{"id":"https://openalex.org/W3198694222","doi":"https://doi.org/10.21437/interspeech.2021-1965","title":"GigaSpeech: An Evolving, Multi-Domain ASR Corpus with 10,000 Hours of Transcribed Audio","display_name":"GigaSpeech: An Evolving, Multi-Domain ASR Corpus with 10,000 Hours of Transcribed Audio","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198694222","doi":"https://doi.org/10.21437/interspeech.2021-1965","mag":"3198694222"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1965","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081371370","display_name":"Guoguo Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Guoguo Chen","raw_affiliation_strings":["Seasalt AI Inc"],"affiliations":[{"raw_affiliation_string":"Seasalt AI Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036170008","display_name":"Shuzhou Chai","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuzhou Chai","raw_affiliation_strings":["Dept EE, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Dept EE, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101514930","display_name":"Guanbo Wang","orcid":"https://orcid.org/0000-0002-9971-442X"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Guan-Bo Wang","raw_affiliation_strings":["Dept EE, Tsinghua University","CLSP & HLTCOE, The Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Dept EE, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"CLSP & HLTCOE, The Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025820127","display_name":"Jiayu Du","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayu Du","raw_affiliation_strings":["Xiaomi Corporation"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Dept EE, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Dept EE, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106404246","display_name":"Chao Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Weng","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Xiaomi Corporation"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017882589","display_name":"Jan Trmal","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jan Trmal","raw_affiliation_strings":["CLSP & HLTCOE, The Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"CLSP & HLTCOE, The Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778479","display_name":"Junbo Zhang","orcid":"https://orcid.org/0000-0001-5947-1374"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junbo Zhang","raw_affiliation_strings":["Xiaomi Corporation"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052541894","display_name":"Mingjie Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjie Jin","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["CLSP & HLTCOE, The Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"CLSP & HLTCOE, The Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]},{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University","CLSP & HLTCOE, The Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"CLSP & HLTCOE, The Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041886705","display_name":"Shuaijiang Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuaijiang Zhao","raw_affiliation_strings":["KE Holdings Inc"],"affiliations":[{"raw_affiliation_string":"KE Holdings Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108286207","display_name":"Wei Zou","orcid":"https://orcid.org/0000-0003-4215-5361"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Zou","raw_affiliation_strings":["KE Holdings Inc"],"affiliations":[{"raw_affiliation_string":"KE Holdings Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081173423","display_name":"Xiangang Li","orcid":"https://orcid.org/0000-0002-7810-1077"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangang Li","raw_affiliation_strings":["KE Holdings Inc"],"affiliations":[{"raw_affiliation_string":"KE Holdings Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103568128","display_name":"Xuchen Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuchen Yao","raw_affiliation_strings":["Seasalt AI Inc"],"affiliations":[{"raw_affiliation_string":"Seasalt AI Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100673739","display_name":"Yongqing Wang","orcid":"https://orcid.org/0000-0003-1164-0137"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqing Wang","raw_affiliation_strings":["Xiaomi Corporation"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101967525","display_name":"Zhao You","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao You","raw_affiliation_strings":["Tencent AI Lab","Xiaomi Corporation"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Xiaomi Corporation","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113948981","display_name":"Zhiyong Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Yan","raw_affiliation_strings":["Xiaomi Corporation"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation","institution_ids":["https://openalex.org/I862669128"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":20,"corresponding_author_ids":["https://openalex.org/A5081371370"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.8973,"has_fulltext":false,"cited_by_count":187,"citation_normalized_percentile":{"value":0.99339329,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3670","last_page":"3674"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7402821779251099},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6051185727119446},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5544259548187256},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3285995125770569},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.051412343978881836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7402821779251099},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6051185727119446},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5544259548187256},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3285995125770569},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.051412343978881836},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1965","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W2089499735","https://openalex.org/W2102113734","https://openalex.org/W2147768505","https://openalex.org/W2404126548","https://openalex.org/W2514741789","https://openalex.org/W2786234940","https://openalex.org/W2962780374","https://openalex.org/W2963250244","https://openalex.org/W2963266252","https://openalex.org/W2972818416","https://openalex.org/W3095697114","https://openalex.org/W3097777922","https://openalex.org/W3101648800","https://openalex.org/W3163793923","https://openalex.org/W3198587774","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"GigaSpeech,":[3],"an":[4],"evolving,":[5],"multi-domain":[6],"English":[7],"speech":[8,80,161],"recognition":[9,81,162],"corpus":[10],"with":[11,88],"10,000":[12],"hours":[13,25,36],"of":[14,26,37,58,97],"high":[15,153],"quality":[16],"labeled":[17],"audio":[18,28,39],"suitable":[19,29,78],"for":[20,30,79,124,159],"supervised":[21],"training,":[22,82,92],"and":[23,32,46,51,55,69,83,104,123,137,168],"40,000":[24,35],"total":[27],"semi-supervised":[31],"unsupervised":[33],"training.Around":[34],"transcribed":[38],"is":[40,72],"first":[41],"collected":[42],"from":[43],"audiobooks,":[44],"podcasts":[45],"YouTube,":[47],"covering":[48],"both":[49],"read":[50],"spontaneous":[52],"speaking":[53],"styles,":[54],"a":[56],"variety":[57],"topics,":[59],"such":[60],"as":[61],"arts,":[62],"science,":[63],"sports,":[64],"etc.A":[65],"new":[66],"forced":[67],"alignment":[68],"segmentation":[70],"pipeline":[71],"proposed":[73],"to":[74,84,151],"create":[75],"sentence":[76],"segments":[77,87],"filter":[85],"out":[86],"low-quality":[89],"transcription.For":[90],"system":[91],"GigaSpeech":[93],"provides":[94],"five":[95],"subsets":[96],"different":[98],"sizes,":[99],"10h,":[100],"250h,":[101],"1000h,":[102],"2500h,":[103],"10000h.For":[105],"our":[106,126],"10,000-hour":[107],"XL":[108],"training":[109,129],"subset,":[110],"we":[111,131],"cap":[112,132],"the":[113,120,142],"word":[114],"error":[115],"rate":[116],"at":[117,134],"4%":[118],"during":[119],"filtering/validation":[121],"stage,":[122],"all":[125],"other":[127,143],"smaller":[128],"subsets,":[130],"it":[133],"0%.The":[135],"DEV":[136],"TEST":[138],"evaluation":[139],"sets,":[140],"on":[141],"hand,":[144],"are":[145,157],"re-processed":[146],"by":[147],"professional":[148],"human":[149],"transcribers":[150],"ensure":[152],"transcription":[154],"quality.Baseline":[155],"systems":[156],"provided":[158],"popular":[160],"toolkits,":[163],"namely":[164],"Athena,":[165],"ESPnet,":[166],"Kaldi":[167],"Pika.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":62},{"year":2024,"cited_by_count":55},{"year":2023,"cited_by_count":44},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":5}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
