{"id":"https://openalex.org/W4412099897","doi":"https://doi.org/10.1145/3725949.3725971","title":"Leveraging Neural Vocoder Artifacts for Improved Synthetic Speech Detection","display_name":"Leveraging Neural Vocoder Artifacts for Improved Synthetic Speech Detection","publication_year":2024,"publication_date":"2024-11-22","ids":{"openalex":"https://openalex.org/W4412099897","doi":"https://doi.org/10.1145/3725949.3725971"},"language":"en","primary_location":{"id":"doi:10.1145/3725949.3725971","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725949.3725971","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725949.3725971","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Sensors, Signal and Image Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3725949.3725971","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113893556","display_name":"Jing-Bo Xue","orcid":"https://orcid.org/0009-0004-4430-2542"},"institutions":[{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Jingxi Xue","raw_affiliation_strings":["City University of Macau, Macau, China"],"raw_orcid":"https://orcid.org/0009-0004-4430-2542","affiliations":[{"raw_affiliation_string":"City University of Macau, Macau, China","institution_ids":["https://openalex.org/I6469544"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015462564","display_name":"Sanshuai Cui","orcid":"https://orcid.org/0000-0002-4709-5786"},"institutions":[{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Sanshuai Cui","raw_affiliation_strings":["City University of Macau, Macau, China"],"raw_orcid":"https://orcid.org/0000-0002-4709-5786","affiliations":[{"raw_affiliation_string":"City University of Macau, Macau, China","institution_ids":["https://openalex.org/I6469544"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002911824","display_name":"W. Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Weinan Zhang","raw_affiliation_strings":["City University of Macau, Macau, China"],"raw_orcid":"https://orcid.org/0009-0002-9132-4272","affiliations":[{"raw_affiliation_string":"City University of Macau, Macau, China","institution_ids":["https://openalex.org/I6469544"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I6469544"],"apc_list":null,"apc_paid":null,"fwci":0.5972,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76281031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"162","last_page":"166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9965999722480774,"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":0.7547326683998108},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6836193799972534},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42795953154563904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4134420156478882}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7547326683998108},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6836193799972534},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42795953154563904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4134420156478882}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3725949.3725971","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725949.3725971","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725949.3725971","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Sensors, Signal and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3725949.3725971","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725949.3725971","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725949.3725971","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Sensors, Signal and Image Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412099897.pdf","grobid_xml":"https://content.openalex.org/works/W4412099897.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1984685202","https://openalex.org/W2194775991","https://openalex.org/W2295634712","https://openalex.org/W2752782242","https://openalex.org/W2936802426","https://openalex.org/W2967606780","https://openalex.org/W2972369255","https://openalex.org/W2972811785","https://openalex.org/W2972909277","https://openalex.org/W3163596559","https://openalex.org/W3170179936","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4245692952","https://openalex.org/W4285149944","https://openalex.org/W4323022270","https://openalex.org/W4375869126","https://openalex.org/W4385800847","https://openalex.org/W4392903636"],"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":{"With":[0],"the":[1,17,41,56,62,69,82,90,100,113,120,126],"advancement":[2],"of":[3,19,84,110,134],"deep":[4],"learning,":[5],"speech":[6,20,27,47,86],"synthesis":[7],"technology":[8],"has":[9],"improved":[10],"significantly,":[11],"but":[12],"this":[13,22,105],"progress":[14],"also":[15],"increases":[16],"risk":[18],"forgery.In":[21],"paper,":[23],"we":[24,88],"enhance":[25,74],"synthetic":[26,46,85],"detection":[28],"by":[29,48,52],"fully":[30],"leveraging":[31],"neural":[32,53],"vocoder":[33],"artifacts":[34,50],"and":[35,61,73,117,136],"improving":[36],"feature":[37,71],"representation.Our":[38],"approach":[39],"enhances":[40],"model's":[42,70],"ability":[43],"to":[44,67,77,97,125],"detect":[45],"identifying":[49],"produced":[51],"vocoder.We":[54],"introduce":[55],"Enhanced":[57],"Feature":[58],"Extraction":[59],"Module":[60,66],"Dynamic":[63],"Layer":[64],"Attention":[65],"improve":[68],"representation":[72],"its":[75],"sensitivity":[76],"artifact":[78],"features,":[79],"significantly":[80],"boosting":[81],"performance":[83],"detection.Additionally,":[87],"apply":[89],"exponential":[91],"moving":[92],"average":[93],"(EMA)":[94],"during":[95],"training":[96],"further":[98],"stabilize":[99],"model.Our":[101],"experiments":[102],"show":[103],"that":[104],"method":[106],"achieves":[107],"an":[108],"EER":[109],"0.03%":[111],"on":[112,119],"public":[114],"datasets":[115],"LibriSeVoc":[116],"3.10%":[118],"ASVspoof":[121],"2019":[122],"LA":[123],"task.Compared":[124],"LFCC-LCNN":[127],"baseline,":[128],"these":[129],"results":[130],"represent":[131],"relative":[132],"reductions":[133],"78.6%":[135],"73.3%,":[137],"respectively.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}