{"id":"https://openalex.org/W4408353460","doi":"https://doi.org/10.1109/icassp49660.2025.10889782","title":"Latent Watermarking of Audio Generative Models","display_name":"Latent Watermarking of Audio Generative Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353460","doi":"https://doi.org/10.1109/icassp49660.2025.10889782"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5108994797","display_name":"Robin San Roman","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Robin San Roman","raw_affiliation_strings":["Meta, FAIR, Univ. de Lorraine, CNRS, Inria, Loria"],"affiliations":[{"raw_affiliation_string":"Meta, FAIR, Univ. de Lorraine, CNRS, Inria, Loria","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210121838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088495817","display_name":"Pierre Fernandez","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pierre Fernandez","raw_affiliation_strings":["Meta, FAIR, Inria Rennes"],"affiliations":[{"raw_affiliation_string":"Meta, FAIR, Inria Rennes","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000981106","display_name":"Antoine Deleforge","orcid":"https://orcid.org/0000-0003-0339-7472"},"institutions":[{"id":"https://openalex.org/I180801515","display_name":"Institute of Rural Management Anand","ror":"https://ror.org/03e096643","country_code":"IN","type":"education","lineage":["https://openalex.org/I180801515"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Antoine Deleforge","raw_affiliation_strings":["IRMA, CNRS, Univ. de Strasbourg, Inria"],"affiliations":[{"raw_affiliation_string":"IRMA, CNRS, Univ. de Strasbourg, Inria","institution_ids":["https://openalex.org/I180801515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005191803","display_name":"Yossi Adi","orcid":"https://orcid.org/0000-0003-2237-3898"},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yossi Adi","raw_affiliation_strings":["Meta, FAIR, Hebrew Univ. of Jerusalem"],"affiliations":[{"raw_affiliation_string":"Meta, FAIR, Hebrew Univ. of Jerusalem","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"last","author":{"id":null,"display_name":"Romain Serizel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Romain Serizel","raw_affiliation_strings":["Univ. de Lorraine, CNRS, Inria, Loria"],"affiliations":[{"raw_affiliation_string":"Univ. de Lorraine, CNRS, Inria, Loria","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5108994797"],"corresponding_institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210121838"],"apc_list":null,"apc_paid":null,"fwci":3.5483,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.9193099,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9905999898910522,"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/digital-watermarking","display_name":"Digital watermarking","score":0.8024417161941528},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7310491800308228},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5377516746520996},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4618346691131592},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41033026576042175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38897204399108887},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0908498764038086}],"concepts":[{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.8024417161941528},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7310491800308228},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5377516746520996},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4618346691131592},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41033026576042175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38897204399108887},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0908498764038086}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":40,"referenced_works":["https://openalex.org/W2041007040","https://openalex.org/W2126726788","https://openalex.org/W3143336910","https://openalex.org/W3198217962","https://openalex.org/W3215615641","https://openalex.org/W4200083849","https://openalex.org/W4307323391","https://openalex.org/W4312933868","https://openalex.org/W4381786045","https://openalex.org/W4382202512","https://openalex.org/W4385245566","https://openalex.org/W4389600306","https://openalex.org/W4390872921","https://openalex.org/W4392903621","https://openalex.org/W4392904158","https://openalex.org/W4402816547","https://openalex.org/W6757220786","https://openalex.org/W6767111847","https://openalex.org/W6778883912","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6787203647","https://openalex.org/W6845479124","https://openalex.org/W6848735303","https://openalex.org/W6849105126","https://openalex.org/W6849109464","https://openalex.org/W6850572961","https://openalex.org/W6851724922","https://openalex.org/W6853096648","https://openalex.org/W6853515095","https://openalex.org/W6853888607","https://openalex.org/W6854866820","https://openalex.org/W6855313532","https://openalex.org/W6855612533","https://openalex.org/W6859472238","https://openalex.org/W6859583170","https://openalex.org/W6861353174","https://openalex.org/W6861666878","https://openalex.org/W6869165705","https://openalex.org/W6910888796"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4391584540","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559"],"abstract_inverted_index":{"The":[0,59],"advancements":[1],"in":[2,11],"audio":[3,89,110],"generative":[4,90],"models":[5,91],"have":[6,26],"opened":[7],"up":[8],"new":[9],"challenges":[10],"their":[12,19,95],"responsible":[13],"disclosure":[14],"and":[15],"the":[16,31,46,54,100,119,137,146,150,154,158,162,165],"detection":[17,32,124,147],"of":[18,33,62,109,152,160],"misuse.":[20],"To":[21],"address":[22],"this,":[23],"watermarking":[24,94],"techniques":[25,42],"been":[27],"recently":[28],"developed,":[29],"enabling":[30],"content":[34],"generated":[35],"by":[36,92],"a":[37,84,106],"deployed":[38],"model.":[39],"For":[40],"such":[41],"to":[43,53,102,117],"be":[44,77,103],"useful,":[45],"watermark":[47],"must":[48],"resist":[49],"typical":[50],"modifications":[51],"applied":[52],"model":[55,65,138,163],"or":[56,115],"its":[57],"outputs.":[58],"use":[60],"case":[61],"an":[63],"open-source":[64],"trained":[66],"on":[67,139],"proprietary":[68],"data":[69],"is":[70],"challenging,":[71],"as":[72],"post-hoc":[73],"watermarks":[74,87],"can":[75,142],"then":[76],"trivially":[78],"removed.":[79],"In":[80],"response,":[81],"we":[82,132],"introduce":[83],"method":[85,101],"that":[86,134],"latent":[88],"directly":[93],"training":[96,167],"data.":[97,168],"We":[98],"show":[99,133],"robust":[104],"against":[105],"broad":[107],"range":[108],"edits":[111],"including":[112],"filtering,":[113],"compression":[114],"even":[116,135],"changing":[118],"model\u2019s":[120],"decoder,":[121],"maintaining":[122],"high":[123],"rates":[125],"with":[126],"very":[127],"few":[128],"false":[129],"positives.":[130],"Interestingly,":[131],"fine-tuning":[136],"another":[140],"dataset":[141],"only":[143],"significantly":[144],"lower":[145],"rate":[148],"at":[149],"cost":[151],"degrading":[153],"generation":[155],"performance":[156],"near":[157],"level":[159],"re-training":[161],"without":[164],"protected":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}