Temporally Aligned Audio for Video with Autoregression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Viertola, Ilpo, Iashin, Vladimir, Rahtu, Esa
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909321287172096
author Viertola, Ilpo
Iashin, Vladimir
Rahtu, Esa
author_facet Viertola, Ilpo
Iashin, Vladimir
Rahtu, Esa
contents 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 https://v-aura.notion.site
format Preprint
id arxiv_https___arxiv_org_abs_2409_13689
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Temporally Aligned Audio for Video with Autoregression
Viertola, Ilpo
Iashin, Vladimir
Rahtu, Esa
Computer Vision and Pattern Recognition
Multimedia
Sound
Audio and Speech Processing
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 https://v-aura.notion.site
title Temporally Aligned Audio for Video with Autoregression
topic Computer Vision and Pattern Recognition
Multimedia
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2409.13689