{"id":"https://openalex.org/W4319780207","doi":"https://doi.org/10.1109/iscslp57327.2022.10037999","title":"Synthetic Voice Detection and Audio Splicing Detection using SE-Res2Net-Conformer Architecture","display_name":"Synthetic Voice Detection and Audio Splicing Detection using SE-Res2Net-Conformer Architecture","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319780207","doi":"https://doi.org/10.1109/iscslp57327.2022.10037999"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10037999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10037999","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5107094040","display_name":"Lei Wang","orcid":"https://orcid.org/0000-0001-8085-2374"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Wang","raw_affiliation_strings":["KLASS Engineering and Solutions Pte Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KLASS Engineering and Solutions Pte Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063147759","display_name":"Benedict Yeoh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benedict Yeoh","raw_affiliation_strings":["KLASS Engineering and Solutions Pte Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KLASS Engineering and Solutions Pte Ltd","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059611340","display_name":"Jun Wah Ng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Wah Ng","raw_affiliation_strings":["KLASS Engineering and Solutions Pte Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KLASS Engineering and Solutions Pte Ltd","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7267,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.72547045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"115","last_page":"119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.7904738187789917},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.6171674728393555},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5910786390304565},{"id":"https://openalex.org/keywords/authentication","display_name":"Authentication (law)","score":0.48575547337532043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47234880924224854},{"id":"https://openalex.org/keywords/rna-splicing","display_name":"RNA splicing","score":0.4721522331237793},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4499458372592926},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4432525634765625},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4239833950996399},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33875057101249695},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.13989272713661194},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.11257094144821167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7904738187789917},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.6171674728393555},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5910786390304565},{"id":"https://openalex.org/C148417208","wikidata":"https://www.wikidata.org/wiki/Q4825882","display_name":"Authentication (law)","level":2,"score":0.48575547337532043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47234880924224854},{"id":"https://openalex.org/C54458228","wikidata":"https://www.wikidata.org/wiki/Q237218","display_name":"RNA splicing","level":4,"score":0.4721522331237793},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4499458372592926},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4432525634765625},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4239833950996399},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33875057101249695},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.13989272713661194},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11257094144821167},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C67705224","wikidata":"https://www.wikidata.org/wiki/Q11053","display_name":"RNA","level":3,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10037999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10037999","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":30,"referenced_works":["https://openalex.org/W1749306293","https://openalex.org/W2144168752","https://openalex.org/W2146675392","https://openalex.org/W2590129515","https://openalex.org/W2708787837","https://openalex.org/W2912458406","https://openalex.org/W2928165649","https://openalex.org/W2972594541","https://openalex.org/W2972811785","https://openalex.org/W2972818416","https://openalex.org/W2973181078","https://openalex.org/W3007328579","https://openalex.org/W3016010032","https://openalex.org/W3024920698","https://openalex.org/W3041816239","https://openalex.org/W3093010840","https://openalex.org/W3093077017","https://openalex.org/W3097073051","https://openalex.org/W3097777922","https://openalex.org/W3098557217","https://openalex.org/W3100448777","https://openalex.org/W3128666957","https://openalex.org/W3131786367","https://openalex.org/W3161011913","https://openalex.org/W3174758275","https://openalex.org/W3197134965","https://openalex.org/W3206655605","https://openalex.org/W4214909824","https://openalex.org/W4241247459","https://openalex.org/W6796730497"],"related_works":["https://openalex.org/W2998478967","https://openalex.org/W2188559950","https://openalex.org/W2989910292","https://openalex.org/W3128793638","https://openalex.org/W2607818178","https://openalex.org/W2123299109","https://openalex.org/W2021230337","https://openalex.org/W4387799680","https://openalex.org/W4308237908","https://openalex.org/W2358945663"],"abstract_inverted_index":{"Synthetic":[0],"voice":[1,20],"and":[2,13],"splicing":[3,93,101],"audio":[4,92],"clips":[5],"have":[6],"been":[7],"generated":[8],"to":[9,48,71,88,107,123],"spoof":[10],"Intemet":[11],"users":[12],"artificial":[14],"intelligence":[15],"(AI)":[16],"technologies":[17],"such":[18],"as":[19,28],"authentication.":[21],"Existing":[22],"research":[23],"work":[24],"treats":[25],"spoofing":[26,74],"countermeasures":[27,75],"a":[29,116],"binary":[30],"classification":[31],"problem:":[32],"bonafide":[33],"vs.":[34],"spoof.":[35],"This":[36],"paper":[37,85],"extends":[38],"the":[39,44,51,65,73,78,90,99,109,112,125,131],"existing":[40,91],"Res2Net":[41],"by":[42],"involving":[43],"recent":[45],"Conformer":[46],"block":[47],"further":[49],"exploit":[50],"local":[52],"patterns":[53],"on":[54,59],"acoustic":[55],"features.":[56],"Experimental":[57],"results":[58],"ASVspoof":[60],"2019":[61],"database":[62],"show":[63],"that":[64],"proposed":[66],"SE-Res2Net-Conformer":[67],"architecture":[68],"is":[69,104,128],"able":[70],"improve":[72],"performance":[76],"for":[77],"logical":[79],"access":[80],"scenario.":[81],"In":[82],"addition,":[83],"this":[84],"also":[86],"proposes":[87],"re-formulate":[89],"detection":[94],"problem.":[95],"Instead":[96],"of":[97,111],"identifying":[98],"complete":[100],"segments,":[102],"it":[103],"more":[105],"useful":[106],"detect":[108],"boundaries":[110],"spliced":[113],"segments.":[114],"Moreover,":[115],"deep":[117],"learning":[118],"approach":[119],"can":[120],"be":[121],"used":[122],"solve":[124],"problem,":[126],"which":[127],"different":[129],"from":[130],"previous":[132],"signal":[133],"processing":[134],"techniques.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}