{"id":"https://openalex.org/W3096160024","doi":"https://doi.org/10.21437/interspeech.2020-1619","title":"Insertion-Based Modeling for End-to-End Automatic Speech Recognition","display_name":"Insertion-Based Modeling for End-to-End Automatic Speech Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096160024","doi":"https://doi.org/10.21437/interspeech.2020-1619","mag":"3096160024"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1619","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5040732498","display_name":"Yuya Fujita","orcid":"https://orcid.org/0000-0001-8155-6040"},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Yuya Fujita","raw_affiliation_strings":["Yahoo Japan Corp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corp","institution_ids":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}]},{"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/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":["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/A5088171135","display_name":"Motoi Omachi","orcid":"https://orcid.org/0000-0002-9159-4371"},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Motoi Omachi","raw_affiliation_strings":["Yahoo Japan Corp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corp","institution_ids":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"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":"Xuankai Chang","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3660","last_page":"3664"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9786999821662903,"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":0.9786999821662903,"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":0.9236999750137329,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8495303988456726},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7126010656356812},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6285305023193359},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3236199617385864}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8495303988456726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7126010656356812},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6285305023193359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3236199617385864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1619","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W2166637769","https://openalex.org/W2193413348","https://openalex.org/W2251321385","https://openalex.org/W2327501763","https://openalex.org/W2750499125","https://openalex.org/W2766219058","https://openalex.org/W2767206889","https://openalex.org/W2799800213","https://openalex.org/W2911291251","https://openalex.org/W2936774411","https://openalex.org/W2946375144","https://openalex.org/W2948629866","https://openalex.org/W2949644922","https://openalex.org/W2962780374","https://openalex.org/W2963242190","https://openalex.org/W2972389417","https://openalex.org/W2972818416","https://openalex.org/W2985694911","https://openalex.org/W3014413043","https://openalex.org/W3015194534","https://openalex.org/W3035445001","https://openalex.org/W3103005696","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2151749779","https://openalex.org/W1999612375","https://openalex.org/W2001405890","https://openalex.org/W2382290278"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"models":[2,16,57,124,153],"have":[3],"gained":[4],"attention":[5],"in":[6,69,167],"the":[7,42,55,70,87,97,100,126,151],"research":[8],"field":[9],"of":[10,24,54,72,99,110,137,147,150],"automatic":[11],"speech":[12],"recognition":[13],"(ASR).Many":[14],"E2E":[15],"proposed":[17,118],"so":[18],"far":[19],"assume":[20],"left-to-right":[21],"autoregressive":[22,183],"generation":[23,135,166],"an":[25,133,138],"output":[26,44,101,139],"token":[27,102,165],"sequence":[28],"except":[29],"for":[30,52,119],"connectionist":[31],"temporal":[32],"classification":[33],"(CTC)":[34],"and":[35,46,64,130,154,177],"its":[36],"variants.However,":[37],"left-toright":[38],"decoding":[39,188],"cannot":[40],"consider":[41],"future":[43],"context,":[45],"it":[47,161],"is":[48,58],"not":[49],"always":[50],"optimal":[51],"ASR.One":[53],"non-left-to-right":[56],"known":[59],"as":[60],"non-autoregressive":[61,169],"Transformer":[62,184],"(NAT)":[63],"has":[65,81],"been":[66,82],"intensively":[67],"investigated":[68],"area":[71],"neural":[73],"machine":[74],"translation":[75],"(NMT)":[76],"research.One":[77],"NAT":[78,111],"model,":[79],"mask-predict,":[80],"applied":[83],"to":[84,95,106,121,181],"ASR":[85,122],"but":[86],"model":[88],"needs":[89],"some":[90],"heuristics":[91],"or":[92],"additional":[93],"component":[94],"estimate":[96],"length":[98],"sequence.This":[103],"paper":[104],"proposes":[105],"apply":[107],"another":[108],"type":[109],"called":[112],"insertion-based":[113,164],"models,":[114],"that":[115],"were":[116],"originally":[117],"NMT,":[120],"tasks.Insertion-based":[123],"solve":[125],"above":[127],"mask-predict":[128],"issues":[129],"can":[131],"generate":[132],"arbitrary":[134],"order":[136],"sequence.In":[140],"addition,":[141],"we":[142],"introduce":[143],"a":[144,168,186],"new":[145],"formulation":[146,156],"joint":[148],"training":[149],"insertionbased":[152],"CTC.This":[155],"reinforces":[157],"CTC":[158],"by":[159],"making":[160],"dependent":[162],"on":[163,173],"manner.We":[170],"conducted":[171],"experiments":[172],"three":[174],"public":[175],"benchmarks":[176],"achieved":[178],"competitive":[179],"performance":[180],"strong":[182],"with":[185],"similar":[187],"condition.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}