{"id":"https://openalex.org/W4390489179","doi":"https://doi.org/10.1109/wifs58808.2023.10374734","title":"On Exploring Audio Anomaly in Speech","display_name":"On Exploring Audio Anomaly in Speech","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4390489179","doi":"https://doi.org/10.1109/wifs58808.2023.10374734"},"language":"en","primary_location":{"id":"doi:10.1109/wifs58808.2023.10374734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wifs58808.2023.10374734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Workshop on Information Forensics and Security (WIFS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5088262626","display_name":"Tiago Roxo","orcid":"https://orcid.org/0000-0001-9563-8039"},"institutions":[{"id":"https://openalex.org/I161321875","display_name":"University of Beira Interior","ror":"https://ror.org/03nf36p02","country_code":"PT","type":"education","lineage":["https://openalex.org/I161321875"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Tiago Roxo","raw_affiliation_strings":["Inst. de Telecomunicacoes Univ. da Beira Interior,Covilha,Portugal","Inst. de Telecomunicacoes Univ. da Beira Interior, Covilha, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inst. de Telecomunicacoes Univ. da Beira Interior,Covilha,Portugal","institution_ids":["https://openalex.org/I161321875"]},{"raw_affiliation_string":"Inst. de Telecomunicacoes Univ. da Beira Interior, Covilha, Portugal","institution_ids":["https://openalex.org/I161321875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016093558","display_name":"Joana C. Costa","orcid":"https://orcid.org/0000-0003-3995-4621"},"institutions":[{"id":"https://openalex.org/I161321875","display_name":"University of Beira Interior","ror":"https://ror.org/03nf36p02","country_code":"PT","type":"education","lineage":["https://openalex.org/I161321875"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Joana Cabral Costa","raw_affiliation_strings":["Inst. de Telecomunicacoes Univ. da Beira Interior,Covilha,Portugal","Inst. de Telecomunicacoes Univ. da Beira Interior, Covilha, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inst. de Telecomunicacoes Univ. da Beira Interior,Covilha,Portugal","institution_ids":["https://openalex.org/I161321875"]},{"raw_affiliation_string":"Inst. de Telecomunicacoes Univ. da Beira Interior, Covilha, Portugal","institution_ids":["https://openalex.org/I161321875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058284019","display_name":"Pedro R. M. In\u00e1cio","orcid":"https://orcid.org/0000-0001-8221-0666"},"institutions":[{"id":"https://openalex.org/I161321875","display_name":"University of Beira Interior","ror":"https://ror.org/03nf36p02","country_code":"PT","type":"education","lineage":["https://openalex.org/I161321875"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Pedro R. M. In\u00e1cio","raw_affiliation_strings":["Inst. de Telecomunicacoes Univ. da Beira Interior,Covilha,Portugal","Inst. de Telecomunicacoes Univ. da Beira Interior, Covilha, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inst. de Telecomunicacoes Univ. da Beira Interior,Covilha,Portugal","institution_ids":["https://openalex.org/I161321875"]},{"raw_affiliation_string":"Inst. de Telecomunicacoes Univ. da Beira Interior, Covilha, Portugal","institution_ids":["https://openalex.org/I161321875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090305015","display_name":"Hugo Proen\u00e7a","orcid":"https://orcid.org/0000-0003-2551-8570"},"institutions":[{"id":"https://openalex.org/I161321875","display_name":"University of Beira Interior","ror":"https://ror.org/03nf36p02","country_code":"PT","type":"education","lineage":["https://openalex.org/I161321875"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Hugo Proen\u00e7a","raw_affiliation_strings":["Inst. de Telecomunicacoes Univ. da Beira Interior,Covilha,Portugal","Inst. de Telecomunicacoes Univ. da Beira Interior, Covilha, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inst. de Telecomunicacoes Univ. da Beira Interior,Covilha,Portugal","institution_ids":["https://openalex.org/I161321875"]},{"raw_affiliation_string":"Inst. de Telecomunicacoes Univ. da Beira Interior, Covilha, Portugal","institution_ids":["https://openalex.org/I161321875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161321875"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9976999759674072,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9976999759674072,"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/T10860","display_name":"Speech and Audio Processing","score":0.98089998960495,"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/T11309","display_name":"Music and Audio Processing","score":0.9624999761581421,"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/anomaly-detection","display_name":"Anomaly detection","score":0.8237572908401489},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.8050358295440674},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.717776358127594},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5729199647903442},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.497882604598999},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46640291810035706},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46567079424858093},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3664066195487976},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07600587606430054}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.8237572908401489},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.8050358295440674},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.717776358127594},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5729199647903442},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.497882604598999},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46640291810035706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46567079424858093},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3664066195487976},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07600587606430054},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C26873012","wikidata":"https://www.wikidata.org/wiki/Q214781","display_name":"Condensed matter physics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wifs58808.2023.10374734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wifs58808.2023.10374734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Workshop on Information Forensics and Security (WIFS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2108287924","https://openalex.org/W2128160875","https://openalex.org/W2144994235","https://openalex.org/W2341058432","https://openalex.org/W2554388950","https://openalex.org/W2557139718","https://openalex.org/W2763008059","https://openalex.org/W2763761345","https://openalex.org/W2786599352","https://openalex.org/W2925312408","https://openalex.org/W2963610939","https://openalex.org/W2976482555","https://openalex.org/W2982294822","https://openalex.org/W3016098309","https://openalex.org/W3022606336","https://openalex.org/W3035240825","https://openalex.org/W3080722105","https://openalex.org/W3099696441","https://openalex.org/W3164104137","https://openalex.org/W3168984673","https://openalex.org/W3184778778","https://openalex.org/W3185010842","https://openalex.org/W3202590754","https://openalex.org/W3205597769","https://openalex.org/W3206008172","https://openalex.org/W4287751198","https://openalex.org/W4296117254","https://openalex.org/W4312772600","https://openalex.org/W4372346631","https://openalex.org/W6744964450","https://openalex.org/W6780257151","https://openalex.org/W6802647179"],"related_works":["https://openalex.org/W2806741695","https://openalex.org/W3210364259","https://openalex.org/W4290647774","https://openalex.org/W3189286258","https://openalex.org/W3207797160","https://openalex.org/W2912112202","https://openalex.org/W2667207928","https://openalex.org/W4300558037","https://openalex.org/W4377864969","https://openalex.org/W3030345572"],"abstract_inverted_index":{"Existing":[0],"anomaly":[1,59,88,99,122,141,150,157,165,168,174,208],"detection":[2],"works":[3,205],"mainly":[4],"focus":[5],"on":[6,130,206],"abnormal":[7],"activities":[8],"in":[9,24,39,71,143,156,164],"image":[10],"and":[11,61,78,104,124,128,132,176,194],"video":[12,121],"settings,":[13],"while":[14,159],"assessing":[15,55],"audio":[16,23,53,134,171,181],"manipulation,":[17],"namely":[18],"the":[19,40,56,73,80,107,114,184],"presence":[20,74],"of":[21,42,58,75,110,116,196],"anomalous":[22],"speech,":[25],"has":[26],"not":[27],"yet":[28],"been":[29],"explored.":[30],"To":[31,86],"overcome":[32],"this":[33,197],"limitation,":[34],"we":[35,67,90,112],"propose":[36,91],"a":[37,49,95,117,201],"setup":[38,63,193],"context":[41],"Active":[43],"Speaker":[44],"Detection":[45],"(ASD)":[46],"by":[47],"defining":[48],"methodology":[50],"to":[51,97,188],"perceive":[52],"anomaly,":[54],"performance":[57,70,115],"models,":[60],"establishing":[62],"variations.":[64],"This":[65],"way,":[66],"evaluate":[68],"models":[69,126,147,161],"identifying":[72],"anomalies":[76],"(detection)":[77],"localizing":[79,133],"timeframe":[81],"where":[82],"they":[83],"occur":[84],"(localization).":[85],"complement":[87],"detection,":[89,158],"Anomaly":[92],"Score":[93],"(AS),":[94],"metric":[96],"assess":[98],"localization":[100],"that":[101],"balances":[102],"precision":[103],"mis-localization.":[105],"Given":[106],"sequential":[108],"nature":[109],"audio,":[111],"explore":[113],"density-based":[118],"approach":[119],"for":[120,203],"(CPD)":[123],"recurrent":[125,160],"(LSTM":[127],"RNN)":[129],"detecting":[131],"anomalies.":[135],"The":[136,192],"results":[137],"show":[138],"that:":[139],"1)":[140],"inclusion":[142],"talking":[144],"portions":[145],"increases":[146],"resilience":[148],"toward":[149],"localization;":[151,166,175],"2)":[152],"CPD":[153],"is":[154,182],"superior":[155],"perform":[162],"better":[163],"3)":[167],"with":[169],"distinctive":[170],"benefits":[172],"precise":[173],"4)":[177],"using":[178],"original":[179],"ASD":[180],"overall":[183],"best":[185],"approach,":[186],"relative":[187],"other":[189],"processing":[190],"approaches.":[191],"experiments":[195],"work":[198],"serve":[199],"as":[200],"baseline":[202],"future":[204],"speech":[207],"detection.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}