{"id":"https://openalex.org/W4221167209","doi":"https://doi.org/10.1109/icassp43922.2022.9746873","title":"VADOI: Voice-Activity-Detection Overlapping Inference for End-To-End Long-Form Speech Recognition","display_name":"VADOI: Voice-Activity-Detection Overlapping Inference for End-To-End Long-Form Speech Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221167209","doi":"https://doi.org/10.1109/icassp43922.2022.9746873"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746873","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5101979902","display_name":"Jinhan Wang","orcid":"https://orcid.org/0000-0003-1930-2271"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinhan Wang","raw_affiliation_strings":["University of California Los Angeles,Department of Electrical and Computer Engineering,USA","Department of Electrical and Computer Engineering, University of California Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California Los Angeles,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086951695","display_name":"Xiaosu Tong","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaosu Tong","raw_affiliation_strings":["Amazon Alexa,USA","Amazon Alexa, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103232491","display_name":"Jinxi Guo","orcid":"https://orcid.org/0000-0001-9563-7351"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinxi Guo","raw_affiliation_strings":["Amazon Alexa,USA","Amazon Alexa, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101086228","display_name":"Di He","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Di He","raw_affiliation_strings":["Amazon Alexa,USA","Amazon Alexa, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086411272","display_name":"Roland Maas","orcid":"https://orcid.org/0000-0003-0567-5640"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roland Maas","raw_affiliation_strings":["Amazon Alexa,USA","Amazon Alexa, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3374,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51233793,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"6977","last_page":"6981"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.8646630048751831},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7783235311508179},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6202389001846313},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6108198761940002},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5722094774246216},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.529839277267456},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4916535019874573},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.48956212401390076},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.44347426295280457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4405183792114258},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2855326533317566},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10037955641746521}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8646630048751831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7783235311508179},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6202389001846313},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6108198761940002},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5722094774246216},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.529839277267456},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4916535019874573},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.48956212401390076},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.44347426295280457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4405183792114258},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2855326533317566},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10037955641746521},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746873","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2064675550","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2129120544","https://openalex.org/W2133564696","https://openalex.org/W2166637769","https://openalex.org/W2291522532","https://openalex.org/W2572044271","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2953384591","https://openalex.org/W2962824709","https://openalex.org/W2985287635","https://openalex.org/W3008181812","https://openalex.org/W3008898571","https://openalex.org/W3097125541","https://openalex.org/W3097882114","https://openalex.org/W3149629662","https://openalex.org/W3161022068","https://openalex.org/W3163203022","https://openalex.org/W3163907627","https://openalex.org/W6603931906","https://openalex.org/W6629717138","https://openalex.org/W6638749077","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6713134421","https://openalex.org/W6731672793","https://openalex.org/W6754299077","https://openalex.org/W6769935647"],"related_works":["https://openalex.org/W2161474341","https://openalex.org/W4302615923","https://openalex.org/W3203142394","https://openalex.org/W2351061015","https://openalex.org/W4220731478","https://openalex.org/W1974101135","https://openalex.org/W2017509870","https://openalex.org/W4251141768","https://openalex.org/W50892825","https://openalex.org/W2944691285"],"abstract_inverted_index":{"While":[0],"end-to-end":[1],"models":[2],"have":[3],"shown":[4,29],"great":[5],"success":[6],"on":[7,33,124],"the":[8,53,62,113,135,141],"Automatic":[9],"Speech":[10,128],"Recognition":[11],"task,":[12],"performance":[13,137],"degrades":[14],"severely":[15],"when":[16,45,138],"target":[17],"sentences":[18],"are":[19,28],"long-form.":[20],"The":[21],"previous":[22],"proposed":[23],"methods,":[24,38],"(partial)":[25],"overlapping":[26,57,68,86,90],"inference":[27,59,75,87,91,145],"to":[30,101,140,151],"be":[31],"effective":[32],"long-form":[34,131],"decoding.":[35],"For":[36],"both":[37],"word":[39],"error":[40],"rate":[41],"(WER)":[42],"decreases":[43],"monotonically":[44],"over-lapping":[46,144],"percentage":[47,69],"decreases.":[48],"Setting":[49],"aside":[50],"computational":[51],"cost,":[52],"setup":[54],"with":[55,92],"50%":[56],"during":[58],"can":[60,116],"achieve":[61,117],"best":[63,142],"performance.":[64],"However,":[65],"a":[66,103,118],"lower":[67],"has":[70],"an":[71],"advantage":[72],"of":[73],"fast":[74],"speed.":[76],"In":[77],"this":[78],"paper,":[79],"we":[80],"first":[81],"conduct":[82],"comprehensive":[83],"experiments":[84],"comparing":[85,139],"and":[88,107,126],"partial":[89],"various":[93],"configurations.":[94],"We":[95,147],"then":[96],"propose":[97,149],"Voice-Activity-Detection":[98],"Overlapping":[99],"Inference":[100],"provide":[102],"trade-off":[104],"between":[105],"WER":[106,136],"computation":[108,121],"cost.":[109],"Results":[110],"show":[111],"that":[112],"pro-posed":[114],"method":[115],"20%":[119],"relative":[120],"cost":[122],"reduction":[123],"Librispeech":[125],"Microsoft":[127],"Language":[129],"Translation":[130],"corpus":[132],"while":[133],"maintaining":[134],"performing":[143],"algorithm.":[146],"also":[148],"Soft-Match":[150],"compensate":[152],"for":[153],"similar":[154],"words":[155],"misaligned":[156],"problem.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}