NLE: Non-autoregressive LLM-based ASR by Transcript Editing
Paper • 2603.08397 • Published • 22
Avihu Dekel
Avihu
AI & ML interests
None yet
Recent Activity
upvoted an article about 9 hours ago
Granite 4.1 LLMs: How They’re Built liked a model about 9 hours ago
ibm-granite/granite-speech-4.1-2b liked a model about 9 hours ago
ibm-granite/granite-speech-4.1-2b-narOrganizations
submitted a
paper to Daily Papers about 2 months ago
authored a
paper 7 months ago
authored 5
papers over 1 year ago
Active Learning Through a Covering Lens
Paper • 2205.11320 • Published
Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets
Paper • 2202.02794 • Published
Exploring the Benefits of Tokenization of Discrete Acoustic Units
Paper • 2406.05547 • Published • 1
Speak While You Think: Streaming Speech Synthesis During Text Generation
Paper • 2309.11210 • Published • 1
Continuous Speech Synthesis using per-token Latent Diffusion
Paper • 2410.16048 • Published • 30