{"id":"https://openalex.org/W4406461290","doi":"https://doi.org/10.1109/slt61566.2024.10832200","title":"Detecting the Undetectable: Assessing the Efficacy of Current Spoof Detection Methods Against Seamless Speech Edits","display_name":"Detecting the Undetectable: Assessing the Efficacy of Current Spoof Detection Methods Against Seamless Speech Edits","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461290","doi":"https://doi.org/10.1109/slt61566.2024.10832200"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5071504898","display_name":"Sung-Feng Huang","orcid":"https://orcid.org/0000-0002-9720-811X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sung-Feng Huang","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110059320","display_name":"Heng-Cheng Kuo","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Heng-Cheng Kuo","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002433660","display_name":"Zhehuai Chen","orcid":"https://orcid.org/0000-0003-4400-5340"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhehuai Chen","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035431928","display_name":"Xuesong Yang","orcid":"https://orcid.org/0000-0003-1798-4715"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuesong Yang","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020376803","display_name":"Chao-Han Huck Yang","orcid":"https://orcid.org/0000-0003-2879-8811"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao-Han Huck Yang","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Acedemia Sinica"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Acedemia Sinica","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090045508","display_name":"Yu-Chiang Frank Wang","orcid":"https://orcid.org/0000-0002-2333-157X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu-Chiang Frank Wang","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071471469","display_name":"Szu\u2010Wei Fu","orcid":"https://orcid.org/0000-0002-3487-8212"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Szu-Wei Fu","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"652","last_page":"659"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9957000017166138,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9851999878883362,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7367382645606995},{"id":"https://openalex.org/keywords/current","display_name":"Current (fluid)","score":0.6053106784820557},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41889888048171997},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12206807732582092},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1085730493068695}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7367382645606995},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.6053106784820557},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41889888048171997},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12206807732582092},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1085730493068695}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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":38,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1647671624","https://openalex.org/W2219249508","https://openalex.org/W2588445447","https://openalex.org/W2745896134","https://openalex.org/W2747874407","https://openalex.org/W2885800352","https://openalex.org/W2936802426","https://openalex.org/W2967606780","https://openalex.org/W2995181338","https://openalex.org/W3036601975","https://openalex.org/W3095259706","https://openalex.org/W3196774886","https://openalex.org/W3197358873","https://openalex.org/W3197457172","https://openalex.org/W3198533616","https://openalex.org/W4221138880","https://openalex.org/W4224920249","https://openalex.org/W4224932929","https://openalex.org/W4288056111","https://openalex.org/W4313306150","https://openalex.org/W4375869244","https://openalex.org/W4377864733","https://openalex.org/W4386302282","https://openalex.org/W4387994989","https://openalex.org/W4389328740","https://openalex.org/W4392903704","https://openalex.org/W4402672020","https://openalex.org/W6636915900","https://openalex.org/W6688816777","https://openalex.org/W6780218876","https://openalex.org/W6841260490","https://openalex.org/W6852755086","https://openalex.org/W6853075663","https://openalex.org/W6853165267","https://openalex.org/W6853696097","https://openalex.org/W6853888607","https://openalex.org/W6855853421"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Neural":[0],"speech":[1,16,76],"editing":[2],"advancements":[3],"have":[4],"raised":[5],"concerns":[6],"about":[7],"their":[8],"misuse":[9],"in":[10,104],"spoofing":[11,47],"attacks.":[12],"Traditional":[13],"partially":[14],"edited":[15,77],"corpora":[17],"primarily":[18],"focus":[19],"on":[20],"cut-and-paste":[21,89],"edits,":[22],"which,":[23],"while":[24],"maintaining":[25],"speaker":[26],"consistency,":[27],"often":[28],"introduce":[29,51],"detectable":[30],"discontinuities.":[31],"Recent":[32],"methods,":[33],"like":[34],"$\\mathrm{A}^{3}":[35],"\\mathrm{~T}$":[36],"and":[37,69,107,115],"Voicebox,":[38],"improve":[39],"transitions":[40],"by":[41],"leveraging":[42],"contextual":[43],"information.":[44],"To":[45],"foster":[46],"detection":[48],"research,":[49],"we":[50],"the":[52,63],"Speech":[53],"INfilling":[54],"Edit":[55],"(SINE)":[56],"dataset,":[57],"created":[58],"with":[59],"Voicebox.":[60],"We":[61],"detailed":[62],"process":[64],"of":[65],"re-implementing":[66],"Voicebox":[67],"training":[68],"dataset":[70,114],"creation.":[71],"Subjective":[72],"evaluations":[73],"confirm":[74],"that":[75,97],"using":[78],"this":[79],"novel":[80],"technique":[81],"is":[82],"more":[83],"challenging":[84],"to":[85],"detect":[86],"than":[87],"conventional":[88],"methods.":[90,112],"Despite":[91],"human":[92],"difficulty,":[93],"experimental":[94],"results":[95],"demonstrate":[96],"self-supervised-based":[98],"detectors":[99],"can":[100],"achieve":[101],"remarkable":[102],"performance":[103],"detection,":[105],"localization,":[106],"generalization":[108],"across":[109],"different":[110],"edit":[111],"The":[113],"related":[116],"models":[117],"will":[118],"be":[119],"made":[120],"available":[121],"at:":[122],"https://jasonswfu.github.io/SINE_dataset/index.html":[123]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}