Multilin- gual ASR (mASR) extends this capability to multiple languages within a single system, enhancing global communication and supporting low-resource languages

Introduction Automatic Speech Recognition (ASR) has advanced significantly, enabling accurate conversion of speech to text · 2025

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

browse 1 citing papers

representative citing papers

cs.CL · 2025-07-04 · conditional · novelty 4.0

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.

Showing 1 of 1 citing paper.

SHNU Multilingual Conversational Speech Recognition System for INTERSPEECH 2025 MLC-SLM Challenge cs.CL · 2025-07-04 · conditional · none · ref 1
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.