{"id":"https://openalex.org/W4392903927","doi":"https://doi.org/10.1109/icassp48485.2024.10446041","title":"MOS-FAD: Improving Fake Audio Detection Via Automatic Mean Opinion Score Prediction","display_name":"MOS-FAD: Improving Fake Audio Detection Via Automatic Mean Opinion Score Prediction","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903927","doi":"https://doi.org/10.1109/icassp48485.2024.10446041"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446041","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":"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/A5032740716","display_name":"Wangjin Zhou","orcid":"https://orcid.org/0009-0007-0693-5316"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wangjin Zhou","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan","Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109209901","display_name":"Zhengdong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhengdong Yang","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan","Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102757632","display_name":"Chenhui Chu","orcid":"https://orcid.org/0000-0001-9848-6384"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chenhui Chu","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan","Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["National Institute of Information and Communications Technology (NICT),Kyoto,Japan","National Institute of Information and Communications Technology (NICT), Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT),Kyoto,Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077362985","display_name":"Raj Dabre","orcid":"https://orcid.org/0000-0003-0664-3421"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Raj Dabre","raw_affiliation_strings":["National Institute of Information and Communications Technology (NICT),Kyoto,Japan","National Institute of Information and Communications Technology (NICT), Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT),Kyoto,Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101151231","display_name":"Yi Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhao","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kawahara Tatsuya","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan","Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"876","last_page":"880"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9997000098228455,"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":0.9994000196456909,"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/mean-opinion-score","display_name":"Mean opinion score","score":0.7961006164550781},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7742176651954651},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5908331274986267},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5717189311981201},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5458295345306396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.541957437992096},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4766945540904999},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4607047140598297},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.45774123072624207},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44967132806777954},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43967217206954956},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42974135279655457},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09662643074989319}],"concepts":[{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.7961006164550781},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7742176651954651},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5908331274986267},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5717189311981201},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5458295345306396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.541957437992096},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4766945540904999},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4607047140598297},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.45774123072624207},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44967132806777954},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43967217206954956},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42974135279655457},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09662643074989319},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446041","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2295634712","https://openalex.org/W2590129515","https://openalex.org/W2745896134","https://openalex.org/W2747024632","https://openalex.org/W2936802426","https://openalex.org/W2963609956","https://openalex.org/W2967606780","https://openalex.org/W2972394484","https://openalex.org/W2972786657","https://openalex.org/W2973181078","https://openalex.org/W3097538987","https://openalex.org/W3098557217","https://openalex.org/W3147454823","https://openalex.org/W3181933907","https://openalex.org/W3196671011","https://openalex.org/W3196774886","https://openalex.org/W3197358873","https://openalex.org/W3197580070","https://openalex.org/W3197934651","https://openalex.org/W3198529186","https://openalex.org/W3202278141","https://openalex.org/W3207932315","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221138880","https://openalex.org/W4223503417","https://openalex.org/W4225956675","https://openalex.org/W4226264925","https://openalex.org/W4296068974","https://openalex.org/W6745609711","https://openalex.org/W6752515464","https://openalex.org/W6763832098","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6810007534","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2033549879","https://openalex.org/W2013629269","https://openalex.org/W2275036366","https://openalex.org/W3161558238","https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W3214791684","https://openalex.org/W2152662039","https://openalex.org/W2151415191","https://openalex.org/W2151664070"],"abstract_inverted_index":{"IEEE":[0],"Automatic":[1],"Mean":[2],"Opinion":[3],"Score":[4],"(MOS)":[5],"prediction":[6],"is":[7,46],"employed":[8],"to":[9,24,40,47],"evaluate":[10],"the":[11,19,25,48,89],"quality":[12],"of":[13,21,27,83],"synthetic":[14],"speech.":[15],"This":[16],"study":[17],"extends":[18],"application":[20],"predicted":[22],"MOS":[23,36,56,79,97],"task":[26],"Fake":[28],"Audio":[29],"Detection":[30],"(FAD)":[31],"as":[32,98],"we":[33,76],"expect":[34],"that":[35,78,95],"can":[37,57],"be":[38,58],"used":[39],"assess":[41],"how":[42],"close":[43],"synthesized":[44],"speech":[45],"natural":[49],"human":[50],"voice.":[51],"We":[52],"propose":[53],"MOS-FAD,":[54],"where":[55],"leveraged":[59],"at":[60],"two":[61],"key":[62],"points":[63],"in":[64,102],"FAD:":[65],"training":[66,73],"data":[67,74],"selection":[68],"and":[69],"model":[70,90,104],"fusion.":[71],"In":[72,88],"selection,":[75],"demonstrate":[77,94],"enables":[80],"effective":[81],"filtering":[82],"samples":[84],"from":[85],"unbalanced":[86],"datasets.":[87],"fusion,":[91],"our":[92],"results":[93],"incorporating":[96],"a":[99],"gating":[100],"mechanism":[101],"FAD":[103],"fusion":[105],"enhances":[106],"overall":[107],"performance.":[108]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
