{"id":"https://openalex.org/W4392904348","doi":"https://doi.org/10.1109/icassp48485.2024.10446807","title":"Semi-Autoregressive Streaming ASR with Label Context","display_name":"Semi-Autoregressive Streaming ASR with Label Context","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904348","doi":"https://doi.org/10.1109/icassp48485.2024.10446807"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446807","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446807","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5047892839","display_name":"Siddhant Arora","orcid":"https://orcid.org/0000-0003-0375-496X"},"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":"Siddhant Arora","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM Research,USA","IBM Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,USA","institution_ids":[]},{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Research,USA","IBM Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,USA","institution_ids":[]},{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11681","last_page":"11685"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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":0.9973000288009644,"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":0.8546157479286194},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8114944696426392},{"id":"https://openalex.org/keywords/subnetwork","display_name":"Subnetwork","score":0.7941601276397705},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7153134942054749},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5957826375961304},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.595773458480835},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5696452856063843},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.541849672794342},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45001477003097534},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4067211449146271},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24974322319030762},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.13796931505203247},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09820964932441711},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09068545699119568}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.8546157479286194},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8114944696426392},{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.7941601276397705},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7153134942054749},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5957826375961304},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.595773458480835},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5696452856063843},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.541849672794342},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45001477003097534},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4067211449146271},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24974322319030762},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13796931505203247},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09820964932441711},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09068545699119568},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446807","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446807","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1353381076","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G1912064254","display_name":"Track 4:  Advanced CI Coordination Ecosystem: Monitoring and Measurement Services","funder_award_id":"2137603","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2507572247","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G4006316252","display_name":"Track 1: ACCESS Resource Allocations Marketplace and Platform Services (RAMPS)","funder_award_id":"2138259","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4010157413","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G4968279142","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G509285653","display_name":"Track 3: COre National Ecosystem for CyberinfrasTructure (CONECT)","funder_award_id":"2138307","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5173294414","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G5464919783","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G6664589177","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G8165146668","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G8300691027","display_name":"Track 2: Customized Multi-tier Assistance, Training, and Computational Help (MATCH) for End User ACCESS to CI","funder_award_id":"2138286","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8819975937","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G8897435675","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307110","display_name":"Delta","ror":"https://ror.org/03g9c1e75"},{"id":"https://openalex.org/F4320312143","display_name":"National Centre for Supercomputing Applications","ror":"https://ror.org/03r10zj06"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2166637769","https://openalex.org/W2251321385","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2739883972","https://openalex.org/W2802023636","https://openalex.org/W2890501761","https://openalex.org/W2902031175","https://openalex.org/W2913718171","https://openalex.org/W2962780374","https://openalex.org/W2963827914","https://openalex.org/W2972837679","https://openalex.org/W2973229104","https://openalex.org/W2987019345","https://openalex.org/W3007433671","https://openalex.org/W3014413043","https://openalex.org/W3015974384","https://openalex.org/W3037029661","https://openalex.org/W3043783436","https://openalex.org/W3092122846","https://openalex.org/W3095311338","https://openalex.org/W3097777922","https://openalex.org/W3097874139","https://openalex.org/W3097882114","https://openalex.org/W3148654612","https://openalex.org/W3162249256","https://openalex.org/W3163300396","https://openalex.org/W3163793923","https://openalex.org/W3197140813","https://openalex.org/W3197304116","https://openalex.org/W3197478142","https://openalex.org/W3210150990","https://openalex.org/W3211278025","https://openalex.org/W4224919446","https://openalex.org/W4283067311","https://openalex.org/W4297841852","https://openalex.org/W4313316127","https://openalex.org/W4384918448","https://openalex.org/W4385245566","https://openalex.org/W4385574035","https://openalex.org/W4385823261","https://openalex.org/W4388017359","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6685711979","https://openalex.org/W6691770337","https://openalex.org/W6770245836","https://openalex.org/W6775187155","https://openalex.org/W6779924452","https://openalex.org/W6784400248","https://openalex.org/W6854866820"],"related_works":["https://openalex.org/W2060724872","https://openalex.org/W2082094785","https://openalex.org/W2202198356","https://openalex.org/W3087203342","https://openalex.org/W2377184161","https://openalex.org/W228984114","https://openalex.org/W4226360758","https://openalex.org/W2151093953","https://openalex.org/W2090026684","https://openalex.org/W2907567977"],"abstract_inverted_index":{"Non-autoregressive":[0],"(NAR)":[1],"modeling":[2],"has":[3],"gained":[4],"significant":[5],"interest":[6],"in":[7,65,90],"speech":[8,31],"processing":[9],"since":[10],"these":[11],"models":[12,21,34,51,62,167],"achieve":[13],"dramatically":[14],"lower":[15,171],"inference":[16,124],"time":[17],"than":[18],"autoregressive":[19],"(AR)":[20],"while":[22,119,168],"also":[23,103,156,174],"achieving":[24,169],"good":[25],"transcription":[26],"accuracy.":[27,195],"Since":[28],"NAR":[29,50,61,73,135,166],"automatic":[30],"recognition":[32],"(ASR)":[33],"must":[35],"wait":[36],"for":[37,56],"the":[38,41,87,123,132,151,158,187],"completion":[39],"of":[40],"entire":[42],"utterance":[43],"before":[44],"processing,":[45],"some":[46],"works":[47],"explore":[48],"streaming":[49,60,69,81,134,162,193],"based":[52],"on":[53,140,143,150],"blockwise":[54],"attention":[55],"low-latency":[57],"applications.":[58],"However,":[59],"significantly":[63,121],"lag":[64],"accuracy":[66,159],"compared":[67],"to":[68,185,190],"AR":[70,163],"and":[71,113,148,164],"non-streaming":[72,165],"models.":[74],"To":[75],"address":[76],"this,":[77],"we":[78],"propose":[79],"a":[80,97,105],"\"semi-autoregressive\"":[82],"ASR":[83,194],"model":[84,136],"that":[85,110,128,176],"incorporates":[86],"labels":[88],"emitted":[89],"previous":[91],"blocks":[92],"as":[93],"additional":[94],"context":[95],"using":[96],"Language":[98],"Model":[99],"(LM)":[100],"subnetwork.":[101],"We":[102,173],"introduce":[104],"novel":[106],"greedy":[107],"decoding":[108],"algorithm":[109],"addresses":[111],"insertion":[112],"deletion":[114],"errors":[115],"near":[116],"block":[117],"boundaries":[118],"not":[120],"increasing":[122],"time.":[125],"Experiments":[126],"show":[127],"our":[129,177],"method":[130],"outperforms":[131],"existing":[133],"by":[137],"19%":[138],"relative":[139],"Tedlium2,":[141],"16%/8%":[142],"Librispeech-100":[144],"clean/other":[145],"test":[146,153],"sets,":[147],"19%/8%":[149],"Switchboard(SWB)/Callhome(CH)":[152],"sets.":[154],"It":[155],"reduced":[157],"gap":[160],"with":[161],"2.5x":[170],"latency.":[172],"demonstrate":[175],"approach":[178],"can":[179],"effectively":[180],"utilize":[181],"external":[182],"text":[183],"data":[184],"pre-train":[186],"LM":[188],"subnetwork":[189],"further":[191],"improve":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}