Scholar
Felix Kreuk
Google Scholar ID: UiERcYsAAAAJ
Meta AI, FAIR
Citations & Impact
Citations
12,526
H-index
15
i10-index
18
Publications
20
Co-authors
4
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Publications:
- - "Textually Pretrained Speech Language Models", arXiv, 2023
- - "AudioGen: Textually Guided Audio Generation", ICLR, 2023
- - "On The Robustness of Self-Supervised Representations for Spoken Language Modeling", IWSLT, 2022
- - "Textless Speech Emotion Conversion using Decomposed and Discrete Representations", EMNLP, 2022
- - "A Systematic Comparison of Phonetic Aware Techniques for Speech Enhancement", Interspeech, 2022
- - "Self-supervised Speaker Diarization", Interspeech, 2022
- - "Formant Estimation and Tracking using Probabilistic Heat-Maps", Interspeech, 2022
- - "Correcting Misproducted Speech using Spectrogram Inpainting", Interspeech, 2022
- - "Speech Time-Scale Modification With GANs", IEEE Signal Processing Letters, 2022
- - "Self-supervised contrastive learning for unsupervised phoneme segmentation", Interspeech, 2020
- - "Hide and Speak: Towards Deep Neural Networks for Speech Steganography", Interspeech, 2020
- - "A Causal View of Compositional Zero-Shot Recognition", NeurIPS, 2020
Research Experience
- Spent time at NVIDIA Research (2019-2020).
Education
- Completed my PhD in Computer-Science from Bar-Ilan University under the supervision of Prof. Joseph Keshet.
Background
- Currently a Research Engineer at Meta AI research, previously Facebook AI Research (FAIR). My research interests lie in the intersection of deep-learning and speech/audio processing. Most of my recent work involves generative models for speech and general audio.
