Thesis Open Access
Pétermann, Darius A,
<?xml version='1.0' encoding='utf-8'?> <resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd"> <identifier identifierType="DOI">10.5281/zenodo.4091247</identifier> <creators> <creator> <creatorName>Pétermann, Darius A,</creatorName> <affiliation>Universitat Pompeu Fabra</affiliation> </creator> </creators> <titles> <title>SATB Voice Segregation For Monoaural Recordings</title> </titles> <publisher>Zenodo</publisher> <publicationYear>2020</publicationYear> <subjects> <subject>source separation, singing voice, SATB recording, convolutional neural networks, choir music.</subject> </subjects> <contributors> <contributor contributorType="Supervisor"> <contributorName>Chandna, Pritish</contributorName> <givenName>Pritish</givenName> <familyName>Chandna</familyName> <affiliation>Universitat Pompeu Fabra</affiliation> </contributor> <contributor contributorType="Supervisor"> <contributorName>Bonada, Jordi</contributorName> <givenName>Jordi</givenName> <familyName>Bonada</familyName> <affiliation>Universitat Pompeu Fabra</affiliation> </contributor> </contributors> <dates> <date dateType="Issued">2020-09-15</date> </dates> <resourceType resourceTypeGeneral="Text">Thesis</resourceType> <alternateIdentifiers> <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/4091247</alternateIdentifier> </alternateIdentifiers> <relatedIdentifiers> <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.4091246</relatedIdentifier> <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/mtgupf</relatedIdentifier> <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/smc-master</relatedIdentifier> </relatedIdentifiers> <rightsList> <rights rightsURI="https://creativecommons.org/licenses/by/3.0/legalcode">Creative Commons Attribution 3.0 Unported</rights> <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights> </rightsList> <descriptions> <description descriptionType="Abstract"><p>Choral singing is a widely practiced form of ensemble singing wherein a group of people sing simultaneously in polyphonic harmony. The most commonly practiced&nbsp;setting for choir ensembles consists of four parts; Soprano, Alto, Tenor and Bass&nbsp;(SATB), each with its own range of fundamental frequencies (F0s). The task of&nbsp;source separation for this choral setting entails separating the SATB mixture into&nbsp;its constituent parts. Source separation for musical mixtures is well studied and&nbsp;many Deep Learning-based methodologies have been proposed for the same. However,<br> most of the research has been focused on a typical case which consists in<br> separating vocal, percussion and bass sources from a mixture, each of which has a&nbsp;distinct spectral structure. In contrast, the simultaneous and harmonic nature of&nbsp;ensemble singing leads to high structural similarity and overlap between the spectral&nbsp;components of the sources in a choral mixture, making source separation for&nbsp;choirs a harder task than the typical case. This, along with the lack of an appropriate&nbsp;consolidated dataset has led to a dearth of research in the field so far. In&nbsp;this work we first assess how well some of the recently developed methodologies for&nbsp;musical source separation perform for the case of SATB choirs. We then propose a&nbsp;novel domain-specific adaptation for conditioning the recently proposed U-Net architecture<br> for musical source separation using the fundamental frequency contour of<br> each of the singing groups and demonstrate that our proposed approach surpasses&nbsp;results from domain-agnostic architectures. Lastly we assess our approach using&nbsp;different evaluation methodologies, going from objective to subjective-based ones,&nbsp;and provide a comparative analysis of the various results.</p></description> </descriptions> </resource>
All versions | This version | |
---|---|---|
Views | 198 | 198 |
Downloads | 138 | 138 |
Data volume | 1.7 GB | 1.7 GB |
Unique views | 165 | 165 |
Unique downloads | 116 | 116 |