Experiments on Open-Set Speaker Identification with Discriminatively Trained Neural Networks

This paper presents a study on discriminative artificial neural network classifiers in the context of open-set speaker identification. Both 2-class and multi-class architectures are tested against the conventional Gaussian mixture model based classifier on enrolled speaker sets of different sizes. T...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Imoscopi, Stefano, Grancharov, Volodya, Sverrisson, Sigurdur, Karlsson, Erlendur, Pobloth, Harald
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Learning Computer Science - Sound Statistics - Machine Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

container_end_page
container_issue
container_start_page
container_title
container_volume
creator	Imoscopi, Stefano Grancharov, Volodya Sverrisson, Sigurdur Karlsson, Erlendur Pobloth, Harald
description	This paper presents a study on discriminative artificial neural network classifiers in the context of open-set speaker identification. Both 2-class and multi-class architectures are tested against the conventional Gaussian mixture model based classifier on enrolled speaker sets of different sizes. The performance evaluation shows that the multi-class neural network system has superior performance for large population sizes.
doi_str_mv	10.48550/arxiv.1904.01269
format	Article
fullrecord	<record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1904_01269</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1904_01269</sourcerecordid><originalsourceid>FETCH-LOGICAL-a679-c4c81c416ab383fda90dc71e755818412d8c51ecac1ac3dbfb838328009f96a23</originalsourceid><addsrcrecordid>eNotj8tOwzAQRb1hgVo-gBX-gQQ7cRJ7WZUClSq6aJZI0WQ8EVaDGzmhj7_HlK6udB-jOYw9SpEqXRTiGcLZHVNphEqFzEpzzz5X54GC-yY_jfzg-XYgn-xo4ruBYE-Br22MXOcQJhfzk5u--IsbMW6cj96R-guvAzhPln_QT4A-ynQ6hP04Z3cd9CM93HTG6tdVvXxPNtu39XKxSaCsTIIKtUQlS2hznXcWjLBYSaqKQkutZGY1FpIQUALmtu1aHXuZFsJ0poQsn7Gn_7NXvGaIr0G4NH-YzRUz_wUEy07p</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Experiments on Open-Set Speaker Identification with Discriminatively Trained Neural Networks</title><source>arXiv.org</source><creator>Imoscopi, Stefano ; Grancharov, Volodya ; Sverrisson, Sigurdur ; Karlsson, Erlendur ; Pobloth, Harald</creator><creatorcontrib>Imoscopi, Stefano ; Grancharov, Volodya ; Sverrisson, Sigurdur ; Karlsson, Erlendur ; Pobloth, Harald</creatorcontrib><description>This paper presents a study on discriminative artificial neural network classifiers in the context of open-set speaker identification. Both 2-class and multi-class architectures are tested against the conventional Gaussian mixture model based classifier on enrolled speaker sets of different sizes. The performance evaluation shows that the multi-class neural network system has superior performance for large population sizes.</description><identifier>DOI: 10.48550/arxiv.1904.01269</identifier><language>eng</language><subject>Computer Science - Learning ; Computer Science - Sound ; Statistics - Machine Learning</subject><creationdate>2019-04</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1904.01269$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1904.01269$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Imoscopi, Stefano</creatorcontrib><creatorcontrib>Grancharov, Volodya</creatorcontrib><creatorcontrib>Sverrisson, Sigurdur</creatorcontrib><creatorcontrib>Karlsson, Erlendur</creatorcontrib><creatorcontrib>Pobloth, Harald</creatorcontrib><title>Experiments on Open-Set Speaker Identification with Discriminatively Trained Neural Networks</title><description>This paper presents a study on discriminative artificial neural network classifiers in the context of open-set speaker identification. Both 2-class and multi-class architectures are tested against the conventional Gaussian mixture model based classifier on enrolled speaker sets of different sizes. The performance evaluation shows that the multi-class neural network system has superior performance for large population sizes.</description><subject>Computer Science - Learning</subject><subject>Computer Science - Sound</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tOwzAQRb1hgVo-gBX-gQQ7cRJ7WZUClSq6aJZI0WQ8EVaDGzmhj7_HlK6udB-jOYw9SpEqXRTiGcLZHVNphEqFzEpzzz5X54GC-yY_jfzg-XYgn-xo4ruBYE-Br22MXOcQJhfzk5u--IsbMW6cj96R-guvAzhPln_QT4A-ynQ6hP04Z3cd9CM93HTG6tdVvXxPNtu39XKxSaCsTIIKtUQlS2hznXcWjLBYSaqKQkutZGY1FpIQUALmtu1aHXuZFsJ0poQsn7Gn_7NXvGaIr0G4NH-YzRUz_wUEy07p</recordid><startdate>20190402</startdate><enddate>20190402</enddate><creator>Imoscopi, Stefano</creator><creator>Grancharov, Volodya</creator><creator>Sverrisson, Sigurdur</creator><creator>Karlsson, Erlendur</creator><creator>Pobloth, Harald</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20190402</creationdate><title>Experiments on Open-Set Speaker Identification with Discriminatively Trained Neural Networks</title><author>Imoscopi, Stefano ; Grancharov, Volodya ; Sverrisson, Sigurdur ; Karlsson, Erlendur ; Pobloth, Harald</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a679-c4c81c416ab383fda90dc71e755818412d8c51ecac1ac3dbfb838328009f96a23</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer Science - Learning</topic><topic>Computer Science - Sound</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Imoscopi, Stefano</creatorcontrib><creatorcontrib>Grancharov, Volodya</creatorcontrib><creatorcontrib>Sverrisson, Sigurdur</creatorcontrib><creatorcontrib>Karlsson, Erlendur</creatorcontrib><creatorcontrib>Pobloth, Harald</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Imoscopi, Stefano</au><au>Grancharov, Volodya</au><au>Sverrisson, Sigurdur</au><au>Karlsson, Erlendur</au><au>Pobloth, Harald</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Experiments on Open-Set Speaker Identification with Discriminatively Trained Neural Networks</atitle><date>2019-04-02</date><risdate>2019</risdate><abstract>This paper presents a study on discriminative artificial neural network classifiers in the context of open-set speaker identification. Both 2-class and multi-class architectures are tested against the conventional Gaussian mixture model based classifier on enrolled speaker sets of different sizes. The performance evaluation shows that the multi-class neural network system has superior performance for large population sizes.</abstract><doi>10.48550/arxiv.1904.01269</doi><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier	DOI: 10.48550/arxiv.1904.01269
ispartof
issn
language	eng
recordid	cdi_arxiv_primary_1904_01269
source	arXiv.org
subjects	Computer Science - Learning Computer Science - Sound Statistics - Machine Learning
title	Experiments on Open-Set Speaker Identification with Discriminatively Trained Neural Networks
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T03%3A22%3A02IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Experiments%20on%20Open-Set%20Speaker%20Identification%20with%20Discriminatively%20Trained%20Neural%20Networks&rft.au=Imoscopi,%20Stefano&rft.date=2019-04-02&rft_id=info:doi/10.48550/arxiv.1904.01269&rft_dat=%3Carxiv_GOX%3E1904_01269%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true