SHNU-mASR, a parallel-encoder LLM system, achieves 11.76% CER/WER on the MLC-SLM blind eval set, 8.41 points better than the official baseline.
Robust speech recognition via large-scale weak su- pervision,
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.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
SHNU Multilingual Conversational Speech Recognition System for INTERSPEECH 2025 MLC-SLM Challenge
SHNU-mASR, a parallel-encoder LLM system, achieves 11.76% CER/WER on the MLC-SLM blind eval set, 8.41 points better than the official baseline.