#natural language process...
Apr 2026
Closing the Speech-Text Gap with Limited Audio for Effective Domain Adaptation in LLM-Based ASR
MB using only 10% of the target-domain speech achieves word error rates comparable to, or better than, conventional ASR fine-tuning with the full dataset, indicating that small amounts of speech provide a strong modality-alignment signal.
Thibault Bañeras-Roux, Sergio Gastón Burdisso, Esaú Villatoro-Tello et al.
· arXiv.org · 3 citations