{"id":"https://openalex.org/W3197304116","doi":"https://doi.org/10.21437/interspeech.2021-1556","title":"Streaming End-to-End ASR Based on Blockwise Non-Autoregressive Models","display_name":"Streaming End-to-End ASR Based on Blockwise Non-Autoregressive Models","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197304116","doi":"https://doi.org/10.21437/interspeech.2021-1556","mag":"3197304116"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1556","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1556","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/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":"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/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"]},{"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":"Xuankai Chang","raw_affiliation_strings":["Carnegie Mellon University","Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"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/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"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","Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"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":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3755","last_page":"3759"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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":0.8337109088897705},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.8227912187576294},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7420127987861633},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7302199602127075},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5901129245758057},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5841599702835083},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5383215546607971},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5335313081741333},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5109581351280212},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.45667052268981934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4094260334968567},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2546324133872986},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21243011951446533}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8337109088897705},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.8227912187576294},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7420127987861633},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7302199602127075},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5901129245758057},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5841599702835083},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5383215546607971},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5335313081741333},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5109581351280212},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.45667052268981934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4094260334968567},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2546324133872986},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21243011951446533},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1556","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1556","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5299999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322638","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1586532344","https://openalex.org/W1828163288","https://openalex.org/W2251321385","https://openalex.org/W2767206889","https://openalex.org/W2892213699","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963242190","https://openalex.org/W2963827914","https://openalex.org/W2964110616","https://openalex.org/W2972818416","https://openalex.org/W2987019345","https://openalex.org/W2988975212","https://openalex.org/W2989134874","https://openalex.org/W3008898571","https://openalex.org/W3014413043","https://openalex.org/W3015457435","https://openalex.org/W3015927303","https://openalex.org/W3015974384","https://openalex.org/W3035445001","https://openalex.org/W3092122846","https://openalex.org/W3093941495","https://openalex.org/W3096160024","https://openalex.org/W3097125541","https://openalex.org/W3097777922","https://openalex.org/W3097874139","https://openalex.org/W3097882114","https://openalex.org/W3148654612","https://openalex.org/W3149509723","https://openalex.org/W3162431424","https://openalex.org/W3162919436","https://openalex.org/W3163793923","https://openalex.org/W3169714379","https://openalex.org/W4294619417"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W1761388607","https://openalex.org/W2038083449","https://openalex.org/W1997922073","https://openalex.org/W3177678247","https://openalex.org/W2916997151","https://openalex.org/W2949174760"],"abstract_inverted_index":{"Non-autoregressive":[0],"(NAR)":[1],"modeling":[2],"has":[3],"gained":[4],"more":[5,7,132],"and":[6,78,95,106],"attention":[8],"in":[9,98,145],"speech":[10,16,52,72],"processing.With":[11],"recent":[12],"state-of-the-art":[13],"attention-based":[14,165],"automatic":[15],"recognition":[17,41,73,144],"(ASR)":[18],"structure,":[19],"NAR":[20,71],"can":[21,130,154],"realize":[22],"promising":[23],"real-time":[24],"factor":[25],"(RTF)":[26],"improvement":[27],"with":[28,82,124],"only":[29],"small":[30,93],"degradation":[31],"of":[32,49,112,115,167],"accuracy":[33],"compared":[34,149,161],"to":[35,44,150,162],"the":[36,40,47,87,104,110,113,138,163],"autoregressive":[37],"(AR)":[38],"models.However,":[39],"inference":[42,159],"needs":[43],"wait":[45],"for":[46],"completion":[48],"a":[50,67,99,125,156],"full":[51],"utterance,":[53],"which":[54],"limits":[55],"their":[56],"applications":[57],"on":[58],"low":[59,146],"latency":[60,147],"scenarios.To":[61],"address":[62,103],"this":[63],"issue,":[64],"we":[65,118],"propose":[66],"novel":[68],"end-to-end":[69],"streaming":[70,101],"system":[74],"by":[75],"combining":[76],"blockwiseattention":[77],"connectionist":[79],"temporal":[80],"classification":[81],"maskpredict":[83],"(Mask-CTC)":[84],"NAR.During":[85],"inference,":[86],"input":[88],"audio":[89],"is":[90],"separated":[91],"into":[92],"blocks":[94],"then":[96],"processed":[97],"blockwise":[100],"way.To":[102],"insertion":[105],"deletion":[107],"error":[108],"at":[109,174],"edge":[111],"output":[114],"each":[116],"block,":[117],"apply":[119],"an":[120],"overlapping":[121],"decoding":[122],"strategy":[123],"dynamic":[126],"mapping":[127],"trick":[128],"that":[129,137],"produce":[131],"coherent":[133],"sentences.Experimental":[134],"results":[135],"show":[136],"proposed":[139],"method":[140],"improves":[141],"online":[142],"ASR":[143],"conditions":[148],"vanilla":[151],"Mask-CTC.Moreover,":[152],"it":[153],"achieve":[155],"much":[157],"faster":[158],"speed":[160],"AR":[164],"models.All":[166],"our":[168],"codes":[169],"will":[170],"be":[171],"publicly":[172],"available":[173],"https://github.com/espnet/espnet.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}