{"id":"https://openalex.org/W3206573929","doi":"https://doi.org/10.1109/asru51503.2021.9688157","title":"A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation","display_name":"A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W3206573929","doi":"https://doi.org/10.1109/asru51503.2021.9688157","mag":"3206573929"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688157","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":"conference-paper","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/A5102017467","display_name":"Yosuke Higuchi","orcid":"https://orcid.org/0000-0003-4500-8957"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yosuke Higuchi","raw_affiliation_strings":["Waseda University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071702566","display_name":"Nanxin Chen","orcid":"https://orcid.org/0000-0001-6698-1604"},"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":"Nanxin Chen","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040732498","display_name":"Yuya Fujita","orcid":"https://orcid.org/0000-0001-8155-6040"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuya Fujita","raw_affiliation_strings":["Yahoo Japan Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040282669","display_name":"Hirofumi Inaguma","orcid":"https://orcid.org/0000-0003-0610-1251"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirofumi Inaguma","raw_affiliation_strings":["Kyoto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113730169","display_name":"Tatsuya Komatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Komatsu","raw_affiliation_strings":["LINE Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corporation","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015578080","display_name":"Jaesong Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaesong Lee","raw_affiliation_strings":["Naver Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Naver Corporation","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047707706","display_name":"Jumon Nozaki","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jumon Nozaki","raw_affiliation_strings":["Kyoto University","LINE Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"LINE Corporation","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407750","display_name":"Tianzi Wang","orcid":"https://orcid.org/0009-0005-5823-3039"},"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":"Tianzi Wang","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"47","last_page":"54"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"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/autoregressive-model","display_name":"Autoregressive model","score":0.825432300567627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7483404278755188},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7401075959205627},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7236691117286682},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6374608874320984},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4602985978126526},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.43225789070129395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3658539652824402},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.1131390631198883},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10038161277770996}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.825432300567627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483404278755188},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7401075959205627},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7236691117286682},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6374608874320984},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4602985978126526},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.43225789070129395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3658539652824402},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.1131390631198883},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10038161277770996},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688157","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/G6824508365","display_name":null,"funder_award_id":"ACI-1548562,ACI-1445606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":97,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W2024490156","https://openalex.org/W2025768430","https://openalex.org/W2043701535","https://openalex.org/W2058094241","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2143612262","https://openalex.org/W2160815625","https://openalex.org/W2251321385","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2559260703","https://openalex.org/W2577366047","https://openalex.org/W2766219058","https://openalex.org/W2767206889","https://openalex.org/W2892009249","https://openalex.org/W2892213699","https://openalex.org/W2896457183","https://openalex.org/W2913318911","https://openalex.org/W2920538220","https://openalex.org/W2936774411","https://openalex.org/W2944255943","https://openalex.org/W2946375144","https://openalex.org/W2948629866","https://openalex.org/W2949644922","https://openalex.org/W2962780374","https://openalex.org/W2962824709","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963434219","https://openalex.org/W2963736842","https://openalex.org/W2963827914","https://openalex.org/W2963979492","https://openalex.org/W2964089333","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W2970832665","https://openalex.org/W2971167892","https://openalex.org/W2972389417","https://openalex.org/W2972818416","https://openalex.org/W2988975212","https://openalex.org/W3007328579","https://openalex.org/W3012492057","https://openalex.org/W3015537910","https://openalex.org/W3015960524","https://openalex.org/W3016167541","https://openalex.org/W3035445001","https://openalex.org/W3036601975","https://openalex.org/W3096160024","https://openalex.org/W3097625183","https://openalex.org/W3097777922","https://openalex.org/W3097874139","https://openalex.org/W3097882114","https://openalex.org/W3099782249","https://openalex.org/W3100753857","https://openalex.org/W3103005696","https://openalex.org/W3112157188","https://openalex.org/W3141854550","https://openalex.org/W3147414526","https://openalex.org/W3154353420","https://openalex.org/W3162249256","https://openalex.org/W3162899666","https://openalex.org/W3162919436","https://openalex.org/W3163793923","https://openalex.org/W3169714379","https://openalex.org/W3196321886","https://openalex.org/W3196500669","https://openalex.org/W3197140813","https://openalex.org/W4225644313","https://openalex.org/W4385245566","https://openalex.org/W6601563604","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6638749077","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6732447497","https://openalex.org/W6741807409","https://openalex.org/W6755207826","https://openalex.org/W6760017253","https://openalex.org/W6762471145","https://openalex.org/W6774835902","https://openalex.org/W6775053297","https://openalex.org/W6780218876","https://openalex.org/W6787023386","https://openalex.org/W6792376965","https://openalex.org/W6841262374"],"related_works":["https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2144453115","https://openalex.org/W2744553356","https://openalex.org/W2128223750","https://openalex.org/W4238532390","https://openalex.org/W2188872161","https://openalex.org/W2961779879","https://openalex.org/W797688974","https://openalex.org/W2002978035"],"abstract_inverted_index":{"Non-autoregressive":[0],"(NAR)":[1],"models":[2,37],"simultaneously":[3],"generate":[4],"multiple":[5],"outputs":[6],"in":[7,41,74,134],"a":[8,57],"sequence,":[9],"which":[10],"significantly":[11],"reduces":[12],"the":[13,17,46,75,97,109,125],"inference":[14],"speed":[15],"at":[16],"cost":[18],"of":[19,35,60,92],"accuracy":[20],"drop":[21],"compared":[22],"to":[23,44,119,130],"autoregressive":[24],"baselines.":[25],"Showing":[26],"great":[27],"potential":[28],"for":[29,65,88,114],"real-time":[30],"applications,":[31],"an":[32,90],"increasing":[33],"number":[34],"NAR":[36,62,93,120,135],"have":[38],"been":[39],"explored":[40],"different":[42],"fields":[43],"mitigate":[45],"performance":[47],"gap":[48],"against":[49,102],"AR":[50],"models.":[51],"In":[52],"this":[53],"work,":[54],"we":[55],"conduct":[56],"comparative":[58],"study":[59],"various":[61,83],"modeling":[63],"methods":[64],"end-to-end":[66,121],"automatic":[67],"speech":[68,122,136],"recognition":[69],"(ASR).":[70],"Experiments":[71],"are":[72,127],"performed":[73],"state-of-the-art":[76],"setting":[77],"using":[78],"ESPnet.":[79],"The":[80],"results":[81],"on":[82],"tasks":[84],"provide":[85],"interesting":[86],"findings":[87],"developing":[89],"understanding":[91],"ASR,":[94],"such":[95],"as":[96],"accuracy-speed":[98],"trade-off":[99],"and":[100,117],"robustness":[101],"long-form":[103],"utterances.":[104],"We":[105],"also":[106],"show":[107],"that":[108],"techniques":[110],"can":[111],"be":[112],"combined":[113],"further":[115,132],"improvement":[116],"applied":[118],"translation.":[123],"All":[124],"implementations":[126],"publicly":[128],"available":[129],"encourage":[131],"research":[133],"processing.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}