{"ID":2890729,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.18051","arxiv_id":"2507.18051","title":"The TEA-ASLP System for Multilingual Conversational Speech Recognition and Speech Diarization in MLC-SLM 2025 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.","short_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 st...","url_abs":"https://arxiv.org/abs/2507.18051","url_pdf":"https://arxiv.org/pdf/2507.18051v1","authors":"[\"Hongfei Xue\",\"Kaixun Huang\",\"Zhikai Zhou\",\"Shen Huang\",\"Shidong Shang\"]","published":"2025-07-24T02:56:29Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"eess.AS\"]","methods":"[\"Large Language Model\",\"Language Model\",\"LoRA\"]","has_code":false}