Get started
Author

Avihu Dekel

Observed name: Dekel, Avihu
Institution: IBM (United States)
OpenAlex ID: A5055632925
Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets
2022 · Hacohen, Guy, Dekel, Avihu, et al. · arXiv (Cornell University) · 107
PDF
Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities
2025 · George Saon, Avihu Dekel, et al. · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · 46
PDF
Active Learning Through a Covering Lens
2022 · Ofer Yehuda, Avihu Dekel, et al. · neural information processing systems · 34
PDF
Speak While You Think: Streaming Speech Synthesis During Text Generation
2024 · Avihu Dekel, Slava Shechtman, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 13
PDF
Speech Synthesis From Continuous Features Using Per-Token Latent Diffusion
2025 · Arnon Turetzky, Avihu Dekel, et al. · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · 9
PDF
Self-Speculative Decoding for LLM-based ASR with CTC Encoder Drafts
2026 · George Saon, Samuel Thomas, et al. · Interspeech (USB) · 5
PDF
Exploring the Benefits of Tokenization of Discrete Acoustic Units
2024 · Avihu Dekel, Raul Fernandez · Interspeech (USB) · 5
PDF
Low Bitrate High-Quality RVQGAN-based Discrete Speech Tokenizer
2024 · Slava Shechtman, Avihu Dekel · Interspeech (USB) · 4
PDF
Advancing Speech Understanding in Speech-Aware Language Models with GRPO
2026 · Avishai Elmakies, Hagai Aronowitz, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 2
PDF
NLE: Non-autoregressive LLM-based ASR by Transcript Editing
2026 · Dekel, Avihu, Thomas, Samuel, et al. · arXiv (Cornell University) · 2
PDF
Spoken Question Answering for Visual Queries
2025 · Nimrod Shabtay, Zvi Kons, et al. · Interspeech (USB) · 2
PDF
Knowing What to Stress: A Discourse-Conditioned Text-to-Speech Benchmark
2026 · Arnon Turetzky, Avihu Dekel, et al. · Interspeech (USB) · 1
PDF
Speaker Attributed Automatic Speech Recognition Using Speech Aware Llms
2026 · Hagai Aronowitz, Zvi Kons, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 1
PDF
Balanced Thinking: Improving Chain of Thought Training in Vision Language Models
2026 · Perek, Shaked, Wiesel, Ben, et al. · arXiv (Cornell University) · 1
PDF
Exploring the Limits of Conformer CTC-Encoder for Speech Emotion Recognition using Large Language Models
2025 · Edmilson Morais, Hagai Aronowitz, et al. · Interspeech (USB) · 1
Watch and Learn: Teaching Visual In-Context Learning by Removing Textual Shortcuts
2026 · Shabtay, Nimrod, Yehudai, Asaf, et al. · arXiv (Cornell University)
PDF
Parameter-Efficient Adaptation of Speech-Aware LLMs for Timestamp Prediction
2026 · Vishal Sunder, Samuel Thomas, et al. · Interspeech (USB)
PDF
Design of the IBM Granite 5.0 TurboCTC ASR Model
2026 · Kingsbury, Brian, Saon, George, et al. · arXiv (Cornell University)
PDF
Word Timestamps and Speaker Attribution with a Non-Autoregressive LLM
2026 · Kons, Zvi, Dekel, Avihu, et al. · arXiv (Cornell University)
PDF
Works count: 19
Citation count: 233
H-index: 5
I10-index: 4
Year
Topic
Type