Read, Watch and Scream! Sound Generation from Text and Video

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jeong, Yujin, Kim, Yunji, Chun, Sanghyuk, Lee, Jiyoung
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917879282139136
author Jeong, Yujin
Kim, Yunji
Chun, Sanghyuk
Lee, Jiyoung
author_facet Jeong, Yujin
Kim, Yunji
Chun, Sanghyuk
Lee, Jiyoung
contents Despite the impressive progress of multimodal generative models, video-to-audio generation still suffers from limited performance and limits the flexibility to prioritize sound synthesis for specific objects within the scene. Conversely, text-to-audio generation methods generate high-quality audio but pose challenges in ensuring comprehensive scene depiction and time-varying control. To tackle these challenges, we propose a novel video-and-text-to-audio generation method, called \ours, where video serves as a conditional control for a text-to-audio generation model. Especially, our method estimates the structural information of sound (namely, energy) from the video while receiving key content cues from a user prompt. We employ a well-performing text-to-audio model to consolidate the video control, which is much more efficient for training multimodal diffusion models with massive triplet-paired (audio-video-text) data. In addition, by separating the generative components of audio, it becomes a more flexible system that allows users to freely adjust the energy, surrounding environment, and primary sound source according to their preferences. Experimental results demonstrate that our method shows superiority in terms of quality, controllability, and training efficiency. Code and demo are available at https://naver-ai.github.io/rewas.
format Preprint
id arxiv_https___arxiv_org_abs_2407_05551
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Read, Watch and Scream! Sound Generation from Text and Video
Jeong, Yujin
Kim, Yunji
Chun, Sanghyuk
Lee, Jiyoung
Computer Vision and Pattern Recognition
Multimedia
Sound
Audio and Speech Processing
Despite the impressive progress of multimodal generative models, video-to-audio generation still suffers from limited performance and limits the flexibility to prioritize sound synthesis for specific objects within the scene. Conversely, text-to-audio generation methods generate high-quality audio but pose challenges in ensuring comprehensive scene depiction and time-varying control. To tackle these challenges, we propose a novel video-and-text-to-audio generation method, called \ours, where video serves as a conditional control for a text-to-audio generation model. Especially, our method estimates the structural information of sound (namely, energy) from the video while receiving key content cues from a user prompt. We employ a well-performing text-to-audio model to consolidate the video control, which is much more efficient for training multimodal diffusion models with massive triplet-paired (audio-video-text) data. In addition, by separating the generative components of audio, it becomes a more flexible system that allows users to freely adjust the energy, surrounding environment, and primary sound source according to their preferences. Experimental results demonstrate that our method shows superiority in terms of quality, controllability, and training efficiency. Code and demo are available at https://naver-ai.github.io/rewas.
title Read, Watch and Scream! Sound Generation from Text and Video
topic Computer Vision and Pattern Recognition
Multimedia
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2407.05551