{"id":"https://openalex.org/W4415034296","doi":"https://doi.org/10.1109/jiot.2025.3620215","title":"AuraVox: mmWave-Augmented Audio Pipeline for Nonintrusive Emotion Sensing in Complex IoT Environments","display_name":"AuraVox: mmWave-Augmented Audio Pipeline for Nonintrusive Emotion Sensing in Complex IoT Environments","publication_year":2025,"publication_date":"2025-10-10","ids":{"openalex":"https://openalex.org/W4415034296","doi":"https://doi.org/10.1109/jiot.2025.3620215"},"language":"en","primary_location":{"id":"doi:10.1109/jiot.2025.3620215","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2025.3620215","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"is_oa":false,"is_in_doaj":false,"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 Internet of Things Journal","raw_type":"journal-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/A5055437764","display_name":"Naveed Imran","orcid":"https://orcid.org/0009-0002-2944-1187"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Naveed Imran","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0002-2944-1187","affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091790870","display_name":"Jian Zhang","orcid":"https://orcid.org/0000-0003-3612-7989"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhang","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086748596","display_name":"Chihhsiong Shih","orcid":"https://orcid.org/0000-0002-9266-0940"},"institutions":[{"id":"https://openalex.org/I169090423","display_name":"Tunghai University","ror":"https://ror.org/00zhvdn11","country_code":"TW","type":"education","lineage":["https://openalex.org/I169090423"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chihhsiong Shih","raw_affiliation_strings":["Department of Computer Science, Tunghai University, Taichung, Taiwan","Department of Computer Science, Tunghai University, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-9266-0940","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tunghai University, Taichung, Taiwan","institution_ids":["https://openalex.org/I169090423"]},{"raw_affiliation_string":"Department of Computer Science, Tunghai University, Taiwan","institution_ids":["https://openalex.org/I169090423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009357487","display_name":"Sana Hameed","orcid":"https://orcid.org/0009-0004-5972-3008"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sana Hameed","raw_affiliation_strings":["School of Cyber Science and Engineering, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0004-5972-3008","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083313870","display_name":"Abid Ishaq","orcid":"https://orcid.org/0000-0002-9557-8889"},"institutions":[{"id":"https://openalex.org/I174731842","display_name":"Islamia University of Bahawalpur","ror":"https://ror.org/002rc4w13","country_code":"PK","type":"education","lineage":["https://openalex.org/I174731842"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Abid Ishaq","raw_affiliation_strings":["Department of Computer Science and Information Technology, The Islamia University of Bahawalpur, Bahawalpur, Pakistan","Department of Computer Science and Information Technology, The Islamia University of Bahawalpur, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Technology, The Islamia University of Bahawalpur, Bahawalpur, Pakistan","institution_ids":["https://openalex.org/I174731842"]},{"raw_affiliation_string":"Department of Computer Science and Information Technology, The Islamia University of Bahawalpur, Pakistan","institution_ids":["https://openalex.org/I174731842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014562556","display_name":"Khursheed Aurangzeb","orcid":"https://orcid.org/0000-0003-3647-8578"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Khursheed Aurangzeb","raw_affiliation_strings":["Department of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0003-3647-8578","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8777,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8866576,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"13","issue":"2","first_page":"1756","last_page":"1777"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12801","display_name":"Bluetooth and Wireless Communication Technologies","score":0.9362999796867371,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12801","display_name":"Bluetooth and Wireless Communication Technologies","score":0.9362999796867371,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9266999959945679,"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/pipeline","display_name":"Pipeline (software)","score":0.49720001220703125},{"id":"https://openalex.org/keywords/bespoke","display_name":"Bespoke","score":0.4636000096797943},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.4478999972343445},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41530001163482666},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.38929998874664307},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.3652999997138977},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.36329999566078186},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.3508000075817108},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34929999709129333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8144999742507935},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.588100016117096},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.49720001220703125},{"id":"https://openalex.org/C44210515","wikidata":"https://www.wikidata.org/wiki/Q16968978","display_name":"Bespoke","level":2,"score":0.4636000096797943},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43470001220703125},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41530001163482666},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38920000195503235},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.31709998846054077},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C87360688","wikidata":"https://www.wikidata.org/wiki/Q740686","display_name":"Synthetic aperture radar","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C142757262","wikidata":"https://www.wikidata.org/wiki/Q76436","display_name":"Doppler effect","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2025.3620215","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2025.3620215","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"is_oa":false,"is_in_doaj":false,"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 Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7444512360","display_name":null,"funder_award_id":"NSTC 113-2622-8-029-004-IE","funder_id":"https://openalex.org/F4320331164","funder_display_name":"National Science and Technology Council"}],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W4309675584","https://openalex.org/W4387087125","https://openalex.org/W4388692349","https://openalex.org/W4389925599","https://openalex.org/W4403465751","https://openalex.org/W4405812613"],"related_works":[],"abstract_inverted_index":{"Reliable,":[0],"privacy-preserving":[1],"emotion":[2,99,169],"sensing":[3],"is":[4,134],"essential":[5],"for":[6,98,149],"next-generation":[7],"IoT":[8],"applications;":[9],"however,":[10],"vision":[11],"or":[12,25],"audio-only":[13,124],"pipelines":[14],"often":[15],"break":[16],"down":[17],"when":[18],"faces":[19],"are":[20,23,80],"masked,":[21],"environments":[22],"noisy,":[24],"multiple":[26],"speakers":[27],"coexist.":[28],"We":[29],"present":[30],"AuraVox,":[31],"a":[32,48,83,95,103,140],"contactless":[33],"system":[34],"that":[35,108,171],"couples":[36],"millimetre-wave":[37],"lip":[38,71,155],"micro-Doppler":[39],"with":[40,157],"speech":[41,78,158],"acoustics":[42],"and":[43,62,76,93,113,123,187],"fuses":[44],"them":[45],"through":[46,160],"AuraNet,":[47,161],"bespoke":[49],"cross-modal":[50],"transformer.":[51],"The":[52],"radar":[53],"first":[54,165],"localizes":[55],"each":[56],"talker":[57],"via":[58],"MUSIC-based":[59],"direction-of-arrival":[60],"estimation":[61],"Bartlett":[63],"beamforming,":[64],"then":[65],"captures":[66],"high-resolution":[67],"Doppler":[68],"signatures":[69],"of":[70],"motion;":[72],"in":[73],"parallel,":[74],"prosodic":[75],"spectral":[77],"cues":[79,159],"extracted":[81],"from":[82],"lapel":[84],"microphone.":[85],"AuraNet":[86],"holistically":[87],"attends":[88],"to":[89,128],"these":[90],"heterogeneous":[91],"streams":[92],"produces":[94],"unified":[96],"representation":[97],"classification.":[100],"Evaluated":[101],"on":[102,139,173],"30-subject":[104],"bilingual":[105],"(English/Mandarin)":[106],"corpus":[107],"includes":[109],"mask-wearing,":[110],"multi-speaker":[111],"overlap,":[112],"30\u201390":[114],"cm":[115],"ranges,":[116],"AuraVox":[117,162],"attains":[118],"96%":[119],"macro-F1,":[120],"outperforming":[121],"radar-only":[122],"baselines":[125],"by":[126],"up":[127],"eight":[129],"percentage":[130],"points.":[131],"End-to-end":[132],"latency":[133],"12.8":[135],"ms":[136],"per":[137],"frame":[138],"10":[141],"W":[142],"Jetson":[143],"Xavier":[144],"NX,":[145],"meeting":[146],"real-time":[147],"constraints":[148],"edge":[150],"deployment.":[151],"By":[152],"unifying":[153],"beamformed":[154],"kinematics":[156],"delivers":[163],"the":[164],"multi-speaker,":[166],"cross-language,":[167],"mask-resilient":[168],"recognizer":[170],"runs":[172],"commodity":[174],"hardware.":[175],"Representative":[176],"use":[177],"cases":[178],"include":[179],"stress-aware":[180],"in-cabin":[181],"driver":[182],"assistance,":[183],"hospital":[184],"check-in":[185],"triage,":[186],"mood-adaptive":[188],"smart-home":[189],"interfaces.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-01-14T23:40:02.550235","created_date":"2025-10-10T00:00:00"}
