{"id":"https://openalex.org/W4283758572","doi":"https://doi.org/10.21437/interspeech.2022-269","title":"The THUEE System Description for the IARPA OpenASR21 Challenge","display_name":"The THUEE System Description for the IARPA OpenASR21 Challenge","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283758572","doi":"https://doi.org/10.21437/interspeech.2022-269"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-269","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-269","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.14660","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059791084","display_name":"Jing Zhao","orcid":"https://orcid.org/0000-0002-0049-1802"},"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":"Jing Zhao","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology Department of Electronic Engineering, Tsinghua University, Beijing 100084, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology Department of Electronic Engineering, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427168","display_name":"Haoyu Wang","orcid":"https://orcid.org/0000-0001-6259-843X"},"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":"Haoyu Wang","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology Department of Electronic Engineering, Tsinghua University, Beijing 100084, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology Department of Electronic Engineering, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100782329","display_name":"Jinpeng Li","orcid":"https://orcid.org/0009-0007-2572-117X"},"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":"Jinpeng Li","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology Department of Electronic Engineering, Tsinghua University, Beijing 100084, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology Department of Electronic Engineering, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"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":["Beijing National Research Center for Information Science and Technology Department of Electronic Engineering, Tsinghua University, Beijing 100084, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology Department of Electronic Engineering, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101514927","display_name":"Guanbo Wang","orcid":"https://orcid.org/0000-0001-8210-8805"},"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":"Guanbo Wang","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology Department of Electronic Engineering, Tsinghua University, Beijing 100084, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology Department of Electronic Engineering, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081371370","display_name":"Guoguo Chen","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":"Guoguo Chen","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology Department of Electronic Engineering, Tsinghua University, Beijing 100084, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology Department of Electronic Engineering, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","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":true,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology Department of Electronic Engineering, Tsinghua University, Beijing 100084, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology Department of Electronic Engineering, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100692904"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.313,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.49099099,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4855","last_page":"4859"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"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":0.9983000159263611,"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/T10346","display_name":"Magnetic confinement fusion research","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9692999720573425,"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/computer-science","display_name":"Computer science","score":0.6688694953918457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6688694953918457}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-269","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-269","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2206.14660","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.14660","pdf_url":"https://arxiv.org/pdf/2206.14660","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2206.14660","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.14660","pdf_url":"https://arxiv.org/pdf/2206.14660","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[{"id":"https://openalex.org/G6450856609","display_name":null,"funder_award_id":"U1836219","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1904457459","https://openalex.org/W2026149468","https://openalex.org/W2028148926","https://openalex.org/W2070737455","https://openalex.org/W2079623482","https://openalex.org/W2116520137","https://openalex.org/W2219249508","https://openalex.org/W2292087804","https://openalex.org/W2407080277","https://openalex.org/W2696967604","https://openalex.org/W2766219058","https://openalex.org/W2802023636","https://openalex.org/W2888867175","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963979492","https://openalex.org/W2991356003","https://openalex.org/W3007432863","https://openalex.org/W3016181583","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3088761213","https://openalex.org/W3095410713","https://openalex.org/W3097777922","https://openalex.org/W3169320628","https://openalex.org/W3181776258","https://openalex.org/W3198429080","https://openalex.org/W4210366248","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,10,28,35,47,53,59,93,99,111,120,129,139,144,157,162,166],"THUEE":[4],"team's":[5],"speech":[6],"recognition":[7],"system":[8,44],"for":[9,66],"IARPA":[11],"Open":[12],"Automatic":[13],"Speech":[14],"Recognition":[15],"Challenge":[16],"(OpenASR21),":[17],"with":[18,106,110],"further":[19],"experiment":[20,105],"explorations.":[21],"We":[22,104,126],"achieve":[23],"outstanding":[24],"results":[25],"under":[26],"both":[27,67],"Constrained":[29,36],"and":[30,69,80],"Constrained-plus":[31,94],"training":[32,37,95],"conditions.":[33],"For":[34,92],"condition,":[38,96],"we":[39,57,97],"construct":[40],"our":[41],"basic":[42],"ASR":[43,148],"based":[45,146],"on":[46,117],"standard":[48],"hybrid":[49],"architecture.":[50,149],"To":[51],"alleviate":[52],"Out-Of-Vocabulary":[54],"(OOV)":[55],"problem,":[56],"extend":[58],"pronunciation":[60],"lexicon":[61],"using":[62,156],"Grapheme-to-Phoneme":[63],"(G2P)":[64],"techniques":[65,89,109],"OOV":[68],"potential":[70],"new":[71],"words.":[72],"Standard":[73],"acoustic":[74],"model":[75,124,142,159],"structures":[76],"such":[77],"as":[78,165],"CNN-TDNN-F":[79],"CNN-TDNN-F-A":[81],"are":[82,90],"adopted.":[83],"In":[84],"addition,":[85],"multiple":[86],"data":[87],"augmentation":[88],"applied.":[91],"use":[98],"self-supervised":[100],"learning":[101],"framework":[102],"wav2vec2.0.":[103],"various":[107],"fine-tuning":[108],"Connectionist":[112],"Temporal":[113],"Classification":[114],"(CTC)":[115],"criterion":[116],"top":[118],"of":[119],"publicly":[121],"available":[122],"pre-trained":[123,141],"XLSR-53.":[125],"find":[127],"that":[128],"frontend":[130,167],"feature":[131,168],"extractor":[132],"plays":[133],"an":[134],"important":[135],"role":[136],"when":[137],"applying":[138],"wav2vec2.0":[140],"to":[143],"encoder-decoder":[145],"CTC/Attention":[147],"Extra":[150],"improvements":[151],"can":[152],"be":[153],"achieved":[154],"by":[155],"CTC":[158],"finetuned":[160],"in":[161],"target":[163],"language":[164],"extractor.":[169]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}