The ins and outs of speaker recognition: lessons from VoxSRC 2020

The ins and outs of speaker recognition: lessons from VoxSRC 2020

The VoxCeleb Speaker Recognition Challenge (VoxSRC) at Interspeech 2020 offers a challenging evaluation for speaker recognition systems, which includes celebrities playing different parts in movies. The goal of this work is robust speaker recognition of utterances recorded in these challenging envir...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2020-10
Hauptverfasser: Kwon, Yoohwan, Hee-Soo Heo, Bong-Jin, Lee, Joon Son Chung
Format: Artikel
Sprache:eng
Schlagworte:
Speech recognition
Training
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Kwon, Yoohwan
Hee-Soo Heo
Bong-Jin, Lee
Joon Son Chung
description The VoxCeleb Speaker Recognition Challenge (VoxSRC) at Interspeech 2020 offers a challenging evaluation for speaker recognition systems, which includes celebrities playing different parts in movies. The goal of this work is robust speaker recognition of utterances recorded in these challenging environments. We utilise variants of the popular ResNet architecture for speaker recognition and perform extensive experiments using a range of loss functions and training parameters. To this end, we optimise an efficient training framework that allows powerful models to be trained with limited time and resources. Our trained models demonstrate improvements over most existing works with lighter models and a simple pipeline. The paper shares the lessons learned from our participation in the challenge.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2456034344</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2456034344</sourcerecordid><originalsourceid>FETCH-proquest_journals_24560343443</originalsourceid><addsrcrecordid>eNqNysEKgkAQgOElCJLyHQY6C9vsatEtpOhc0lWWGkuzHdtR6PHz0AN0-g__N1ERGrNKNhZxpmKRRmuN2RrT1ERqVzwIai_g_A146AW4AunIPSlAoCvffd3X7LfQkgiPsAr8ggt_zqccUKNeqGnlWqH417laHvZFfky6wO-BpC8bHoIfV4k2zbSxxlrzn_oC33I39A</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2456034344</pqid></control><display><type>article</type><title>The ins and outs of speaker recognition: lessons from VoxSRC 2020</title><source>Free E- Journals</source><creator>Kwon, Yoohwan ; Hee-Soo Heo ; Bong-Jin, Lee ; Joon Son Chung</creator><creatorcontrib>Kwon, Yoohwan ; Hee-Soo Heo ; Bong-Jin, Lee ; Joon Son Chung</creatorcontrib><description>The VoxCeleb Speaker Recognition Challenge (VoxSRC) at Interspeech 2020 offers a challenging evaluation for speaker recognition systems, which includes celebrities playing different parts in movies. The goal of this work is robust speaker recognition of utterances recorded in these challenging environments. We utilise variants of the popular ResNet architecture for speaker recognition and perform extensive experiments using a range of loss functions and training parameters. To this end, we optimise an efficient training framework that allows powerful models to be trained with limited time and resources. Our trained models demonstrate improvements over most existing works with lighter models and a simple pipeline. The paper shares the lessons learned from our participation in the challenge.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Speech recognition ; Training</subject><ispartof>arXiv.org, 2020-10</ispartof><rights>2020. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Kwon, Yoohwan</creatorcontrib><creatorcontrib>Hee-Soo Heo</creatorcontrib><creatorcontrib>Bong-Jin, Lee</creatorcontrib><creatorcontrib>Joon Son Chung</creatorcontrib><title>The ins and outs of speaker recognition: lessons from VoxSRC 2020</title><title>arXiv.org</title><description>The VoxCeleb Speaker Recognition Challenge (VoxSRC) at Interspeech 2020 offers a challenging evaluation for speaker recognition systems, which includes celebrities playing different parts in movies. The goal of this work is robust speaker recognition of utterances recorded in these challenging environments. We utilise variants of the popular ResNet architecture for speaker recognition and perform extensive experiments using a range of loss functions and training parameters. To this end, we optimise an efficient training framework that allows powerful models to be trained with limited time and resources. Our trained models demonstrate improvements over most existing works with lighter models and a simple pipeline. The paper shares the lessons learned from our participation in the challenge.</description><subject>Speech recognition</subject><subject>Training</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNysEKgkAQgOElCJLyHQY6C9vsatEtpOhc0lWWGkuzHdtR6PHz0AN0-g__N1ERGrNKNhZxpmKRRmuN2RrT1ERqVzwIai_g_A146AW4AunIPSlAoCvffd3X7LfQkgiPsAr8ggt_zqccUKNeqGnlWqH417laHvZFfky6wO-BpC8bHoIfV4k2zbSxxlrzn_oC33I39A</recordid><startdate>20201029</startdate><enddate>20201029</enddate><creator>Kwon, Yoohwan</creator><creator>Hee-Soo Heo</creator><creator>Bong-Jin, Lee</creator><creator>Joon Son Chung</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20201029</creationdate><title>The ins and outs of speaker recognition: lessons from VoxSRC 2020</title><author>Kwon, Yoohwan ; Hee-Soo Heo ; Bong-Jin, Lee ; Joon Son Chung</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_24560343443</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Speech recognition</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Kwon, Yoohwan</creatorcontrib><creatorcontrib>Hee-Soo Heo</creatorcontrib><creatorcontrib>Bong-Jin, Lee</creatorcontrib><creatorcontrib>Joon Son Chung</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kwon, Yoohwan</au><au>Hee-Soo Heo</au><au>Bong-Jin, Lee</au><au>Joon Son Chung</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>The ins and outs of speaker recognition: lessons from VoxSRC 2020</atitle><jtitle>arXiv.org</jtitle><date>2020-10-29</date><risdate>2020</risdate><eissn>2331-8422</eissn><abstract>The VoxCeleb Speaker Recognition Challenge (VoxSRC) at Interspeech 2020 offers a challenging evaluation for speaker recognition systems, which includes celebrities playing different parts in movies. The goal of this work is robust speaker recognition of utterances recorded in these challenging environments. We utilise variants of the popular ResNet architecture for speaker recognition and perform extensive experiments using a range of loss functions and training parameters. To this end, we optimise an efficient training framework that allows powerful models to be trained with limited time and resources. Our trained models demonstrate improvements over most existing works with lighter models and a simple pipeline. The paper shares the lessons learned from our participation in the challenge.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2020-10
issn 2331-8422
language eng
recordid cdi_proquest_journals_2456034344
source Free E- Journals
subjects Speech recognition
Training
title The ins and outs of speaker recognition: lessons from VoxSRC 2020
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-27T13%3A30%3A45IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=The%20ins%20and%20outs%20of%20speaker%20recognition:%20lessons%20from%20VoxSRC%202020&rft.jtitle=arXiv.org&rft.au=Kwon,%20Yoohwan&rft.date=2020-10-29&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2456034344%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2456034344&rft_id=info:pmid/&rfr_iscdi=true