{"id":"https://openalex.org/W7160264520","doi":"https://doi.org/10.1109/lsp.2026.3690581","title":"Reinforced Temporally Sparse Gating for High-Fidelity Speech Watermarking","display_name":"Reinforced Temporally Sparse Gating for High-Fidelity Speech Watermarking","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7160264520","doi":"https://doi.org/10.1109/lsp.2026.3690581"},"language":null,"primary_location":{"id":"doi:10.1109/lsp.2026.3690581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3690581","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-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/A5135284160","display_name":"Xin Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Fang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-4796-9444","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135303719","display_name":"Jin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Li","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0003-1261-4771","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135290177","display_name":"Junhua Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhua Liu","raw_affiliation_strings":["Anhui SparkShield Intelligent Technology Company, Ltd., Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui SparkShield Intelligent Technology Company, Ltd., Hefei, China","institution_ids":["https://openalex.org/I4210099079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135368263","display_name":"Liang Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Zou","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7322-5735","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.53372225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1936","last_page":"1940"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.5766000151634216,"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":0.5766000151634216,"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/T11034","display_name":"Digital Filter Design and Implementation","score":0.05559999868273735,"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/T10860","display_name":"Speech and Audio Processing","score":0.04349999874830246,"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":0.7882000207901001},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42719998955726624},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3366999924182892},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.3366999924182892},{"id":"https://openalex.org/keywords/gating","display_name":"Gating","score":0.32899999618530273},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3215999901294708},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.31209999322891235},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.29980000853538513}],"concepts":[{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.7882000207901001},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.732200026512146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5555999875068665},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5198000073432922},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4740000069141388},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42719998955726624},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3366999924182892},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C194544171","wikidata":"https://www.wikidata.org/wiki/Q21105679","display_name":"Gating","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3215999901294708},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28299999237060547},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28189998865127563},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.2757999897003174},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.26429998874664307},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2026.3690581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3690581","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7351844533","display_name":null,"funder_award_id":"62373360","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8905246704","display_name":null,"funder_award_id":"62473368","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Conventional":[0],"neural":[1],"speech":[2,53],"watermarking":[3],"often":[4],"embeds":[5],"watermarks":[6],"across":[7],"all":[8],"acoustic":[9],"frames,":[10],"which":[11],"can":[12],"unnecessarily":[13],"perturb":[14],"low-energy":[15],"regions":[16],"and":[17,62],"degrade":[18],"perceptual":[19,79,112,119],"quality.":[20],"To":[21,76],"address":[22],"this":[23],"issue,":[24],"we":[25,84],"propose":[26],"a":[27,36,63,93],"reinforced":[28],"temporally":[29],"sparse":[30],"gating":[31,57],"framework":[32],"that":[33,97],"adaptively":[34],"selects":[35],"small":[37],"subset":[38],"of":[39],"frames":[40,48],"for":[41],"watermark":[42],"insertion,":[43],"while":[44,121],"leaving":[45],"the":[46,108,114],"remaining":[47],"unchanged":[49],"to":[50,69],"better":[51],"preserve":[52],"naturalness.":[54],"A":[55],"lightweight":[56],"module":[58],"predicts":[59],"frame-level":[60],"masks,":[61],"sparsity-promoting":[64],"loss":[65],"encourages":[66],"temporal":[67],"dispersion":[68],"improve":[70],"robustness":[71,124],"against":[72],"localized":[73],"signal":[74],"dropouts.":[75],"further":[77],"enhance":[78],"fidelity":[80],"beyond":[81],"reconstruction-based":[82],"training,":[83],"introduce":[85],"Speech":[86],"Fidelity":[87],"Group":[88],"Relative":[89],"Policy":[90],"Optimization":[91],"as":[92,102],"post-training":[94],"refinement":[95],"strategy":[96],"leverages":[98],"non-differentiable":[99],"PESQ":[100],"scores":[101],"optimization":[103],"signals.":[104],"By":[105],"directly":[106],"aligning":[107],"embedding":[109,132],"policy":[110],"with":[111],"quality,":[113],"proposed":[115],"method":[116],"substantially":[117],"improves":[118],"transparency":[120],"maintaining":[122],"near-perfect":[123],"under":[125],"common":[126],"distortions,":[127],"significantly":[128],"outperforming":[129],"global":[130],"frame-wise":[131],"baselines.":[133]},"counts_by_year":[],"updated_date":"2026-05-19T06:13:58.757530","created_date":"2026-05-06T00:00:00"}