{"id":"https://openalex.org/W4309995582","doi":"https://doi.org/10.1109/acii55700.2022.9953889","title":"Audio and ASR-based Filled Pause Detection","display_name":"Audio and ASR-based Filled Pause Detection","publication_year":2022,"publication_date":"2022-10-18","ids":{"openalex":"https://openalex.org/W4309995582","doi":"https://doi.org/10.1109/acii55700.2022.9953889"},"language":"en","primary_location":{"id":"doi:10.1109/acii55700.2022.9953889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acii55700.2022.9953889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 10th International Conference on Affective Computing and Intelligent Interaction (ACII)","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/A5059880574","display_name":"Aggelina Chatziagapi","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aggelina Chatziagapi","raw_affiliation_strings":["Stony Brook University & Behavioral Signal Technologies,New York,U.S.A"],"affiliations":[{"raw_affiliation_string":"Stony Brook University & Behavioral Signal Technologies,New York,U.S.A","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016108502","display_name":"Dimitris Sgouropoulos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dimitris Sgouropoulos","raw_affiliation_strings":["Behavioral Signal Technologies,Athens,Greece","Behavioral Signal Technologies, Athens, Greece"],"affiliations":[{"raw_affiliation_string":"Behavioral Signal Technologies,Athens,Greece","institution_ids":[]},{"raw_affiliation_string":"Behavioral Signal Technologies, Athens, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053198720","display_name":"Constantinos Karouzos","orcid":"https://orcid.org/0000-0003-0521-6217"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Constantinos Karouzos","raw_affiliation_strings":["Behavioral Signal Technologies,Athens,Greece","Behavioral Signal Technologies, Athens, Greece"],"affiliations":[{"raw_affiliation_string":"Behavioral Signal Technologies,Athens,Greece","institution_ids":[]},{"raw_affiliation_string":"Behavioral Signal Technologies, Athens, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007179145","display_name":"\u0398\u03c9\u03bc\u03ac\u03c2 \u039c\u03b5\u03bb\u03af\u03c3\u03c4\u03b1\u03c2","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Melistas","raw_affiliation_strings":["Behavioral Signal Technologies,Athens,Greece","Behavioral Signal Technologies, Athens, Greece"],"affiliations":[{"raw_affiliation_string":"Behavioral Signal Technologies,Athens,Greece","institution_ids":[]},{"raw_affiliation_string":"Behavioral Signal Technologies, Athens, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069190127","display_name":"\u0398\u03b5\u03cc\u03b4\u03c9\u03c1\u03bf\u03c2 \u0393\u03b9\u03b1\u03bd\u03bd\u03b1\u03ba\u03cc\u03c0\u03bf\u03c5\u03bb\u03bf\u03c2","orcid":"https://orcid.org/0000-0003-1634-824X"},"institutions":[{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Theodoros Giannakopoulos","raw_affiliation_strings":["Behavioral Signal Technologies & NCSR Demokritos,Athens,Greece"],"affiliations":[{"raw_affiliation_string":"Behavioral Signal Technologies & NCSR Demokritos,Athens,Greece","institution_ids":["https://openalex.org/I203474044"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061662829","display_name":"Athanasios Katsamanis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Athanasios Katsamanis","raw_affiliation_strings":["Behavioral Signal Technologies,Athens,Greece","Behavioral Signal Technologies, Athens, Greece"],"affiliations":[{"raw_affiliation_string":"Behavioral Signal Technologies,Athens,Greece","institution_ids":[]},{"raw_affiliation_string":"Behavioral Signal Technologies, Athens, Greece","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103555640","display_name":"Shrikanth Narayanan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129254","display_name":"Active Signal Technologies (United States)","ror":"https://ror.org/03q358129","country_code":"US","type":"company","lineage":["https://openalex.org/I4210129254"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["Behavioral Signal Technologies,Los Angeles,U.S.A","Behavioral Signal Technologies, Los Angeles, U.S.A"],"affiliations":[{"raw_affiliation_string":"Behavioral Signal Technologies,Los Angeles,U.S.A","institution_ids":[]},{"raw_affiliation_string":"Behavioral Signal Technologies, Los Angeles, U.S.A","institution_ids":["https://openalex.org/I4210129254"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5059880574"],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":null,"apc_paid":null,"fwci":0.5517,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72625319,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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":0.8471221923828125},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7170453071594238},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5624651908874512},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.49686887860298157},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.48241743445396423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.479388952255249},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.477411150932312},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41725340485572815},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36914917826652527}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8471221923828125},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7170453071594238},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5624651908874512},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.49686887860298157},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.48241743445396423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.479388952255249},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.477411150932312},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41725340485572815},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36914917826652527}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acii55700.2022.9953889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acii55700.2022.9953889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 10th International Conference on Affective Computing and Intelligent Interaction (ACII)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W198720948","https://openalex.org/W1995562189","https://openalex.org/W2067030274","https://openalex.org/W2077630439","https://openalex.org/W2089654579","https://openalex.org/W2124470987","https://openalex.org/W2144005487","https://openalex.org/W2163605009","https://openalex.org/W2166637769","https://openalex.org/W2250539671","https://openalex.org/W2253429366","https://openalex.org/W2279900378","https://openalex.org/W2403021840","https://openalex.org/W2562607067","https://openalex.org/W2747549721","https://openalex.org/W2747786714","https://openalex.org/W2756923881","https://openalex.org/W2766272105","https://openalex.org/W2787521618","https://openalex.org/W2794150026","https://openalex.org/W2796738181","https://openalex.org/W2803417255","https://openalex.org/W2896457183","https://openalex.org/W2963451564","https://openalex.org/W2963691377","https://openalex.org/W2963729456","https://openalex.org/W2972493869","https://openalex.org/W2972606665","https://openalex.org/W2972640480","https://openalex.org/W2972951327","https://openalex.org/W2973110385","https://openalex.org/W3034323214","https://openalex.org/W4297734170","https://openalex.org/W4385245566","https://openalex.org/W6678572281","https://openalex.org/W6679434410","https://openalex.org/W6684191040","https://openalex.org/W6739901393","https://openalex.org/W6748315912","https://openalex.org/W6755207826","https://openalex.org/W6776109479"],"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":{"Filled":[0,37],"pauses":[1,38,110],"(or":[2],"fillers)":[3],"are":[4,39],"the":[5,59,79,94,106,134,158,183,189,204,224,231,240,255],"most":[6],"common":[7],"form":[8],"of":[9,61,83,108,143,257],"speech":[10,81],"disfluencies":[11],"and":[12,22,73,130,246],"they":[13],"can":[14,77,89],"be":[15,90],"recognized":[16],"as":[17,87,147],"hesitation":[18],"markers":[19],"(\u201cum\u201d,":[20],"\u201cuh\u201d":[21],"\u201cer\u201d)":[23],"made":[24],"by":[25,211],"speakers,":[26],"usually":[27],"to":[28,193,248],"gain":[29],"extra":[30],"time":[31],"while":[32],"thinking":[33],"their":[34,56,75],"next":[35],"words.":[36],"very":[40],"frequent":[41],"in":[42,70,111],"spontaneous":[43],"speech.":[44],"Their":[45],"detection":[46,107,126],"is":[47,206,234,243],"therefore":[48],"rather":[49],"important":[50],"for":[51,105,123,188,202,236],"two":[52],"basic":[53],"reasons:":[54],"(a)":[55],"existence":[57],"influences":[58],"performance":[60,225],"individual":[62],"components,":[63],"like":[64],"Automatic":[65],"Speech":[66],"Recognition":[67],"system":[68],"(ASR),":[69],"human-machine":[71],"interaction":[72],"(b)":[74],"frequency":[76],"characterize":[78],"overall":[80],"quality":[82],"a":[84,121,141,163,218],"particular":[85],"speaker,":[86],"it":[88],"strongly":[91],"associated":[92],"with":[93],"speaker's":[95],"confidence.":[96],"Despite":[97],"that,":[98],"only":[99],"limited":[100],"work":[101],"has":[102,247],"been":[103],"published":[104],"filled":[109,124],"speech,":[112],"especially":[113],"through":[114],"audio.":[115],"In":[116,181,215],"this":[117,216],"work,":[118],"we":[119,137,161],"propose":[120],"framework":[122],"pause":[125],"using":[127,152],"both":[128],"audio":[129,135,190,232],"textual":[131,174,258],"information.":[132],"For":[133,157],"modality,":[136,160],"transfer":[138,185],"knowledge":[139],"from":[140,177],"plethora":[142],"supervised":[144],"tasks,":[145],"such":[146],"emotion":[148],"or":[149,253],"speaking":[150],"rate,":[151],"Convolutional":[153],"Neural":[154,166],"Networks":[155],"(CNNs).":[156],"text":[159,205,242],"develop":[162],"temporal":[164],"Recurrent":[165],"Network":[167],"(RNN)":[168],"method":[169],"that":[170,230],"takes":[171],"into":[172],"account":[173],"information":[175,259],"derived":[176],"an":[178,212],"ASR":[179,213,251],"system.":[180,214],"addition,":[182],"proposed":[184],"learning":[186],"approach":[187,222,233],"classifier":[191],"leads":[192],"better":[194],"results":[195],"when":[196],"benchmarked":[197],"on":[198],"our":[199],"internal":[200],"dataset":[201],"which":[203],"not":[207,244],"transcribed":[208,241],"but":[209],"estimated":[210],"case,":[217],"simple":[219],"late":[220],"fusion":[221],"boosts":[223],"even":[226,254],"further.":[227],"This":[228],"proves":[229],"suitable":[235],"real-world":[237],"applications":[238],"where":[239],"available":[245],"leverage":[249],"imperfect":[250],"results,":[252],"absence":[256],"(to":[260],"reduce":[261],"computational":[262],"cost).":[263]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}