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

TL;DR

This paper presents Triple X, a multilingual speech recognition system that combines large language models with domain-specific adaptations, achieving competitive accuracy in the INTERSPEECH2025 challenge.

Contribution

The work introduces an encoder-adapter-LLM architecture and a multi-stage training strategy for improved multilingual speech recognition.

Findings

Achieved second place in the challenge ranking.

Demonstrated competitive Word Error Rate performance.

Effectively integrated LLM reasoning into speech recognition.

Abstract

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.