Evaluating Tibetan Speech Recognition Across Dialects and Adaptation Regimes: A Multi-Granularity Analysis
arXiv:2610.27002v1 Announce Type: new Abstract: Tibetan speech recognition is usually evaluated with character or syllable error rates because the writing system does not mark word boundaries. These metrics can rank systems differently and respond differently to adaptation failures. We combine char…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-10-21 04:00 · arXiv cs.CL
Evaluating Tibetan Speech Recognition Across Dialects and Adaptation Regimes: A Multi-Granularity Analysis