paper-with-me

Papers

Audio-visual Contrastive Alignment for Diffusion-based Visual-conditioned Speech Enhancement

2026-06-16 · Colombe Mboungou, Mostafa Sadeghi, Jean-Eudes Ayilo, Romain Serizel arxiv

Audio-visual speech enhancement (AVSE) exploits visual cues such as lip movements to recover speech in noisy environments. Recent work introduced diffusion-based unsupervised AVSE, where a speech diffusion model conditioned on visual features via cross-attention is trained and used as a data-driven prior for posterior sampling-based speech enhancement. Despite promising performance over its audio-only counterpart, the impact of explicitly enforcing cross-modal alignment in the fusion remains unclear. In this work, we propose to augment the diffusion training objective with a contrastive audio-visual loss to encourage stronger use of visual information while keeping the posterior sampling framework unchanged. Experiments across matched and mismatched test data show consistent improvements in interference suppression, signal reconstruction, and perceptual quality, with the largest gains at low SNRs. Code is available at https://github.com/ cexauce/AV-CA-DiffUSE

📄 PDF Abstract BibTeX arXiv:2606.23712

Code (0)

등록된 구현이 없습니다.

Tasks

Speech Enhancement

Similar Papers 제목 키워드 기반

CMMD: Contrastive Multi-Modal Diffusion for Video-Audio Conditional Modeling

2023-12-08 · Ruihan Yang, Hannes Gamper, Sebastian Braun

We introduce a multi-modal diffusion model tailored for the bi-directional conditional generation of video and audio. We propose a joint contrastive training loss to improve the synchronization between visual and auditor…

Audio Generation

DiffAVA: Personalized Text-to-Audio Generation with Visual Alignment

2023-05-22 · Shentong Mo, Jing Shi, Yapeng Tian

Text-to-audio (TTA) generation is a recent popular problem that aims to synthesize general audio given text descriptions. Previous methods utilized latent diffusion models to learn audio embedding in a latent space with …

AudioCapsAudio GenerationContrastive Learning

Text-to-Audio Generation Synchronized with Videos

2024-03-08 · Shentong Mo, Jing Shi, Yapeng Tian

In recent times, the focus on text-to-audio (TTA) generation has intensified, as researchers strive to synthesize audio from textual descriptions. However, most existing methods, though leveraging latent diffusion models…

AudioCapsAudio GenerationContrastive Learning

Contrastive Conditional Latent Diffusion for Audio-visual Segmentation

2023-07-31 · Yuxin Mao, Jing Zhang, Mochu Xiang, Yunqiu Lv 외

We propose a latent diffusion model with contrastive learning for audio-visual segmentation (AVS) to extensively explore the contribution of audio. We interpret AVS as a conditional generation task, where audio is define…

Contrastive LearningDenoisingRepresentation LearningSegmentation

Language-Guided Contrastive Audio-Visual Masked Autoencoder with Automatically Generated Audio-Visual-Text Triplets from Videos

2025-07-16 · Yuchi Ishikawa, Shota Nakada, Hokuto Munakata, Kazuhiro Saito 외

In this paper, we propose Language-Guided Contrastive Audio-Visual Masked Autoencoders (LG-CAV-MAE) to improve audio-visual representation learning. LG-CAV-MAE integrates a pretrained text encoder into contrastive audio-…

Image CaptioningRepresentation LearningRetrieval