NTU Speechlab LLM-Based Multilingual ASR System for Interspeech MLC-SLM Challenge 2025
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech RecognitionLanguage ModelingLanguage Modellingspeech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
SHNU Multilingual Conversational Speech Recognition System for INTERSPEECH 2025 MLC-SLM Challenge
This paper describes SHNU multilingual conversational speech recognition system (SHNU-mASR, team name-"maybe"), submitted to Track 1 of the INTERSPEECH 2025 MLC-SLM Challenge. Our system integrates a parallel-speech-enco…
Speech RecognitionText GenerationTalTech Systems for the Interspeech 2025 ML-SUPERB 2.0 Challenge
This paper describes the language identification and multilingual speech recognition system developed at Tallinn University of Technology for the Interspeech 2025 ML-SUPERB 2.0 Challenge. A hybrid language identification…
Language Identificationspeech-recognitionSpeech RecognitionTriple X: A LLM-Based Multilingual Speech Recognition System for the INTERSPEECH2025 MLC-SLM Challenge
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…
Speech RecognitionThe ML-SUPERB 2.0 Challenge: Towards Inclusive ASR Benchmarking for All Language Varieties
Recent improvements in multilingual ASR have not been equally distributed across languages and language varieties. To advance state-of-the-art (SOTA) ASR models, we present the Interspeech 2025 ML-SUPERB 2.0 Challenge. W…
HunterSpeechLab at GermEval 2021: Does Your Comment Claim A Fact? Contextualized Embeddings for German Fact-Claiming Comment Classification
In this paper we investigate the efficacy of using contextual embeddings from multilingual BERT and German BERT in identifying fact-claiming comments in German on social media. Additionally, we examine the impact of form…
Fact-Claiming Comment ClassificationMulti-Task Learning