{"id":"https://openalex.org/W3015383801","doi":"https://doi.org/10.1109/icassp40776.2020.9054358","title":"End-to-End Automatic Speech Recognition Integrated with CTC-Based Voice Activity Detection","display_name":"End-to-End Automatic Speech Recognition Integrated with CTC-Based Voice Activity Detection","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015383801","doi":"https://doi.org/10.1109/icassp40776.2020.9054358","mag":"3015383801"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5101948311","display_name":"Takenori Yoshimura","orcid":"https://orcid.org/0000-0003-3964-5677"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takenori Yoshimura","raw_affiliation_strings":["Nagoya University, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078778981","display_name":"Tomoki Hayashi","orcid":"https://orcid.org/0000-0001-8782-4093"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Hayashi","raw_affiliation_strings":["Nagoya University, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042118446","display_name":"Kazuya Takeda","orcid":"https://orcid.org/0000-0002-0330-1787"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuya Takeda","raw_affiliation_strings":["Nagoya University, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101948311"],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":5.173,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.9646208,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6999","last_page":"7003"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/computer-science","display_name":"Computer science","score":0.7949342727661133},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.7548156380653381},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7486833333969116},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.6988717913627625},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6900440454483032},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5184628367424011},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.49723437428474426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4543853998184204},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44687631726264954},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.42502832412719727},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42070138454437256},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4181459844112396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7949342727661133},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.7548156380653381},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7486833333969116},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.6988717913627625},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6900440454483032},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5184628367424011},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.49723437428474426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4543853998184204},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44687631726264954},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.42502832412719727},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42070138454437256},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4181459844112396},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/G4611969921","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"},{"id":"https://openalex.org/G4864544293","display_name":null,"funder_award_id":"Japan","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"},{"id":"https://openalex.org/G7485138276","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"}],"funders":[{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W191108438","https://openalex.org/W1536730100","https://openalex.org/W1563939609","https://openalex.org/W1586532344","https://openalex.org/W1828163288","https://openalex.org/W1985242443","https://openalex.org/W2048497537","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2129120544","https://openalex.org/W2133564696","https://openalex.org/W2135933868","https://openalex.org/W2178654303","https://openalex.org/W2251321385","https://openalex.org/W2398042456","https://openalex.org/W2406262283","https://openalex.org/W2627092829","https://openalex.org/W2745439869","https://openalex.org/W2766219058","https://openalex.org/W2799800213","https://openalex.org/W2886025712","https://openalex.org/W2936123380","https://openalex.org/W2962760690","https://openalex.org/W2962780374","https://openalex.org/W2963414781","https://openalex.org/W2963785710","https://openalex.org/W2964308564","https://openalex.org/W2972439411","https://openalex.org/W2972551158","https://openalex.org/W2972780808","https://openalex.org/W2972818416","https://openalex.org/W2972977747","https://openalex.org/W2973091309","https://openalex.org/W3007328579","https://openalex.org/W3011207290","https://openalex.org/W3034729383","https://openalex.org/W6607851514","https://openalex.org/W6632057044","https://openalex.org/W6635078382","https://openalex.org/W6638749077","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6685711979","https://openalex.org/W6691770337","https://openalex.org/W6713752823","https://openalex.org/W6747398299","https://openalex.org/W6756286202","https://openalex.org/W6756319913","https://openalex.org/W6779469704"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2069501481","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W2103239478","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340"],"abstract_inverted_index":{"This":[0,60],"paper":[1],"integrates":[2],"a":[3,52,72,80,99],"voice":[4],"activity":[5],"detection":[6],"(VAD)":[7],"function":[8],"with":[9,55,86],"end-to-end":[10],"automatic":[11],"speech":[12,17,84],"recognition":[13],"toward":[14],"an":[15,41,138],"online":[16],"interface":[18],"and":[19,32,106,132,136],"transcribing":[20],"very":[21],"long":[22,64],"audio":[23],"recordings.":[24],"We":[25,75],"focus":[26],"on":[27,51,116],"connectionist":[28],"temporal":[29],"classification":[30],"(CTC)":[31],"its":[33],"extension":[34],"of":[35,98],"CTC/attention":[36],"architectures.":[37],"As":[38],"opposed":[39],"to":[40,95,108],"attention-based":[42],"architecture,":[43],"input-synchronous":[44],"label":[45],"prediction":[46,61],"can":[47,68],"be":[48,69],"performed":[49],"based":[50],"greedy":[53],"search":[54],"the":[56,77,96,121,125,129],"CTC":[57],"(pre-)softmax":[58],"output.":[59],"includes":[62],"consecutive":[63],"blank":[65],"labels,":[66],"which":[67,102],"regarded":[70],"as":[71,79],"non-speech":[73,100],"region.":[74],"use":[76],"labels":[78],"cue":[81],"for":[82],"detecting":[83],"segments":[85],"simple":[87],"thresholding.":[88],"The":[89,143],"threshold":[90],"value":[91],"is":[92,103,146],"directly":[93],"related":[94],"length":[97],"region,":[101],"more":[104],"intuitive":[105],"easier":[107],"control":[109],"than":[110,141],"conventional":[111,130],"VAD":[112,134],"hyperparameters.":[113],"Experimental":[114],"results":[115],"unsegmented":[117],"data":[118],"show":[119],"that":[120],"proposed":[122,144],"method":[123,145],"outperformed":[124],"baseline":[126],"methods":[127,135],"using":[128],"energy-based":[131],"neural-network-based":[133],"achieved":[137],"RTF":[139],"less":[140],"0.2.":[142],"publicly":[147],"available.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":6}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}