{"id":"https://openalex.org/W7220928646","doi":"https://doi.org/10.48550/arxiv.2610.07524","title":"Region-Aware Masking for Accent-Robust Cross-Lingual Text-to-Speech","display_name":"Region-Aware Masking for Accent-Robust Cross-Lingual Text-to-Speech","publication_year":2026,"publication_date":"2026-10-05","ids":{"openalex":"https://openalex.org/W7220928646","doi":"https://doi.org/10.48550/arxiv.2610.07524"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.07524","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.07524","pdf_url":"https://arxiv.org/pdf/2610.07524","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/2610.07524","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157985619","display_name":"Haoqi Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Haoqi","raw_affiliation_strings":["Netflix Inc. , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netflix Inc. , USA","institution_ids":["https://openalex.org/I869089601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103054907","display_name":"Shivam Mehta","orcid":"https://orcid.org/0000-0002-1886-681X","observed_orcids":["https://orcid.org/0000-0002-1886-681X"]},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehta, Shivam","raw_affiliation_strings":["Netflix Inc. , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netflix Inc. , USA","institution_ids":["https://openalex.org/I869089601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050071432","display_name":"Ravi Teja Gadde","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gadde, Ravi Teja","raw_affiliation_strings":["Netflix Inc. , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netflix Inc. , USA","institution_ids":["https://openalex.org/I869089601"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052989421","display_name":"Yinghong Lan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lan, Yinghong","raw_affiliation_strings":["Netflix Inc. , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netflix Inc. , USA","institution_ids":["https://openalex.org/I869089601"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I869089601"],"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/zero-shot-text-to-speech","display_name":"zero-shot text-to-speech","score":0.8389999866485596},{"id":"https://openalex.org/keywords/mask-geometry","display_name":"mask geometry","score":0.37599998712539673}],"concepts":[{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7146000266075134},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6139000058174133},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.53329998254776},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4627000093460083},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4620000123977661},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4212000072002411},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.32739999890327454},{"id":"https://openalex.org/C2983864324","wikidata":"https://www.wikidata.org/wiki/Q16872183","display_name":"Line drawings","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3077999949455261},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.28940001130104065},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2689000070095062},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26019999384880066}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.07524","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.07524","pdf_url":"https://arxiv.org/pdf/2610.07524","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.2610.07524","doi":"https://doi.org/10.48550/arxiv.2610.07524","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.07524","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:2610.07524","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.07524","pdf_url":"https://arxiv.org/pdf/2610.07524","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":[{"id":"https://metadata.un.org/sdg/10","score":0.4000000059604645,"display_name":"Reduced inequalities"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220928646.pdf","grobid_xml":"https://content.openalex.org/works/W7220928646.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W4308615697","https://openalex.org/W4323651091","https://openalex.org/W4415124086","https://openalex.org/W7134244375","https://openalex.org/W7155028488","https://openalex.org/W7160645978","https://openalex.org/W7165899286"],"related_works":["https://openalex.org/W7165899286","https://openalex.org/W7214337081","https://openalex.org/W7164927113","https://openalex.org/W7206155534","https://openalex.org/W7134244375","https://openalex.org/W7134856253","https://openalex.org/W4399400218","https://openalex.org/W7214722934","https://openalex.org/W7134805317","https://openalex.org/W2990124956"],"abstract_inverted_index":{"Accent":[0],"leakage":[1],"remains":[2],"a":[3,33,97,113,188],"critical":[4],"challenge":[5],"in":[6,123,140],"cross-lingual":[7,45,71],"zero-shot":[8],"text-to-speech":[9],"(TTS),":[10],"where":[11],"models":[12],"inadvertently":[13],"transfer":[14],"both":[15],"the":[16,23,59,64,70,74,92,117,151,155,166,174],"speaker's":[17],"timbre":[18],"and":[19,57,120,126,160],"source-language":[20],"accent":[21,84,107,158,170,193],"into":[22],"target-language":[24],"output.":[25],"In":[26,96],"mask-reconstruction":[27],"TTS":[28],"this":[29,49],"is":[30,186],"amplified":[31],"by":[32,51,121],"train--inference":[34],"mismatch:":[35],"training":[36,68],"reconstructs":[37],"from":[38,54,108],"same-language":[39],"context,":[40],"while":[41],"inference":[42],"conditions":[43],"on":[44,112,128],"context.":[46],"We":[47],"close":[48],"gap":[50],"concatenating":[52],"utterances":[53],"two":[55],"languages":[56,131],"placing":[58],"reconstruction":[60,167],"mask":[61,93,145],"relative":[62],"to":[63,110,165],"language":[65,82],"boundary,":[66],"so":[67],"presents":[69],"prompting":[72],"pattern":[73],"model":[75],"encounters":[76],"at":[77],"inference.":[78],"This":[79],"requires":[80],"no":[81,137],"IDs,":[83],"labels,":[85],"parallel":[86],"same-speaker":[87],"recordings,":[88],"or":[89,142],"architectural":[90],"changes---only":[91],"geometry":[94,185],"differs.":[95],"listening":[98],"study":[99],"with":[100,136],"native":[101],"speakers,":[102],"region-aware":[103],"masking":[104,181],"reduces":[105],"perceived":[106],"4.3":[109],"0.5":[111],"0-5":[114],"scale":[115],"against":[116,132],"unadapted":[118],"baseline,":[119],"18-51\\%":[122],"seen":[124],"regimes":[125],"35-55\\%":[127],"unseen":[129],"source":[130],"bilingual":[133],"adaptation":[134],"alone,":[135],"measurable":[138],"loss":[139],"intelligibility":[141],"naturalness.":[143],"Comparing":[144],"geometries":[146],"shows":[147],"that":[148],"placement,":[149],"not":[150],"amount":[152],"masked,":[153],"governs":[154],"balance":[156],"between":[157],"suppression":[159],"speaker":[161,176],"preservation:":[162],"masks":[163],"confined":[164],"region":[168],"suppress":[169],"most":[171],"but":[172],"retain":[173],"reference":[175],"least":[177],"reliably,":[178],"whereas":[179],"two-region":[180],"achieves":[182],"both.":[183],"Mask":[184],"thus":[187],"simple,":[189],"effective":[190],"lever":[191],"for":[192],"robustness.":[194]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-09T00:00:00"}