{"id":"https://openalex.org/W7148437532","doi":"https://doi.org/10.1109/asru65441.2025.11434650","title":"Efficient Speech Watermarking for Speech Synthesis via Progressive Knowledge Distillation","display_name":"Efficient Speech Watermarking for Speech Synthesis via Progressive Knowledge Distillation","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148437532","doi":"https://doi.org/10.1109/asru65441.2025.11434650"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5100708268","display_name":"Yang Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yang Cui","raw_affiliation_strings":["Microsoft,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Microsoft,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132759115","display_name":"Peter Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peter Pan","raw_affiliation_strings":["Microsoft,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Microsoft,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132828157","display_name":"Lei He","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei He","raw_affiliation_strings":["Microsoft,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Microsoft,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132811339","display_name":"Sheng Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Zhao","raw_affiliation_strings":["Microsoft,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Microsoft,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100708268"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87565853,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.19470000267028809,"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":0.19470000267028809,"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/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.19419999420642853,"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":0.07249999791383743,"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":0.6743999719619751},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.38769999146461487},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.36160001158714294},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3352000117301941},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.33410000801086426},{"id":"https://openalex.org/keywords/watermark","display_name":"Watermark","score":0.2992999851703644}],"concepts":[{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.6743999719619751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6643999814987183},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5993000268936157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4650000035762787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4490000009536743},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.36160001158714294},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C164112704","wikidata":"https://www.wikidata.org/wiki/Q7974348","display_name":"Watermark","level":3,"score":0.2992999851703644},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2637999951839447}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Zero hunger","score":0.45409226417541504,"id":"https://metadata.un.org/sdg/2"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2339254090","https://openalex.org/W2407386500","https://openalex.org/W2893249048","https://openalex.org/W2972359262","https://openalex.org/W3034368386","https://openalex.org/W3204816216","https://openalex.org/W4367046920","https://openalex.org/W4382202512","https://openalex.org/W4392904158","https://openalex.org/W4399728845","https://openalex.org/W4402112250","https://openalex.org/W4402116009","https://openalex.org/W4402401223","https://openalex.org/W4403780894","https://openalex.org/W4404178880","https://openalex.org/W4404479744","https://openalex.org/W4406572737","https://openalex.org/W4408353460","https://openalex.org/W4408354258","https://openalex.org/W4409363619","https://openalex.org/W4415433313"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,59,68,73,112],"rapid":[2],"advancement":[3],"of":[4,61,135,153,158],"speech":[5,82,165,169],"generative":[6],"models,":[7],"unauthorized":[8],"voice":[9],"cloning":[10],"poses":[11],"significant":[12],"privacy":[13],"and":[14,26,39,71,109,138],"security":[15],"risks.":[16],"Speech":[17],"watermarking":[18,30,83,166],"offers":[19],"a":[20,78,99,116,156],"viable":[21],"solution":[22],"for":[23,167],"tracing":[24],"sources":[25],"preventing":[27],"misuse.":[28],"Current":[29],"technologies":[31],"fall":[32],"mainly":[33],"into":[34],"two":[35,95],"categories:":[36],"DSP-based":[37,43],"methods":[38,44,54],"deep":[40,52,80],"learning-based":[41,53,81],"methods.":[42],"are":[45],"efficient":[46,164],"but":[47],"vulnerable":[48],"to":[49,115],"attacks,":[50],"whereas":[51],"offer":[55],"robust":[56,136],"protection":[57],"at":[58],"expense":[60],"significantly":[62],"higher":[63],"computational":[64,69,127],"cost.":[65],"To":[66],"improve":[67],"efficiency":[70],"enhance":[72],"robustness,":[74],"we":[75],"propose":[76],"PKDMark,":[77],"lightweight":[79],"method":[84],"that":[85,143],"leverages":[86],"progressive":[87,121],"knowledge":[88,122],"distillation":[89],"(PKD).":[90],"Our":[91],"approach":[92],"proceeds":[93],"in":[94,160],"stages:":[96],"(1)":[97],"training":[98],"high-performance":[100],"teacher":[101],"model":[102,119,146],"using":[103],"an":[104,148],"invertible":[105],"neural":[106],"network-based":[107],"architecture,":[108],"(2)":[110],"transferring":[111],"teacher\u2019s":[113],"capabilities":[114],"compact":[117],"student":[118],"through":[120],"distillation.":[123],"This":[124],"process":[125],"reduces":[126],"costs":[128],"by":[129],"93.6%":[130],"while":[131],"maintaining":[132],"high":[133],"level":[134],"performance":[137],"imperceptibility.":[139],"Experimental":[140],"results":[141],"demonstrate":[142],"our":[144],"distilled":[145],"achieves":[147],"average":[149],"detection":[150],"F1":[151],"score":[152],"99.6%":[154],"with":[155],"PESQ":[157],"4.30":[159],"advanced":[161],"distortions,":[162],"enabling":[163],"real-time":[168],"synthesis":[170],"applications.":[171]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}