{"id":"https://openalex.org/W4396753653","doi":"https://doi.org/10.1109/access.2024.3398584","title":"Identification of Non-Speaking and Minimal-Speaking Individuals Using Nonverbal Vocalizations","display_name":"Identification of Non-Speaking and Minimal-Speaking Individuals Using Nonverbal Vocalizations","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4396753653","doi":"https://doi.org/10.1109/access.2024.3398584"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3398584","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3398584","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10526253.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10526253.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010107824","display_name":"Van-Thuan Tran","orcid":"https://orcid.org/0000-0002-3197-679X"},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"van-Thuan Tran","raw_affiliation_strings":["Department of Electronic Engineering, National Taipei University of Technology, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-3197-679X","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, National Taipei University of Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I118292597"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020303183","display_name":"Wei-Ho Tsai","orcid":"https://orcid.org/0000-0002-0867-7951"},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Ho Tsai","raw_affiliation_strings":["Department of Electronic Engineering, National Taipei University of Technology, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-0867-7951","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, National Taipei University of Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I118292597"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010107824"],"corresponding_institution_ids":["https://openalex.org/I118292597"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.9718,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72569942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"12","issue":null,"first_page":"68954","last_page":"68967"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.711618185043335},{"id":"https://openalex.org/keywords/nonverbal-communication","display_name":"Nonverbal communication","score":0.6745975017547607},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6384392976760864},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6025606989860535},{"id":"https://openalex.org/keywords/pid-controller","display_name":"PID controller","score":0.48011088371276855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4474155008792877},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.44549819827079773},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.41176581382751465},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2582881450653076},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.1533675491809845},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11297142505645752},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.0713910460472107}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.711618185043335},{"id":"https://openalex.org/C145633318","wikidata":"https://www.wikidata.org/wiki/Q207125","display_name":"Nonverbal communication","level":2,"score":0.6745975017547607},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6384392976760864},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6025606989860535},{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.48011088371276855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4474155008792877},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.44549819827079773},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.41176581382751465},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2582881450653076},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.1533675491809845},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11297142505645752},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0713910460472107},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C536315585","wikidata":"https://www.wikidata.org/wiki/Q7698332","display_name":"Temperature control","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3398584","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3398584","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10526253.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:63367bd711344e0e86902fde90fe1966","is_oa":true,"landing_page_url":"https://doaj.org/article/63367bd711344e0e86902fde90fe1966","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 68954-68967 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3398584","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3398584","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10526253.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396753653.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1969761120","https://openalex.org/W1987215124","https://openalex.org/W1997402792","https://openalex.org/W2002311796","https://openalex.org/W2005289882","https://openalex.org/W2095705004","https://openalex.org/W2126908019","https://openalex.org/W2128980425","https://openalex.org/W2158074454","https://openalex.org/W2187089797","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2344582429","https://openalex.org/W2625969058","https://openalex.org/W2766510149","https://openalex.org/W2773125336","https://openalex.org/W2788991015","https://openalex.org/W2798991696","https://openalex.org/W2803579178","https://openalex.org/W2945925916","https://openalex.org/W2950271124","https://openalex.org/W2965939923","https://openalex.org/W2978673921","https://openalex.org/W3035524453","https://openalex.org/W3100517161","https://openalex.org/W3128347371","https://openalex.org/W3135577589","https://openalex.org/W3135791241","https://openalex.org/W3157722160","https://openalex.org/W3161704976","https://openalex.org/W3181410678","https://openalex.org/W3192610910","https://openalex.org/W4226219311","https://openalex.org/W4318776428","https://openalex.org/W4377966828","https://openalex.org/W4385607386","https://openalex.org/W4387543539","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6674330103","https://openalex.org/W6713134421","https://openalex.org/W6746528099","https://openalex.org/W6776700526","https://openalex.org/W6791439336","https://openalex.org/W6791762498","https://openalex.org/W6798708526"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2942893872","https://openalex.org/W2016904525"],"abstract_inverted_index":{"Speech":[0],"remains":[1],"a":[2,24,177],"prevalent":[3],"mode":[4],"of":[5,27,62,76,103,166],"communication":[6],"powering":[7],"various":[8],"intelligent":[9],"functions":[10],"in":[11,16,127,200,227],"human-computer":[12,216],"interaction":[13,217],"applications,":[14],"notably":[15],"Speaker/Person":[17],"Identification":[18],"(PID)":[19],"systems.":[20],"However,":[21],"there":[22],"is":[23],"considerable":[25],"population":[26],"Non-speaking":[28],"and":[29,41,72,91,107,116,124,158,197,225,229,234],"Minimal-speaking":[30],"(NMS)":[31],"individuals,":[32],"who":[33],"heavily":[34],"rely":[35],"on":[36,149,244],"nonverbal":[37,63,105],"vocalizations":[38,64,106],"for":[39,51,122,185,214,220],"communication,":[40],"the":[42,60,74,98,164,173],"existing":[43],"speech-based":[44,245],"PID":[45],"systems":[46],"may":[47],"not":[48],"be":[49],"suitable":[50],"users":[52,87,93],"from":[53,131,203],"this":[54],"community.":[55],"This":[56,209],"study":[57],"delves":[58],"into":[59],"use":[61],"to":[65,133,172],"identify":[66],"NMS":[67,92,104,221],"subjects,":[68],"termed":[69],"as":[70,156],"NMS-PID,":[71],"explores":[73],"feasibility":[75],"developing":[77],"an":[78],"identification":[79,237],"system,":[80],"namely":[81],"S-NMS-PID,":[82,125],"that":[83],"accommodates":[84],"both":[85],"speaking":[86],"(with":[88,94],"speech":[89,109],"input)":[90],"nonverbal-vocalization":[95],"input).":[96],"Leveraging":[97],"recently":[99],"published":[100],"ReCANVo":[101],"dataset":[102],"our":[108,111],"dataset,":[110],"experiments":[112],"with":[113,151,191],"multiple":[114],"networks":[115],"acoustic":[117],"features":[118,170],"demonstrate":[119],"promising":[120],"results":[121,147],"NMS-PID":[123,224],"evident":[126],"average":[128],"accuracies":[129],"ranging":[130],"70%":[132],"92%.":[134],"The":[135],"proposed":[136],"convolutional":[137],"recurrent":[138],"neural":[139],"network-based":[140],"model,":[141],"despite":[142],"its":[143],"smaller":[144],"size,":[145],"achieves":[146],"nearly":[148],"par":[150],"much":[152],"deeper":[153],"models":[154],"such":[155],"VGG16":[157],"ResNet50.":[159],"Our":[160],"findings":[161],"also":[162],"highlight":[163],"efficacy":[165],"Mel-frequency":[167],"cepstral":[168],"coefficients":[169],"compared":[171],"spectrogram":[174],"features.":[175],"Furthermore,":[176],"two-step":[178],"training":[179],"strategy":[180],"involving":[181],"supervised":[182],"contrastive":[183],"learning":[184,187],"representation":[186],"followed":[188],"by":[189],"fine-tuning":[190],"cross-entropy":[192],"loss":[193],"significantly":[194],"enhances":[195],"robustness":[196],"accuracy,":[198],"particularly":[199],"classifying":[201],"data":[202],"minority":[204],"classes,":[205],"enhancing":[206],"overall":[207],"performance.":[208],"study\u2019s":[210],"outcomes":[211],"hold":[212],"potential":[213],"tailoring":[215],"applications":[218],"specifically":[219],"users.":[222],"Implementing":[223],"S-NMS-PID":[226],"security":[228],"authentication":[230],"processes":[231],"ensures":[232],"secure":[233],"reliable":[235],"user":[236],"across":[238],"diverse":[239],"platforms,":[240],"transcending":[241],"sole":[242],"reliance":[243],"methods.":[246]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}