Cover Image

Probing Cross-modal Information Hubs in Audio-Visual LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jung, Jihoo, Jung, Chaeyoung, Kim, Ji-Hoon, Chung, Joon Son
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FlowAVSE: Efficient Audio-Visual Speech Enhancement with Conditional Flow Matching
by: Jung, Chaeyoung, et al.
Published: (2024)

InfiniteAudio: Infinite-Length Audio Generation with Consistency
by: Jung, Chaeyoung, et al.
Published: (2025)

From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech
by: Kim, Ji-Hoon, et al.
Published: (2025)

SEED: Speaker Embedding Enhancement Diffusion Model
by: Nam, KiHyun, et al.
Published: (2025)

UNMIXX: Untangling Highly Correlated Singing Voices Mixtures
by: Jung, Jihoo, et al.
Published: (2026)

MATE: Matryoshka Audio-Text Embeddings for Open-Vocabulary Keyword Spotting
by: Jung, Youngmoon, et al.
Published: (2026)

Let There Be Sound: Reconstructing High Quality Speech from Silent Videos
by: Kim, Ji-Hoon, et al.
Published: (2023)

TAVID: Text-Driven Audio-Visual Interactive Dialogue Generation
by: Kim, Ji-Hoon, et al.
Published: (2025)

Adversarial Deep Metric Learning for Cross-Modal Audio-Text Alignment in Open-Vocabulary Keyword Spotting
by: Jung, Youngmoon, et al.
Published: (2025)

EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning
by: Kim, Jaeyeon, et al.
Published: (2024)

FreGrad: Lightweight and Fast Frequency-aware Diffusion Vocoder
by: Nguyen, Tan Dat, et al.
Published: (2024)

CrossSpeech++: Cross-lingual Speech Synthesis with Decoupled Language and Speaker Generation
by: Kim, Ji-Hoon, et al.
Published: (2024)

LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport
by: Rho, Kyeongha, et al.
Published: (2025)

Audio Mamba: Bidirectional State Space Model for Audio Representation Learning
by: Erol, Mehmet Hamza, et al.
Published: (2024)

Relational Proxy Loss for Audio-Text based Keyword Spotting
by: Jung, Youngmoon, et al.
Published: (2024)

ElasticAST: An Audio Spectrogram Transformer for All Length and Resolutions
by: Feng, Jiu, et al.
Published: (2024)

VoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech Synthesis
by: Jung, Jaemin, et al.
Published: (2024)

Expanding on EnCLAP with Auxiliary Retrieval Model for Automated Audio Captioning
by: Kim, Jaeyeon, et al.
Published: (2024)

EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance
by: Kim, Jaeyeon, et al.
Published: (2024)

Accelerating Codec-based Speech Synthesis with Multi-Token Prediction and Speculative Decoding
by: Nguyen, Tan Dat, et al.
Published: (2024)

Bridging the Gap between Audio and Text using Parallel-attention for User-defined Keyword Spotting
by: Kim, Youkyum, et al.
Published: (2024)

DAME: Duration-Aware Matryoshka Embedding for Duration-Robust Speaker Verification
by: Jung, Youngmoon, et al.
Published: (2026)

Text-To-Speech Synthesis In The Wild
by: Jung, Jee-weon, et al.
Published: (2024)

To what extent can ASV systems naturally defend against spoofing attacks?
by: Jung, Jee-weon, et al.
Published: (2024)

The VoxCeleb Speaker Recognition Challenge: A Retrospective
by: Huh, Jaesung, et al.
Published: (2024)

PAL: Probing Audio Encoders via LLMs -- Audio Information Transfer into LLMs
by: Alex, Tony, et al.
Published: (2025)

SCORE: Scaling audio generation using Standardized COmposite REwards
by: Jung, Jaemin, et al.
Published: (2025)

SpoofCeleb: Speech Deepfake Detection and SASV In The Wild
by: Jung, Jee-weon, et al.
Published: (2024)

Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation
by: Zhang, Kang, et al.
Published: (2025)

Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models
by: Jung, Kyudan, et al.
Published: (2026)

LAV: Audio-Driven Dynamic Visual Generation with Neural Compression and StyleGAN2
by: Jung, Jongmin, et al.
Published: (2025)

MamTra: A Hybrid Mamba-Transformer Backbone for Speech Synthesis
by: Nguyen, Tan Dat, et al.
Published: (2026)

Unified Cross-modal Translation of Score Images, Symbolic Music, and Performance Audio
by: Jung, Jongmin, et al.
Published: (2025)

Improving Noise Robust Audio-Visual Speech Recognition via Router-Gated Cross-Modal Feature Fusion
by: Lim, DongHoon, et al.
Published: (2025)

CORD: Bridging the Audio-Text Reasoning Gap via Weighted On-policy Cross-modal Distillation
by: Hu, Jing, et al.
Published: (2026)

Text-Aware Adapter for Few-Shot Keyword Spotting
by: Jung, Youngmoon, et al.
Published: (2024)

MathReader : Text-to-Speech for Mathematical Documents
by: Hyeon, Sieun, et al.
Published: (2025)

Do Models Hear Like Us? Probing the Representational Alignment of Audio LLMs and Naturalistic EEG
by: Yang, Haoyun, et al.
Published: (2026)

FADEL: Uncertainty-aware Fake Audio Detection with Evidential Deep Learning
by: Kang, Ju Yeon, et al.
Published: (2025)

Plug-and-Steer: Decoupling Separation and Selection in Audio-Visual Target Speaker Extraction
by: Kwak, Doyeop, et al.
Published: (2026)