{"id":"https://openalex.org/W4416798572","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249305","title":"Real-time VAD-less Speech Recognition by Fine-tuning SSL Model with Data Containing Tagged Non-speech Segments","display_name":"Real-time VAD-less Speech Recognition by Fine-tuning SSL Model with Data Containing Tagged Non-speech Segments","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798572","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249305"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5120390113","display_name":"Jotaro Emoto","orcid":null},"institutions":[{"id":"https://openalex.org/I922474255","display_name":"Tokushima University","ror":"https://ror.org/044vy1d05","country_code":"JP","type":"education","lineage":["https://openalex.org/I922474255"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jotaro Emoto","raw_affiliation_strings":["Tokushima University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokushima University,Japan","institution_ids":["https://openalex.org/I922474255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024519127","display_name":"Ryota Nishimura","orcid":"https://orcid.org/0000-0002-2948-530X"},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryota Nishimura","raw_affiliation_strings":["Toyohashi University of Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyohashi University of Technology,Japan","institution_ids":["https://openalex.org/I136259955"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090927220","display_name":"Kengo Ohta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092186","display_name":"Anan National College of Technology","ror":"https://ror.org/01bb68v37","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210092186"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kengo Ohta","raw_affiliation_strings":["National Institute of Technology Anan College,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology Anan College,Japan","institution_ids":["https://openalex.org/I4210092186"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077234015","display_name":"Norihide Kitaoka","orcid":"https://orcid.org/0000-0003-2028-8585"},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Norihide Kitaoka","raw_affiliation_strings":["Toyohashi University of Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyohashi University of Technology,Japan","institution_ids":["https://openalex.org/I136259955"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39266407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"980","last_page":"985"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.6984000205993652,"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":0.6984000205993652,"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":0.2720000147819519,"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":0.0044999998062849045,"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/voice-activity-detection","display_name":"Voice activity detection","score":0.6887000203132629},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5098000168800354},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48989999294281006},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46720001101493835},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4343000054359436},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.41600000858306885},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4050999879837036},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.3747999966144562},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.37450000643730164}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.794700026512146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7918000221252441},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6887000203132629},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5098000168800354},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48989999294281006},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46720001101493835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4422999918460846},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4343000054359436},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.41600000858306885},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3747999966144562},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.37450000643730164},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.3018999993801117},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2879999876022339},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1974387177","https://openalex.org/W2005522781","https://openalex.org/W2127141656","https://openalex.org/W3015783745","https://openalex.org/W3157070662","https://openalex.org/W3160628828","https://openalex.org/W3196419581","https://openalex.org/W4221140371","https://openalex.org/W4296068805","https://openalex.org/W4402112520"],"related_works":[],"abstract_inverted_index":{"Real-time":[0],"speech":[1,68,76,92,109],"recognition":[2,24,69,135],"is":[3,33,81],"crucial":[4],"in":[5,26,100,111,125,148],"systems":[6,14],"requiring":[7],"quick":[8],"responses,":[9],"such":[10,42],"as":[11,43],"spoken":[12],"dialogue":[13],"and":[15,46,77],"other":[16],"interactive":[17],"applications.":[18],"However,":[19],"background":[20],"noise":[21],"significantly":[22],"reduces":[23],"accuracy":[25],"real-world":[27,150],"environments.":[28],"Voice":[29],"activity":[30],"detection":[31],"(VAD)":[32],"a":[34,47,66,86,134],"common":[35],"countermeasure,":[36],"but":[37],"it":[38],"has":[39],"significant":[40],"drawbacks":[41],"false":[44],"detections":[45],"fundamental":[48],"lack":[49],"of":[50,72,138],"real-time":[51,67],"performance":[52,136],"due":[53],"to":[54,133,140,144],"its":[55],"reliance":[56],"on":[57],"future":[58],"audio":[59],"segments.":[60,79,129],"In":[61],"this":[62],"study,":[63],"we":[64],"develop":[65],"model":[70,90,121],"capable":[71],"simultaneously":[73],"processing":[74],"both":[75],"non-speech":[78,95,112,128],"This":[80,130],"achieved":[82],"by":[83],"CTC":[84],"fine-tuning":[85],"self-supervised":[87],"learning":[88],"(SSL)":[89],"using":[91],"data":[93],"where":[94],"segments":[96],"are":[97],"explicitly":[98],"tagged":[99],"the":[101],"transcription.":[102],"Our":[103],"experimental":[104],"results":[105],"demonstrate":[106],"that":[107,114],"for":[108],"rich":[110],"intervals":[113],"would":[115],"typically":[116],"require":[117],"VAD,":[118],"our":[119],"proposed":[120],"achieves":[122],"VAD-like":[123],"behavior":[124],"handling":[126],"these":[127],"approach":[131],"led":[132],"increase":[137],"up":[139],"9":[141],"%":[142],"compared":[143],"conventional":[145],"VAD":[146],"methods":[147],"noisy,":[149],"scenarios.":[151]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}