Imagen de Portada

Listening, Imagining & Refining: A Heuristic Optimized ASR Correction Framework with LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Yutong, Zhang, Ziyue, Huang, Cheng, Yu, Yongbin, Wang, Xiangxiang, Cai, Yuqing, Tashi, Nyima
Formato:	Preprint
Publicado:	2025
Materias:	Audio and Speech Processing Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

FMSD-TTS: Few-shot Multi-Speaker Multi-Dialect Text-to-Speech Synthesis for Ü-Tsang, Amdo and Kham Speech Dataset Generation
por: Liu, Yutong, et al.
Publicado: (2025)

A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data
por: Chou, Cheng-Kang, et al.
Publicado: (2025)

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

Audio-Conditioned Diffusion LLMs for ASR and Deliberation Processing
por: Wang, Mengqi, et al.
Publicado: (2025)

Zero-Shot Imagined Speech Decoding via Imagined-to-Listened MEG Mapping
por: Maghsoudi, Maryam, et al.
Publicado: (2026)

AS-ASR: A Lightweight Framework for Aphasia-Specific Automatic Speech Recognition
por: Bao, Chen, et al.
Publicado: (2025)

Can Speech LLMs Think while Listening?
por: Shih, Yi-Jen, et al.
Publicado: (2025)

Speech Recognition on TV Series with Video-guided Post-ASR Correction
por: Yang, Haoyuan, et al.
Publicado: (2025)

Tracking Listener Attention: Gaze-Guided Audio-Visual Speech Enhancement Framework
por: Yang, Hsiang-Cheng, et al.
Publicado: (2026)

Listening and Seeing Again: Generative Error Correction for Audio-Visual Speech Recognition
por: Liu, Rui, et al.
Publicado: (2025)

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

Advancing Multi-talker ASR Performance with Large Language Models
por: Shi, Mohan, et al.
Publicado: (2024)

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

Transferable Adversarial Attacks against ASR
por: Gao, Xiaoxue, et al.
Publicado: (2024)

VIBEVOICE-ASR Technical Report
por: Peng, Zhiliang, et al.
Publicado: (2026)

Bridging ASR and LLMs for Dysarthric Speech Recognition: Benchmarking Self-Supervised and Generative Approaches
por: Aboeitta, Ahmed, et al.
Publicado: (2025)

Cross-modal Knowledge Transfer Learning as Graph Matching Based on Optimal Transport for ASR
por: Lu, Xugang, et al.
Publicado: (2025)

A Convolutional Framework for Mapping Imagined Auditory MEG into Listened Brain Responses
por: Maghsoudi, Maryam, et al.
Publicado: (2025)

Progressive Residual Extraction based Pre-training for Speech Representation Learning
por: Wang, Tianrui, et al.
Publicado: (2024)

Retrieval-Augmented Self-Taught Reasoning Model with Adaptive Chain-of-Thought for ASR Named Entity Correction
por: An, Junjie, et al.
Publicado: (2026)

FlanEC: Exploring Flan-T5 for Post-ASR Error Correction
por: La Quatra, Moreno, et al.
Publicado: (2025)

Better Pseudo-labeling with Multi-ASR Fusion and Error Correction by SpeechLLM
por: Prakash, Jeena, et al.
Publicado: (2025)

OCR-Enhanced Multimodal ASR Can Read While Listening
por: Chen, Junli, et al.
Publicado: (2026)

CHSER: A Dataset and Case Study on Generative Speech Error Correction for Child ASR
por: Shankar, Natarajan Balaji, et al.
Publicado: (2025)

Leveraging ASR Pretrained Conformers for Speaker Verification through Transfer Learning and Knowledge Distillation
por: Cai, Danwei, et al.
Publicado: (2023)

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

Training-Free Intelligibility-Guided Observation Addition for Noisy ASR
por: Li, Haoyang, et al.
Publicado: (2026)

Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities
por: Saon, George, et al.
Publicado: (2025)

Leveraging Multiple Speech Enhancers for Non-Intrusive Intelligibility Prediction for Hearing-Impaired Listeners
por: Cao, Boxuan, et al.
Publicado: (2025)

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

Self-supervised ASR Models and Features For Dysarthric and Elderly Speech Recognition
por: Hu, Shujie, et al.
Publicado: (2024)

Enhanced Generative Machine Listener
por: Raj, Vishnu, et al.
Publicado: (2025)

Unifying Streaming and Non-streaming Zipformer-based ASR
por: Sharma, Bidisha, et al.
Publicado: (2025)

LTS-VoiceAgent: A Listen-Think-Speak Framework for Efficient Streaming Voice Interaction via Semantic Triggering and Incremental Reasoning
por: Zou, Wenhao, et al.
Publicado: (2026)

Listen, Think, and Understand
por: Gong, Yuan, et al.
Publicado: (2023)

AdaLTM: Adaptive Layer-wise Task Vector Merging for Categorical Speech Emotion Recognition with ASR Knowledge Integration
por: Lee, Chia-Yu, et al.
Publicado: (2026)

The Cascade Equivalence Hypothesis: When Do Speech LLMs Behave Like ASR$\rightarrow$LLM Pipelines?
por: Billa, Jayadev
Publicado: (2026)

Align-Consistency: Improving Non-autoregressive and Semi-supervised ASR with Consistency Regularization
por: Huang, Wanting, et al.
Publicado: (2026)

MDM-ASR: Bridging Accuracy and Efficiency in ASR with Diffusion-Based Non-Autoregressive Decoding
por: Yen, Hao, et al.
Publicado: (2026)

UniVoice: Unifying Autoregressive ASR and Flow-Matching based TTS with Large Language Models
por: Guan, Wenhao, et al.
Publicado: (2025)