{"id":"https://openalex.org/W7204203245","doi":"https://doi.org/10.48550/arxiv.2608.22186","title":"AudioNoisePrints: Model-free audio watermarking using spatial correlation in flow matching TTS","display_name":"AudioNoisePrints: Model-free audio watermarking using spatial correlation in flow matching TTS","publication_year":2026,"publication_date":"2026-08-23","ids":{"openalex":"https://openalex.org/W7204203245","doi":"https://doi.org/10.48550/arxiv.2608.22186"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.22186","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22186","pdf_url":"https://arxiv.org/pdf/2608.22186","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.22186","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114418475","display_name":"Timothy Tin-Long Tse","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tin-Long, Timothy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148044633","display_name":"Jian Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhu, Jian","raw_affiliation_strings":["University of British Columbia , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia , Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028411499","display_name":"Aidan Pine","orcid":"https://orcid.org/0000-0001-6552-5324","observed_orcids":["https://orcid.org/0000-0001-6552-5324"]},"institutions":[{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Pine, Aidan","raw_affiliation_strings":["National Research Council Canada , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Research Council Canada , Canada","institution_ids":["https://openalex.org/I4210159778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003895235","display_name":"Mengzhe Geng","orcid":"https://orcid.org/0000-0002-7886-439X","observed_orcids":["https://orcid.org/0000-0002-7886-439X"]},"institutions":[{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Geng, Mengzhe","raw_affiliation_strings":["National Research Council Canada , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Research Council Canada , Canada","institution_ids":["https://openalex.org/I4210159778"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.7734000086784363,"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":0.7734000086784363,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.12229999899864197,"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/T11309","display_name":"Music and Audio Processing","score":0.02759999968111515,"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/audio-watermarking","display_name":"audio watermarking","score":0.9950000047683716},{"id":"https://openalex.org/keywords/flow-matching","display_name":"flow matching","score":0.7390000224113464},{"id":"https://openalex.org/keywords/watermark-detection","display_name":"watermark detection","score":0.7260000109672546},{"id":"https://openalex.org/keywords/vocoder","display_name":"vocoder","score":0.6949999928474426}],"concepts":[{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.7206000089645386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6360999941825867},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5033000111579895},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49410000443458557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4887999892234802},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.460999995470047},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.43959999084472656},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.41519999504089355},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.3921999931335449},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3792000114917755},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.3285999894142151},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C164112704","wikidata":"https://www.wikidata.org/wiki/Q7974348","display_name":"Watermark","level":3,"score":0.3176000118255615},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30250000953674316},{"id":"https://openalex.org/C150060386","wikidata":"https://www.wikidata.org/wiki/Q7574054","display_name":"Spatial correlation","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.2808000147342682},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C53622274","wikidata":"https://www.wikidata.org/wiki/Q2496679","display_name":"Correlation function (quantum field theory)","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C112633086","wikidata":"https://www.wikidata.org/wiki/Q381287","display_name":"White noise","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26669999957084656},{"id":"https://openalex.org/C74050887","wikidata":"https://www.wikidata.org/wiki/Q848368","display_name":"Rotation (mathematics)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25920000672340393}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.22186","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22186","pdf_url":"https://arxiv.org/pdf/2608.22186","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.22186","doi":"https://doi.org/10.48550/arxiv.2608.22186","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22186","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.22186","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22186","pdf_url":"https://arxiv.org/pdf/2608.22186","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.7010176777839661,"id":"https://metadata.un.org/sdg/6","display_name":"Clean water and sanitation"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334601","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204203245.pdf","grobid_xml":"https://content.openalex.org/works/W7204203245.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7117148818","https://openalex.org/W7221766903","https://openalex.org/W7164381945","https://openalex.org/W7101470820","https://openalex.org/W7137892315","https://openalex.org/W4408352686","https://openalex.org/W7169657797","https://openalex.org/W4408353460","https://openalex.org/W4412985463","https://openalex.org/W7162413862"],"abstract_inverted_index":{"We":[0,34,103],"present":[1],"AudioNoisePrints,":[2],"a":[3,60,81,94],"training-free":[4],"watermarking":[5,99,125],"pipeline":[6],"for":[7,86,97,130],"flow":[8,55],"matching":[9,56],"and":[10,21,48,54,68,107,110,113,135],"diffusion":[11,53],"TTS":[12,27,109,133],"models,":[13,57,112],"which":[14],"requires":[15],"minimal":[16],"extra":[17],"computation":[18],"during":[19],"inference":[20],"does":[22],"not":[23],"require":[24],"retraining":[25],"the":[26,31,36,44,49,65,69,139],"model":[28],"or":[29],"reducing":[30],"generation":[32],"quality.":[33],"exploited":[35],"fact":[37],"that":[38,59,115],"there":[39],"are":[40],"strong":[41,95,101],"correlations":[42],"between":[43,64],"initial":[45,66],"Gaussian":[46],"noises":[47],"generated":[50,70],"outputs":[51],"in":[52,138],"such":[58],"simple":[61],"cosine":[62],"correlation":[63,121],"noise":[67],"output":[71],"can":[72,127],"be":[73,128],"used":[74,129],"to":[75],"perform":[76],"watermaking.":[77],"Moreover,":[78],"we":[79],"train":[80],"lightweight":[82],"detector":[83],"on":[84,105],"top":[85],"more":[87,131],"aggressive":[88],"augmentations.":[89,102],"Our":[90],"method":[91],"outperforms":[92],"AudioSeal,":[93],"baseline":[96],"audio":[98],"under":[100],"experimented":[104],"F5TTS":[106],"other":[108],"vocoder":[111],"concluded":[114],"they":[116],"all":[117],"exhibit":[118],"similar":[119],"spatial":[120],"properties,":[122],"suggesting":[123],"our":[124],"scheme":[126],"flow-matching":[132],"models":[134],"even":[136],"vocoders":[137],"future.":[140]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-26T00:00:00"}