{"id":"https://openalex.org/W3198116002","doi":"https://doi.org/10.21437/interspeech.2021-1131","title":"Toward Streaming ASR with Non-Autoregressive Insertion-Based Model","display_name":"Toward Streaming ASR with Non-Autoregressive Insertion-Based Model","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198116002","doi":"https://doi.org/10.21437/interspeech.2021-1131","mag":"3198116002"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1131","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuya Fujita","raw_affiliation_strings":["Yahoo Japan Corporation, Tokyo, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation, Tokyo, JAPAN","institution_ids":[]}]},{"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, MD, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, MD, USA,","institution_ids":["https://openalex.org/I145311948"]}]},{"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/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, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088171135","display_name":"Motoi Omachi","orcid":"https://orcid.org/0000-0002-9159-4371"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Motoi Omachi","raw_affiliation_strings":["Yahoo Japan Corporation, Tokyo, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation, Tokyo, JAPAN","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3740","last_page":"3744"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9979000091552734,"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":0.9965999722480774,"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/autoregressive-model","display_name":"Autoregressive model","score":0.7994617223739624},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7267919778823853},{"id":"https://openalex.org/keywords/star-model","display_name":"STAR model","score":0.44070807099342346},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.36328065395355225},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3518930971622467},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.32481762766838074},{"id":"https://openalex.org/keywords/autoregressive-integrated-moving-average","display_name":"Autoregressive integrated moving average","score":0.20333802700042725},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.16678842902183533},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13208693265914917},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.13143786787986755},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08113083243370056}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7994617223739624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7267919778823853},{"id":"https://openalex.org/C194657046","wikidata":"https://www.wikidata.org/wiki/Q7394685","display_name":"STAR model","level":4,"score":0.44070807099342346},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.36328065395355225},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3518930971622467},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.32481762766838074},{"id":"https://openalex.org/C24338571","wikidata":"https://www.wikidata.org/wiki/Q2566298","display_name":"Autoregressive integrated moving average","level":3,"score":0.20333802700042725},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.16678842902183533},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13208693265914917},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.13143786787986755},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08113083243370056}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1131","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/W2193413348","https://openalex.org/W2251321385","https://openalex.org/W2327501763","https://openalex.org/W2766219058","https://openalex.org/W2767206889","https://openalex.org/W2946375144","https://openalex.org/W2948629866","https://openalex.org/W2949644922","https://openalex.org/W2962760690","https://openalex.org/W2962780374","https://openalex.org/W2964110616","https://openalex.org/W2972818416","https://openalex.org/W2973122799","https://openalex.org/W2988975212","https://openalex.org/W3007528493","https://openalex.org/W3014413043","https://openalex.org/W3015194534","https://openalex.org/W3015927303","https://openalex.org/W3020336359","https://openalex.org/W3035445001","https://openalex.org/W3096160024","https://openalex.org/W3097882114","https://openalex.org/W3103005696","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2439807930","https://openalex.org/W2009692134","https://openalex.org/W2024529895","https://openalex.org/W1972271943","https://openalex.org/W2019155478","https://openalex.org/W2168175994","https://openalex.org/W1902630399","https://openalex.org/W3120578569","https://openalex.org/W1487412319","https://openalex.org/W1515771853"],"abstract_inverted_index":{"Neural":[0],"end-to-end":[1],"(E2E)":[2],"models":[3,64,114],"have":[4],"become":[5],"a":[6,19,43,66,84,101,121,132,147],"promising":[7,67],"technique":[8],"to":[9,29,86,93],"realize":[10,94],"practical":[11],"automatic":[12],"speech":[13],"recognition":[14],"(ASR)":[15],"systems.When":[16],"realizing":[17],"such":[18],"system,":[20],"one":[21],"important":[22],"issue":[23],"is":[24,48,107],"the":[25,39,51,54,104,144],"segmentation":[26,89,116,127],"of":[27,53,111],"audio":[28,37,88,126],"deal":[30],"with":[31,42,78,155],"streaming":[32],"input":[33],"or":[34],"long":[35],"recording.After":[36],"segmentation,":[38],"ASR":[40,60,92,130],"model":[41,106],"small":[44],"real-time":[45],"factor":[46],"(RTF)":[47],"preferable":[49],"because":[50],"latency":[52],"system":[55,85],"can":[56,71],"be":[57],"faster.Recently,":[58],"E2E":[59],"based":[61],"on":[62,137],"non-autoregressive":[63,91,102,129],"becomes":[65],"approach":[68],"since":[69],"it":[70],"decode":[72],"an":[73],"N":[74,81],"-length":[75],"token":[76],"sequence":[77],"less":[79],"than":[80],"iterations.We":[82],"propose":[83],"concatenate":[87],"and":[90,97,117,128,139,152,159],"high":[95],"accuracy":[96,151],"low":[98],"RTF":[99,153],"ASR.As":[100],"ASR,":[103,118],"insertion-based":[105],"used.In":[108],"addition,":[109],"instead":[110],"concatenating":[112],"separated":[113],"for":[115],"we":[119],"introduce":[120],"new":[122],"architecture":[123],"that":[124,143],"realizes":[125],"by":[131],"single":[133],"neural":[134],"network.Experimental":[135],"results":[136],"Japanese":[138],"English":[140],"dataset":[141],"show":[142],"method":[145],"achieved":[146],"reasonable":[148],"trade-off":[149],"between":[150],"compared":[154],"baseline":[156],"autoregressive":[157],"Transformer":[158],"connectionist":[160],"temporal":[161],"classification.":[162]},"counts_by_year":[{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}