{"id":"https://openalex.org/W4408352443","doi":"https://doi.org/10.1109/icassp49660.2025.10888430","title":"WMCodec: End-to-End Neural Speech Codec with Deep Watermarking for Authenticity Verification","display_name":"WMCodec: End-to-End Neural Speech Codec with Deep Watermarking for Authenticity Verification","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352443","doi":"https://doi.org/10.1109/icassp49660.2025.10888430"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888430","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/A5101311024","display_name":"Junzuo Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junzuo Zhou","raw_affiliation_strings":["Institute of Automation Chinese Academy of Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyan Yi","raw_affiliation_strings":["Institute of Automation Chinese Academy of Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413319","display_name":"Yong Ren","orcid":"https://orcid.org/0000-0002-6016-5582"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Ren","raw_affiliation_strings":["Institute of Automation Chinese Academy of Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071038184","display_name":"Tao Wang","orcid":"https://orcid.org/0000-0003-1490-6973"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Wang","raw_affiliation_strings":["Institute of Automation Chinese Academy of Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026641664","display_name":"Chu Yuan Zhang","orcid":"https://orcid.org/0009-0006-3461-3034"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chu Yuan Zhang","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101311024"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02010299,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962999820709229,"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":0.9962999820709229,"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":0.9952999949455261,"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":0.9940999746322632,"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/codec","display_name":"Codec","score":0.7554242610931396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7366042137145996},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7275510430335999},{"id":"https://openalex.org/keywords/digital-watermarking","display_name":"Digital watermarking","score":0.6659364700317383},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5375335812568665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28946465253829956},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.1954764723777771},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14942926168441772}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7554242610931396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7366042137145996},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7275510430335999},{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.6659364700317383},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5375335812568665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28946465253829956},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.1954764723777771},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14942926168441772}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888430","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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335869","display_name":"National Social Science Fund of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2014485509","https://openalex.org/W2054812163","https://openalex.org/W2067295501","https://openalex.org/W2081326826","https://openalex.org/W2164588373","https://openalex.org/W2165291881","https://openalex.org/W2405506115","https://openalex.org/W2972359262","https://openalex.org/W3037038648","https://openalex.org/W3215615641","https://openalex.org/W4372340947","https://openalex.org/W4376455521","https://openalex.org/W4391421559","https://openalex.org/W4391725339","https://openalex.org/W4392903006","https://openalex.org/W4402111703","https://openalex.org/W4402112140","https://openalex.org/W4402112250","https://openalex.org/W6846857581","https://openalex.org/W6852581948","https://openalex.org/W6855612533","https://openalex.org/W7051469422"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2361629745","https://openalex.org/W2107922825","https://openalex.org/W3094285444","https://openalex.org/W1568204688","https://openalex.org/W2381262728","https://openalex.org/W2111592878","https://openalex.org/W4404782863"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,9,77,123,140],"speech":[3,11,28,68],"spoofing":[4],"necessitate":[5],"stronger":[6],"verification":[7],"mechanisms":[8],"neural":[10,67],"codecs":[12],"to":[13,50,70],"ensure":[14],"authenticity.":[15],"Current":[16],"methods":[17],"embed":[18],"numerical":[19],"watermarks":[20],"before":[21],"compression":[22],"and":[23,42,44,56,74,84,104,130,137],"extract":[24],"them":[25],"from":[26],"reconstructed":[27],"for":[29,39,98,127],"verification,":[30],"but":[31],"face":[32],"limitations":[33],"such":[34],"as":[35],"separate":[36],"training":[37],"processes":[38],"the":[40,65,87,107,113],"watermark":[41,52,75,103,128,152],"codec,":[43],"insufficient":[45],"cross-modal":[46],"information":[47],"integration,":[48],"leading":[49],"reduced":[51],"imperceptibility,":[53],"extraction":[54,141,161],"accuracy,":[55],"capacity.":[57],"To":[58],"address":[59],"these":[60],"issues,":[61],"we":[62],"propose":[63],"WMCodec,":[64],"first":[66],"codec":[69],"jointly":[71],"train":[72],"compression-reconstruction":[73],"embedding-extraction":[76],"an":[78,92],"end-to-end":[79],"manner,":[80],"optimizing":[81],"both":[82,133],"imperceptibility":[83,129],"extractability":[85],"of":[86,102,109,143,147,154],"watermark.":[88,114,144],"Furthermore,":[89],"We":[90],"design":[91],"iterative":[93],"Attention":[94],"Imprint":[95],"Unit":[96],"(AIU)":[97],"deeper":[99],"feature":[100],"integration":[101],"speech,":[105],"reducing":[106],"impact":[108],"quantization":[110],"noise":[111],"on":[112],"Experimental":[115],"results":[116],"show":[117],"WMCodec":[118,157],"outperforms":[119],"AudioSeal":[120,134],"with":[121,135,150],"Encodec":[122,136],"most":[124],"quality":[125],"metrics":[126],"consistently":[131],"exceeds":[132],"reinforced":[138],"TraceableSpeech":[139],"accuracy":[142,162],"At":[145],"bandwidth":[146],"6":[148],"kbps":[149],"a":[151],"capacity":[153],"16":[155],"bps,":[156],"maintains":[158],"over":[159],"99%":[160],"under":[163],"common":[164],"attacks,":[165],"demonstrating":[166],"strong":[167],"robustness.":[168]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}