I4U Submission to NIST SRE 2018: Leveraging from a Decade of Shared Experiences

The I4U consortium was established to facilitate a joint entry to NIST speaker recognition evaluations (SRE). The latest edition of such joint submission was in SRE 2018, in which the I4U submission was among the best-performing systems. SRE'18 also marks the 10-year anniversary of I4U consorti...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lee, Kong Aik, Hautamaki, Ville, Kinnunen, Tomi, Yamamoto, Hitoshi, Okabe, Koji, Vestman, Ville, Huang, Jing, Ding, Guohong, Sun, Hanwu, Larcher, Anthony, Das, Rohan Kumar, Li, Haizhou, Rouvier, Mickael, Bousquet, Pierre-Michel, Rao, Wei, Wang, Qing, Zhang, Chunlei, Bahmaninezhad, Fahimeh, Delgado, Hector, Patino, Jose, Wang, Qiongqiong, Guo, Ling, Koshinaka, Takafumi, Zhang, Jiacen, Shinoda, Koichi, Trong, Trung Ngo, Sahidullah, Md, Lu, Fan, Tang, Yun, Tu, Ming, Teh, Kah Kuan, Tran, Huy Dat, George, Kuruvachan K, Kukanov, Ivan, Desnous, Florent, Yang, Jichen, Yilmaz, Emre, Xu, Longting, Bonastre, Jean-Francois, Xu, Chenglin, Lim, Zhi Hao, Chng, Eng Siong, Ranjan, Shivesh, Hansen, John H. L, Todisco, Massimiliano, Evans, Nicholas
Format: Artikel
Sprache:eng
Schlagworte:
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 Lee, Kong Aik
Hautamaki, Ville
Kinnunen, Tomi
Yamamoto, Hitoshi
Okabe, Koji
Vestman, Ville
Huang, Jing
Ding, Guohong
Sun, Hanwu
Larcher, Anthony
Das, Rohan Kumar
Li, Haizhou
Rouvier, Mickael
Bousquet, Pierre-Michel
Rao, Wei
Wang, Qing
Zhang, Chunlei
Bahmaninezhad, Fahimeh
Delgado, Hector
Patino, Jose
Wang, Qiongqiong
Guo, Ling
Koshinaka, Takafumi
Zhang, Jiacen
Shinoda, Koichi
Trong, Trung Ngo
Sahidullah, Md
Lu, Fan
Tang, Yun
Tu, Ming
Teh, Kah Kuan
Tran, Huy Dat
George, Kuruvachan K
Kukanov, Ivan
Desnous, Florent
Yang, Jichen
Yilmaz, Emre
Xu, Longting
Bonastre, Jean-Francois
Xu, Chenglin
Lim, Zhi Hao
Chng, Eng Siong
Ranjan, Shivesh
Hansen, John H. L
Todisco, Massimiliano
Evans, Nicholas
description The I4U consortium was established to facilitate a joint entry to NIST speaker recognition evaluations (SRE). The latest edition of such joint submission was in SRE 2018, in which the I4U submission was among the best-performing systems. SRE'18 also marks the 10-year anniversary of I4U consortium into NIST SRE series of evaluation. The primary objective of the current paper is to summarize the results and lessons learned based on the twelve sub-systems and their fusion submitted to SRE'18. It is also our intention to present a shared view on the advancements, progresses, and major paradigm shifts that we have witnessed as an SRE participant in the past decade from SRE'08 to SRE'18. In this regard, we have seen, among others, a paradigm shift from supervector representation to deep speaker embedding, and a switch of research challenge from channel compensation to domain adaptation.
doi_str_mv 10.48550/arxiv.1904.07386
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1904_07386</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1904_07386</sourcerecordid><originalsourceid>FETCH-arxiv_primary_1904_073863</originalsourceid><addsrcrecordid>eNqFjsEKgkAUAPfSIaoP6NT7gWxNLetaRkIUtHaWlz5tIV15W2J_H0X3TnMZmBFi7ErHD4NAzpA73TruSvqOXHrhoi9OsX8B9bxW2lptangYOMYqAXWOYC7dcA0Haomx1HUJBZsKELaUYU5gClA3ZMoh6hpiTXVGdih6Bd4tjX4ciMkuSjb76TedNqwr5Ff6WUi_C95_4w06XTl5</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>I4U Submission to NIST SRE 2018: Leveraging from a Decade of Shared Experiences</title><source>arXiv.org</source><creator>Lee, Kong Aik ; Hautamaki, Ville ; Kinnunen, Tomi ; Yamamoto, Hitoshi ; Okabe, Koji ; Vestman, Ville ; Huang, Jing ; Ding, Guohong ; Sun, Hanwu ; Larcher, Anthony ; Das, Rohan Kumar ; Li, Haizhou ; Rouvier, Mickael ; Bousquet, Pierre-Michel ; Rao, Wei ; Wang, Qing ; Zhang, Chunlei ; Bahmaninezhad, Fahimeh ; Delgado, Hector ; Patino, Jose ; Wang, Qiongqiong ; Guo, Ling ; Koshinaka, Takafumi ; Zhang, Jiacen ; Shinoda, Koichi ; Trong, Trung Ngo ; Sahidullah, Md ; Lu, Fan ; Tang, Yun ; Tu, Ming ; Teh, Kah Kuan ; Tran, Huy Dat ; George, Kuruvachan K ; Kukanov, Ivan ; Desnous, Florent ; Yang, Jichen ; Yilmaz, Emre ; Xu, Longting ; Bonastre, Jean-Francois ; Xu, Chenglin ; Lim, Zhi Hao ; Chng, Eng Siong ; Ranjan, Shivesh ; Hansen, John H. L ; Todisco, Massimiliano ; Evans, Nicholas</creator><creatorcontrib>Lee, Kong Aik ; Hautamaki, Ville ; Kinnunen, Tomi ; Yamamoto, Hitoshi ; Okabe, Koji ; Vestman, Ville ; Huang, Jing ; Ding, Guohong ; Sun, Hanwu ; Larcher, Anthony ; Das, Rohan Kumar ; Li, Haizhou ; Rouvier, Mickael ; Bousquet, Pierre-Michel ; Rao, Wei ; Wang, Qing ; Zhang, Chunlei ; Bahmaninezhad, Fahimeh ; Delgado, Hector ; Patino, Jose ; Wang, Qiongqiong ; Guo, Ling ; Koshinaka, Takafumi ; Zhang, Jiacen ; Shinoda, Koichi ; Trong, Trung Ngo ; Sahidullah, Md ; Lu, Fan ; Tang, Yun ; Tu, Ming ; Teh, Kah Kuan ; Tran, Huy Dat ; George, Kuruvachan K ; Kukanov, Ivan ; Desnous, Florent ; Yang, Jichen ; Yilmaz, Emre ; Xu, Longting ; Bonastre, Jean-Francois ; Xu, Chenglin ; Lim, Zhi Hao ; Chng, Eng Siong ; Ranjan, Shivesh ; Hansen, John H. L ; Todisco, Massimiliano ; Evans, Nicholas</creatorcontrib><description>The I4U consortium was established to facilitate a joint entry to NIST speaker recognition evaluations (SRE). The latest edition of such joint submission was in SRE 2018, in which the I4U submission was among the best-performing systems. SRE'18 also marks the 10-year anniversary of I4U consortium into NIST SRE series of evaluation. The primary objective of the current paper is to summarize the results and lessons learned based on the twelve sub-systems and their fusion submitted to SRE'18. It is also our intention to present a shared view on the advancements, progresses, and major paradigm shifts that we have witnessed as an SRE participant in the past decade from SRE'08 to SRE'18. In this regard, we have seen, among others, a paradigm shift from supervector representation to deep speaker embedding, and a switch of research challenge from channel compensation to domain adaptation.</description><identifier>DOI: 10.48550/arxiv.1904.07386</identifier><language>eng</language><subject>Computer Science - Computation and Language ; Computer Science - Sound</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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1904.07386$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1904.07386$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Lee, Kong Aik</creatorcontrib><creatorcontrib>Hautamaki, Ville</creatorcontrib><creatorcontrib>Kinnunen, Tomi</creatorcontrib><creatorcontrib>Yamamoto, Hitoshi</creatorcontrib><creatorcontrib>Okabe, Koji</creatorcontrib><creatorcontrib>Vestman, Ville</creatorcontrib><creatorcontrib>Huang, Jing</creatorcontrib><creatorcontrib>Ding, Guohong</creatorcontrib><creatorcontrib>Sun, Hanwu</creatorcontrib><creatorcontrib>Larcher, Anthony</creatorcontrib><creatorcontrib>Das, Rohan Kumar</creatorcontrib><creatorcontrib>Li, Haizhou</creatorcontrib><creatorcontrib>Rouvier, Mickael</creatorcontrib><creatorcontrib>Bousquet, Pierre-Michel</creatorcontrib><creatorcontrib>Rao, Wei</creatorcontrib><creatorcontrib>Wang, Qing</creatorcontrib><creatorcontrib>Zhang, Chunlei</creatorcontrib><creatorcontrib>Bahmaninezhad, Fahimeh</creatorcontrib><creatorcontrib>Delgado, Hector</creatorcontrib><creatorcontrib>Patino, Jose</creatorcontrib><creatorcontrib>Wang, Qiongqiong</creatorcontrib><creatorcontrib>Guo, Ling</creatorcontrib><creatorcontrib>Koshinaka, Takafumi</creatorcontrib><creatorcontrib>Zhang, Jiacen</creatorcontrib><creatorcontrib>Shinoda, Koichi</creatorcontrib><creatorcontrib>Trong, Trung Ngo</creatorcontrib><creatorcontrib>Sahidullah, Md</creatorcontrib><creatorcontrib>Lu, Fan</creatorcontrib><creatorcontrib>Tang, Yun</creatorcontrib><creatorcontrib>Tu, Ming</creatorcontrib><creatorcontrib>Teh, Kah Kuan</creatorcontrib><creatorcontrib>Tran, Huy Dat</creatorcontrib><creatorcontrib>George, Kuruvachan K</creatorcontrib><creatorcontrib>Kukanov, Ivan</creatorcontrib><creatorcontrib>Desnous, Florent</creatorcontrib><creatorcontrib>Yang, Jichen</creatorcontrib><creatorcontrib>Yilmaz, Emre</creatorcontrib><creatorcontrib>Xu, Longting</creatorcontrib><creatorcontrib>Bonastre, Jean-Francois</creatorcontrib><creatorcontrib>Xu, Chenglin</creatorcontrib><creatorcontrib>Lim, Zhi Hao</creatorcontrib><creatorcontrib>Chng, Eng Siong</creatorcontrib><creatorcontrib>Ranjan, Shivesh</creatorcontrib><creatorcontrib>Hansen, John H. L</creatorcontrib><creatorcontrib>Todisco, Massimiliano</creatorcontrib><creatorcontrib>Evans, Nicholas</creatorcontrib><title>I4U Submission to NIST SRE 2018: Leveraging from a Decade of Shared Experiences</title><description>The I4U consortium was established to facilitate a joint entry to NIST speaker recognition evaluations (SRE). The latest edition of such joint submission was in SRE 2018, in which the I4U submission was among the best-performing systems. SRE'18 also marks the 10-year anniversary of I4U consortium into NIST SRE series of evaluation. The primary objective of the current paper is to summarize the results and lessons learned based on the twelve sub-systems and their fusion submitted to SRE'18. It is also our intention to present a shared view on the advancements, progresses, and major paradigm shifts that we have witnessed as an SRE participant in the past decade from SRE'08 to SRE'18. In this regard, we have seen, among others, a paradigm shift from supervector representation to deep speaker embedding, and a switch of research challenge from channel compensation to domain adaptation.</description><subject>Computer Science - Computation and Language</subject><subject>Computer Science - Sound</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNqFjsEKgkAUAPfSIaoP6NT7gWxNLetaRkIUtHaWlz5tIV15W2J_H0X3TnMZmBFi7ErHD4NAzpA73TruSvqOXHrhoi9OsX8B9bxW2lptangYOMYqAXWOYC7dcA0Haomx1HUJBZsKELaUYU5gClA3ZMoh6hpiTXVGdih6Bd4tjX4ciMkuSjb76TedNqwr5Ff6WUi_C95_4w06XTl5</recordid><startdate>20190415</startdate><enddate>20190415</enddate><creator>Lee, Kong Aik</creator><creator>Hautamaki, Ville</creator><creator>Kinnunen, Tomi</creator><creator>Yamamoto, Hitoshi</creator><creator>Okabe, Koji</creator><creator>Vestman, Ville</creator><creator>Huang, Jing</creator><creator>Ding, Guohong</creator><creator>Sun, Hanwu</creator><creator>Larcher, Anthony</creator><creator>Das, Rohan Kumar</creator><creator>Li, Haizhou</creator><creator>Rouvier, Mickael</creator><creator>Bousquet, Pierre-Michel</creator><creator>Rao, Wei</creator><creator>Wang, Qing</creator><creator>Zhang, Chunlei</creator><creator>Bahmaninezhad, Fahimeh</creator><creator>Delgado, Hector</creator><creator>Patino, Jose</creator><creator>Wang, Qiongqiong</creator><creator>Guo, Ling</creator><creator>Koshinaka, Takafumi</creator><creator>Zhang, Jiacen</creator><creator>Shinoda, Koichi</creator><creator>Trong, Trung Ngo</creator><creator>Sahidullah, Md</creator><creator>Lu, Fan</creator><creator>Tang, Yun</creator><creator>Tu, Ming</creator><creator>Teh, Kah Kuan</creator><creator>Tran, Huy Dat</creator><creator>George, Kuruvachan K</creator><creator>Kukanov, Ivan</creator><creator>Desnous, Florent</creator><creator>Yang, Jichen</creator><creator>Yilmaz, Emre</creator><creator>Xu, Longting</creator><creator>Bonastre, Jean-Francois</creator><creator>Xu, Chenglin</creator><creator>Lim, Zhi Hao</creator><creator>Chng, Eng Siong</creator><creator>Ranjan, Shivesh</creator><creator>Hansen, John H. L</creator><creator>Todisco, Massimiliano</creator><creator>Evans, Nicholas</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20190415</creationdate><title>I4U Submission to NIST SRE 2018: Leveraging from a Decade of Shared Experiences</title><author>Lee, Kong Aik ; Hautamaki, Ville ; Kinnunen, Tomi ; Yamamoto, Hitoshi ; Okabe, Koji ; Vestman, Ville ; Huang, Jing ; Ding, Guohong ; Sun, Hanwu ; Larcher, Anthony ; Das, Rohan Kumar ; Li, Haizhou ; Rouvier, Mickael ; Bousquet, Pierre-Michel ; Rao, Wei ; Wang, Qing ; Zhang, Chunlei ; Bahmaninezhad, Fahimeh ; Delgado, Hector ; Patino, Jose ; Wang, Qiongqiong ; Guo, Ling ; Koshinaka, Takafumi ; Zhang, Jiacen ; Shinoda, Koichi ; Trong, Trung Ngo ; Sahidullah, Md ; Lu, Fan ; Tang, Yun ; Tu, Ming ; Teh, Kah Kuan ; Tran, Huy Dat ; George, Kuruvachan K ; Kukanov, Ivan ; Desnous, Florent ; Yang, Jichen ; Yilmaz, Emre ; Xu, Longting ; Bonastre, Jean-Francois ; Xu, Chenglin ; Lim, Zhi Hao ; Chng, Eng Siong ; Ranjan, Shivesh ; Hansen, John H. L ; Todisco, Massimiliano ; Evans, Nicholas</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_1904_073863</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer Science - Computation and Language</topic><topic>Computer Science - Sound</topic><toplevel>online_resources</toplevel><creatorcontrib>Lee, Kong Aik</creatorcontrib><creatorcontrib>Hautamaki, Ville</creatorcontrib><creatorcontrib>Kinnunen, Tomi</creatorcontrib><creatorcontrib>Yamamoto, Hitoshi</creatorcontrib><creatorcontrib>Okabe, Koji</creatorcontrib><creatorcontrib>Vestman, Ville</creatorcontrib><creatorcontrib>Huang, Jing</creatorcontrib><creatorcontrib>Ding, Guohong</creatorcontrib><creatorcontrib>Sun, Hanwu</creatorcontrib><creatorcontrib>Larcher, Anthony</creatorcontrib><creatorcontrib>Das, Rohan Kumar</creatorcontrib><creatorcontrib>Li, Haizhou</creatorcontrib><creatorcontrib>Rouvier, Mickael</creatorcontrib><creatorcontrib>Bousquet, Pierre-Michel</creatorcontrib><creatorcontrib>Rao, Wei</creatorcontrib><creatorcontrib>Wang, Qing</creatorcontrib><creatorcontrib>Zhang, Chunlei</creatorcontrib><creatorcontrib>Bahmaninezhad, Fahimeh</creatorcontrib><creatorcontrib>Delgado, Hector</creatorcontrib><creatorcontrib>Patino, Jose</creatorcontrib><creatorcontrib>Wang, Qiongqiong</creatorcontrib><creatorcontrib>Guo, Ling</creatorcontrib><creatorcontrib>Koshinaka, Takafumi</creatorcontrib><creatorcontrib>Zhang, Jiacen</creatorcontrib><creatorcontrib>Shinoda, Koichi</creatorcontrib><creatorcontrib>Trong, Trung Ngo</creatorcontrib><creatorcontrib>Sahidullah, Md</creatorcontrib><creatorcontrib>Lu, Fan</creatorcontrib><creatorcontrib>Tang, Yun</creatorcontrib><creatorcontrib>Tu, Ming</creatorcontrib><creatorcontrib>Teh, Kah Kuan</creatorcontrib><creatorcontrib>Tran, Huy Dat</creatorcontrib><creatorcontrib>George, Kuruvachan K</creatorcontrib><creatorcontrib>Kukanov, Ivan</creatorcontrib><creatorcontrib>Desnous, Florent</creatorcontrib><creatorcontrib>Yang, Jichen</creatorcontrib><creatorcontrib>Yilmaz, Emre</creatorcontrib><creatorcontrib>Xu, Longting</creatorcontrib><creatorcontrib>Bonastre, Jean-Francois</creatorcontrib><creatorcontrib>Xu, Chenglin</creatorcontrib><creatorcontrib>Lim, Zhi Hao</creatorcontrib><creatorcontrib>Chng, Eng Siong</creatorcontrib><creatorcontrib>Ranjan, Shivesh</creatorcontrib><creatorcontrib>Hansen, John H. L</creatorcontrib><creatorcontrib>Todisco, Massimiliano</creatorcontrib><creatorcontrib>Evans, Nicholas</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Lee, Kong Aik</au><au>Hautamaki, Ville</au><au>Kinnunen, Tomi</au><au>Yamamoto, Hitoshi</au><au>Okabe, Koji</au><au>Vestman, Ville</au><au>Huang, Jing</au><au>Ding, Guohong</au><au>Sun, Hanwu</au><au>Larcher, Anthony</au><au>Das, Rohan Kumar</au><au>Li, Haizhou</au><au>Rouvier, Mickael</au><au>Bousquet, Pierre-Michel</au><au>Rao, Wei</au><au>Wang, Qing</au><au>Zhang, Chunlei</au><au>Bahmaninezhad, Fahimeh</au><au>Delgado, Hector</au><au>Patino, Jose</au><au>Wang, Qiongqiong</au><au>Guo, Ling</au><au>Koshinaka, Takafumi</au><au>Zhang, Jiacen</au><au>Shinoda, Koichi</au><au>Trong, Trung Ngo</au><au>Sahidullah, Md</au><au>Lu, Fan</au><au>Tang, Yun</au><au>Tu, Ming</au><au>Teh, Kah Kuan</au><au>Tran, Huy Dat</au><au>George, Kuruvachan K</au><au>Kukanov, Ivan</au><au>Desnous, Florent</au><au>Yang, Jichen</au><au>Yilmaz, Emre</au><au>Xu, Longting</au><au>Bonastre, Jean-Francois</au><au>Xu, Chenglin</au><au>Lim, Zhi Hao</au><au>Chng, Eng Siong</au><au>Ranjan, Shivesh</au><au>Hansen, John H. L</au><au>Todisco, Massimiliano</au><au>Evans, Nicholas</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>I4U Submission to NIST SRE 2018: Leveraging from a Decade of Shared Experiences</atitle><date>2019-04-15</date><risdate>2019</risdate><abstract>The I4U consortium was established to facilitate a joint entry to NIST speaker recognition evaluations (SRE). The latest edition of such joint submission was in SRE 2018, in which the I4U submission was among the best-performing systems. SRE'18 also marks the 10-year anniversary of I4U consortium into NIST SRE series of evaluation. The primary objective of the current paper is to summarize the results and lessons learned based on the twelve sub-systems and their fusion submitted to SRE'18. It is also our intention to present a shared view on the advancements, progresses, and major paradigm shifts that we have witnessed as an SRE participant in the past decade from SRE'08 to SRE'18. In this regard, we have seen, among others, a paradigm shift from supervector representation to deep speaker embedding, and a switch of research challenge from channel compensation to domain adaptation.</abstract><doi>10.48550/arxiv.1904.07386</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.1904.07386
ispartof
issn
language eng
recordid cdi_arxiv_primary_1904_07386
source arXiv.org
subjects Computer Science - Computation and Language
Computer Science - Sound
title I4U Submission to NIST SRE 2018: Leveraging from a Decade of Shared Experiences
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-30T23%3A10%3A54IST&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=I4U%20Submission%20to%20NIST%20SRE%202018:%20Leveraging%20from%20a%20Decade%20of%20Shared%20Experiences&rft.au=Lee,%20Kong%20Aik&rft.date=2019-04-15&rft_id=info:doi/10.48550/arxiv.1904.07386&rft_dat=%3Carxiv_GOX%3E1904_07386%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