Enhancing Audio Generation Diversity with Visual Information

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xie, Zeyu, Li, Baihan, Xu, Xuenan, Wu, Mengyue, Yu, Kai
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910350781186048
author Xie, Zeyu
Li, Baihan
Xu, Xuenan
Wu, Mengyue
Yu, Kai
author_facet Xie, Zeyu
Li, Baihan
Xu, Xuenan
Wu, Mengyue
Yu, Kai
contents Audio and sound generation has garnered significant attention in recent years, with a primary focus on improving the quality of generated audios. However, there has been limited research on enhancing the diversity of generated audio, particularly when it comes to audio generation within specific categories. Current models tend to produce homogeneous audio samples within a category. This work aims to address this limitation by improving the diversity of generated audio with visual information. We propose a clustering-based method, leveraging visual information to guide the model in generating distinct audio content within each category. Results on seven categories indicate that extra visual input can largely enhance audio generation diversity. Audio samples are available at https://zeyuxie29.github.io/DiverseAudioGeneration.
format Preprint
id arxiv_https___arxiv_org_abs_2403_01278
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing Audio Generation Diversity with Visual Information
Xie, Zeyu
Li, Baihan
Xu, Xuenan
Wu, Mengyue
Yu, Kai
Sound
Audio and Speech Processing
I.2
Audio and sound generation has garnered significant attention in recent years, with a primary focus on improving the quality of generated audios. However, there has been limited research on enhancing the diversity of generated audio, particularly when it comes to audio generation within specific categories. Current models tend to produce homogeneous audio samples within a category. This work aims to address this limitation by improving the diversity of generated audio with visual information. We propose a clustering-based method, leveraging visual information to guide the model in generating distinct audio content within each category. Results on seven categories indicate that extra visual input can largely enhance audio generation diversity. Audio samples are available at https://zeyuxie29.github.io/DiverseAudioGeneration.
title Enhancing Audio Generation Diversity with Visual Information
topic Sound
Audio and Speech Processing
I.2
url https://arxiv.org/abs/2403.01278