{"id":"https://openalex.org/W4402402534","doi":"https://doi.org/10.1109/icasspw62465.2024.10669901","title":"Listening Between the Lines: Synthetic Speech Detection Disregarding Verbal Content","display_name":"Listening Between the Lines: Synthetic Speech Detection Disregarding Verbal Content","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4402402534","doi":"https://doi.org/10.1109/icasspw62465.2024.10669901"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10669901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10669901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5033038241","display_name":"Davide Salvi","orcid":"https://orcid.org/0000-0002-5163-3364"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Davide Salvi","raw_affiliation_strings":["Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria,Milan,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria,Milan,Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093902812","display_name":"Temesgen Semu Balcha","orcid":null},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Temesgen Semu Balcha","raw_affiliation_strings":["Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria,Milan,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria,Milan,Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051370303","display_name":"Paolo Bestagini","orcid":"https://orcid.org/0000-0003-0406-0222"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Bestagini","raw_affiliation_strings":["Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria,Milan,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria,Milan,Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005378965","display_name":"Stefano Tubaro","orcid":"https://orcid.org/0000-0002-1990-9869"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Stefano Tubaro","raw_affiliation_strings":["Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria,Milan,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria,Milan,Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033038241"],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":2.111,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88245903,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"883","last_page":"887"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.9979000091552734,"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/active-listening","display_name":"Active listening","score":0.7999159097671509},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6688367128372192},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6586617231369019},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.49067652225494385},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.44592300057411194},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3758082389831543},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1666923463344574},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.13000008463859558},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07145968079566956}],"concepts":[{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.7999159097671509},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6688367128372192},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6586617231369019},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.49067652225494385},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.44592300057411194},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3758082389831543},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1666923463344574},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.13000008463859558},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07145968079566956},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10669901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10669901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2005768155","https://openalex.org/W2541922885","https://openalex.org/W2913181996","https://openalex.org/W2936802426","https://openalex.org/W2964052309","https://openalex.org/W2967606780","https://openalex.org/W2989571531","https://openalex.org/W3015191643","https://openalex.org/W3024758142","https://openalex.org/W3024805264","https://openalex.org/W3097906045","https://openalex.org/W3097945073","https://openalex.org/W3163596559","https://openalex.org/W3163652268","https://openalex.org/W3197358873","https://openalex.org/W3200527256","https://openalex.org/W3203575608","https://openalex.org/W4221138880","https://openalex.org/W4225288420","https://openalex.org/W4225904138","https://openalex.org/W4297841787","https://openalex.org/W4311591823","https://openalex.org/W4311591887","https://openalex.org/W4312743281","https://openalex.org/W4360992936","https://openalex.org/W4385466335","https://openalex.org/W4388117344"],"related_works":["https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W2997121352","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W4237969969","https://openalex.org/W1594297642","https://openalex.org/W127416991"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,49,83,141,170],"synthetic":[3,37,58,108,143,156],"speech":[4,67,95,109,134,144,157],"generation":[5],"have":[6,46,72],"led":[7],"to":[8,52],"the":[9,29,34,50,63,66,75,84,118,122,133,138,152,167,171],"creation":[10],"of":[11,36,65,121,154],"forged":[12],"audio":[13,172],"data":[14],"that":[15,74,132],"are":[16],"almost":[17],"indistinguishable":[18],"from":[19],"real":[20],"speech.":[21],"This":[22],"phenomenon":[23],"poses":[24],"a":[25],"new":[26,155],"challenge":[27],"for":[28,80,151],"multimedia":[30],"forensics":[31,173],"community,":[32],"as":[33],"misuse":[35],"media":[38],"can":[39,111],"potentially":[40],"cause":[41],"adverse":[42],"consequences.":[43],"Several":[44],"methods":[45],"been":[47],"proposed":[48],"literature":[51],"mitigate":[53],"potential":[54],"risks":[55],"and":[56,105,159],"detect":[57],"speech,":[59],"mainly":[60],"focusing":[61,115],"on":[62,117,166],"analysis":[64],"itself.":[68],"However,":[69],"recent":[70],"studies":[71],"revealed":[73],"most":[76],"crucial":[77],"frequency":[78],"bands":[79],"detection":[81,110],"lie":[82],"highest":[85],"ranges":[86],"(above":[87],"6000":[88],"Hz),":[89],"which":[90],"do":[91],"not":[92,137],"include":[93],"any":[94],"content.":[96,128],"In":[97],"this":[98,103],"work,":[99],"we":[100],"extensively":[101],"explore":[102],"aspect":[104],"investigate":[106],"whether":[107],"be":[112],"performed":[113],"by":[114],"only":[116],"background":[119],"component":[120,135],"signal":[123],"while":[124],"disregarding":[125],"its":[126],"verbal":[127],"Our":[129],"findings":[130],"indicate":[131],"is":[136],"predominant":[139],"factor":[140],"performing":[142],"detection.":[145],"These":[146],"insights":[147],"provide":[148],"valuable":[149],"guidance":[150],"development":[153],"detectors":[158],"their":[160],"interpretability,":[161],"together":[162],"with":[163],"some":[164],"considerations":[165],"existing":[168],"work":[169],"field.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}