A multi-pass LLM architecture alternating speaker and word recognition passes yields significant WDER reductions on French suicide prevention conversations while remaining stable on neurosurgery consultations using Qwen3-Next-80B.
Context is all you need? low-resource conversational asr profits from context, coming from the same or from the other speaker
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Iterative LLM-based improvement for French Clinical Interview Transcription and Speaker Diarization
A multi-pass LLM architecture alternating speaker and word recognition passes yields significant WDER reductions on French suicide prevention conversations while remaining stable on neurosurgery consultations using Qwen3-Next-80B.