Image de couverture de livre

Hearing More with Less: Multi-Modal Retrieval-and-Selection Augmented Conversational LLM-Based ASR

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Mu, Bingshen, Liu, Hexin, Xue, Hongfei, Wei, Kun, Xie, Lei
Format:	Preprint
Publié:	2025
Sujets:	Sound
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Efficient Scaling for LLM-based ASR
par: Mu, Bingshen, et autres
Publié: (2025)

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition
par: Mu, Bingshen, et autres
Publié: (2025)

HDMoLE: Mixture of LoRA Experts with Hierarchical Routing and Dynamic Thresholds for Fine-Tuning LLM-based ASR Models
par: Mu, Bingshen, et autres
Publié: (2024)

LLM-ForcedAligner: A Non-Autoregressive and Accurate LLM-Based Forced Aligner for Multilingual and Long-Form Speech
par: Mu, Bingshen, et autres
Publié: (2026)

Unveiling the Potential of LLM-Based ASR on Chinese Open-Source Datasets
par: Geng, Xuelong, et autres
Publié: (2024)

dLLM-ASR: A Faster Diffusion LLM-based Framework for Speech Recognition
par: Tian, Wenjie, et autres
Publié: (2026)

Weakly Supervised Data Refinement and Flexible Sequence Compression for Efficient Thai LLM-based ASR
par: Shao, Mingchen, et autres
Publié: (2025)

MMGER: Multi-modal and Multi-granularity Generative Error Correction with LLM for Joint Accent and Speech Recognition
par: Mu, Bingshen, et autres
Publié: (2024)

E-chat: Emotion-sensitive Spoken Dialogue System with Large Language Models
par: Xue, Hongfei, et autres
Publié: (2023)

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty
par: Xue, Hongfei, et autres
Publié: (2025)

CLAR: CIF-Localized Alignment for Retrieval-Augmented Speech LLM-Based Contextual ASR
par: Huang, Shangkun, et autres
Publié: (2026)

Summary on The Multilingual Conversational Speech Language Model Challenge: Datasets, Tasks, Baselines, and Methods
par: Mu, Bingshen, et autres
Publié: (2025)

Enhancing Non-Core Language Instruction-Following in Speech LLMs via Semi-Implicit Cross-Lingual CoT Reasoning
par: Xue, Hongfei, et autres
Publié: (2025)

Semantic-Aware Interruption Detection in Spoken Dialogue Systems: Benchmark, Metric, and Model
par: Xia, Kangxiang, et autres
Publié: (2026)

Delayed-KD: Delayed Knowledge Distillation based CTC for Low-Latency Streaming ASR
par: Li, Longhao, et autres
Publié: (2025)

Custom Data Augmentation for low resource ASR using Bark and Retrieval-Based Voice Conversion
par: Kamble, Anand, et autres
Publié: (2023)

Ideal-LLM: Integrating Dual Encoders and Language-Adapted LLM for Multilingual Speech-to-Text
par: Xue, Hongfei, et autres
Publié: (2024)

LA-RAG:Enhancing LLM-based ASR Accuracy with Retrieval-Augmented Generation
par: Li, Shaojun, et autres
Publié: (2024)

CoHear: Conversation Enhancement via Multi-Earphone Collaboration
par: He, Lixing, et autres
Publié: (2025)

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages
par: Shao, Mingchen, et autres
Publié: (2025)

Multi-level Temporal-channel Speaker Retrieval for Zero-shot Voice Conversion
par: Wang, Zhichao, et autres
Publié: (2023)

ASR Benchmarking: Need for a More Representative Conversational Dataset
par: Maheshwari, Gaurav, et autres
Publié: (2024)

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR
par: Xie, Yuan, et autres
Publié: (2026)

OSUM-Pangu: An Open-Source Multidimension Speech Understanding Foundation Model Built upon OpenPangu on Ascend NPUs
par: Liao, Yujie, et autres
Publié: (2026)

WenetSpeech-Wu: Datasets, Benchmarks, and Models for a Unified Chinese Wu Dialect Speech Processing Ecosystem
par: Wang, Chengyou, et autres
Publié: (2026)

Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation
par: Ghosh, Sreyan, et autres
Publié: (2024)

EASY: Emotion-aware Speaker Anonymization via Factorized Distillation
par: Yao, Jixun, et autres
Publié: (2025)

Towards Environmental Preference Based Speech Enhancement For Individualised Multi-Modal Hearing Aids
par: Kirton-Wingate, Jasper, et autres
Publié: (2024)

Distilling LLM Semantic Priors into Encoder-Only Multi-Talker ASR with Talker-Count Routing
par: Shi, Hao, et autres
Publié: (2026)

BR-ASR: Efficient and Scalable Bias Retrieval Framework for Contextual Biasing ASR in Speech LLM
par: Gong, Xun, et autres
Publié: (2025)

Advancing Hearing Assessment: An ASR-Based Frequency-Specific Speech Test for Diagnosing Presbycusis
par: Bleeck, Stefan
Publié: (2025)

The ICASSP 2026 Automatic Song Aesthetics Evaluation Challenge
par: Ma, Guobin, et autres
Publié: (2026)

Seeing the Context: Rich Visual Context-Aware Speech Recognition via Multimodal Reasoning
par: Tian, Wenjie, et autres
Publié: (2026)

Benchmarking Japanese Speech Recognition on ASR-LLM Setups with Multi-Pass Augmented Generative Error Correction
par: Ko, Yuka, et autres
Publié: (2024)

Less is More: Data Curation Matters in Scaling Speech Enhancement
par: Li, Chenda, et autres
Publié: (2025)

Soundwave: Less is More for Speech-Text Alignment in LLMs
par: Zhang, Yuhao, et autres
Publié: (2025)

Identifying Hearing Difficulty Moments in Conversational Audio
par: Collins, Jack, et autres
Publié: (2025)

Synthetic Data Domain Adaptation for ASR via LLM-based Text and Phonetic Respelling Augmentation
par: Yamashita, Natsuo, et autres
Publié: (2026)

The TEA-ASLP System for Multilingual Conversational Speech Recognition and Speech Diarization in MLC-SLM 2025 Challenge
par: Xue, Hongfei, et autres
Publié: (2025)

Few-Shot Accent Synthesis for ASR with LLM-Guided Phoneme Editing
par: Halychanskyi, Yurii, et autres
Publié: (2026)