Stationary/transient audio separation using convolutional autoencoders

Gerard Roma, Owen Green, Pierre Alexandre Tremblay

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)


Extraction of stationary and transient components from audio has many potential applications to audio effects for audio content pro- duction. In this paper we explore stationary/transient separation using convolutional autoencoders. We propose two novel unsuper- vised algorithms for individual and and joint separation. We de- scribe our implementation and show examples. Our results show promise for the use of convolutional autoencoders in the extraction of sparse components from audio spectrograms, particularly using monophonic sounds.
Original languageEnglish
Title of host publicationProceedings of the 21st International Conference on Digital Audio Effects (DAFx-18)
Number of pages7
Publication statusPublished - 4 Sep 2018
Event21st International Conference on Digital Audio Effects - Universidade de Aveiro, Aveiro, Portugal
Duration: 4 Sep 20188 Sep 2018 (Link to Conference Website)

Publication series

ISSN (Print)2413-6700
ISSN (Electronic)2413-6689


Conference21st International Conference on Digital Audio Effects
Abbreviated titleDAFx-18
Internet address


Dive into the research topics of 'Stationary/transient audio separation using convolutional autoencoders'. Together they form a unique fingerprint.

Cite this