{"id":"https://openalex.org/W4411799389","doi":"https://doi.org/10.1109/jstsp.2025.3584195","title":"Resolving Domain Mismatches in Electrolaryngeal Speech Enhancement With Linguistic Intermediates","display_name":"Resolving Domain Mismatches in Electrolaryngeal Speech Enhancement With Linguistic Intermediates","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4411799389","doi":"https://doi.org/10.1109/jstsp.2025.3584195"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2025.3584195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2025.3584195","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal Processing","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/A5013549148","display_name":"Lester Phillip Violeta","orcid":"https://orcid.org/0000-0001-9118-2994"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Lester Phillip Violeta","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Nagoya, Japan","Graduate School of Informatics, Nagoya University, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9118-2994","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000377034","display_name":"Wen-Chin Huang","orcid":"https://orcid.org/0000-0003-3172-3335"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wen-Chin Huang","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Nagoya, Japan","Graduate School of Informatics, Nagoya University, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3172-3335","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106406933","display_name":"Ding Ma","orcid":"https://orcid.org/0009-0002-6564-4571"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ding Ma","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Nagoya, Japan","Graduate School of Informatics, Nagoya University, Japan"],"raw_orcid":"https://orcid.org/0009-0002-6564-4571","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669485","display_name":"Ryuichi Yamamoto","orcid":"https://orcid.org/0000-0003-0299-5470"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryuichi Yamamoto","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Nagoya, Japan","Graduate School of Informatics, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kazuhiro Kobayashi","orcid":"https://orcid.org/0000-0001-5047-4165"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Kobayashi","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Nagoya, Japan","Graduate School of Informatics, Nagoya University, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5047-4165","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Information Technology Center, Nagoya University, Nagoya, Japan","Information Technology Center, Nagoya University, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8146-1279","affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Information Technology Center, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":0.9024,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.7323175,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"19","issue":"5","first_page":"827","last_page":"839"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9916999936103821,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9916999936103821,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9793999791145325,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9650999903678894,"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/computer-science","display_name":"Computer science","score":0.7219074964523315},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5985528230667114},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5728777050971985},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5124295353889465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46307575702667236},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.35511332750320435},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1618480384349823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7219074964523315},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5985528230667114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5728777050971985},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5124295353889465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46307575702667236},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.35511332750320435},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1618480384349823},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2025.3584195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2025.3584195","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W180052447","https://openalex.org/W1596477320","https://openalex.org/W2012122078","https://openalex.org/W2022125261","https://openalex.org/W2120605154","https://openalex.org/W2127141656","https://openalex.org/W2161501672","https://openalex.org/W2526425061","https://openalex.org/W2741920812","https://openalex.org/W2888922217","https://openalex.org/W2895118591","https://openalex.org/W2962826786","https://openalex.org/W2964525587","https://openalex.org/W2972970915","https://openalex.org/W3034420534","https://openalex.org/W3083423753","https://openalex.org/W3096567388","https://openalex.org/W3097777922","https://openalex.org/W3098557217","https://openalex.org/W3113687514","https://openalex.org/W3118753411","https://openalex.org/W3158762648","https://openalex.org/W3161018648","https://openalex.org/W3161109662","https://openalex.org/W3161669994","https://openalex.org/W3162517041","https://openalex.org/W3194248215","https://openalex.org/W3196001064","https://openalex.org/W3196305160","https://openalex.org/W3197150384","https://openalex.org/W3197712601","https://openalex.org/W3205665014","https://openalex.org/W3209059054","https://openalex.org/W3210530853","https://openalex.org/W4210590938","https://openalex.org/W4210774711","https://openalex.org/W4225956675","https://openalex.org/W4226074601","https://openalex.org/W4319862397","https://openalex.org/W4372266901","https://openalex.org/W4375868803","https://openalex.org/W4385245566","https://openalex.org/W4388820620","https://openalex.org/W4390912371","https://openalex.org/W4392902750","https://openalex.org/W4392909911","https://openalex.org/W4392931276","https://openalex.org/W4397026467"],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W4376623224","https://openalex.org/W4387849428","https://openalex.org/W3204019825"],"abstract_inverted_index":{"We":[0,18,58,208],"investigate":[1],"the":[2,12,21,44,47,51,74,124,128,138,141,164,195,210,214],"use":[3,22,32,129],"of":[4,23,46,130,140,144,152,179,185,204,218],"linguistic":[5,24],"intermediates":[6,197],"to":[7,26,43,81,123,163],"resolve":[8],"domain":[9],"mismatches":[10,49,72],"in":[11,112,119,154,160,202],"electrolaryngeal":[13],"(EL)":[14,56,76],"speech":[15,100,146],"enhancement":[16],"task.":[17],"first":[19],"propose":[20],"encoders":[25],"produce":[27],"bottleneck":[28,92],"feature":[29,93],"intermediates,":[30,67,94,133],"and":[31,36,54,77,97,116,147,158,182,216],"a":[33,108,175],"recognition,":[34],"alignment,":[35],"synthesis":[37],"framework,":[38],"effectively":[39,69],"improving":[40],"performance":[41],"due":[42],"removal":[45],"timbre":[48],"between":[50,73],"pretraining":[52],"(typical)":[53,79],"fine-tuning":[55],"data.":[57],"then":[59],"further":[60,136],"improve":[61,82,137],"this":[62],"by":[63,89,107,212],"introducing":[64],"discrete":[65,131],"text":[66],"which":[68,190],"alleviate":[70],"temporal":[71,142],"source":[75],"target":[78],"data":[80],"prosody":[83],"modeling.":[84],"Our":[85],"findings":[86,173],"show":[87,192],"that":[88,193],"simply":[90],"using":[91,194],"more":[95],"intelligible":[96],"naturally":[98],"sounding":[99],"can":[101,135],"already":[102],"be":[103],"synthesized,":[104],"as":[105],"shown":[106],"significant":[109],"16%":[110],"improvement":[111,118,151],"character":[113,155],"error":[114,156,206],"rate":[115,157],"0.83":[117],"naturalness":[120,161],"score":[121],"compared":[122,162],"baseline.":[125],"Moreover,":[126],"through":[127],"phoneme-level":[132,196],"we":[134,169],"modeling":[139],"structure":[143],"typical":[145],"get":[148],"another":[149,183],"absolute":[150],"1.4%":[153],"0.2":[159],"initially":[165],"proposed":[166,220],"system.":[167],"Finally,":[168],"also":[170],"verify":[171],"these":[172],"on":[174],"larger":[176],"pseudo-EL":[177],"dataset":[178],"14":[180],"speakers":[181],"set":[184],"3":[186],"real-world":[187],"EL":[188],"speakers,":[189],"consistently":[191],"is":[198],"most":[199],"effective":[200],"approach":[201],"terms":[203],"phoneme":[205],"rate.":[207],"conclude":[209],"research":[211],"summarizing":[213],"advantages":[215],"disadvantages":[217],"each":[219],"technique.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-04T23:47:47.292601","created_date":"2025-10-10T00:00:00"}