{"id":"https://openalex.org/W4405490841","doi":"https://doi.org/10.1109/embc53108.2024.10781979","title":"Robust Sequence-to-sequence Voice Conversion for Electrolaryngeal Speech Enhancement in Noisy and Reverberant Conditions","display_name":"Robust Sequence-to-sequence Voice Conversion for Electrolaryngeal Speech Enhancement in Noisy and Reverberant Conditions","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4405490841","doi":"https://doi.org/10.1109/embc53108.2024.10781979","pmid":"https://pubmed.ncbi.nlm.nih.gov/40039698"},"language":"en","primary_location":{"id":"doi:10.1109/embc53108.2024.10781979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc53108.2024.10781979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","pubmed"],"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,Graduate School of Informatics,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Graduate School of Informatics,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047211536","display_name":"Yeonjong Choi","orcid":null},"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":"Yeonjong Choi","raw_affiliation_strings":["Nagoya University,Graduate School of Informatics,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Graduate School of Informatics,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011197978","display_name":"Fengji Li","orcid":"https://orcid.org/0009-0009-8169-5484"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengji Li","raw_affiliation_strings":["Beihang University,School of Biological Science and Medical Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,School of Biological Science and Medical Engineering,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045231545","display_name":"Chao Xie","orcid":"https://orcid.org/0000-0001-7542-1270"},"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":"Chao Xie","raw_affiliation_strings":["Nagoya University,Graduate School of Informatics,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Graduate School of Informatics,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074727414","display_name":"Kazuhiro Kobayashi","orcid":"https://orcid.org/0000-0002-3366-3586"},"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,Graduate School of Informatics,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Graduate School of Informatics,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,Information Technology Center,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Information Technology Center,Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2024","issue":null,"first_page":"1","last_page":"4"},"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":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/T10403","display_name":"Phonetics and Phonology Research","score":0.9922999739646912,"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/sequence","display_name":"Sequence (biology)","score":0.7584789991378784},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7352846264839172},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6638396382331848},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.65035080909729},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.25527459383010864},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.170545756816864}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7584789991378784},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7352846264839172},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6638396382331848},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.65035080909729},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.25527459383010864},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.170545756816864},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007831","descriptor_name":"Larynx, Artificial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007831","descriptor_name":"Larynx, Artificial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009622","descriptor_name":"Noise","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009622","descriptor_name":"Noise","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009622","descriptor_name":"Noise","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013071","descriptor_name":"Speech, Alaryngeal","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013071","descriptor_name":"Speech, Alaryngeal","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D013071","descriptor_name":"Speech, Alaryngeal","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014831","descriptor_name":"Voice","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D014831","descriptor_name":"Voice","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D014831","descriptor_name":"Voice","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/embc53108.2024.10781979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc53108.2024.10781979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)","raw_type":"proceedings-article"},{"id":"pmid:40039698","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40039698","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W144921701","https://openalex.org/W2012122078","https://openalex.org/W2120605154","https://openalex.org/W2130942839","https://openalex.org/W2765486990","https://openalex.org/W2902967674","https://openalex.org/W2962780374","https://openalex.org/W3015191643","https://openalex.org/W3096567388","https://openalex.org/W4210590938","https://openalex.org/W4283768328","https://openalex.org/W4319862397","https://openalex.org/W4372260214","https://openalex.org/W4385822808","https://openalex.org/W6679436768","https://openalex.org/W6745289305","https://openalex.org/W6796464841"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Electrolaryngeal":[0],"(EL)":[1],"speech,":[2,23,64,179],"an":[3,8],"artificial":[4],"speech":[5,46,49,77,133],"produced":[6],"by":[7,125],"electrolarynx":[9],"for":[10],"laryngectomees,":[11],"lacks":[12],"essential":[13],"phonetic":[14],"features,":[15],"and":[16,28,84,130,176],"differs":[17],"in":[18,25,43,70,164,185],"temporal":[19],"structure":[20],"from":[21,137],"normal":[22,48],"resulting":[24],"poor":[26],"naturalness":[27],"intelligibility.":[29],"To":[30],"address":[31],"this":[32],"deficiency,":[33],"sequence-to-sequence":[34],"(seq2seq)":[35],"voice":[36],"conversion":[37],"(VC)":[38],"models":[39],"have":[40],"been":[41],"applied":[42],"converting":[44,61],"EL":[45,63,76,132,178],"to":[47,99,152],"(EL2SP),":[50],"showing":[51],"some":[52],"promising":[53],"performances.":[54],"However,":[55],"previous":[56],"studies":[57],"mostly":[58],"focus":[59],"on":[60,96,115],"clean":[62,144,175],"thereby":[65],"restricting":[66],"the":[67,75,101,155,181],"further":[68],"applicability":[69],"real-world":[71,104,186],"scenarios,":[72],"especially":[73],"when":[74],"is":[78,123],"inevitably":[79],"interfered":[80],"with":[81],"background":[82],"noise":[83],"reverberation.":[85],"In":[86],"light":[87],"of":[88,103,142,157,183],"this,":[89],"we":[90],"suggest":[91],"novel":[92],"training":[93],"techniques":[94],"based":[95,114],"seq2seq":[97,111],"VC":[98,112],"enhance":[100],"robustness":[102,182],"EL2SP.":[105],"We":[106],"first":[107],"pretrain":[108],"a":[109,116,120,139],"normal-to-normal":[110],"model":[113],"text-to-speech":[117],"model.":[118],"Then,":[119],"two-stage":[121],"fine-tuning":[122],"conducted":[124],"effectively":[126],"using":[127],"pseudo":[128],"noisy":[129],"reverberant":[131],"data":[134,145],"artificially":[135],"generated":[136],"only":[138],"small":[140],"amount":[141],"original":[143],"available.":[146],"Several":[147],"design":[148],"options":[149],"are":[150],"investigated":[151],"figure":[153],"out":[154],"effectiveness":[156],"our":[158,169],"method.":[159],"The":[160],"significant":[161],"improvements":[162],"presented":[163],"experimental":[165],"results":[166],"indicate":[167],"that":[168],"method":[170],"can":[171],"non-trivially":[172],"handle":[173],"both":[174],"noisy-reverberant":[177],"enhancing":[180],"EL2SP":[184],"scenarios.":[187]},"counts_by_year":[],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}
