YingSound: Video-Guided Sound Effects Generation with Multi-modal Chain-of-Thought Controls

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Zihao, Zhang, Haomin, Di, Xinhan, Wang, Haoyu, Shan, Sizhe, Zheng, Junjie, Liang, Yunming, Fan, Yihan, Zhu, Xinfa, Tian, Wenjie, Wang, Yihua, Ding, Chaofan, Xie, Lei
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917867055742976
author Chen, Zihao
Zhang, Haomin
Di, Xinhan
Wang, Haoyu
Shan, Sizhe
Zheng, Junjie
Liang, Yunming
Fan, Yihan
Zhu, Xinfa
Tian, Wenjie
Wang, Yihua
Ding, Chaofan
Xie, Lei
author_facet Chen, Zihao
Zhang, Haomin
Di, Xinhan
Wang, Haoyu
Shan, Sizhe
Zheng, Junjie
Liang, Yunming
Fan, Yihan
Zhu, Xinfa
Tian, Wenjie
Wang, Yihua
Ding, Chaofan
Xie, Lei
contents Generating sound effects for product-level videos, where only a small amount of labeled data is available for diverse scenes, requires the production of high-quality sounds in few-shot settings. To tackle the challenge of limited labeled data in real-world scenes, we introduce YingSound, a foundation model designed for video-guided sound generation that supports high-quality audio generation in few-shot settings. Specifically, YingSound consists of two major modules. The first module uses a conditional flow matching transformer to achieve effective semantic alignment in sound generation across audio and visual modalities. This module aims to build a learnable audio-visual aggregator (AVA) that integrates high-resolution visual features with corresponding audio features at multiple stages. The second module is developed with a proposed multi-modal visual-audio chain-of-thought (CoT) approach to generate finer sound effects in few-shot settings. Finally, an industry-standard video-to-audio (V2A) dataset that encompasses various real-world scenarios is presented. We show that YingSound effectively generates high-quality synchronized sounds across diverse conditional inputs through automated evaluations and human studies. Project Page: \url{https://giantailab.github.io/yingsound/}
format Preprint
id arxiv_https___arxiv_org_abs_2412_09168
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle YingSound: Video-Guided Sound Effects Generation with Multi-modal Chain-of-Thought Controls
Chen, Zihao
Zhang, Haomin
Di, Xinhan
Wang, Haoyu
Shan, Sizhe
Zheng, Junjie
Liang, Yunming
Fan, Yihan
Zhu, Xinfa
Tian, Wenjie
Wang, Yihua
Ding, Chaofan
Xie, Lei
Sound
Computer Vision and Pattern Recognition
Multimedia
Audio and Speech Processing
Generating sound effects for product-level videos, where only a small amount of labeled data is available for diverse scenes, requires the production of high-quality sounds in few-shot settings. To tackle the challenge of limited labeled data in real-world scenes, we introduce YingSound, a foundation model designed for video-guided sound generation that supports high-quality audio generation in few-shot settings. Specifically, YingSound consists of two major modules. The first module uses a conditional flow matching transformer to achieve effective semantic alignment in sound generation across audio and visual modalities. This module aims to build a learnable audio-visual aggregator (AVA) that integrates high-resolution visual features with corresponding audio features at multiple stages. The second module is developed with a proposed multi-modal visual-audio chain-of-thought (CoT) approach to generate finer sound effects in few-shot settings. Finally, an industry-standard video-to-audio (V2A) dataset that encompasses various real-world scenarios is presented. We show that YingSound effectively generates high-quality synchronized sounds across diverse conditional inputs through automated evaluations and human studies. Project Page: \url{https://giantailab.github.io/yingsound/}
title YingSound: Video-Guided Sound Effects Generation with Multi-modal Chain-of-Thought Controls
topic Sound
Computer Vision and Pattern Recognition
Multimedia
Audio and Speech Processing
url https://arxiv.org/abs/2412.09168