Audio Morphing Using Matrix Decomposition and Optimal Transport

Gerard Roma; Owen Green; Pierre Alexandre Tremblay

Audio Morphing Using Matrix Decomposition and Optimal Transport

Gerard Roma, Owen Green, Pierre Alexandre Tremblay

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This paper presents a system for morphing between audio recordings in a continuous parameter space. The proposed approach combines matrix decompositions used for audio source separation with displacement interpolation enabled by 1D optimal transport. Using NMF decompositions, the system allows varying the timbre of a sound in real time, while reproducing the temporal activations of its main components. Using HPSS as a preprocessing step, the system affords more detailed control of the interpolation in perceptually meaningful dimensions.

Original language	English
Title of host publication	Proceedings of the 23rd International Conference on Digital Audio Effects
Editors	Gianpaolo Evangelista
Pages	147-154
Number of pages	8
Volume	1
Publication status	Published - 9 Sep 2020
Event	23rd International Conference on Digital Audio Effects - Virtual Conference Duration: 9 Sep 2021 → 11 Sep 2021 Conference number: 23 http://www.dafx.de/index.html

Publication series

Name	Digital Audio Effects (DAFx) Proceedings Series
ISSN (Print)	2413-6700
ISSN (Electronic)	2413-6689

Conference

Conference	23rd International Conference on Digital Audio Effects
Abbreviated title	eDAFx2020
Period	9/09/21 → 11/09/21
Internet address	http://www.dafx.de/index.html

Access to Document

https://dafx2020.mdw.ac.at/proceedings/DAFx2020Proceedings.pdfLicence: CC BY

Cite this

@inproceedings{17e543e5fadc4946bf3bddafc3093494,

title = "Audio Morphing Using Matrix Decomposition and Optimal Transport",

abstract = "This paper presents a system for morphing between audio recordings in a continuous parameter space. The proposed approach combines matrix decompositions used for audio source separation with displacement interpolation enabled by 1D optimal transport. Using NMF decompositions, the system allows varying the timbre of a sound in real time, while reproducing the temporal activations of its main components. Using HPSS as a preprocessing step, the system affords more detailed control of the interpolation in perceptually meaningful dimensions.",

keywords = "Audio Morphing, Matrix Decomposition, Optimal Transport",

author = "Gerard Roma and Owen Green and Tremblay, {Pierre Alexandre}",

year = "2020",

month = sep,

day = "9",

language = "English",

volume = "1",

series = "Digital Audio Effects (DAFx) Proceedings Series",

pages = "147--154",

editor = "Gianpaolo Evangelista",

booktitle = "Proceedings of the 23rd International Conference on Digital Audio Effects",

note = "23rd International Conference on Digital Audio Effects, eDAFx2020 ; Conference date: 09-09-2021 Through 11-09-2021",

url = "http://www.dafx.de/index.html",

}

Roma, G, Green, O & Tremblay, PA 2020, Audio Morphing Using Matrix Decomposition and Optimal Transport. in G Evangelista (ed.), Proceedings of the 23rd International Conference on Digital Audio Effects. vol. 1, Digital Audio Effects (DAFx) Proceedings Series, pp. 147-154, 23rd International Conference on Digital Audio Effects, 9/09/21. <https://dafx2020.mdw.ac.at/proceedings/DAFx2020Proceedings.pdf>

Audio Morphing Using Matrix Decomposition and Optimal Transport. / Roma, Gerard; Green, Owen; Tremblay, Pierre Alexandre.

Proceedings of the 23rd International Conference on Digital Audio Effects. ed. / Gianpaolo Evangelista. Vol. 1 2020. p. 147-154 (Digital Audio Effects (DAFx) Proceedings Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Audio Morphing Using Matrix Decomposition and Optimal Transport

AU - Roma, Gerard

AU - Green, Owen

AU - Tremblay, Pierre Alexandre

N1 - Conference code: 23

PY - 2020/9/9

Y1 - 2020/9/9

N2 - This paper presents a system for morphing between audio recordings in a continuous parameter space. The proposed approach combines matrix decompositions used for audio source separation with displacement interpolation enabled by 1D optimal transport. Using NMF decompositions, the system allows varying the timbre of a sound in real time, while reproducing the temporal activations of its main components. Using HPSS as a preprocessing step, the system affords more detailed control of the interpolation in perceptually meaningful dimensions.

AB - This paper presents a system for morphing between audio recordings in a continuous parameter space. The proposed approach combines matrix decompositions used for audio source separation with displacement interpolation enabled by 1D optimal transport. Using NMF decompositions, the system allows varying the timbre of a sound in real time, while reproducing the temporal activations of its main components. Using HPSS as a preprocessing step, the system affords more detailed control of the interpolation in perceptually meaningful dimensions.

KW - Audio Morphing

KW - Matrix Decomposition

KW - Optimal Transport

UR - https://dafx2020.mdw.ac.at/

UR - http://www.scopus.com/inward/record.url?scp=85130693365&partnerID=8YFLogxK

M3 - Conference contribution

VL - 1

T3 - Digital Audio Effects (DAFx) Proceedings Series

SP - 147

EP - 154

BT - Proceedings of the 23rd International Conference on Digital Audio Effects

A2 - Evangelista, Gianpaolo

T2 - 23rd International Conference on Digital Audio Effects

Y2 - 9 September 2021 through 11 September 2021

ER -

Audio Morphing Using Matrix Decomposition and Optimal Transport

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this