Towards Controllable Audio Texture Morphing

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gupta, Chitralekha, Kamath, Purnima, Wei, Yize, Li, Zhuoyao, Nanayakkara, Suranga, Wyse, Lonce
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917794404106240
author Gupta, Chitralekha
Kamath, Purnima
Wei, Yize
Li, Zhuoyao
Nanayakkara, Suranga
Wyse, Lonce
author_facet Gupta, Chitralekha
Kamath, Purnima
Wei, Yize
Li, Zhuoyao
Nanayakkara, Suranga
Wyse, Lonce
contents In this paper, we propose a data-driven approach to train a Generative Adversarial Network (GAN) conditioned on "soft-labels" distilled from the penultimate layer of an audio classifier trained on a target set of audio texture classes. We demonstrate that interpolation between such conditions or control vectors provides smooth morphing between the generated audio textures, and shows similar or better audio texture morphing capability compared to the state-of-the-art methods. The proposed approach results in a well-organized latent space that generates novel audio outputs while remaining consistent with the semantics of the conditioning parameters. This is a step towards a general data-driven approach to designing generative audio models with customized controls capable of traversing out-of-distribution regions for novel sound synthesis.
format Preprint
id arxiv_https___arxiv_org_abs_2304_11648
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Towards Controllable Audio Texture Morphing
Gupta, Chitralekha
Kamath, Purnima
Wei, Yize
Li, Zhuoyao
Nanayakkara, Suranga
Wyse, Lonce
Audio and Speech Processing
Artificial Intelligence
Sound
In this paper, we propose a data-driven approach to train a Generative Adversarial Network (GAN) conditioned on "soft-labels" distilled from the penultimate layer of an audio classifier trained on a target set of audio texture classes. We demonstrate that interpolation between such conditions or control vectors provides smooth morphing between the generated audio textures, and shows similar or better audio texture morphing capability compared to the state-of-the-art methods. The proposed approach results in a well-organized latent space that generates novel audio outputs while remaining consistent with the semantics of the conditioning parameters. This is a step towards a general data-driven approach to designing generative audio models with customized controls capable of traversing out-of-distribution regions for novel sound synthesis.
title Towards Controllable Audio Texture Morphing
topic Audio and Speech Processing
Artificial Intelligence
Sound
url https://arxiv.org/abs/2304.11648