- I’m a Deep Learning researcher, working on deep speech processing at IBM Research.
- I’m also experienced in computer vision and clinical/biological data.
- I’m a M.Sc. graduate in Computer Science from the Hebrew University of Jerusalem.
More Information
- I graduated B.Sc. in Computational Biology (gradueted Magna Cum Laude).
- I worked as an Algorithm Developer in Mobileye, focusing on Semantic Segmentation.
- During my M.Sc., I had the pleasure of working in Daphna Weinshall’s Lab.
- My research focused on Low Budget Active Learning, as well as Semi-Supervised learning, Anomaly detection, Unsupervised Learning and various related fields.
- I was also a Research Intern at IBM AI for Healthcare, training Transformers on multi-modal health records dataset.
Publications
- Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets - Guy Hacohen, Avihu Dekel (Equal contribution), Daphna Weinshall (Accepted to ICML2022)
- Active Learning Through a Covering Lens - Ofer Yehuda, Avihu Dekel, Guy Hacohen, Daphna Weinshall (Accepted to NeurIPS2022)
- Speak While You Think: Streaming Speech Synthesis During Text Generation - Avihu Dekel, Slava Shechtman, Raul Fernandez, David Haws, Zvi Kons, Ron Hoory (Accepted to ICASSP2024)
- Exploring the Benefits of Tokenization of Discrete Acoustic Units - Avihu Dekel, Raul Fernandez (Accepted to Interspeech 2024)
- Low Bitrate High-Quality RVQGAN-based Discrete Speech Tokenizer - Slava Shechtman, Avihu Dekel (Accepted to Interspeech 2024)
- Continuous Speech Synthesis using per-token Latent Diffusion - Arnon Turetzky, Nimrod Shabtay, Slava Shechtman, Hagai Aronowitz, David Haws, Ron Hoory, Avihu Dekel (Core Contributor)