{"id":"https://openalex.org/W4405709412","doi":"https://doi.org/10.1109/iscslp63861.2024.10799995","title":"EnvFake: An Initial Environmental-Fake Audio Dataset for Scene-Consistency Detection","display_name":"EnvFake: An Initial Environmental-Fake Audio Dataset for Scene-Consistency Detection","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709412","doi":"https://doi.org/10.1109/iscslp63861.2024.10799995"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10799995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10799995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th 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/A5041608153","display_name":"Harvey Cheng","orcid":"https://orcid.org/0009-0003-1966-5889"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]},{"id":"https://openalex.org/I4391768176","display_name":"State Key Laboratory of Media Convergence and Communication","ror":"https://ror.org/0595ys057","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391768176","https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hannan Cheng","raw_affiliation_strings":["Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing"],"affiliations":[{"raw_affiliation_string":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing","institution_ids":["https://openalex.org/I75689368","https://openalex.org/I4391768176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107947965","display_name":"Ke Li","orcid":"https://orcid.org/0009-0000-1697-3323"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]},{"id":"https://openalex.org/I4391768176","display_name":"State Key Laboratory of Media Convergence and Communication","ror":"https://ror.org/0595ys057","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391768176","https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kangyue Li","raw_affiliation_strings":["Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing"],"affiliations":[{"raw_affiliation_string":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing","institution_ids":["https://openalex.org/I75689368","https://openalex.org/I4391768176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100600271","display_name":"Long Ye","orcid":"https://orcid.org/0000-0002-3562-5612"},"institutions":[{"id":"https://openalex.org/I4391768176","display_name":"State Key Laboratory of Media Convergence and Communication","ror":"https://ror.org/0595ys057","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391768176","https://openalex.org/I75689368"]},{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Ye","raw_affiliation_strings":["Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing"],"affiliations":[{"raw_affiliation_string":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing","institution_ids":["https://openalex.org/I75689368","https://openalex.org/I4391768176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045675134","display_name":"Jingling Wang","orcid":"https://orcid.org/0009-0002-4239-4530"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]},{"id":"https://openalex.org/I4391768176","display_name":"State Key Laboratory of Media Convergence and Communication","ror":"https://ror.org/0595ys057","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391768176","https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingling Wang","raw_affiliation_strings":["Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing"],"affiliations":[{"raw_affiliation_string":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing","institution_ids":["https://openalex.org/I75689368","https://openalex.org/I4391768176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5041608153"],"corresponding_institution_ids":["https://openalex.org/I4391768176","https://openalex.org/I75689368"],"apc_list":null,"apc_paid":null,"fwci":0.7501,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72812935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9968000054359436,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9968000054359436,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9503999948501587,"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/computer-science","display_name":"Computer science","score":0.685919463634491},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6616803407669067},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37291860580444336},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35095906257629395}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.685919463634491},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6616803407669067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37291860580444336},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35095906257629395}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10799995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10799995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/13"}],"awards":[{"id":"https://openalex.org/G1688272981","display_name":null,"funder_award_id":"CUC24SG011","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3139283728","display_name":null,"funder_award_id":"62201524","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2360958417","https://openalex.org/W2937949426","https://openalex.org/W3093604190","https://openalex.org/W3097073051","https://openalex.org/W3160085755","https://openalex.org/W3163596559","https://openalex.org/W3207579445","https://openalex.org/W4245919820","https://openalex.org/W4296069136","https://openalex.org/W4297841787","https://openalex.org/W4376877074","https://openalex.org/W4385807442","https://openalex.org/W4385822347","https://openalex.org/W4390872369","https://openalex.org/W4391488862","https://openalex.org/W4394019163","https://openalex.org/W6757210188","https://openalex.org/W6780218876","https://openalex.org/W6804030475","https://openalex.org/W6808573671"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0,71],"virtual":[1],"reality":[2],"scenarios,":[3],"audio":[4,25,37],"realism":[5,34],"plays":[6],"a":[7,87,114,134],"crucial":[8],"role":[9],"in":[10,121],"enhancing":[11],"the":[12,22,33,36,45,49,76,95,101,108],"user's":[13],"immersive":[14],"experience.":[15],"Recently,":[16],"many":[17],"studies":[18,29],"have":[19],"focused":[20],"on":[21,32],"determination":[23],"of":[24,35,48,68,79,104,137],"authenticity.":[26],"However,":[27],"existing":[28],"mainly":[30],"focus":[31],"itself,":[38],"e.g.,":[39],"automatic":[40],"speaker":[41],"verification,":[42],"while":[43],"ignoring":[44],"authenticity":[46],"detection":[47,84,131],"audio's":[50],"background":[51,54],"information.":[52],"This":[53],"information":[55],"usually":[56],"contains":[57],"ambient,":[58],"reverberant,":[59],"and":[60,81,110,118],"reflective":[61],"sounds,":[62],"which":[63],"can":[64],"provide":[65],"rich":[66],"cues":[67],"scene-consistency":[69,83],"detection.":[70],"this":[72,122],"paper,":[73],"we":[74],"address":[75],"under-explored":[77],"task":[78],"acoustic":[80,102,138],"visual":[82,111],"by":[85],"introducing":[86],"new":[88],"Environmental":[89],"Fake":[90],"Dataset":[91],"named":[92],"EnvFake":[93,98],"for":[94,116],"first":[96],"step.":[97],"uniquely":[99],"alters":[100],"scenes":[103],"recordings":[105],"without":[106],"changing":[107],"linguistic":[109],"content,":[112],"providing":[113],"benchmark":[115],"training":[117],"evaluating":[119],"models":[120],"field.":[123],"Our":[124],"work":[125],"shifts":[126],"from":[127],"traditional":[128],"speech-centric":[129],"forgery":[130],"to":[132],"encompassing":[133],"broader":[135],"range":[136],"scenes.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}