Transsion Multilingual Speech Recognition System for MLC-SLM 2025 Challenge

This paper presents the architecture and performance of a novel Multilingual Automatic Speech Recognition (ASR) system developed by the Transsion Speech Team for Track 1 of the MLC-SLM 2025 Challenge. The proposed system comprises three key components: 1) a frozen Whisper-large-v3 based speech encod...

Full description

Saved in:
Bibliographic Details
Main Authors Li, Xiaoxiao, Zhu, An, Jiang, Youhai, Zhu, Fengjie
Format Journal Article
LanguageEnglish
Published 15.08.2025
Subjects
Computer Science - Artificial Intelligence
Computer Science - Computation and Language
Online AccessGet full text

Cover

More Information
Summary:This paper presents the architecture and performance of a novel Multilingual Automatic Speech Recognition (ASR) system developed by the Transsion Speech Team for Track 1 of the MLC-SLM 2025 Challenge. The proposed system comprises three key components: 1) a frozen Whisper-large-v3 based speech encoder, leveraging large-scale pretraining to ensure robust acoustic feature extraction; 2) a trainable adaptor module using Linear-ReLU-Linear transformation mechanisms to effectively align speech and text representations; and 3) a frozen Qwen2.5-7B-Instruct large language model (LLM) integrated with trainable LoRA for optimized contextual linguistic decoding. By systematically combining pretrained models with task specific fine-tuning, the system achieved a word/character error rate (WER/CER) of 9.83% across 11 languages in the evaluation set and ranked third place among global participants.
DOI:10.48550/arxiv.2508.14916