A local-window speech LLM with prompt-based speaker context and an external diarization alignment module achieves 27.25 tcpWER/tcpCER on the MLC-SLM Task II evaluation set, a 54.87% relative improvement over the official baseline.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations
A local-window speech LLM with prompt-based speaker context and an external diarization alignment module achieves 27.25 tcpWER/tcpCER on the MLC-SLM Task II evaluation set, a 54.87% relative improvement over the official baseline.