mlsanityData to 14 Oct 2026

NTU Speechlab LLM-Based Multilingual ASR System for Interspeech MLC-SLM Challenge 2025

arXiv 2506.13339 ↗First posted 16 Jun 2025cs.CL eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

This report details the NTU Speechlab system developed for the Interspeech 2025 Multilingual Conversational Speech and Language Model (MLC-SLM) Challenge (Task I), where we achieved 5th place. We present comprehensive analyses of our multilingual automatic speech recognition system, highlighting key advancements in model architecture, data selection, and training strategies. In particular, language-specific prompts and model averaging techniques were instrumental in boosting system performance across diverse languages. Compared to the initial baseline system, our final model reduced the average Mix Error Rate from 20.2% to 10.6%, representing an absolute improvement of 9.6% (a relative improvement of 48%) on the evaluation set. Our results demonstrate the effectiveness of our approach and offer practical insights for future Speech Large Language Models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 20 references that are in the map. First posted on arXiv 16 Jun 2025.

Builds on

17 of 20 references.

References · 17

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  3. 2023Qwen Technical Reportcited by 3,344
  4. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  5. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  6. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  7. 2023Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Modelscited by 608
  8. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 558
  9. 2023SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilitiescited by 529
  10. 2020MLS: A Large-Scale Multilingual Dataset for Speech Researchcited by 476
  11. 2021GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audiocited by 399
  12. 2023BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questionscited by 125
5 more
  1. 2021The Multilingual TEDx Corpus for Speech Recognition and Translationcited by 101
  2. 2024An Embarrassingly Simple Approach for LLM with Strong ASR Capacitycited by 88
  3. 2025Step-Audio: Unified Understanding and Generation in Intelligent Speech Interactioncited by 83
  4. 2024Mamba in Speech: Towards an Alternative to Self-Attentioncited by 60
  5. 2024GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinementcited by 34

Built on by

Not cited yet.