{"id":"https://openalex.org/W7127389727","doi":"https://doi.org/10.48550/arxiv.2602.00560","title":"Edit Content, Preserve Acoustics: Imperceptible Text-Based Speech Editing via Self-Consistency Rewards","display_name":"Edit Content, Preserve Acoustics: Imperceptible Text-Based Speech Editing via Self-Consistency Rewards","publication_year":2026,"publication_date":"2026-01-31","ids":{"openalex":"https://openalex.org/W7127389727","doi":"https://doi.org/10.48550/arxiv.2602.00560"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.00560","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.00560","pdf_url":"https://arxiv.org/pdf/2602.00560","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.00560","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122098611","display_name":"Yong Ren","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ren, Yong","raw_affiliation_strings":["School of Artificial Intelligence , University of Chinese Academy of Sciences","The State Key Laboratory of Multimodal Artificial Intelligence Systems , Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"The State Key Laboratory of Multimodal Artificial Intelligence Systems , Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618","observed_orcids":["https://orcid.org/0000-0003-2422-4618"]},"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":"Yi, Jiangyan","raw_affiliation_strings":["Department of Automation , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124906375","display_name":"Jianhua Tao","orcid":null,"observed_orcids":[]},"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":"Tao, Jianhua","raw_affiliation_strings":["BNRist , Tsinghua University","Department of Automation , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BNRist , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159959112","display_name":"Tao Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122020144","display_name":"Le Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","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":"Xu, Le","raw_affiliation_strings":["The State Key Laboratory of Multimodal Artificial Intelligence Systems , Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The State Key Laboratory of Multimodal Artificial Intelligence Systems , Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122040764","display_name":"Zhengqi Wen","orcid":null,"observed_orcids":[]},"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":"Wen, Zhengqi","raw_affiliation_strings":["BNRist , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BNRist , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9945999979972839,"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":0.9945999979972839,"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/T10860","display_name":"Speech and Audio Processing","score":0.0038999998942017555,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0006000000284984708,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-editing","display_name":"speech editing","score":0.3700000047683716},{"id":"https://openalex.org/keywords/duration-constraints","display_name":"duration constraints","score":0.8629999756813049},{"id":"https://openalex.org/keywords/perceptual-consistency","display_name":"perceptual consistency","score":0.5740000009536743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8061000108718872},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5622000098228455},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5526999831199646},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.48399999737739563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4648999869823456},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4595000147819519},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.37700000405311584},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3758000135421753},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3601999878883362},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30250000953674316},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.00560","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.00560","pdf_url":"https://arxiv.org/pdf/2602.00560","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.2602.00560","doi":"https://doi.org/10.48550/arxiv.2602.00560","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.00560","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:2602.00560","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.00560","pdf_url":"https://arxiv.org/pdf/2602.00560","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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4467224230","display_name":null,"funder_award_id":"2025T180461","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G533509358","display_name":null,"funder_award_id":"62306316","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5784019134","display_name":null,"funder_award_id":"U2436210","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6859477402","display_name":null,"funder_award_id":"2025M771685","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7003438179","display_name":null,"funder_award_id":"62322120","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7270707897","display_name":null,"funder_award_id":"62206278","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"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7127389727.pdf","grobid_xml":"https://content.openalex.org/works/W7127389727.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W4310290453","https://openalex.org/W4387323811","https://openalex.org/W4391631327","https://openalex.org/W4399425629","https://openalex.org/W4400434308","https://openalex.org/W4414972224","https://openalex.org/W4415035377","https://openalex.org/W4415108646","https://openalex.org/W4416156439","https://openalex.org/W4416258110","https://openalex.org/W4416786421","https://openalex.org/W7127153865"],"related_works":["https://openalex.org/W7155014716","https://openalex.org/W4297841480","https://openalex.org/W4408351987","https://openalex.org/W4408354705","https://openalex.org/W7123249598","https://openalex.org/W4402112176","https://openalex.org/W4392677874","https://openalex.org/W4403714293","https://openalex.org/W4415481591","https://openalex.org/W7164930456"],"abstract_inverted_index":{"Imperceptible":[0],"text-based":[1],"speech":[2],"editing":[3],"modifies":[4],"spoken":[5],"content":[6],"through":[7],"transcript":[8],"manipulation":[9],"while":[10,48],"preserving":[11],"acoustic":[12,49],"continuity.":[13],"Prior":[14],"acoustic-space":[15],"approaches":[16],"suffer":[17],"from":[18],"content-style":[19],"entanglement,":[20],"causing":[21],"unstable":[22],"generation":[23],"and":[24,83,93,99],"boundary":[25],"artifacts.":[26],"We":[27],"introduce":[28],"a":[29,44,54,72],"framework":[30],"guided":[31],"by":[32,53],"the":[33],"principle":[34],"of":[35],"\"Edit":[36],"Content,":[37],"Preserve":[38],"Acoustics\".":[39],"Editing":[40],"is":[41,51],"conducted":[42],"in":[43,96],"stable":[45],"semantic":[46],"space,":[47],"realization":[50],"handled":[52],"Flow":[55],"Matching":[56],"decoder.":[57],"To":[58],"ensure":[59],"perceptual":[60,100],"consistency,":[61],"we":[62],"propose":[63],"Self-Consistency":[64],"Rewards":[65],"Group":[66],"Relative":[67],"Policy":[68],"Optimization,":[69],"which":[70],"leverages":[71],"pre-trained":[73],"Text-to-Speech":[74],"model":[75],"as":[76],"an":[77],"implicit":[78],"critic,":[79],"together":[80],"with":[81],"intelligibility":[82],"duration":[84],"constraints.":[85],"Experiments":[86],"demonstrate":[87],"consistent":[88],"improvements":[89],"over":[90],"state-of-the-art":[91],"autoregressive":[92],"non-autoregressive":[94],"baselines":[95],"intelligibility,":[97],"robustness,":[98],"quality.":[101]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-02-04T00:00:00"}