{"id":"https://openalex.org/W4392902958","doi":"https://doi.org/10.1109/icassp48485.2024.10448243","title":"On The Role of Room Acoustics in Audio Presentation Attack Detection","display_name":"On The Role of Room Acoustics in Audio Presentation Attack Detection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902958","doi":"https://doi.org/10.1109/icassp48485.2024.10448243"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5050288940","display_name":"Nikolay D. Gaubitch","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nikolay D. Gaubitch","raw_affiliation_strings":["Pindrop Inc.,London,UK","Pindrop Inc., London, UK"],"affiliations":[{"raw_affiliation_string":"Pindrop Inc.,London,UK","institution_ids":[]},{"raw_affiliation_string":"Pindrop Inc., London, UK","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007939707","display_name":"David Looney","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Looney","raw_affiliation_strings":["Pindrop Inc.,London,UK","Pindrop Inc., London, UK"],"affiliations":[{"raw_affiliation_string":"Pindrop Inc.,London,UK","institution_ids":[]},{"raw_affiliation_string":"Pindrop Inc., London, UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5050288940"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.375,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.49400364,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"906","last_page":"910"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9995999932289124,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/microphone","display_name":"Microphone","score":0.7170706987380981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7135431170463562},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.7033248543739319},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6496033668518066},{"id":"https://openalex.org/keywords/room-acoustics","display_name":"Room acoustics","score":0.5877688527107239},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.5689208507537842},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.5638254880905151},{"id":"https://openalex.org/keywords/presentation","display_name":"Presentation (obstetrics)","score":0.5455725193023682},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5111313462257385},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.4421810507774353},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.3210597038269043},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10577675700187683}],"concepts":[{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7170706987380981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7135431170463562},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.7033248543739319},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6496033668518066},{"id":"https://openalex.org/C178432105","wikidata":"https://www.wikidata.org/wiki/Q2182127","display_name":"Room acoustics","level":3,"score":0.5877688527107239},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.5689208507537842},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5638254880905151},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.5455725193023682},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5111313462257385},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.4421810507774353},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.3210597038269043},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10577675700187683},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/icassp48485.2024.10448243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2047346462","https://openalex.org/W2086286498","https://openalex.org/W2117678320","https://openalex.org/W2136682440","https://openalex.org/W2410879554","https://openalex.org/W2745896134","https://openalex.org/W2807325376","https://openalex.org/W2895056394","https://openalex.org/W2916877209","https://openalex.org/W2936802426","https://openalex.org/W2967606780","https://openalex.org/W3160312829","https://openalex.org/W4254118426","https://openalex.org/W4381198892","https://openalex.org/W4399379205","https://openalex.org/W6634389747","https://openalex.org/W6637373629"],"related_works":["https://openalex.org/W3199097733","https://openalex.org/W2738771020","https://openalex.org/W1562475690","https://openalex.org/W1488529827","https://openalex.org/W1607021895","https://openalex.org/W2733029664","https://openalex.org/W2801062816","https://openalex.org/W2987432963","https://openalex.org/W2053167664","https://openalex.org/W2780118011"],"abstract_inverted_index":{"Presentation":[0],"attack":[1],"detection":[2],"(PAD)":[3],"aims":[4],"to":[5,34,93,136,148],"determine":[6],"if":[7,22],"a":[8,13,18,27,61,75,95,116,128,144,149],"speech":[9,59,145],"signal":[10],"observed":[11,58],"at":[12],"microphone":[14],"was":[15,24],"produced":[16],"by":[17],"live":[19,122],"talker":[20],"or":[21],"it":[23],"replayed":[25,124],"through":[26],"loudspeaker.":[28],"This":[29],"is":[30,55,115],"an":[31,113],"important":[32],"problem":[33],"address":[35],"for":[36,119],"secure":[37],"human-computer":[38],"voice":[39],"interactions.":[40],"One":[41],"characteristic":[42],"of":[43,77,112,155],"presentation":[44,96],"attacks":[45],"where":[46],"recording":[47],"and":[48,123,169],"replay":[49,82],"occur":[50],"within":[51],"enclosed":[52],"reverberant":[53],"environments":[54],"that":[56,107],"the":[57,81,108,138,156],"in":[60,80,102],"live-talker":[62],"scenario":[63],"will":[64,73],"undergo":[65],"one":[66],"acoustic":[67],"impulse":[68],"response":[69],"(AIR)":[70],"while":[71],"there":[72],"be":[74,91],"pair":[76],"convolved":[78],"AIRs":[79],"scenario.":[83],"We":[84,126],"investigate":[85],"how":[86],"this":[87],"physical":[88],"fact":[89],"may":[90],"used":[92],"detect":[94],"attack.":[97],"Drawing":[98],"on":[99,131,159],"established":[100],"results":[101],"room":[103,160],"acoustics,":[104],"we":[105],"show":[106],"spectral":[109,139],"standard":[110,140],"deviation":[111,141],"AIR":[114],"promising":[117],"feature":[118],"distinguishing":[120],"between":[121],"speech.":[125],"develop":[127],"method":[129],"based":[130,158],"convolutional":[132],"neural":[133],"networks":[134],"(CNNs)":[135],"estimate":[137],"directly":[142],"from":[143,167],"signal,":[146],"leading":[147],"zero-shot":[150],"PAD":[151],"approach.":[152],"Several":[153],"aspects":[154],"detectability":[157],"acoustics":[161],"alone":[162],"are":[163],"illustrated":[164],"using":[165],"data":[166],"ASVspoof2019":[168],"ASVspoof2021.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
