Time scale modification of audio using non-negative matrix factorization

Gerard Roma; Owen Green; Pierre Alexandre Tremblay

Time scale modification of audio using non-negative matrix factorization

Gerard Roma, Owen Green, Pierre Alexandre Tremblay

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

Abstract

This paper introduces an algorithm for time-scale modification of audio signals based on using non-negative matrix factorization. The activation signals attributed to the detected components are used for identifying sound events. The segmentation of these events is used for detecting and preserving transients. In addition, the algorithm introduces the possibility of preserving the envelopes of overlapping sound events while globally modifying the duration of an audio clip.

Original language	English
Title of host publication	Proceedings of the 22nd International Conference on Digital Audio Effects
Editors	Ryan Stables, Jason Hockman, David Moffat
Place of Publication	Birmingham
Number of pages	6
Publication status	Published - 2 Sept 2019
Externally published	Yes
Event	22nd International Conference on Digital Audio Effects - Birmingham City University, Birmingham, United Kingdom Duration: 2 Sept 2019 → 6 Sept 2019

Academic conference

Academic conference	22nd International Conference on Digital Audio Effects
Abbreviated title	DAFx 2019
Country/Territory	United Kingdom
City	Birmingham
Period	2/09/19 → 6/09/19

Keywords

Audio Signals
Non-Negative Matrix Factorization
Transients
Algorithm

Access to Document

https://dafx2019.bcu.ac.uk/assets/DAFx19Proceedings.pdfLicence: Unspecified

Cite this

@inproceedings{4276dfa83cbd43c0abf2956e54a7ae4b,

title = "Time scale modification of audio using non-negative matrix factorization",

abstract = "This paper introduces an algorithm for time-scale modification of audio signals based on using non-negative matrix factorization. The activation signals attributed to the detected components are used for identifying sound events. The segmentation of these events is used for detecting and preserving transients. In addition, the algorithm introduces the possibility of preserving the envelopes of overlapping sound events while globally modifying the duration of an audio clip.",

keywords = "Audio Signals, Non-Negative Matrix Factorization, Transients, Algorithm",

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

year = "2019",

month = sep,

day = "2",

language = "English",

editor = "Ryan Stables and Jason Hockman and David Moffat",

booktitle = "Proceedings of the 22nd International Conference on Digital Audio Effects",

note = "22nd International Conference on Digital Audio Effects, DAFx 2019 ; Conference date: 02-09-2019 Through 06-09-2019",

}

Roma, G, Green, O & Tremblay, PA 2019, Time scale modification of audio using non-negative matrix factorization. in R Stables, J Hockman & D Moffat (eds), Proceedings of the 22nd International Conference on Digital Audio Effects. Birmingham, 22nd International Conference on Digital Audio Effects, Birmingham, United Kingdom, 2/09/19. <https://dafx2019.bcu.ac.uk/assets/DAFx19Proceedings.pdf>

Time scale modification of audio using non-negative matrix factorization. / Roma, Gerard; Green, Owen; Tremblay, Pierre Alexandre.
Proceedings of the 22nd International Conference on Digital Audio Effects. ed. / Ryan Stables; Jason Hockman; David Moffat. Birmingham, 2019.

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

TY - GEN

T1 - Time scale modification of audio using non-negative matrix factorization

AU - Roma, Gerard

AU - Green, Owen

AU - Tremblay, Pierre Alexandre

PY - 2019/9/2

Y1 - 2019/9/2

N2 - This paper introduces an algorithm for time-scale modification of audio signals based on using non-negative matrix factorization. The activation signals attributed to the detected components are used for identifying sound events. The segmentation of these events is used for detecting and preserving transients. In addition, the algorithm introduces the possibility of preserving the envelopes of overlapping sound events while globally modifying the duration of an audio clip.

AB - This paper introduces an algorithm for time-scale modification of audio signals based on using non-negative matrix factorization. The activation signals attributed to the detected components are used for identifying sound events. The segmentation of these events is used for detecting and preserving transients. In addition, the algorithm introduces the possibility of preserving the envelopes of overlapping sound events while globally modifying the duration of an audio clip.

KW - Audio Signals

KW - Non-Negative Matrix Factorization

KW - Transients

KW - Algorithm

M3 - Conference contribution

BT - Proceedings of the 22nd International Conference on Digital Audio Effects

A2 - Stables, Ryan

A2 - Hockman, Jason

A2 - Moffat, David

CY - Birmingham

T2 - 22nd International Conference on Digital Audio Effects

Y2 - 2 September 2019 through 6 September 2019

ER -

Time scale modification of audio using non-negative matrix factorization

Abstract

Academic conference

Keywords

Access to Document

Fingerprint

Cite this