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

2025/07/23 by Miaomiao Gao, Gao, Miaomiao, Xiaoxiao Xiang +3 · 1 citation
Computer Science · #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Speech Recognition and Synthesis #Speech and Audio Processing #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2507.17288

openalex publication_date 2025/07/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration
• GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement
• OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer
• Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models
• Qwen Technical Report
• GPT-4 Technical Report
• LLaMA: Open and Efficient Foundation Language Models
• Robust Speech Recognition via Large-Scale Weak Supervision
• Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition
• Listen, Attend and Spell
• Speech Recognition with Deep Recurrent Neural Networks

Cited by

• Summary on The Multilingual Conversational Speech Language Model Challenge: Datasets, Tasks, Baselines, and Methods

Related

• NTU Speechlab LLM-Based Multilingual ASR System for Interspeech MLC-SLM Challenge 2025
• Transsion Multilingual Speech Recognition System for MLC-SLM 2025 Challenge
• SHNU Multilingual Conversational Speech Recognition System for INTERSPEECH 2025 MLC-SLM Challenge
• The Eloquence team submission for task 1 of MLC-SLM challenge
• Findings of the 2023 ML-SUPERB Challenge: Pre-Training and Evaluation over More Languages and Beyond