Year: 2025
Type: conference-paper
Abstract: We introduce V-AURA, the first autoregressive model to achieve high temporal alignment and relevance in video-to-audio generation. V-AURA uses a high-framerate visual feature extractor and a cross-modal audio-visual feature fusion strategy to capture fine-grained visual motion events and ensure precise temporal alignment. Additionally, we propose VisualSound, a benchmark dataset with high audio-visual relevance. VisualSound is based on VGGSound, a video dataset consisting of in-the-wild samples extracted from YouTube. During the curation, we remove samples where auditory events are not aligned with the visual ones. V-AURA outperforms current state-of-the-art models in temporal alignment and semantic relevance while maintaining comparable audio quality. Code, samples, VisualSound and models are available at v-aura.notion.site.
Authors: Ilpo Viertola, Vladimir Iashin, Esa Rahtu
Institutions: Tampere University, University of Oxford
Language: English
Topic: Music and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Academy of Finland
OpenAlex ID: W4408352828