{"id":"https://openalex.org/W7118002173","doi":"https://doi.org/10.3390/jsan15010006","title":"From Sound to Risk: Streaming Audio Flags for Real-World Hazard Inference Based on AI","display_name":"From Sound to Risk: Streaming Audio Flags for Real-World Hazard Inference Based on AI","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7118002173","doi":"https://doi.org/10.3390/jsan15010006"},"language":"en","primary_location":{"id":"doi:10.3390/jsan15010006","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jsan15010006","pdf_url":null,"source":{"id":"https://openalex.org/S2736633529","display_name":"Journal of Sensor and Actuator Networks","issn_l":"2224-2708","issn":["2224-2708"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Sensor and Actuator Networks","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/jsan15010006","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050529028","display_name":"Ilyas Potamitis","orcid":"https://orcid.org/0000-0002-7111-3331"},"institutions":[{"id":"https://openalex.org/I26840924","display_name":"Mediterranean University","ror":"https://ror.org/03tsjvt68","country_code":"ME","type":"education","lineage":["https://openalex.org/I26840924"]}],"countries":["ME"],"is_corresponding":true,"raw_author_name":"Ilyas Potamitis","raw_affiliation_strings":["Department of Music Technology and Acoustics, Hellenic Mediterranean University, 71410 Heraklion, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Music Technology and Acoustics, Hellenic Mediterranean University, 71410 Heraklion, Greece","institution_ids":["https://openalex.org/I26840924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5050529028"],"corresponding_institution_ids":["https://openalex.org/I26840924"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02496191,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":"1","first_page":"6","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.12330000102519989,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.12330000102519989,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.08910000324249268,"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/T12488","display_name":"Mental Health via Writing","score":0.08299999684095383,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7228000164031982},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7049999833106995},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.47369998693466187},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.44020000100135803},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4268999993801117},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4036000072956085},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.39989998936653137},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.38449999690055847},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3637999892234802},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.35280001163482666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8751999735832214},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7228000164031982},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7049999833106995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5343000292778015},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.47369998693466187},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.44020000100135803},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4268999993801117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41999998688697815},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4036000072956085},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.38449999690055847},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3698999881744385},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.3249000012874603},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3190999925136566},{"id":"https://openalex.org/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.3147999942302704},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.3034999966621399},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29580000042915344},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29100000858306885},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.27239999175071716},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/jsan15010006","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jsan15010006","pdf_url":null,"source":{"id":"https://openalex.org/S2736633529","display_name":"Journal of Sensor and Actuator Networks","issn_l":"2224-2708","issn":["2224-2708"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Sensor and Actuator Networks","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:e36f260117984d4bb867a799c2817fe1","is_oa":true,"landing_page_url":"https://doaj.org/article/e36f260117984d4bb867a799c2817fe1","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Sensor and Actuator Networks, Vol 15, Iss 1, p 6 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/jsan15010006","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jsan15010006","pdf_url":null,"source":{"id":"https://openalex.org/S2736633529","display_name":"Journal of Sensor and Actuator Networks","issn_l":"2224-2708","issn":["2224-2708"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Sensor and Actuator Networks","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7096918821334839,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1844944916","https://openalex.org/W1976725440","https://openalex.org/W2091425152","https://openalex.org/W2118774185","https://openalex.org/W2167894329","https://openalex.org/W2771727220","https://openalex.org/W2954420970","https://openalex.org/W2962866891","https://openalex.org/W3089682612","https://openalex.org/W3094550259","https://openalex.org/W3136793533","https://openalex.org/W3155425633","https://openalex.org/W3160045550","https://openalex.org/W3196974791","https://openalex.org/W3205743929","https://openalex.org/W3209895620","https://openalex.org/W3210447534","https://openalex.org/W4200162263","https://openalex.org/W4210416950","https://openalex.org/W4220685517","https://openalex.org/W4226442948","https://openalex.org/W4283827116","https://openalex.org/W4285206108","https://openalex.org/W4289521424","https://openalex.org/W4289868886","https://openalex.org/W4304098292","https://openalex.org/W4313061427","https://openalex.org/W4327955601","https://openalex.org/W4362654577","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4378072574","https://openalex.org/W4382461973","https://openalex.org/W4386336847","https://openalex.org/W4387072950","https://openalex.org/W4392520346","https://openalex.org/W4393153999","https://openalex.org/W4399895956","https://openalex.org/W4402112408","https://openalex.org/W4402945872","https://openalex.org/W4403044819","https://openalex.org/W4404692180","https://openalex.org/W4409606465","https://openalex.org/W4412627971","https://openalex.org/W4413236961","https://openalex.org/W4415026456"],"related_works":[],"abstract_inverted_index":{"Seconds":[0],"count":[1],"differently":[2],"for":[3,13,173],"people":[4],"in":[5,87],"danger.":[6],"We":[7,202,216],"present":[8],"a":[9,31,46,69,77,103,140,168,188,192,206],"real-time":[10],"streaming":[11,129,141],"pipeline":[12],"audio-based":[14],"detection":[15],"of":[16,45,143,208],"hazardous":[17],"life":[18,21],"events":[19,136],"affecting":[20],"and":[22,51,72,113,154,162,176,191,200,224,234],"property.":[23],"The":[24,57,81,165,196],"system":[25,166,197],"operates":[26],"online":[27,89,174],"rather":[28],"than":[29],"as":[30,64],"retrospective":[32],"analysis":[33],"tool.":[34],"Its":[35],"objective":[36],"is":[37,60,126],"to":[38,61,227,231],"reduce":[39],"the":[40,43,52,74,209,229],"latency":[41],"between":[42],"occurrence":[44],"crime,":[47],"conflict,":[48],"or":[49],"accident":[50],"corresponding":[53],"response":[54],"by":[55,66,102,139],"authorities.":[56],"key":[58],"idea":[59],"map":[62],"reality":[63],"perceived":[65],"audio":[67,135],"into":[68,95],"written":[70],"story":[71],"question":[73],"text":[75],"via":[76],"large":[78,169],"language":[79,105,170],"model.":[80,106],"method":[82],"integrates":[83],"streaming,":[84],"zero-shot":[85],"algorithms":[86],"an":[88],"decoding":[90,175],"mode":[91],"that":[92],"convert":[93],"sound":[94],"short,":[96],"interpretable":[97],"tokens,":[98],"which":[99],"are":[100,137,150],"processed":[101],"lightweight":[104],"CLAP":[107],"text\u2013audio":[108],"prompting":[109],"identifies":[110],"agitation,":[111],"panic,":[112],"distress":[114],"cues,":[115],"combined":[116],"with":[117,187],"conversational":[118],"dynamics":[119],"derived":[120,157],"from":[121,158],"speaker":[122],"diarization.":[123],"Lexical":[124],"information":[125],"obtained":[127],"through":[128],"automatic":[130],"speech":[131],"recognition,":[132],"while":[133],"general":[134],"detected":[138],"version":[142],"Audio":[144],"Spectrogram":[145],"Transformer":[146],"tagger.":[147],"Prosodic":[148],"features":[149],"incorporated":[151],"using":[152],"pitch-":[153],"energy-based":[155],"rules":[156],"robust":[159],"F0":[160],"tracking":[161],"periodicity":[163],"measures.":[164],"uses":[167],"model":[171],"configured":[172],"outputs":[177],"binary":[178],"(YES/NO)":[179],"life-threatening":[180],"risk":[181],"decisions":[182],"every":[183],"two":[184],"seconds,":[185],"along":[186],"brief":[189],"justification":[190],"final":[193],"session-level":[194],"verdict.":[195],"emphasizes":[198],"interpretability":[199],"accountability.":[201],"evaluate":[203],"it":[204],"on":[205],"subset":[207],"X-Violence":[210],"dataset,":[211],"comprising":[212],"only":[213],"real-world":[214],"videos.":[215],"release":[217],"code,":[218],"prompts,":[219],"decision":[220],"policies,":[221],"evaluation":[222],"splits,":[223],"example":[225],"logs":[226],"enable":[228],"community":[230],"replicate,":[232],"critique,":[233],"extend":[235],"our":[236],"blueprint.":[237]},"counts_by_year":[],"updated_date":"2026-02-28T09:26:25.869077","created_date":"2026-01-02T00:00:00"}
