{"id":"https://openalex.org/W4224256913","doi":"https://doi.org/10.1109/icassp43922.2022.9746820","title":"Audio Deepfake Detection System with Neural Stitching for ADD 2022","display_name":"Audio Deepfake Detection System with Neural Stitching for ADD 2022","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224256913","doi":"https://doi.org/10.1109/icassp43922.2022.9746820"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746820","doi":"https://doi.org/10.1109/icassp43922.2022.9746820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746820","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W4224256913"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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/A5090814066","display_name":"Rui Yan","orcid":"https://orcid.org/0009-0008-7280-1612","observed_orcids":["https://orcid.org/0009-0008-7280-1612"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Yan","raw_affiliation_strings":["Beike, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beike, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100344183","display_name":"Wen Ming Cheng","orcid":"https://orcid.org/0000-0002-9063-1177","observed_orcids":["https://orcid.org/0000-0002-9063-1177"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng Wen","raw_affiliation_strings":["Beike, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beike, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043550392","display_name":"Shuran Zhou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuran Zhou","raw_affiliation_strings":["Beike, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beike, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tingwei Guo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tingwei Guo","raw_affiliation_strings":["Beike, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beike, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090002307","display_name":"Wei Zou","orcid":"https://orcid.org/0000-0001-5307-4685","observed_orcids":["https://orcid.org/0000-0001-5307-4685"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Zou","raw_affiliation_strings":["Beike, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beike, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081173423","display_name":"Xiangang Li","orcid":"https://orcid.org/0000-0002-7810-1077","observed_orcids":["https://orcid.org/0000-0002-7810-1077"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangang Li","raw_affiliation_strings":["Beike, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beike, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7239,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.92664168,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9226","last_page":"9230"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9854000210762024,"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":0.9854000210762024,"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":0.005900000222027302,"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":0.00430000014603138,"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/audio-deepfake-detection","display_name":"audio deepfake detection","score":0.9869999885559082},{"id":"https://openalex.org/keywords/spoofing-detection","display_name":"anti-spoofing","score":0.7509999871253967},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.6430000066757202},{"id":"https://openalex.org/keywords/voice-conversion","display_name":"voice conversion","score":0.9890000224113464},{"id":"https://openalex.org/keywords/resnet","display_name":"ResNet","score":0.6769999861717224},{"id":"https://openalex.org/keywords/discriminative-embedding","display_name":"discriminative embedding","score":0.6019999980926514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.863669216632843},{"id":"https://openalex.org/C29081049","wikidata":"https://www.wikidata.org/wiki/Q1364242","display_name":"Image stitching","level":2,"score":0.8444346189498901},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6701617240905762},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.6305021047592163},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5753177404403687},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5494191646575928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5188073515892029},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.517238199710846},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4940236210823059},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.43820804357528687},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3247325122356415},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746820","doi":"https://doi.org/10.1109/icassp43922.2022.9746820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746820","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1849277567","https://openalex.org/W1912570122","https://openalex.org/W2088399049","https://openalex.org/W2219249508","https://openalex.org/W2295634712","https://openalex.org/W2794506738","https://openalex.org/W2807627734","https://openalex.org/W2936774411","https://openalex.org/W2936802426","https://openalex.org/W2949526695","https://openalex.org/W2963077989","https://openalex.org/W2963351448","https://openalex.org/W2964350391","https://openalex.org/W2969937244","https://openalex.org/W2998508940","https://openalex.org/W3015197287","https://openalex.org/W3024920698","https://openalex.org/W3033411150","https://openalex.org/W3098403858","https://openalex.org/W3162427973","https://openalex.org/W3198129070","https://openalex.org/W4221138880","https://openalex.org/W4313984387","https://openalex.org/W6688816777","https://openalex.org/W6778823374"],"related_works":["https://openalex.org/W4221138880","https://openalex.org/W4226264925","https://openalex.org/W4224932929","https://openalex.org/W4385823361","https://openalex.org/W4391827480","https://openalex.org/W4298397801","https://openalex.org/W4298636010","https://openalex.org/W7204153744","https://openalex.org/W4392910532","https://openalex.org/W4392903644"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3,73,133],"best":[4],"system":[5,21],"and":[6,96,119],"methodology":[7],"for":[8,24,93],"ADD":[9],"2022:":[10],"The":[11,18,37,129],"First":[12],"Audio":[13],"Deep":[14],"Synthesis":[15],"Detection":[16],"Challenge[1].":[17],"very":[19],"same":[20],"was":[22],"used":[23],"both":[25],"two":[26],"rounds":[27],"of":[28,40,57,60],"evaluation":[29],"in":[30,67,110,116,125,145],"Track":[31,41,68,146],"3.2":[32,42],"with":[33,83,140],"similar":[34],"training":[35],"methodology.":[36],"first":[38],"round":[39,56],"data":[43,58],"is":[44],"generated":[45,61],"from":[46,64],"Text-to-Speech(TTS)":[47],"or":[48],"voice":[49],"conversion":[50],"(VC)":[51],"algorithms,":[52],"while":[53],"the":[54,90,106,126],"second":[55],"consists":[59],"fake":[62,94],"audio":[63,95],"other":[65,138],"participants":[66],"3.1,":[69],"aming":[70],"to":[71,88,104,112],"spoof":[72,97],"systems.":[74],"Our":[75],"systems":[76,139],"uses":[77],"a":[78],"standard":[79],"34-layer":[80],"ResNet":[81],"[2],":[82],"multi-head":[84],"attention":[85],"pooling":[86],"[3]":[87],"learn":[89],"discriminative":[91],"embedding":[92],"detection.":[98],"We":[99],"further":[100],"utilize":[101],"neural":[102],"stitching":[103],"boost":[105],"model\u2019s":[107],"generalization":[108],"capability":[109],"order":[111],"perform":[113],"equally":[114],"well":[115],"different":[117],"tasks,":[118],"more":[120],"details":[121],"will":[122],"be":[123],"explained":[124],"following":[127],"sessions.":[128],"experiments":[130],"show":[131],"that":[132],"proposed":[134],"method":[135],"outperforms":[136],"all":[137],"10.1%":[141],"equal":[142],"error":[143],"rate(EER)":[144],"3.2.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2022-04-26T00:00:00"}