Felix Kreuk

My name is Felix Kreuk. I am currently a Research Engineer at Meta AI research, previously Facebook AI Research (FAIR). I completed my PhD in Computer-Science from Bar-Ilan University under the supervision of Prof. Joseph Keshet. I have also spent time at NVIDIA Research (2019-2020).

My research interests lie in the intersection of deep-learning and speech/audio processing. Most of my recent work involves with generative models for speech and general audio.


felix.kreuk at gmail dot com

News

Publications

    2023

  1. Michael Hassid, Tal Remez, Tu Anh Nguyen, Itai Gat, Alexis Conneau, Felix Kreuk, Jade Copet, Alexandre Defossez, Gabriel Synnaeve, Emmanuel Dupoux, Roy Schwartz, Yossi Adi. Textually Pretrained Speech Language Models. arXiv, 2023
    2. [ PDF, Samples ]
  2. Felix Kreuk, Gabriel Synnaeve, Adam Polyak, Uriel Singer, Alexandre Défossez, Jade Copet, Devi Parikh, Yaniv Taigman, Yossi Adi. AudioGen: Textually Guided Audio Generation. International Conference on Learning Representations (ICLR), 2023
    3. [ PDF, Samples ]

    2022

  3. Itai Gat, Felix Kreuk, Ann Lee, Jade Copet, Gabriel Synnaeve, Emmanuel Dupoux, Yossi Adi. On The Robustness of Self-Supervised Representations for Spoken Language Modeling. The International Conference on Spoken Language Translation (IWSLT), 2022
    4. [ PDF ]
  4. Felix Kreuk, Adam Polyak, Jade Copet, Eugene Kharitonov, Tu-Anh Nguyen, Morgane Rivière, Wei-Ning Hsu, Abdelrahman Mohamed Emmanuel Dupoux, Yossi Adi. Textless Speech Emotion Conversion using Decomposed and Discrete Representations. Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022
    5. [ PDF, Code, Samples, Blog ]
  5. Or Tal, Moshe Mandel, Felix Kreuk, Yossi Adi. A Systematic Comparison of Phonetic Aware Techniques for Speech Enhancement. The 23rd Annual Conference of the International Speech Communication Association (Interspeech), 2022
    6. [ PDF, Code ]
  6. Yehoshua Dissen, Felix Kreuk, Joseph Keshet. Self-supervised Speaker Diarization. The 23rd Annual Conference of the International Speech Communication Association (Interspeech), 2022
    7. [ PDF ]
  7. Yossi Shrem, Felix Kreuk, Joseph Keshet. Formant Estimation and Tracking using Probabilistic Heat-Maps. The 23rd Annual Conference of the International Speech Communication Association (Interspeech), 2022
    8. [ PDF ]
  8. Talia Ben-Simon, Felix Kreuk, Faten Awwad, Jacob T. Cohen, Joseph Keshet. Correcting Misproducted Speech using Spectrogram Inpainting. The 23rd Annual Conference of the International Speech Communication Association (Interspeech), 2022
    9. [ PDF ]
  9. Eyal Cohen, Felix Kreuk, Joseph Keshet. Speech Time-Scale Modification With GANs. IEEE Signal Processing Letters, 2022
    10. [ PDF ]

    2020

  10. Felix Kreuk, Joseph Keshet, Yossi Adi. Self-supervised contrastive learning for unsupervised phoneme segmentation. The 21st Annual Conference of the International Speech Communication Association (Interspeech), 2020
    11. [ PDF, Code ]
  11. Felix Kreuk, Yossi Adi, Bhiksha Raj, Rita Singh, Joseph Keshet. Hide and Speak: Towards Deep Neural Networks for Speech Steganography. The 21st Annual Conference of the International Speech Communication Association (Interspeech), 2020
    12. [ PDF, Samples, Code ]
  12. Yuval Atzmon, Felix Kreuk, Uri Shalit, Gal Chechik. A Causal View of Compositional Zero-Shot Recognition. The 34th Annual Conference on Neural Information Processing Systems (NeurIPS), 2020
    13. [ PDF ]
  13. Felix Kreuk, Yaniv Sheena, Joseph Keshet, Yossi Adi. Phoneme Boundary Detection using Learnable Segmental Features. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020
    14. [ PDF, Code ]

    2018

  14. Felix Kreuk, Assi Barak, Shir Aviv-Reuven, Moran Baruch, Benny Pinkas, Joseph Keshet. Deceiving End-to-End Deep Learning Malware Detectors using Adversarial Examples. Workshop track at 32nd Conference on Neural Information Processing Systems (NeurIPS), 2018
    15. [ PDF ]
  15. Felix Kreuk, Yossi Adi, Moustapha Cisse, Joseph Keshet. Fooling End-to-end Speaker Verification by Adversarial Examples. IEEE International Conference in Acoustic, Speech and Signal Processing (ICASSP), 2018
    16. [ PDF ]