absorb.md

Tasu2

1 mentions across 0 people

Unknown speaker
paper · 2026-04-10
Recommended

We propose \textbf{TASU2}, a controllable CTC simulation framework that simulates CTC posterior distributions under a specified WER range, producing text-derived supervision that better matches the acoustic decoding interface. This enables principled post-training curricula that smoothly vary supervision difficulty without TTS. Across multiple source-to-target adaptation settings, TASU2 improves in-domain and out-of-domain recognition over TASU, and consistently outperforms strong baselines incl

Controllable CTC Simulation for Efficient Speech LLM Adaptation