{"id":"https://openalex.org/W3178727019","doi":"https://doi.org/10.21437/interspeech.2021-1107","title":"VAD-Free Streaming Hybrid CTC/Attention ASR for Unsegmented Recording","display_name":"VAD-Free Streaming Hybrid CTC/Attention ASR for Unsegmented Recording","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3178727019","doi":"https://doi.org/10.21437/interspeech.2021-1107","mag":"3178727019"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1107","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1107","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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2107.07509","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"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":"Tatsuya Kawahara","raw_affiliation_strings":["Kyoto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4049","last_page":"4053"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8301566243171692},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.8274900913238525},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6383235454559326},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6001327037811279},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5789306163787842},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5783342123031616},{"id":"https://openalex.org/keywords/reset","display_name":"Reset (finance)","score":0.5328866243362427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36522161960601807},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22658070921897888}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8301566243171692},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.8274900913238525},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6383235454559326},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6001327037811279},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5789306163787842},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5783342123031616},{"id":"https://openalex.org/C2779795794","wikidata":"https://www.wikidata.org/wiki/Q7315343","display_name":"Reset (finance)","level":2,"score":0.5328866243362427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36522161960601807},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22658070921897888},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-1107","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1107","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"},{"id":"pmh:oai:arXiv.org:2107.07509","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.07509","pdf_url":"https://arxiv.org/pdf/2107.07509","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3178727019","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2107.07509.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2107.07509","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2107.07509","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2107.07509","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.07509","pdf_url":"https://arxiv.org/pdf/2107.07509","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3178727019.pdf","grobid_xml":"https://content.openalex.org/works/W3178727019.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W2048497537","https://openalex.org/W2127141656","https://openalex.org/W2250357346","https://openalex.org/W2291513470","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2605141709","https://openalex.org/W2750499125","https://openalex.org/W2766219058","https://openalex.org/W2913718171","https://openalex.org/W2935756939","https://openalex.org/W2962784628","https://openalex.org/W2963382396","https://openalex.org/W2963747784","https://openalex.org/W2963827914","https://openalex.org/W2964084166","https://openalex.org/W2964272710","https://openalex.org/W2972780808","https://openalex.org/W2972977747","https://openalex.org/W3008181812","https://openalex.org/W3008898571","https://openalex.org/W3015383801","https://openalex.org/W3015654466","https://openalex.org/W3015927303","https://openalex.org/W3016167541","https://openalex.org/W3018242354","https://openalex.org/W3021515889","https://openalex.org/W3028382961","https://openalex.org/W3034729383","https://openalex.org/W3037465386","https://openalex.org/W3094759821","https://openalex.org/W3095311338","https://openalex.org/W3096702180","https://openalex.org/W3097777922","https://openalex.org/W3115772496","https://openalex.org/W3128478537","https://openalex.org/W3133822476","https://openalex.org/W3135771040","https://openalex.org/W3148654612","https://openalex.org/W3149509723","https://openalex.org/W3161022068","https://openalex.org/W3161873870","https://openalex.org/W3198260227"],"related_works":["https://openalex.org/W3198603187","https://openalex.org/W3133822476","https://openalex.org/W3162899666","https://openalex.org/W3036462239","https://openalex.org/W3197304116","https://openalex.org/W3115772496","https://openalex.org/W3167906573","https://openalex.org/W3148654612","https://openalex.org/W3097438275","https://openalex.org/W3148986242","https://openalex.org/W3180465246","https://openalex.org/W3037029661","https://openalex.org/W2892611740","https://openalex.org/W3096147599","https://openalex.org/W3174032041","https://openalex.org/W3096976027","https://openalex.org/W2953188895","https://openalex.org/W2494535400","https://openalex.org/W3157233339","https://openalex.org/W3198413388"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"propose":[4,39,58],"novel":[5],"decoding":[6,44,90],"algorithms":[7],"to":[8,45,67,72,77,81,94,109],"enable":[9],"streaming":[10],"automatic":[11],"speech":[12,105],"recognition":[13],"(ASR)":[14],"on":[15,25],"unsegmented":[16],"long-form":[17,82,104],"recordings":[18],"without":[19],"voice":[20],"activity":[21],"detection":[22],"(VAD),":[23],"based":[24],"monotonic":[26],"chunkwise":[27],"attention":[28],"(MoChA)":[29],"with":[30],"an":[31],"auxiliary":[32],"connectionist":[33],"temporal":[34],"classification":[35],"(CTC)":[36],"objective.":[37],"We":[38,56],"a":[40,59,69,110],"block-synchronous":[41,89],"beam":[42],"search":[43],"take":[46],"advantage":[47],"of":[48],"efficient":[49],"batched":[50],"output-synchronous":[51],"and":[52],"low-latency":[53],"input-synchronous":[54],"searches.":[55],"also":[57],"VAD-free":[60,100],"inference":[61,101],"algorithm":[62],"that":[63,87],"leverages":[64],"CTC":[65],"probabilities":[66],"determine":[68],"suitable":[70],"timing":[71],"reset":[73],"the":[74,79,88,95,99],"model":[75],"states":[76],"tackle":[78],"vulnerability":[80],"data.":[83],"Experimental":[84],"evaluations":[85],"demonstrate":[86],"achieves":[91],"comparable":[92],"accuracy":[93],"label-synchronous":[96],"one.":[97],"Moreover,":[98],"can":[102],"recognize":[103],"robustly":[106],"for":[107],"up":[108],"few":[111],"hours.":[112]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}