The ID R&D VoxCeleb Speaker Recognition Challenge 2023 System Description
This report describes ID R&D team submissions for Track 2 (open) to the VoxCeleb Speaker Recognition Challenge 2023 (VoxSRC-23). Our solution is based on the fusion of deep ResNets and self-supervised learning (SSL) based models trained on a mixture of a VoxCeleb2 dataset and a large version of...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2023-08 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| 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 | Torgashov, Nikita Makarov, Rostislav Yakovlev, Ivan Malov, Pavel Balykin, Andrei Okhotnikov, Anton |
| description | This report describes ID R&D team submissions for Track 2 (open) to the VoxCeleb Speaker Recognition Challenge 2023 (VoxSRC-23). Our solution is based on the fusion of deep ResNets and self-supervised learning (SSL) based models trained on a mixture of a VoxCeleb2 dataset and a large version of a VoxTube dataset. The final submission to the Track 2 achieved the first place on the VoxSRC-23 public leaderboard with a minDCF(0.05) of 0.0762 and EER of 1.30%. |
| format | Article |
| fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2852160540</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2852160540</sourcerecordid><originalsourceid>FETCH-proquest_journals_28521605403</originalsourceid><addsrcrecordid>eNqNys0KgkAUQOEhCJLyHS4E7YTxjmPutcitSlsxufmTzdiMQr19BT1Aq7M434I5KITvRQHiirnW9pxzDPcopXBYWrQEaQLZLoGzfsY00AXykaobGcio1o3qpk4riNtqGEg1BMhRQP6yE90hIVubbvyKDVteq8GS--uabY-HIj55o9GPmexU9no26rNKjCT6IZcBF_-pN18XOlE</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2852160540</pqid></control><display><type>article</type><title>The ID R&D VoxCeleb Speaker Recognition Challenge 2023 System Description</title><source>Free E- Journals</source><creator>Torgashov, Nikita ; Makarov, Rostislav ; Yakovlev, Ivan ; Malov, Pavel ; Balykin, Andrei ; Okhotnikov, Anton</creator><creatorcontrib>Torgashov, Nikita ; Makarov, Rostislav ; Yakovlev, Ivan ; Malov, Pavel ; Balykin, Andrei ; Okhotnikov, Anton</creatorcontrib><description>This report describes ID R&D team submissions for Track 2 (open) to the VoxCeleb Speaker Recognition Challenge 2023 (VoxSRC-23). Our solution is based on the fusion of deep ResNets and self-supervised learning (SSL) based models trained on a mixture of a VoxCeleb2 dataset and a large version of a VoxTube dataset. The final submission to the Track 2 achieved the first place on the VoxSRC-23 public leaderboard with a minDCF(0.05) of 0.0762 and EER of 1.30%.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Datasets ; R&D ; Research & development ; Self-supervised learning ; Speech recognition</subject><ispartof>arXiv.org, 2023-08</ispartof><rights>2023. 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>780,784</link.rule.ids></links><search><creatorcontrib>Torgashov, Nikita</creatorcontrib><creatorcontrib>Makarov, Rostislav</creatorcontrib><creatorcontrib>Yakovlev, Ivan</creatorcontrib><creatorcontrib>Malov, Pavel</creatorcontrib><creatorcontrib>Balykin, Andrei</creatorcontrib><creatorcontrib>Okhotnikov, Anton</creatorcontrib><title>The ID R&D VoxCeleb Speaker Recognition Challenge 2023 System Description</title><title>arXiv.org</title><description>This report describes ID R&D team submissions for Track 2 (open) to the VoxCeleb Speaker Recognition Challenge 2023 (VoxSRC-23). Our solution is based on the fusion of deep ResNets and self-supervised learning (SSL) based models trained on a mixture of a VoxCeleb2 dataset and a large version of a VoxTube dataset. The final submission to the Track 2 achieved the first place on the VoxSRC-23 public leaderboard with a minDCF(0.05) of 0.0762 and EER of 1.30%.</description><subject>Datasets</subject><subject>R&D</subject><subject>Research & development</subject><subject>Self-supervised learning</subject><subject>Speech recognition</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNys0KgkAUQOEhCJLyHS4E7YTxjmPutcitSlsxufmTzdiMQr19BT1Aq7M434I5KITvRQHiirnW9pxzDPcopXBYWrQEaQLZLoGzfsY00AXykaobGcio1o3qpk4riNtqGEg1BMhRQP6yE90hIVubbvyKDVteq8GS--uabY-HIj55o9GPmexU9no26rNKjCT6IZcBF_-pN18XOlE</recordid><startdate>20230820</startdate><enddate>20230820</enddate><creator>Torgashov, Nikita</creator><creator>Makarov, Rostislav</creator><creator>Yakovlev, Ivan</creator><creator>Malov, Pavel</creator><creator>Balykin, Andrei</creator><creator>Okhotnikov, Anton</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>PTHSS</scope></search><sort><creationdate>20230820</creationdate><title>The ID R&D VoxCeleb Speaker Recognition Challenge 2023 System Description</title><author>Torgashov, Nikita ; Makarov, Rostislav ; Yakovlev, Ivan ; Malov, Pavel ; Balykin, Andrei ; Okhotnikov, Anton</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28521605403</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Datasets</topic><topic>R&D</topic><topic>Research & development</topic><topic>Self-supervised learning</topic><topic>Speech recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Torgashov, Nikita</creatorcontrib><creatorcontrib>Makarov, Rostislav</creatorcontrib><creatorcontrib>Yakovlev, Ivan</creatorcontrib><creatorcontrib>Malov, Pavel</creatorcontrib><creatorcontrib>Balykin, Andrei</creatorcontrib><creatorcontrib>Okhotnikov, Anton</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & 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>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Torgashov, Nikita</au><au>Makarov, Rostislav</au><au>Yakovlev, Ivan</au><au>Malov, Pavel</au><au>Balykin, Andrei</au><au>Okhotnikov, Anton</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>The ID R&D VoxCeleb Speaker Recognition Challenge 2023 System Description</atitle><jtitle>arXiv.org</jtitle><date>2023-08-20</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>This report describes ID R&D team submissions for Track 2 (open) to the VoxCeleb Speaker Recognition Challenge 2023 (VoxSRC-23). Our solution is based on the fusion of deep ResNets and self-supervised learning (SSL) based models trained on a mixture of a VoxCeleb2 dataset and a large version of a VoxTube dataset. The final submission to the Track 2 achieved the first place on the VoxSRC-23 public leaderboard with a minDCF(0.05) of 0.0762 and EER of 1.30%.</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, 2023-08 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_proquest_journals_2852160540 |
| source | Free E- Journals |
| subjects | Datasets R&D Research & development Self-supervised learning Speech recognition |
| title | The ID R&D VoxCeleb Speaker Recognition Challenge 2023 System Description |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-11T14%3A22%3A55IST&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%20ID%20R&D%20VoxCeleb%20Speaker%20Recognition%20Challenge%202023%20System%20Description&rft.jtitle=arXiv.org&rft.au=Torgashov,%20Nikita&rft.date=2023-08-20&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2852160540%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2852160540&rft_id=info:pmid/&rfr_iscdi=true |