{"id":"https://openalex.org/W4210590938","doi":"https://doi.org/10.1109/asru51503.2021.9687908","title":"Mandarin Electrolaryngeal Speech Voice Conversion with Sequence-to-Sequence Modeling","display_name":"Mandarin Electrolaryngeal Speech Voice Conversion with Sequence-to-Sequence Modeling","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210590938","doi":"https://doi.org/10.1109/asru51503.2021.9687908"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9687908","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687908","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5014941783","display_name":"Ming-Chi Yen","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ming-Chi Yen","raw_affiliation_strings":["National Taiwan University,Taiwan","National Taiwan University, Taiwan","Institute of Information Science, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"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":["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":"middle","author":{"id":"https://openalex.org/A5066130866","display_name":"Yuhuai Peng","orcid":"https://orcid.org/0000-0001-9343-5377"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Huai Peng","raw_affiliation_strings":["Institute of Information Science, Academia Sinica,Taiwan","Institute of Information Science, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082770847","display_name":"Shu-Wei Tsai","orcid":"https://orcid.org/0000-0001-8335-9825"},"institutions":[{"id":"https://openalex.org/I4210158999","display_name":"National Cheng Kung University Hospital","ror":"https://ror.org/04zx3rq17","country_code":"TW","type":"healthcare","lineage":["https://openalex.org/I4210158999"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shu-Wei Tsai","raw_affiliation_strings":["National Cheng Kung University Hospital,Dept. of Otolaryngology,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Cheng Kung University Hospital,Dept. of Otolaryngology,Taiwan","institution_ids":["https://openalex.org/I4210158999"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica,Taiwan","Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073451247","display_name":"Jyh\u2010Shing Roger Jang","orcid":"https://orcid.org/0000-0002-7319-9095"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jyh-Shing Roger Jang","raw_affiliation_strings":["National Taiwan University,Taiwan","National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica,Taiwan","Institute of Information Science, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"650","last_page":"657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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":0.9962000250816345,"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/naturalness","display_name":"Naturalness","score":0.8599917888641357},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7991390824317932},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7863268256187439},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6627576351165771},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5831922292709351},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5294351577758789},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43952417373657227},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4281073212623596},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.41741225123405457}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8599917888641357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7991390824317932},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7863268256187439},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6627576351165771},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5831922292709351},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5294351577758789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43952417373657227},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4281073212623596},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.41741225123405457},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9687908","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687908","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7675973762","display_name":null,"funder_award_id":"107-2221-E-001-008-MY3","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W240387242","https://openalex.org/W1600744878","https://openalex.org/W1902237438","https://openalex.org/W2013996527","https://openalex.org/W2022125261","https://openalex.org/W2023694213","https://openalex.org/W2048646122","https://openalex.org/W2096779346","https://openalex.org/W2116593694","https://openalex.org/W2128653836","https://openalex.org/W2133564696","https://openalex.org/W2145892079","https://openalex.org/W2151500768","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2749651610","https://openalex.org/W2786868129","https://openalex.org/W2892009249","https://openalex.org/W2897353073","https://openalex.org/W2901254300","https://openalex.org/W2902967674","https://openalex.org/W2962780374","https://openalex.org/W2963242190","https://openalex.org/W2991015288","https://openalex.org/W3006777338","https://openalex.org/W3015338123","https://openalex.org/W3016160783","https://openalex.org/W3034420534","https://openalex.org/W3096567388","https://openalex.org/W3099078140","https://openalex.org/W3102905810","https://openalex.org/W3114898335","https://openalex.org/W6609372888","https://openalex.org/W6679434410","https://openalex.org/W6743855016","https://openalex.org/W6769513855","https://openalex.org/W6769767169","https://openalex.org/W6771070734"],"related_works":["https://openalex.org/W2912293245","https://openalex.org/W1604114751","https://openalex.org/W2079655441","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W2549308614","https://openalex.org/W2023694213","https://openalex.org/W2085637247","https://openalex.org/W2958354987","https://openalex.org/W2146137281"],"abstract_inverted_index":{"The":[0,77,142],"electrolaryngeal":[1],"speech":[2,42,51,56,73,84,87,114],"(EL":[3],"speech)":[4],"is":[5,101],"typically":[6],"spoken":[7],"with":[8,138,162],"an":[9,89,146],"electrolarynx":[10],"device":[11],"that":[12,47,168],"generates":[13],"excitation":[14,24],"signals":[15,25],"to":[16,81,149],"substitute":[17],"human":[18],"vocal":[19,33],"fold":[20],"vibrations.":[21],"Because":[22],"the":[23,35,40,49,107,112,120,169],"cannot":[26],"perfectly":[27],"characterize":[28],"sound":[29],"sources":[30],"generated":[31],"by":[32],"folds,":[34],"naturalness":[36],"and":[37,65,117,154,182],"intelligibility":[38],"of":[39,48,111,178],"EL":[41,72,83,113],"are":[43],"inevitably":[44],"worse":[45],"than":[46],"natural":[50],"(NL":[52],"speech).":[53],"To":[54,92,123],"improve":[55],"naturalness,":[57],"statistical":[58],"models,":[59,67],"such":[60],"as":[61],"Gaussian":[62],"mixture":[63],"models":[64],"deep-learning-based":[66],"have":[68],"been":[69],"employed":[70],"for":[71,103],"voice":[74],"conversion":[75],"(ELVC).":[76],"ELVC":[78,90,96,121,131,171,190],"task":[79],"aims":[80],"convert":[82],"into":[85],"NL":[86],"through":[88],"model.":[91],"implement":[93],"a":[94,129,187],"frame-wise":[95,189],"system,":[97],"accurate":[98],"feature":[99],"alignment":[100],"crucial":[102],"model":[104,144],"training.":[105],"However,":[106],"abnormal":[108],"acoustic":[109],"characteristics":[110],"cause":[115],"misalignments":[116],"accordingly":[118],"limit":[119],"performance.":[122],"address":[124],"this":[125],"issue,":[126],"we":[127],"propose":[128],"novel":[130],"system":[132,172],"based":[133],"on":[134],"sequence-to-sequence":[135],"(seq2seq)":[136],"modeling":[137],"text-to-speech":[139],"(TTS)":[140],"pretraining.":[141],"seq2seq":[143],"involves":[145],"attention":[147],"mechanism":[148],"concurrently":[150],"perform":[151],"representation":[152],"learning":[153],"alignment.":[155],"Meanwhile,":[156],"TTS":[157],"pretraining":[158],"provides":[159],"efficient":[160],"training":[161],"limited":[163],"data.":[164],"Experimental":[165],"results":[166],"show":[167],"proposed":[170],"yields":[173],"notable":[174],"improvements":[175],"in":[176],"terms":[177],"standardized":[179],"evaluation":[180],"metrics":[181],"subjective":[183],"listening":[184],"tests":[185],"over":[186],"well-known":[188],"system.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
