Cover Image

MOSA: Mixtures of Simple Adapters Outperform Monolithic Approaches in LLM-based Multilingual ASR

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Junjie, Peng, Jing, Fang, Yangui, Wang, Shuai, Yu, Kai
Format:	Preprint
Published:	2025
Subjects:	Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TC-BiMamba: Trans-Chunk bidirectionally within BiMamba for unified streaming and non-streaming ASR
by: She, Qingshun, et al.
Published: (2026)

Joint decoding method for controllable contextual speech recognition based on Speech LLM
by: Fang, Yangui, et al.
Published: (2025)

Fewer Hallucinations, More Verification: A Three-Stage LLM-Based Framework for ASR Error Correction
by: Fang, Yangui, et al.
Published: (2025)

TASU: Text-Only Alignment for Speech Understanding
by: Peng, Jing, et al.
Published: (2025)

A Survey on Speech Large Language Models for Understanding
by: Peng, Jing, et al.
Published: (2024)

Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning
by: Fang, Yangui, et al.
Published: (2025)

Semi-supervised Learning for Code-Switching ASR with Large Language Model Filter
by: Xi, Yu, et al.
Published: (2024)

Romanization Encoding For Multilingual ASR
by: Ding, Wen, et al.
Published: (2024)

Delayed-KD: Delayed Knowledge Distillation based CTC for Low-Latency Streaming ASR
by: Li, Longhao, et al.
Published: (2025)

Mixture to Beamformed Mixture: Leveraging Beamformed Mixture as Weak-Supervision for Speech Enhancement and Noise-Robust ASR
by: Wang, Zhong-Qiu, et al.
Published: (2025)

Efficient Adapter Finetuning for Tail Languages in Streaming Multilingual ASR
by: Bai, Junwen, et al.
Published: (2024)

Efficient Scaling for LLM-based ASR
by: Mu, Bingshen, et al.
Published: (2025)

MOSA: Music Motion with Semantic Annotation Dataset for Cross-Modal Music Processing
by: Huang, Yu-Fen, et al.
Published: (2024)

NTU Speechlab LLM-Based Multilingual ASR System for Interspeech MLC-SLM Challenge 2025
by: Peng, Yizhou, et al.
Published: (2025)

NLE: Non-autoregressive LLM-based ASR by Transcript Editing
by: Dekel, Avihu, et al.
Published: (2026)

Phonemes vs. Projectors: An Investigation of Speech-Language Interfaces for LLM-based ASR
by: Li, Ziwei, et al.
Published: (2026)

SAML: Speaker Adaptive Mixture of LoRA Experts for End-to-End ASR
by: Zhao, Qiuming, et al.
Published: (2024)

Self-Speculative Decoding for LLM-based ASR with CTC Encoder Drafts
by: Saon, George, et al.
Published: (2026)

An Embarrassingly Simple Approach for LLM with Strong ASR Capacity
by: Ma, Ziyang, et al.
Published: (2024)

Improving Multilingual ASR in the Wild Using Simple N-best Re-ranking
by: Yan, Brian, et al.
Published: (2024)

Towards Effective and Efficient Non-autoregressive decoders for Conformer and LLM-based ASR using Block-based Attention Mask
by: Wang, Tianzi, et al.
Published: (2025)

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty
by: Xue, Hongfei, et al.
Published: (2025)

LUPET: Incorporating Hierarchical Information Path into Multilingual ASR
by: Liu, Wei, et al.
Published: (2024)

SuperM2M: Supervised and Mixture-to-Mixture Co-Learning for Speech Enhancement and Noise-Robust ASR
by: Wang, Zhong-Qiu
Published: (2024)

HDMoLE: Mixture of LoRA Experts with Hierarchical Routing and Dynamic Thresholds for Fine-Tuning LLM-based ASR Models
by: Mu, Bingshen, et al.
Published: (2024)

DM-ASR: Diarization-aware Multi-speaker ASR with Large Language Models
by: Li, Li, et al.
Published: (2026)

Contextual Biasing for Streaming ASR via CTC-based Word Spotting
by: Tsai, Kai-Chen, et al.
Published: (2026)

Contextual Biasing for LLM-Based ASR with Hotword Retrieval and Reinforcement Learning
by: Kong, YuXiang, et al.
Published: (2025)

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding
by: Wei, Linye, et al.
Published: (2025)

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs
by: Peng, Jing, et al.
Published: (2026)

DQLoRA: A Lightweight Domain-Aware Denoising ASR via Adapter-guided Distillation
by: Yang, Yiru
Published: (2025)

Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition
by: Bai, Ye, et al.
Published: (2024)

BLR-MoE: Boosted Language-Routing Mixture of Experts for Domain-Robust Multilingual E2E ASR
by: Ma, Guodong, et al.
Published: (2025)

MaLa-ASR: Multimedia-Assisted LLM-Based ASR
by: Yang, Guanrou, et al.
Published: (2024)

Bi-directional Context-Enhanced Speech Large Language Models for Multilingual Conversational ASR
by: Peng, Yizhou, et al.
Published: (2025)

dLLM-ASR: A Faster Diffusion LLM-based Framework for Speech Recognition
by: Tian, Wenjie, et al.
Published: (2026)

Boosting Code-Switching ASR with Mixture of Experts Enhanced Speech-Conditioned LLM
by: Zhang, Fengrun, et al.
Published: (2024)

Weakly Supervised Data Refinement and Flexible Sequence Compression for Efficient Thai LLM-based ASR
by: Shao, Mingchen, et al.
Published: (2025)

Mel-FullSubNet: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR
by: Zhou, Rui, et al.
Published: (2024)

Exploring SSL Discrete Tokens for Multilingual ASR
by: Cui, Mingyu, et al.
Published: (2024)