Triple X: A LLM-Based Multilingual Speech Recognition System for the INTERSPEECH2025 MLC-SLM Challenge

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Miaomiao, Xiang, Xiaoxiao, Guo, Yiwen
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911510541893632
author Gao, Miaomiao
Xiang, Xiaoxiao
Guo, Yiwen
author_facet Gao, Miaomiao
Xiang, Xiaoxiao
Guo, Yiwen
contents This paper describes our Triple X speech recognition system submitted to Task 1 of the Multi-Lingual Conversational Speech Language Modeling (MLC-SLM) Challenge. Our work focuses on optimizing speech recognition accuracy in multilingual conversational scenarios through an innovative encoder-adapter-LLM architecture. This framework harnesses the powerful reasoning capabilities of text-based large language models while incorporating domain-specific adaptations. To further enhance multilingual recognition performance, we adopted a meticulously designed multi-stage training strategy leveraging extensive multilingual audio datasets. Experimental results demonstrate that our approach achieves competitive Word Error Rate (WER) performance on both dev and test sets, obtaining second place in the challenge ranking.
format Preprint
id arxiv_https___arxiv_org_abs_2507_17288
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Triple X: A LLM-Based Multilingual Speech Recognition System for the INTERSPEECH2025 MLC-SLM Challenge
Gao, Miaomiao
Xiang, Xiaoxiao
Guo, Yiwen
Computation and Language
Audio and Speech Processing
This paper describes our Triple X speech recognition system submitted to Task 1 of the Multi-Lingual Conversational Speech Language Modeling (MLC-SLM) Challenge. Our work focuses on optimizing speech recognition accuracy in multilingual conversational scenarios through an innovative encoder-adapter-LLM architecture. This framework harnesses the powerful reasoning capabilities of text-based large language models while incorporating domain-specific adaptations. To further enhance multilingual recognition performance, we adopted a meticulously designed multi-stage training strategy leveraging extensive multilingual audio datasets. Experimental results demonstrate that our approach achieves competitive Word Error Rate (WER) performance on both dev and test sets, obtaining second place in the challenge ranking.
title Triple X: A LLM-Based Multilingual Speech Recognition System for the INTERSPEECH2025 MLC-SLM Challenge
topic Computation and Language
Audio and Speech Processing
url https://arxiv.org/abs/2507.17288