
International Conference on Learning Representations (ICLR), 2017
Houdini: Fooling deep structured prediction models
M Cisse, Y Adi, N Neverova, J Keshet
Advances in Neural Information Processing Systems, 2017, 2017
Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring
Y Adi, C Baum, M Cisse, B Pinkas, J Keshet
27th {USENIX} Security Symposium ({USENIX} Security 18), 1615--1631, 2018
Fooling End-to-end Speaker Verification by Adversarial Examples
F Kreuk, Y Adi, M Cisse, J Keshet
IEEE International Conference in Acoustic, Speech and Signal Processing (ICASSP), 2018
Voice separation with an unknown number of multiple speakers
E Nachmani, Y Adi, L Wolf
International Conference on Machine Learning, 7164-7175, 2020
Out-of-distribution detection using multiple semantic label representations
G Shalev, Y Adi, J Keshet
arXiv preprint arXiv:1808.06664, 2018
Real time speech enhancement in the waveform domain
A Defossez, G Synnaeve, Y Adi
arXiv preprint arXiv:2006.12847, 2020
DNS Cache-Based User Tracking.
A Klein, B Pinkas
NDSS, 2019
Sequence segmentation using joint RNN and structured prediction models
Y Adi, J Keshet, E Cibelli, M Goldrick
Proceedings of the... IEEE International Conference on Acoustics, Speech …, 2017
Analysis of sentence embedding models using prediction tasks in natural language processing
Y Adi, E Kermany, Y Belinkov, O Lavi, Y Goldberg
IBM Journal of Research and Development 61 (4/5), 3: 1-3: 9, 2017
To reverse the gradient or not: An empirical comparison of adversarial and multi-task learning in speech recognition
Y Adi, N Zeghidour, R Collobert, N Usunier, V Liptchinsky, G Synnaeve
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
Minimal Modifications of Deep Neural Networks using Verification.
B Goldberger, G Katz, Y Adi, J Keshet
LPAR 2020, 23rd, 2020
Hide and speak: Towards deep neural networks for speech steganography
F Kreuk, Y Adi, B Raj, R Singh, J Keshet
arXiv preprint arXiv:1902.03083, 2019
SAGRNN: Self-attentive gated RNN for binaural speaker separation with Interaural Cue Preservation
K Tan, B Xu, A Kumar, E Nachmani, Y Adi
IEEE Signal Processing Letters 28, 26-30, 2020
Self-supervised contrastive learning for unsupervised phoneme segmentation
F Kreuk, J Keshet, Y Adi
arXiv preprint arXiv:2007.13465, 2020
Unsupervised cross-domain singing voice conversion
A Polyak, L Wolf, Y Adi, Y Taigman
arXiv preprint arXiv:2008.02830, 2020
Automatic measurement of vowel duration via structured prediction
Y Adi, J Keshet, E Cibelli, E Gustafson, C Clopper, M Goldrick
The Journal of the Acoustical Society of America 140 (6), 4517-4527, 2016
Vowel duration measurement using deep neural networks
Y Adi, J Keshet, M Goldrick
2015 IEEE 25th International Workshop on Machine Learning for Signal …, 2015
The influence of lexical selection disruptions on articulation.
M Goldrick, R McClain, E Cibelli, Y Adi, E Gustafson, C Moers, J Keshet
Journal of Experimental Psychology: Learning, Memory, and Cognition 45 (6), 1107, 2019
Automatic Measurement of Voice Onset Time and Prevoicing Using Recurrent Neural Networks.
Y Adi, J Keshet, O Dmitrieva, M Goldrick
INTERSPEECH (2016), 3152-3155, 2016
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–20