{"id":"https://openalex.org/W4392904158","doi":"https://doi.org/10.1109/icassp48485.2024.10447253","title":"Maskmark: Robust Neuralwatermarking for Real and Synthetic Speech","display_name":"Maskmark: Robust Neuralwatermarking for Real and Synthetic Speech","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904158","doi":"https://doi.org/10.1109/icassp48485.2024.10447253"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447253","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5075935325","display_name":"Patrick O\u2019Reilly","orcid":"https://orcid.org/0000-0002-6205-2354"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick O\u2019Reilly","raw_affiliation_strings":["Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702050","display_name":"Zeyu Jin","orcid":"https://orcid.org/0000-0003-0161-5915"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Jin","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101859099","display_name":"Jiaqi Su","orcid":"https://orcid.org/0000-0001-6038-0808"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaqi Su","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102878078","display_name":"Bryan Pardo","orcid":"https://orcid.org/0000-0002-1427-6492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bryan Pardo","raw_affiliation_strings":["Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University","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":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4650","last_page":"4654"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9994999766349792,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9994000196456909,"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/spectrogram","display_name":"Spectrogram","score":0.8157405853271484},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8004404902458191},{"id":"https://openalex.org/keywords/digital-watermarking","display_name":"Digital watermarking","score":0.7985166907310486},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7617785930633545},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7047593593597412},{"id":"https://openalex.org/keywords/watermark","display_name":"Watermark","score":0.5057344436645508},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49695613980293274},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4904303252696991},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47764623165130615},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4305621087551117},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4236030876636505},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41767340898513794}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8157405853271484},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8004404902458191},{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.7985166907310486},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7617785930633545},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7047593593597412},{"id":"https://openalex.org/C164112704","wikidata":"https://www.wikidata.org/wiki/Q7974348","display_name":"Watermark","level":3,"score":0.5057344436645508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49695613980293274},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4904303252696991},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47764623165130615},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4305621087551117},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4236030876636505},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41767340898513794},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/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/icassp48485.2024.10447253","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":36,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2086381917","https://openalex.org/W2126270135","https://openalex.org/W2219249508","https://openalex.org/W2555915854","https://openalex.org/W2696967604","https://openalex.org/W2963964246","https://openalex.org/W2972541922","https://openalex.org/W3092028330","https://openalex.org/W3093964892","https://openalex.org/W3097777922","https://openalex.org/W3097945073","https://openalex.org/W3129651364","https://openalex.org/W3169905056","https://openalex.org/W3197912330","https://openalex.org/W4200083849","https://openalex.org/W4281736089","https://openalex.org/W4286899907","https://openalex.org/W4307323391","https://openalex.org/W4307977691","https://openalex.org/W4313306150","https://openalex.org/W4379251513","https://openalex.org/W4379259581","https://openalex.org/W4380551955","https://openalex.org/W4381198892","https://openalex.org/W4382202512","https://openalex.org/W6688816777","https://openalex.org/W6757107679","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6802838302","https://openalex.org/W6838843145","https://openalex.org/W6852629737","https://openalex.org/W6853165267","https://openalex.org/W6853515095"],"related_works":["https://openalex.org/W2511915070","https://openalex.org/W1550675871","https://openalex.org/W2137631325","https://openalex.org/W2496295964","https://openalex.org/W2357801821","https://openalex.org/W1976952689","https://openalex.org/W2121173104","https://openalex.org/W1753970369","https://openalex.org/W2336887028","https://openalex.org/W4360764600"],"abstract_inverted_index":{"High-quality":[0],"speech":[1,78,97,111],"synthesis":[2],"models":[3],"may":[4],"be":[5],"used":[6],"to":[7,33,89],"spread":[8],"misinformation":[9],"or":[10,84],"impersonate":[11],"voices.":[12],"Audio":[13],"watermarking":[14,55],"can":[15],"combat":[16],"misuse":[17],"by":[18],"embedding":[19],"a":[20,35,50,62,69,90,100],"traceable":[21],"signature":[22],"in":[23,66,108],"generated":[24],"audio.":[25,43],"However,":[26],"existing":[27],"audio":[28,54,67],"watermarks":[29],"typically":[30],"demonstrate":[31,104],"robustness":[32,107],"only":[34],"small":[36],"set":[37],"of":[38,40,76],"transformations":[39],"the":[41,74],"watermarked":[42,77,110],"To":[44],"address":[45],"this,":[46],"we":[47],"propose":[48],"MaskMark,":[49],"neural":[51,85],"network-based":[52,86],"digital":[53],"technique":[56],"optimized":[57],"for":[58],"speech.":[59],"MaskMark":[60],"embeds":[61],"secret":[63],"key":[64],"vector":[65],"via":[68],"multiplicative":[70],"spectrogram":[71],"mask,":[72],"allowing":[73],"detection":[75],"segments":[79],"even":[80],"under":[81],"substantial":[82],"signal-processing":[83],"transformations.":[87],"Comparisons":[88],"state-of-the-art":[91],"baseline":[92],"on":[93],"natural":[94],"and":[95,99],"synthetic":[96],"corpora":[98],"human":[101],"subjects":[102],"evaluation":[103],"MaskMark\u2019s":[105],"superior":[106],"detecting":[109],"while":[112],"maintaining":[113],"high":[114],"perceptual":[115],"transparency.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}