{"id":"https://openalex.org/W4399795275","doi":"https://doi.org/10.48550/arxiv.2406.11546","title":"GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement","display_name":"GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement","publication_year":2024,"publication_date":"2024-06-17","ids":{"openalex":"https://openalex.org/W4399795275","doi":"https://doi.org/10.48550/arxiv.2406.11546"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.11546","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.11546","pdf_url":"https://arxiv.org/pdf/2406.11546","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.11546","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081062397","display_name":"Yifan Yang","orcid":"https://orcid.org/0009-0002-9114-1951"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yang, Yifan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104331000","display_name":"Zheshu Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Zheshu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110937314","display_name":"Jianheng Zhuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuo, Jianheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031479191","display_name":"Mingyu Cui","orcid":"https://orcid.org/0009-0000-9906-946X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Mingyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100782329","display_name":"Jinpeng Li","orcid":"https://orcid.org/0009-0007-2572-117X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jinpeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041317124","display_name":"Bo Yang","orcid":"https://orcid.org/0000-0002-1347-3718"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Bo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101230916","display_name":"Yexing Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Yexing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101838736","display_name":"Ziyang Ma","orcid":"https://orcid.org/0000-0002-8195-3262"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Ziyang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xunying","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379628","display_name":"Ziyuan Wang","orcid":"https://orcid.org/0000-0003-1611-2085"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Ziyuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102020099","display_name":"Ke Li","orcid":"https://orcid.org/0000-0002-2236-6578"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ke","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101598386","display_name":"Shuai Fan","orcid":"https://orcid.org/0000-0002-8593-9329"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Shuai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100692615","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0001-6593-2130"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Kai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wei-Qiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081371370","display_name":"Guoguo Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Guoguo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101293966","display_name":"Xie Chen","orcid":"https://orcid.org/0009-0004-4458-0753"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xie","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":16,"corresponding_author_ids":["https://openalex.org/A5081062397"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9871000051498413,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9871000051498413,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.867722749710083},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.662057101726532},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5991372466087341},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.55312579870224},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5314630270004272},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4843083918094635},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39128124713897705},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.32866621017456055},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.18931332230567932},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14743873476982117},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10120180249214172},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09905955195426941},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06395730376243591},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06383389234542847}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.867722749710083},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.662057101726532},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5991372466087341},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.55312579870224},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5314630270004272},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4843083918094635},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39128124713897705},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32866621017456055},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.18931332230567932},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14743873476982117},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10120180249214172},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09905955195426941},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06395730376243591},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06383389234542847},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.11546","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.11546","pdf_url":"https://arxiv.org/pdf/2406.11546","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.11546","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.11546","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.11546","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.11546","pdf_url":"https://arxiv.org/pdf/2406.11546","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3278014984","display_name":null,"funder_award_id":"U23B2018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8721642152","display_name":null,"funder_award_id":"2021SHZDZX0102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8863666567","display_name":null,"funder_award_id":"and No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399795275.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4321258516","https://openalex.org/W2051833850","https://openalex.org/W4287845917","https://openalex.org/W3156164993","https://openalex.org/W2385015894","https://openalex.org/W2171573941","https://openalex.org/W4317382653","https://openalex.org/W3119324922","https://openalex.org/W4390135167","https://openalex.org/W4360873893"],"abstract_inverted_index":{"The":[0],"evolution":[1],"of":[2,24,68],"speech":[3,16,43,58,228],"technology":[4],"has":[5],"been":[6],"spurred":[7],"by":[8,184],"the":[9,167],"rapid":[10],"increase":[11],"in":[12,234],"dataset":[13],"sizes.":[14],"Traditional":[15],"models":[17,160,200],"generally":[18],"depend":[19],"on":[20,56,134,162,176,202],"a":[21,39,223],"large":[22],"amount":[23],"labeled":[25],"training":[26],"data,":[27],"which":[28],"is":[29,47,119],"scarce":[30],"for":[31,49,88,100,104,110,171,226],"low-resource":[32,50,227],"languages.":[33],"This":[34],"paper":[35],"presents":[36],"GigaSpeech":[37,62,163,203],"2,":[38],"large-scale,":[40],"multi-domain,":[41],"multilingual":[42],"recognition":[44,229],"corpus.":[45],"It":[46],"designed":[48],"languages":[51],"and":[52,59,75,92,107,140,148,155,174,179,219,230],"does":[53],"not":[54],"rely":[55],"paired":[57],"text":[60],"data.":[61],"2":[63,164,204],"comprises":[64],"about":[65],"30,000":[66],"hours":[67],"automatically":[69],"transcribed":[70,137],"speech,":[71],"including":[72],"Thai,":[73,172],"Indonesian,":[74,173],"Vietnamese,":[76],"gathered":[77],"from":[78,145],"unlabeled":[79],"YouTube":[80,181],"videos.":[81],"We":[82,212],"also":[83],"introduce":[84],"an":[85],"automated":[86],"pipeline":[87,97,220],"data":[89,111],"crawling,":[90],"transcription,":[91,102],"label":[93],"refinement.":[94],"Specifically,":[95],"this":[96,235],"involves":[98],"Whisper":[99,190],"initial":[101],"MMS":[103],"forced":[105],"alignment,":[106],"multi-dimensional":[108],"filtering":[109],"quality":[112,154],"assurance.":[113],"A":[114],"modified":[115],"Noisy":[116],"Student":[117],"Training":[118],"developed":[120],"to":[121,186,189,209],"further":[122],"refine":[123],"flawed":[124],"pseudo":[125],"labels":[126],"iteratively,":[127],"thereby":[128],"enhancing":[129],"model":[130,195],"performance.":[131],"Experimental":[132],"results":[133],"our":[135,151,177,198,215],"manually":[136],"evaluation":[138],"set":[139,183],"two":[141],"public":[142],"test":[143,182],"sets":[144],"Common":[146],"Voice":[147],"FLEURS":[149],"confirm":[150],"corpus's":[152],"high":[153],"broad":[156],"applicability.":[157],"Notably,":[158],"ASR":[159,199],"trained":[161,201],"can":[165],"reduce":[166],"word":[168],"error":[169],"rate":[170],"Vietnamese":[175],"challenging":[178],"realistic":[180],"25%":[185],"40%":[187],"compared":[188,208],"large-v3,":[191],"with":[192],"merely":[193],"10%":[194],"parameters.":[196],"Furthermore,":[197],"yield":[205],"superior":[206],"performance":[207],"commercial":[210],"services.":[211],"hope":[213],"that":[214],"newly":[216],"introduced":[217],"corpus":[218],"will":[221],"open":[222],"new":[224],"avenue":[225],"significantly":[231],"facilitate":[232],"research":[233],"area.":[236]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}