The TEA-ASLP System for Multilingual Conversational Speech Recognition and Speech Diarization in MLC-SLM 2025 Challenge

TL;DR

This paper describes the TEA-ASLP system for multilingual conversational speech recognition and diarization, achieving top challenge results through model enhancements and data strategies.

Contribution

The paper introduces novel multilingual modeling techniques and prompt strategies that significantly improve speech recognition and diarization performance.

Findings

30.8% reduction in WER over baseline

Final WER of 9.60% in Task I

Second place in speech diarization challenge

Abstract

This paper presents the TEA-ASLP's system submitted to the MLC-SLM 2025 Challenge, addressing multilingual conversational automatic speech recognition (ASR) in Task I and speech diarization ASR in Task II. For Task I, we enhance Ideal-LLM model by integrating known language identification and a multilingual MOE LoRA structure, along with using CTC-predicted tokens as prompts to improve autoregressive generation. The model is trained on approximately 180k hours of multilingual ASR data. In Task II, we replace the baseline English-Chinese speaker diarization model with a more suitable English-only version. Our approach achieves a 30.8% reduction in word error rate (WER) compared to the baseline speech language model, resulting in a final WER of 9.60% in Task I and a time-constrained minimum-permutation WER of 17.49% in Task II, earning first and second place in the respective challenge tasks.