{"id":"https://openalex.org/W4319862397","doi":"https://doi.org/10.1109/slt54892.2023.10023033","title":"Two-Stage Training Method for Japanese Electrolaryngeal Speech Enhancement Based on Sequence-to-Sequence Voice Conversion","display_name":"Two-Stage Training Method for Japanese Electrolaryngeal Speech Enhancement Based on Sequence-to-Sequence Voice Conversion","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862397","doi":"https://doi.org/10.1109/slt54892.2023.10023033"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023033","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","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/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":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","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":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037417355","display_name":"Kazuhiro Kobayashi","orcid":"https://orcid.org/0000-0001-7801-147X"},"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":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"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":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"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":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"949","last_page":"954"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9990000128746033,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.781646728515625},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.690488338470459},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6741217374801636},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5515562891960144},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5464353561401367},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4937833249568939},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4840535521507263},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.42201143503189087},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.382843554019928}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.781646728515625},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.690488338470459},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6741217374801636},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5515562891960144},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5464353561401367},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4937833249568939},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4840535521507263},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.42201143503189087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.382843554019928},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/slt54892.2023.10023033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023033","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4337773688","display_name":null,"funder_award_id":"JP21dk0310114","funder_id":"https://openalex.org/F4320311405","funder_display_name":"Japan Agency for Medical Research and Development"},{"id":"https://openalex.org/G5000949750","display_name":null,"funder_award_id":"JPMJCR19A3","funder_id":"https://openalex.org/F4320320907","funder_display_name":"Japan Science and Technology Corporation"}],"funders":[{"id":"https://openalex.org/F4320311405","display_name":"Japan Agency for Medical Research and Development","ror":"https://ror.org/004rtk039"},{"id":"https://openalex.org/F4320320907","display_name":"Japan Science and Technology Corporation","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2012122078","https://openalex.org/W2022125261","https://openalex.org/W2023694213","https://openalex.org/W2100819376","https://openalex.org/W2130942839","https://openalex.org/W2765486990","https://openalex.org/W2897353073","https://openalex.org/W2901254300","https://openalex.org/W2962780374","https://openalex.org/W2972970915","https://openalex.org/W3015338123","https://openalex.org/W3034420534","https://openalex.org/W3096567388","https://openalex.org/W3097777922","https://openalex.org/W3098557217","https://openalex.org/W3099078140","https://openalex.org/W3102905810","https://openalex.org/W3161669994","https://openalex.org/W3198218550","https://openalex.org/W3213248030","https://openalex.org/W4210590938","https://openalex.org/W4226074601","https://openalex.org/W4385245566","https://openalex.org/W4390912400","https://openalex.org/W6679436768","https://openalex.org/W6745289305"],"related_works":["https://openalex.org/W2374250903","https://openalex.org/W2487056937","https://openalex.org/W1546413948","https://openalex.org/W42072456","https://openalex.org/W2263832889","https://openalex.org/W2243884323","https://openalex.org/W2089057551","https://openalex.org/W2607023851","https://openalex.org/W2012179620","https://openalex.org/W4243095785"],"abstract_inverted_index":{"Sequence-to-sequence":[0],"(seq2seq)":[1],"voice":[2],"conversion":[3],"(VC)":[4],"models":[5],"have":[6],"greater":[7],"potential":[8],"in":[9,93],"converting":[10],"electrolaryngeal":[11],"(EL)":[12],"speech":[13,16],"to":[14,19,66,88],"normal":[15,110],"(EL2SP)":[17],"compared":[18],"conventional":[20],"VC":[21,28,75,117],"models.":[22],"However,":[23],"EL2SP":[24,71,144],"based":[25,72,145],"on":[26,70,73,146],"seq2seq":[27,74,147],"requires":[29],"a":[30,62,77,99,120],"sufficiently":[31],"large":[32,100],"amount":[33,50,79,101],"of":[34,51,80,102,107,143],"parallel":[35,82,105,129],"data":[36,53,91,106],"for":[37],"the":[38,49,68,81,113,127,136,141],"model":[39],"training":[40,52,123],"and":[41,109],"it":[42],"suffers":[43],"from":[44],"significant":[45],"performance":[46,69,142],"degradation":[47],"when":[48,76],"is":[54,84,124],"insufficient.":[55],"To":[56],"address":[57],"this":[58],"issue,":[59],"we":[60,96],"suggest":[61],"novel,":[63],"two-stage":[64],"strategy":[65],"optimize":[67],"small":[78],"dataset":[83,115,130],"available.":[85],"In":[86],"contrast":[87],"utilizing":[89],"high-quality":[90],"augmentations":[92],"previous":[94],"studies,":[95],"first":[97],"combine":[98],"imperfect":[103],"synthetic":[104],"EL":[108],"speech,":[111],"with":[112,126],"original":[114,128],"into":[116],"training.":[118],"Then,":[119],"second":[121],"stage":[122],"conducted":[125],"only.":[131],"The":[132],"results":[133],"show":[134],"that":[135],"proposed":[137],"method":[138],"progressively":[139],"improves":[140],"VC.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}