The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods

The variety of accents has posed a big challenge to speech recognition. The Accented English Speech Recognition Challenge (AESRC2020) is designed for providing a common testbed and promoting accent-related research. Two tracks are set in the challenge - English accent recognition (track 1) and accen...

Full description

Saved in:
Bibliographic Details
Main Authors: Shi, Xian, Yu, Fan, Lu, Yizhou, Liang, Yuhao, Feng, Qiangze, Wang, Daliang, Qian, Yanmin, Xie, Lei
Format: Conference Proceeding
Language:English
Subjects:
accent recognition
Accented speech recognition
acoustic modeling
Acoustics
Conferences
end-to-end ASR
Signal processing
Speech processing
Speech recognition
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 6922
container_issue
container_start_page 6918
container_title
container_volume
creator Shi, Xian
Yu, Fan
Lu, Yizhou
Liang, Yuhao
Feng, Qiangze
Wang, Daliang
Qian, Yanmin
Xie, Lei
description The variety of accents has posed a big challenge to speech recognition. The Accented English Speech Recognition Challenge (AESRC2020) is designed for providing a common testbed and promoting accent-related research. Two tracks are set in the challenge - English accent recognition (track 1) and accented English speech recognition (track 2). A set of 160 hours of accented English speech collected from 8 countries is released with labels as the training set. Another 20 hours of speech without labels is later released as the test set, including two unseen accents from another two countries used to test the model generalization ability in track 2. We also provide baseline systems for the participants. This paper first reviews the released dataset, track setups, baselines and then summarizes the challenge results and major techniques used in the submissions.
doi_str_mv 10.1109/ICASSP39728.2021.9413386
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_9413386</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9413386</ieee_id><sourcerecordid>9413386</sourcerecordid><originalsourceid>FETCH-LOGICAL-i319t-1628dd83c3970758371ce4cf06d321a99b4ef60e67d070512fc3b40a2bd3a0b73</originalsourceid><addsrcrecordid>eNotUM1OAjEYrCYmIvIEXvoALn5td7etN0T8STAYwMQb6bbfstWlEFoPvr1N5DQ_h5nMEEIZjBkDffc6naxW70JLrsYcOBvrkgmh6jMy0lKxbDNZQ1WdkwEXUhdMw-cluYrxCwCULNWA7NYd0om1GBI6Ogvb3seOrg6ItqNLtPtt8MnvA512pu8xbJHmJriniwMG-miSiZjiLV0fjf3O-JB17wNmusT406dITXD0DVO3d_GaXLSmjzg64ZB8PM3W05divnjOY-aFF0yngtVcOaeEzdNAVkpIZrG0LdROcGa0bkpsa8BaOpBQMd5a0ZRgeOOEgUaKIbn5z_WIuDkc_c4cfzend8QfBhpZVA</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods</title><source>IEEE Xplore All Conference Series</source><creator>Shi, Xian ; Yu, Fan ; Lu, Yizhou ; Liang, Yuhao ; Feng, Qiangze ; Wang, Daliang ; Qian, Yanmin ; Xie, Lei</creator><creatorcontrib>Shi, Xian ; Yu, Fan ; Lu, Yizhou ; Liang, Yuhao ; Feng, Qiangze ; Wang, Daliang ; Qian, Yanmin ; Xie, Lei</creatorcontrib><description>The variety of accents has posed a big challenge to speech recognition. The Accented English Speech Recognition Challenge (AESRC2020) is designed for providing a common testbed and promoting accent-related research. Two tracks are set in the challenge - English accent recognition (track 1) and accented English speech recognition (track 2). A set of 160 hours of accented English speech collected from 8 countries is released with labels as the training set. Another 20 hours of speech without labels is later released as the test set, including two unseen accents from another two countries used to test the model generalization ability in track 2. We also provide baseline systems for the participants. This paper first reviews the released dataset, track setups, baselines and then summarizes the challenge results and major techniques used in the submissions.</description><identifier>EISSN: 2379-190X</identifier><identifier>EISBN: 9781728176055</identifier><identifier>EISBN: 1728176050</identifier><identifier>DOI: 10.1109/ICASSP39728.2021.9413386</identifier><language>eng</language><publisher>IEEE</publisher><subject>accent recognition ; Accented speech recognition ; acoustic modeling ; Acoustics ; Conferences ; end-to-end ASR ; Signal processing ; Speech processing ; Speech recognition ; Training</subject><ispartof>ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, p.6918-6922</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9413386$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,777,781,786,787,27906,54536,54913</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9413386$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Shi, Xian</creatorcontrib><creatorcontrib>Yu, Fan</creatorcontrib><creatorcontrib>Lu, Yizhou</creatorcontrib><creatorcontrib>Liang, Yuhao</creatorcontrib><creatorcontrib>Feng, Qiangze</creatorcontrib><creatorcontrib>Wang, Daliang</creatorcontrib><creatorcontrib>Qian, Yanmin</creatorcontrib><creatorcontrib>Xie, Lei</creatorcontrib><title>The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods</title><title>ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</title><addtitle>ICASSP</addtitle><description>The variety of accents has posed a big challenge to speech recognition. The Accented English Speech Recognition Challenge (AESRC2020) is designed for providing a common testbed and promoting accent-related research. Two tracks are set in the challenge - English accent recognition (track 1) and accented English speech recognition (track 2). A set of 160 hours of accented English speech collected from 8 countries is released with labels as the training set. Another 20 hours of speech without labels is later released as the test set, including two unseen accents from another two countries used to test the model generalization ability in track 2. We also provide baseline systems for the participants. This paper first reviews the released dataset, track setups, baselines and then summarizes the challenge results and major techniques used in the submissions.</description><subject>accent recognition</subject><subject>Accented speech recognition</subject><subject>acoustic modeling</subject><subject>Acoustics</subject><subject>Conferences</subject><subject>end-to-end ASR</subject><subject>Signal processing</subject><subject>Speech processing</subject><subject>Speech recognition</subject><subject>Training</subject><issn>2379-190X</issn><isbn>9781728176055</isbn><isbn>1728176050</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2021</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotUM1OAjEYrCYmIvIEXvoALn5td7etN0T8STAYwMQb6bbfstWlEFoPvr1N5DQ_h5nMEEIZjBkDffc6naxW70JLrsYcOBvrkgmh6jMy0lKxbDNZQ1WdkwEXUhdMw-cluYrxCwCULNWA7NYd0om1GBI6Ogvb3seOrg6ItqNLtPtt8MnvA512pu8xbJHmJriniwMG-miSiZjiLV0fjf3O-JB17wNmusT406dITXD0DVO3d_GaXLSmjzg64ZB8PM3W05divnjOY-aFF0yngtVcOaeEzdNAVkpIZrG0LdROcGa0bkpsa8BaOpBQMd5a0ZRgeOOEgUaKIbn5z_WIuDkc_c4cfzend8QfBhpZVA</recordid><startdate>20210101</startdate><enddate>20210101</enddate><creator>Shi, Xian</creator><creator>Yu, Fan</creator><creator>Lu, Yizhou</creator><creator>Liang, Yuhao</creator><creator>Feng, Qiangze</creator><creator>Wang, Daliang</creator><creator>Qian, Yanmin</creator><creator>Xie, Lei</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>20210101</creationdate><title>The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods</title><author>Shi, Xian ; Yu, Fan ; Lu, Yizhou ; Liang, Yuhao ; Feng, Qiangze ; Wang, Daliang ; Qian, Yanmin ; Xie, Lei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i319t-1628dd83c3970758371ce4cf06d321a99b4ef60e67d070512fc3b40a2bd3a0b73</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2021</creationdate><topic>accent recognition</topic><topic>Accented speech recognition</topic><topic>acoustic modeling</topic><topic>Acoustics</topic><topic>Conferences</topic><topic>end-to-end ASR</topic><topic>Signal processing</topic><topic>Speech processing</topic><topic>Speech recognition</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Shi, Xian</creatorcontrib><creatorcontrib>Yu, Fan</creatorcontrib><creatorcontrib>Lu, Yizhou</creatorcontrib><creatorcontrib>Liang, Yuhao</creatorcontrib><creatorcontrib>Feng, Qiangze</creatorcontrib><creatorcontrib>Wang, Daliang</creatorcontrib><creatorcontrib>Qian, Yanmin</creatorcontrib><creatorcontrib>Xie, Lei</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE/IET Electronic Library</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Shi, Xian</au><au>Yu, Fan</au><au>Lu, Yizhou</au><au>Liang, Yuhao</au><au>Feng, Qiangze</au><au>Wang, Daliang</au><au>Qian, Yanmin</au><au>Xie, Lei</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods</atitle><btitle>ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</btitle><stitle>ICASSP</stitle><date>2021-01-01</date><risdate>2021</risdate><spage>6918</spage><epage>6922</epage><pages>6918-6922</pages><eissn>2379-190X</eissn><eisbn>9781728176055</eisbn><eisbn>1728176050</eisbn><abstract>The variety of accents has posed a big challenge to speech recognition. The Accented English Speech Recognition Challenge (AESRC2020) is designed for providing a common testbed and promoting accent-related research. Two tracks are set in the challenge - English accent recognition (track 1) and accented English speech recognition (track 2). A set of 160 hours of accented English speech collected from 8 countries is released with labels as the training set. Another 20 hours of speech without labels is later released as the test set, including two unseen accents from another two countries used to test the model generalization ability in track 2. We also provide baseline systems for the participants. This paper first reviews the released dataset, track setups, baselines and then summarizes the challenge results and major techniques used in the submissions.</abstract><pub>IEEE</pub><doi>10.1109/ICASSP39728.2021.9413386</doi><tpages>5</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2379-190X
ispartof ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, p.6918-6922
issn 2379-190X
language eng
recordid cdi_ieee_primary_9413386
source IEEE Xplore All Conference Series
subjects accent recognition
Accented speech recognition
acoustic modeling
Acoustics
Conferences
end-to-end ASR
Signal processing
Speech processing
Speech recognition
Training
title The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T01%3A06%3A08IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=The%20Accented%20English%20Speech%20Recognition%20Challenge%202020:%20Open%20Datasets,%20Tracks,%20Baselines,%20Results%20and%20Methods&rft.btitle=ICASSP%202021%20-%202021%20IEEE%20International%20Conference%20on%20Acoustics,%20Speech%20and%20Signal%20Processing%20(ICASSP)&rft.au=Shi,%20Xian&rft.date=2021-01-01&rft.spage=6918&rft.epage=6922&rft.pages=6918-6922&rft.eissn=2379-190X&rft_id=info:doi/10.1109/ICASSP39728.2021.9413386&rft.eisbn=9781728176055&rft.eisbn_list=1728176050&rft_dat=%3Cieee_CHZPO%3E9413386%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i319t-1628dd83c3970758371ce4cf06d321a99b4ef60e67d070512fc3b40a2bd3a0b73%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=9413386&rfr_iscdi=true