Saved in:
Bibliographic Details
Main Authors: Manor, Hila, Michaeli, Tomer
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.10009
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910461487742976
author Manor, Hila
Michaeli, Tomer
author_facet Manor, Hila
Michaeli, Tomer
contents Editing signals using large pre-trained models, in a zero-shot manner, has recently seen rapid advancements in the image domain. However, this wave has yet to reach the audio domain. In this paper, we explore two zero-shot editing techniques for audio signals, which use DDPM inversion with pre-trained diffusion models. The first, which we coin ZEro-shot Text-based Audio (ZETA) editing, is adopted from the image domain. The second, named ZEro-shot UnSupervized (ZEUS) editing, is a novel approach for discovering semantically meaningful editing directions without supervision. When applied to music signals, this method exposes a range of musically interesting modifications, from controlling the participation of specific instruments to improvisations on the melody. Samples and code can be found in https://hilamanor.github.io/AudioEditing/ .
format Preprint
id arxiv_https___arxiv_org_abs_2402_10009
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversion
Manor, Hila
Michaeli, Tomer
Sound
Machine Learning
Audio and Speech Processing
Editing signals using large pre-trained models, in a zero-shot manner, has recently seen rapid advancements in the image domain. However, this wave has yet to reach the audio domain. In this paper, we explore two zero-shot editing techniques for audio signals, which use DDPM inversion with pre-trained diffusion models. The first, which we coin ZEro-shot Text-based Audio (ZETA) editing, is adopted from the image domain. The second, named ZEro-shot UnSupervized (ZEUS) editing, is a novel approach for discovering semantically meaningful editing directions without supervision. When applied to music signals, this method exposes a range of musically interesting modifications, from controlling the participation of specific instruments to improvisations on the melody. Samples and code can be found in https://hilamanor.github.io/AudioEditing/ .
title Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversion
topic Sound
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2402.10009