{"id":"https://openalex.org/W4392903636","doi":"https://doi.org/10.1109/icassp48485.2024.10446612","title":"Robust Spoof Speech Detection Based on Multi-Scale Feature Aggregation and Dynamic Convolution","display_name":"Robust Spoof Speech Detection Based on Multi-Scale Feature Aggregation and Dynamic Convolution","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903636","doi":"https://doi.org/10.1109/icassp48485.2024.10446612"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446612","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/A5101803910","display_name":"Haochen Wu","orcid":"https://orcid.org/0000-0001-5252-6707"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haochen Wu","raw_affiliation_strings":["University of Science and Technology of China,NERC-SLIP,Hefei,China","NERC-SLIP, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NERC-SLIP, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436848","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0003-1124-0854"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["University of Science and Technology of China,NERC-SLIP,Hefei,China","NERC-SLIP, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NERC-SLIP, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100655310","display_name":"Zhentao Zhang","orcid":"https://orcid.org/0009-0007-9178-0979"},"institutions":[{"id":"https://openalex.org/I73669364","display_name":"China Development Bank","ror":"https://ror.org/00pp12j94","country_code":"CN","type":"other","lineage":["https://openalex.org/I73669364"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhentao Zhang","raw_affiliation_strings":["China Merchants Bank,Shenzhen,China","China Merchants Bank, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"China Merchants Bank,Shenzhen,China","institution_ids":["https://openalex.org/I73669364"]},{"raw_affiliation_string":"China Merchants Bank, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107945458","display_name":"Wenting Zhao","orcid":"https://orcid.org/0000-0002-5769-6331"},"institutions":[{"id":"https://openalex.org/I73669364","display_name":"China Development Bank","ror":"https://ror.org/00pp12j94","country_code":"CN","type":"other","lineage":["https://openalex.org/I73669364"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenting Zhao","raw_affiliation_strings":["China Merchants Bank,Shenzhen,China","China Merchants Bank, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"China Merchants Bank,Shenzhen,China","institution_ids":["https://openalex.org/I73669364"]},{"raw_affiliation_string":"China Merchants Bank, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101875578","display_name":"Bin Gu","orcid":"https://orcid.org/0000-0003-1621-7311"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Gu","raw_affiliation_strings":["University of Science and Technology of China,NERC-SLIP,Hefei,China","NERC-SLIP, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NERC-SLIP, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038369085","display_name":"Wu Guo","orcid":"https://orcid.org/0000-0002-3779-7944"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Guo","raw_affiliation_strings":["University of Science and Technology of China,NERC-SLIP,Hefei,China","NERC-SLIP, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NERC-SLIP, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101803910"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":4.3108,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.9469891,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10156","last_page":"10160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9975000023841858,"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":0.9855999946594238,"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/computer-science","display_name":"Computer science","score":0.8667889833450317},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.8169838190078735},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6183288097381592},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6147375702857971},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5969563722610474},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5540852546691895},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.551690936088562},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5119465589523315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4716483950614929},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4534566104412079},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.44988706707954407},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4372550845146179},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.429006963968277},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10112285614013672},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08205893635749817}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8667889833450317},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.8169838190078735},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6183288097381592},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6147375702857971},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5969563722610474},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5540852546691895},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.551690936088562},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5119465589523315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4716483950614929},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4534566104412079},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.44988706707954407},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4372550845146179},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.429006963968277},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10112285614013672},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08205893635749817},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446612","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":[{"score":0.44999998807907104,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2121812409","https://openalex.org/W2152859600","https://openalex.org/W2219249508","https://openalex.org/W2471520273","https://openalex.org/W2696967604","https://openalex.org/W2752782242","https://openalex.org/W2799053639","https://openalex.org/W2963508548","https://openalex.org/W3036601975","https://openalex.org/W3128666957","https://openalex.org/W3131786367","https://openalex.org/W3161011913","https://openalex.org/W3163596559","https://openalex.org/W3186285959","https://openalex.org/W3198837656","https://openalex.org/W3199161700","https://openalex.org/W3200636257","https://openalex.org/W3206191467","https://openalex.org/W3207579445","https://openalex.org/W3211424380","https://openalex.org/W3212117663","https://openalex.org/W3213029956","https://openalex.org/W4206285316","https://openalex.org/W4221154746","https://openalex.org/W4225331914","https://openalex.org/W4225527248","https://openalex.org/W4226264925","https://openalex.org/W4306867196","https://openalex.org/W4319862221","https://openalex.org/W4372260253","https://openalex.org/W4375869011","https://openalex.org/W4375869126","https://openalex.org/W4381198892","https://openalex.org/W6631190155","https://openalex.org/W6688816777","https://openalex.org/W6754496211","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6852755086"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W1978893398","https://openalex.org/W2201908702","https://openalex.org/W3034421924","https://openalex.org/W2982536526","https://openalex.org/W4386858688","https://openalex.org/W4380302312","https://openalex.org/W3008689640","https://openalex.org/W4385338604","https://openalex.org/W3081626085"],"abstract_inverted_index":{"Spoof":[0],"speech":[1],"detection":[2],"(SSD)":[3],"can":[4],"help":[5],"to":[6,43,65,94],"protect":[7],"an":[8,40],"automatic":[9],"speaker":[10],"recognition":[11],"system":[12,42],"against":[13],"malicious":[14],"attacks.":[15,46,75],"However,":[16],"there":[17],"exists":[18],"a":[19,36],"great":[20],"diversity":[21],"in":[22,35,86],"the":[23,62,89,99,106,113,132,135],"spoof":[24],"utterances":[25],"generated":[26,104],"by":[27,105],"different":[28,67],"text-to-speech":[29],"and":[30,57,69,98,108,126],"voice":[31],"conversion":[32],"algorithms,":[33],"resulting":[34],"poor":[37],"generality":[38],"of":[39,72,112,134],"SSD":[41],"unseen":[44,73],"spoofing":[45,74],"To":[47],"address":[48],"this":[49],"problem,":[50],"we":[51],"integrate":[52],"multi-scale":[53,96],"feature":[54],"aggregation":[55],"(MFA)":[56],"dynamic":[58],"convolution":[59],"operations":[60],"into":[61],"anti-spoofing":[63],"framework":[64,78],"detect":[66],"local":[68,107],"global":[70,109],"artifacts":[71],"The":[76],"proposed":[77,136],"mainly":[79],"contains":[80],"eight":[81],"stacked":[82],"MFA":[83],"blocks,":[84],"where":[85],"each":[87],"block":[88],"light-Res2Net":[90],"module":[91],"is":[92,102],"used":[93],"capture":[95],"features":[97],"convolutional":[100],"kernel":[101],"dynamically":[103],"statistical":[110],"information":[111],"inputs.":[114],"Results":[115],"on":[116],"two":[117],"benchmark":[118],"datasets":[119],"(i.e.,":[120],"ADD":[121],"2023":[122],"Fake":[123],"Audio":[124],"Detection":[125],"ASVspoof":[127],"2021":[128],"Logical":[129],"Access)":[130],"show":[131],"superiority":[133],"method":[137],"over":[138],"existing":[139],"state-of-the-art":[140],"systems.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
