{"id":"https://openalex.org/W4404178880","doi":"https://doi.org/10.1109/taslp.2024.3486206","title":"Enhancing Robustness of Speech Watermarking Using a Transformer-Based Framework Exploiting Acoustic Features","display_name":"Enhancing Robustness of Speech Watermarking Using a Transformer-Based Framework Exploiting Acoustic Features","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404178880","doi":"https://doi.org/10.1109/taslp.2024.3486206"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3486206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3486206","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058551557","display_name":"Chuxuan Tong","orcid":"https://orcid.org/0000-0003-1800-1290"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Chuxuan Tong","raw_affiliation_strings":["School of Information Technology, Deakin University, Geelong, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University, Geelong, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004146766","display_name":"Iynkaran Natgunanathan","orcid":"https://orcid.org/0000-0003-4215-000X"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Iynkaran Natgunanathan","raw_affiliation_strings":["School of Information Technology, Deakin University, Geelong, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University, Geelong, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yong Xiang","orcid":"https://orcid.org/0000-0003-3545-7863"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yong Xiang","raw_affiliation_strings":["School of Information Technology, Deakin University, Geelong, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University, Geelong, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391345","display_name":"Jianhua Li","orcid":"https://orcid.org/0000-0001-5878-6032"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jianhua Li","raw_affiliation_strings":["School of Information Technology, Deakin University, Geelong, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University, Geelong, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009007482","display_name":"Tianrui Zong","orcid":"https://orcid.org/0000-0002-9925-2261"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tianrui Zong","raw_affiliation_strings":["School of Information Technology, Deakin University, Geelong, VIC, Australia","School of Information Technology, Deakin University, Geelong, Australia"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University, Geelong, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]},{"raw_affiliation_string":"School of Information Technology, Deakin University, Geelong, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081182489","display_name":"Xi Zheng","orcid":"https://orcid.org/0000-0002-2572-2355"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xi Zheng","raw_affiliation_strings":["Department of Computing, Macquarie University, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"Department of Computing, Macquarie University, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012293028","display_name":"Longxiang Gao","orcid":"https://orcid.org/0000-0002-3026-7537"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longxiang Gao","raw_affiliation_strings":["Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5058551557"],"corresponding_institution_ids":["https://openalex.org/I149704539"],"apc_list":null,"apc_paid":null,"fwci":1.9416,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.87794757,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"4822","last_page":"4837"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10388","display_name":"Advanced Steganography and Watermarking Techniques","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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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/digital-watermarking","display_name":"Digital watermarking","score":0.7873533964157104},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7548805475234985},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6266783475875854},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5829812288284302},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5681549310684204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31833261251449585},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1498231589794159},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07051056623458862},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.047692060470581055}],"concepts":[{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.7873533964157104},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7548805475234985},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6266783475875854},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5829812288284302},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5681549310684204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31833261251449585},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1498231589794159},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07051056623458862},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.047692060470581055},{"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},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2024.3486206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3486206","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:figshare.com:article/27798624","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/27798624","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G328715258","display_name":null,"funder_award_id":"2024QZJH02","funder_id":"https://openalex.org/F4320328720","funder_display_name":"Qilu University of Technology"},{"id":"https://openalex.org/G8851846645","display_name":null,"funder_award_id":"DP210102447","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320328720","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1580389772","https://openalex.org/W1901129140","https://openalex.org/W1981501272","https://openalex.org/W1983457661","https://openalex.org/W2011052242","https://openalex.org/W2035924602","https://openalex.org/W2059193620","https://openalex.org/W2084936871","https://openalex.org/W2112796928","https://openalex.org/W2119991698","https://openalex.org/W2145909217","https://openalex.org/W2339254090","https://openalex.org/W2560266880","https://openalex.org/W2607126301","https://openalex.org/W2625561724","https://openalex.org/W2753751342","https://openalex.org/W2758170342","https://openalex.org/W2883233582","https://openalex.org/W2888578066","https://openalex.org/W2893249048","https://openalex.org/W2926043533","https://openalex.org/W2970373593","https://openalex.org/W2997594966","https://openalex.org/W3035671550","https://openalex.org/W3035729089","https://openalex.org/W3089622076","https://openalex.org/W3132731116","https://openalex.org/W3153920232","https://openalex.org/W3176660455","https://openalex.org/W3185788529","https://openalex.org/W4200083849","https://openalex.org/W4312812783","https://openalex.org/W4376481109","https://openalex.org/W4382202512","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6691509046","https://openalex.org/W6746523225","https://openalex.org/W6758677337","https://openalex.org/W6768909792","https://openalex.org/W6781514399","https://openalex.org/W6785895317","https://openalex.org/W6799370634","https://openalex.org/W6802330313","https://openalex.org/W6840100749","https://openalex.org/W6855612533","https://openalex.org/W6910888796"],"related_works":["https://openalex.org/W2361629745","https://openalex.org/W2107922825","https://openalex.org/W2122982227","https://openalex.org/W2163290991","https://openalex.org/W2361184779","https://openalex.org/W3174961728","https://openalex.org/W2474386553","https://openalex.org/W2125329004","https://openalex.org/W2141752560","https://openalex.org/W4288057808"],"abstract_inverted_index":{"Digital":[0],"watermarking":[1,33],"serves":[2],"as":[3,57,99,130],"an":[4,176],"effective":[5],"approach":[6],"for":[7,133],"safeguarding":[8],"speech":[9,76],"signal":[10,22],"copyrights,":[11],"achieved":[12],"by":[13,103],"the":[14,20,28,42,71,117,138,142,148,168,173],"incorporation":[15],"of":[16,75,150,156,194],"ownership":[17],"information":[18],"into":[19],"original":[21],"and":[23,37,73,82,93,159,190],"its":[24],"subsequent":[25],"extraction":[26],"from":[27,96],"watermarked":[29,43],"signal.":[30],"While":[31],"traditional":[32],"methods":[34,52],"can":[35],"embed":[36,124],"extract":[38],"watermarks":[39],"successfully":[40],"when":[41],"signals":[44],"are":[45],"not":[46],"exposed":[47],"to":[48,69,89,122,167],"severe":[49],"alterations,":[50],"these":[51],"cannot":[53],"withstand":[54],"attacks":[55],"such":[56,98],"de-synchronization.":[58],"In":[59],"this":[60],"work,":[61],"we":[62],"introduce":[63],"a":[64,109,131],"novel":[65],"transformer-based":[66],"framework":[67,79,153,174],"designed":[68],"enhance":[70],"imperceptibility":[72,158],"robustness":[74,140,160],"watermarking.":[77],"This":[78],"incorporates":[80],"encoders":[81],"decoders":[83],"built":[84],"on":[85],"multi-scale":[86],"transformer":[87],"blocks":[88],"effectively":[90],"capture":[91],"local":[92],"long-range":[94],"features":[95,101],"inputs,":[97],"acoustic":[100],"extracted":[102],"Short-Time":[104],"Fourier":[105],"Transformation":[106],"(STFT).":[107],"Further,":[108,182],"deep":[110],"neural":[111],"networks":[112],"(DNNs)":[113],"based":[114],"generator,":[115],"notably":[116],"Transformer":[118],"architecture,":[119],"is":[120],"employed":[121],"adaptively":[123],"imperceptible":[125],"watermarks.":[126],"These":[127],"perturbations":[128],"serve":[129],"step":[132],"simulating":[134],"noise,":[135],"thereby":[136],"bolstering":[137],"watermark":[139,157,163],"during":[141],"training":[143],"phase.":[144],"Experimental":[145],"results":[146],"show":[147],"superiority":[149],"our":[151],"proposed":[152],"in":[154,179],"terms":[155],"against":[161],"various":[162],"attacks.":[164],"When":[165],"compared":[166],"currently":[169],"available":[170],"related":[171],"techniques,":[172],"exhibits":[175],"eightfold":[177],"increase":[178],"embedding":[180],"rate.":[181],"it":[183],"also":[184],"presents":[185],"superior":[186],"practicality":[187],"with":[188],"scalability":[189],"reduced":[191],"inference":[192],"time":[193],"DNN":[195],"models.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}