Combining dual encoders, LID-routed MoE LoRA, and CTC prompts yields top challenge results for multilingual conversational ASR and speech diarization.
Recently, there has been growing interest in combining LLMs with audio encoders, en- abling the models to process and understand audio modali- ties [6, 7, 8, 9, 10, 11]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
The TEA-ASLP System for Multilingual Conversational Speech Recognition and Speech Diarization in MLC-SLM 2025 Challenge
Combining dual encoders, LID-routed MoE LoRA, and CTC prompts yields top challenge results for multilingual conversational ASR and speech diarization.