{"id":"https://openalex.org/W4210366248","doi":"https://doi.org/10.1109/asru51503.2021.9688260","title":"Automatic Speech Recognition for Low-Resource Languages: The Thuee Systems for the IARPA Openasr20 Evaluation","display_name":"Automatic Speech Recognition for Low-Resource Languages: The Thuee Systems for the IARPA Openasr20 Evaluation","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210366248","doi":"https://doi.org/10.1109/asru51503.2021.9688260"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688260","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5107342072","display_name":"Jing Zhao","orcid":"https://orcid.org/0009-0006-6839-9355"},"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":"Jing Zhao","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University,Department of Electronic Engineering,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University,Department of Electronic Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033435176","display_name":"Gui-Xin Shi","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":"Guixin Shi","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University,Department of Electronic Engineering,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University,Department of Electronic Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046540992","display_name":"Guan-Bo Wang","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":"Guan-Bo Wang","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University,Department of Electronic Engineering,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University,Department of Electronic Engineering,Beijing,China,100084","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":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University,Department of Electronic Engineering,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University,Department of Electronic Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5107342072"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.7616,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.75658442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"335","last_page":"341"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9988999962806702,"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":0.998199999332428,"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":0.8723698854446411},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7616133093833923},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5333991050720215},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.528424084186554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47524428367614746},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4705871641635895},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4680722951889038},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4656425714492798},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4620939791202545},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.45616278052330017},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4272744357585907}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8723698854446411},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7616133093833923},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5333991050720215},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.528424084186554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47524428367614746},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4705871641635895},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4680722951889038},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4656425714492798},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4620939791202545},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.45616278052330017},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4272744357585907},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688260","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"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":32,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1631260214","https://openalex.org/W1904457459","https://openalex.org/W2079623482","https://openalex.org/W2155273149","https://openalex.org/W2345190899","https://openalex.org/W2402146185","https://openalex.org/W2407080277","https://openalex.org/W2514741789","https://openalex.org/W2802023636","https://openalex.org/W2888867175","https://openalex.org/W2936774411","https://openalex.org/W2972384088","https://openalex.org/W2979476256","https://openalex.org/W2982223350","https://openalex.org/W2991356003","https://openalex.org/W3007432863","https://openalex.org/W3016181583","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3144810982","https://openalex.org/W3198429080","https://openalex.org/W3198608154","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6636811518","https://openalex.org/W6769196770","https://openalex.org/W6779919476","https://openalex.org/W6780218876","https://openalex.org/W6780361010","https://openalex.org/W6780483730","https://openalex.org/W6784426525"],"related_works":["https://openalex.org/W2121652828","https://openalex.org/W2556771176","https://openalex.org/W2640905660","https://openalex.org/W2402949781","https://openalex.org/W1955848339","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W642007152","https://openalex.org/W2122233706","https://openalex.org/W2105439218"],"abstract_inverted_index":{"The":[0,76],"paper":[1],"introduces":[2],"our":[3,72],"Automatic":[4,13],"Speech":[5,14,134],"Recognition":[6,15],"(ASR)":[7],"systems":[8],"for":[9,34,48,99,111,128,164],"the":[10,30,35,43,59,129,148,165],"IARPA":[11],"Open":[12],"Challenge":[16],"(OpenASR20)":[17],"as":[18,20,38,81,114,116,133],"well":[19,115],"some":[21],"post":[22],"explorations":[23],"with":[24,168],"speech":[25,45,162],"pre-training.":[26],"We":[27,57],"compete":[28],"in":[29],"Constrained":[31],"training":[32,49],"condition":[33],"10":[36],"languages":[37],"team":[39],"THUEE,":[40],"under":[41],"which":[42,83,173],"only":[44],"data":[46,112,117],"permissible":[47],"of":[50,125,171],"each":[51],"language":[52],"is":[53,79],"a":[54,169],"10-hour":[55],"corpus.":[56],"adopt":[58],"hybrid":[60,166],"NN-HMM":[61],"acoustic":[62,77],"model":[63,78,157],"and":[64,95,105,109,140],"an":[65],"N-gram":[66],"Language":[67],"Model":[68],"(LM)":[69],"to":[70,119,146,158],"construct":[71],"basic":[73],"ASR":[74],"systems.":[75],"proposed":[80],"CNN-TDNNF-A,":[82],"combines":[84],"Convolution":[85],"Neural":[86,92],"Network":[87,93],"(CNN),":[88],"Factored":[89],"Time":[90],"Delay":[91],"(TDNN-F)":[94],"self-attention":[96],"mechanism.":[97],"As":[98],"low-resource":[100],"condition,":[101],"we":[102,152],"apply":[103],"speed":[104],"volume":[106],"perturbation,":[107],"SpecAugment":[108],"reverberation":[110],"enhancement":[113],"clean-up":[118],"filter":[120],"interference":[121],"information.":[122],"A":[123],"series":[124,170],"pre-and-post-processing":[126],"procedures":[127],"evaluation":[130],"set,":[131],"such":[132],"Activity":[135],"Detection":[136],"(SAD),":[137],"system":[138,167],"fusion":[139],"results":[141],"filtering":[142],"are":[143],"carried":[144],"out":[145],"obtain":[147,159],"final":[149],"results.":[150],"Furthermore,":[151],"exploit":[153],"wav2vec":[154],"2.0":[155],"pre-trained":[156],"more":[160],"effective":[161],"representations":[163],"explorations,":[172],"brings":[174],"about":[175],"evident":[176],"improvements.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}