Saved in:
Bibliographic Details
Main Authors: Liu, Jing, Lian, Enqi, Deng, Moyao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.11811
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913973971976192
author Liu, Jing
Lian, Enqi
Deng, Moyao
author_facet Liu, Jing
Lian, Enqi
Deng, Moyao
contents An abstract sound is defined as a sound that does not disclose identifiable real-world sound events to a listener. Sound fusion aims to synthesize an original sound and a reference sound to generate a novel sound that exhibits auditory features beyond mere additive superposition of the sound constituents. To achieve this fusion, we employ inversion techniques that preserve essential features of the original sample while enabling controllable synthesis. We propose novel SDE and ODE inversion models based on DPMSolver++ samplers that reverse the sampling process by configuring model outputs as constants, eliminating circular dependencies incurred by noise prediction terms. Our inversion approach requires no prompt conditioning while maintaining flexible guidance during sampling.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11811
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Abstract Sound Fusion with Unconditional Inversion Models
Liu, Jing
Lian, Enqi
Deng, Moyao
Sound
Artificial Intelligence
Audio and Speech Processing
An abstract sound is defined as a sound that does not disclose identifiable real-world sound events to a listener. Sound fusion aims to synthesize an original sound and a reference sound to generate a novel sound that exhibits auditory features beyond mere additive superposition of the sound constituents. To achieve this fusion, we employ inversion techniques that preserve essential features of the original sample while enabling controllable synthesis. We propose novel SDE and ODE inversion models based on DPMSolver++ samplers that reverse the sampling process by configuring model outputs as constants, eliminating circular dependencies incurred by noise prediction terms. Our inversion approach requires no prompt conditioning while maintaining flexible guidance during sampling.
title Abstract Sound Fusion with Unconditional Inversion Models
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2506.11811