High-Quality Visually-Guided Sound Separation from Diverse Categories

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Huang, Chao, Liang, Susan, Tian, Yapeng, Kumar, Anurag, Xu, Chenliang
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913541069471744
author Huang, Chao
Liang, Susan
Tian, Yapeng
Kumar, Anurag
Xu, Chenliang
author_facet Huang, Chao
Liang, Susan
Tian, Yapeng
Kumar, Anurag
Xu, Chenliang
contents We propose DAVIS, a Diffusion-based Audio-VIsual Separation framework that solves the audio-visual sound source separation task through generative learning. Existing methods typically frame sound separation as a mask-based regression problem, achieving significant progress. However, they face limitations in capturing the complex data distribution required for high-quality separation of sounds from diverse categories. In contrast, DAVIS leverages a generative diffusion model and a Separation U-Net to synthesize separated sounds directly from Gaussian noise, conditioned on both the audio mixture and the visual information. With its generative objective, DAVIS is better suited to achieving the goal of high-quality sound separation across diverse sound categories. We compare DAVIS to existing state-of-the-art discriminative audio-visual separation methods on the AVE and MUSIC datasets, and results show that DAVIS outperforms other methods in separation quality, demonstrating the advantages of our framework for tackling the audio-visual source separation task.
format Preprint
id arxiv_https___arxiv_org_abs_2308_00122
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle High-Quality Visually-Guided Sound Separation from Diverse Categories
Huang, Chao
Liang, Susan
Tian, Yapeng
Kumar, Anurag
Xu, Chenliang
Computer Vision and Pattern Recognition
Sound
Audio and Speech Processing
We propose DAVIS, a Diffusion-based Audio-VIsual Separation framework that solves the audio-visual sound source separation task through generative learning. Existing methods typically frame sound separation as a mask-based regression problem, achieving significant progress. However, they face limitations in capturing the complex data distribution required for high-quality separation of sounds from diverse categories. In contrast, DAVIS leverages a generative diffusion model and a Separation U-Net to synthesize separated sounds directly from Gaussian noise, conditioned on both the audio mixture and the visual information. With its generative objective, DAVIS is better suited to achieving the goal of high-quality sound separation across diverse sound categories. We compare DAVIS to existing state-of-the-art discriminative audio-visual separation methods on the AVE and MUSIC datasets, and results show that DAVIS outperforms other methods in separation quality, demonstrating the advantages of our framework for tackling the audio-visual source separation task.
title High-Quality Visually-Guided Sound Separation from Diverse Categories
topic Computer Vision and Pattern Recognition
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2308.00122