Show simple item record

dc.contributor.authorVenkatesh, S
dc.contributor.authorMoffat, David
dc.contributor.authorKirke, Alexis
dc.contributor.authorShakeri, G
dc.contributor.authorBrewster, S
dc.contributor.authorFachner, J
dc.contributor.authorOdell-Miller, H
dc.contributor.authorStreet, A
dc.contributor.authorFarina, Nicolas
dc.contributor.authorBanerjee, Sube
dc.contributor.authorMiranda, Eduardo
dc.date.accessioned2021-03-09T18:10:52Z
dc.date.issued2021-05-07
dc.identifier.issn1520-6149
dc.identifier.issn2379-190X
dc.identifier.urihttp://hdl.handle.net/10026.1/16930
dc.description.abstract

Segmenting audio into homogeneous sections such as music and speech helps us understand the content of audio. It is useful as a pre-processing step to index, store, and modify audio recordings, radio broadcasts and TV programmes. Deep learning models for segmentation are generally trained on copyrighted material, which cannot be shared. Annotating these datasets is time-consuming and expensive and therefore, it significantly slows down research progress. In this study, we present a novel procedure that artificially synthesises data that resembles radio signals. We replicate the workflow of a radio DJ in mixing audio and investigate parameters like fade curves and audio ducking. We trained a Convolutional Recurrent Neural Network (CRNN) on this synthesised data and outperformed state-of-the-art algorithms for music-speech detection. This paper demonstrates the data synthesis procedure as a highly effective technique to generate large training sets for deep neural networks.

dc.format.extent636-640
dc.language.isoen
dc.publisherIEEE
dc.subjectAudio Classification
dc.subjectAudio Segmentation
dc.subjectDeep Learning
dc.subjectMusic-speech Detection
dc.subjectTraining Set Synthesis
dc.titleArtificially Synthesising Data for Audio Classification and Segmentation to Improve Speech and Music Detection in Radio Broadcast
dc.typeconference
dc.typeConference Proceeding
plymouth.author-urlhttps://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000704288400128&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=11bb513d99f797142bcfeffcc58ea008
plymouth.date-start2021-06-06
plymouth.date-finish2021-06-11
plymouth.volume2021-June
plymouth.publisher-urlhttps://ieeexplore.ieee.org/document/9413597
plymouth.conference-nameIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
plymouth.publication-statusPublished
plymouth.journalICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
dc.identifier.doi10.1109/ICASSP39728.2021.9413597
plymouth.organisational-group/Plymouth
plymouth.organisational-group/Plymouth/Faculty of Arts, Humanities and Business
plymouth.organisational-group/Plymouth/Faculty of Arts, Humanities and Business/School of Society and Culture
plymouth.organisational-group/Plymouth/Faculty of Health
plymouth.organisational-group/Plymouth/Faculty of Health/Peninsula Medical School
plymouth.organisational-group/Plymouth/Faculty of Health/Peninsula Medical School/PMS - Manual
plymouth.organisational-group/Plymouth/REF 2021 Researchers by UoA
plymouth.organisational-group/Plymouth/REF 2021 Researchers by UoA/UoA03 Allied Health Professions, Dentistry, Nursing and Pharmacy
plymouth.organisational-group/Plymouth/REF 2021 Researchers by UoA/UoA33 Music, Drama, Dance, Performing Arts, Film and Screen Studies
plymouth.organisational-group/Plymouth/Users by role
plymouth.organisational-group/Plymouth/Users by role/Academics
plymouth.organisational-group/Plymouth/Users by role/Researchers in ResearchFish submission
dcterms.dateAccepted2021-02-01
dc.rights.embargodate2021-7-17
dc.identifier.eissn2379-190X
dc.rights.embargoperiodNot known
rioxxterms.funderEngineering and Physical Sciences Research Council
rioxxterms.identifier.projectRadio Me: Real-time Radio Remixing for people with mild to moderate dementia who live alone, incorporating Agitation Reduction, and Reminders
rioxxterms.versionofrecord10.1109/ICASSP39728.2021.9413597
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.licenseref.startdate2021-05-07
rioxxterms.typeConference Paper/Proceeding/Abstract
plymouth.funderRadio Me: Real-time Radio Remixing for people with mild to moderate dementia who live alone, incorporating Agitation Reduction, and Reminders::Engineering and Physical Sciences Research Council
plymouth.funderRadio Me: Real-time Radio Remixing for people with mild to moderate dementia who live alone, incorporating Agitation Reduction, and Reminders::Engineering and Physical Sciences Research Council
atmire.cua.enabled


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record


All items in PEARL are protected by copyright law.
Author manuscripts deposited to comply with open access mandates are made available in accordance with publisher policies. Please cite only the published version using the details provided on the item record or document. In the absence of an open licence (e.g. Creative Commons), permissions for further reuse of content should be sought from the publisher or author.
Theme by 
Atmire NV