{"id":"https://openalex.org/W7161675290","doi":"https://doi.org/10.1109/tbme.2026.3694703","title":"Advancing Electrolaryngeal Speech Enhancement Through Speech\u2013Text Representation Learning","display_name":"Advancing Electrolaryngeal Speech Enhancement Through Speech\u2013Text Representation Learning","publication_year":2026,"publication_date":"2026-05-19","ids":{"openalex":"https://openalex.org/W7161675290","doi":"https://doi.org/10.1109/tbme.2026.3694703","pmid":"https://pubmed.ncbi.nlm.nih.gov/42154697"},"language":"en","primary_location":{"id":"doi:10.1109/tbme.2026.3694703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbme.2026.3694703","pdf_url":null,"source":{"id":"https://openalex.org/S5240358","display_name":"IEEE Transactions on Biomedical Engineering","issn_l":"0018-9294","issn":["0018-9294","1558-2531"],"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 Transactions on Biomedical Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2606.01905","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132587372","display_name":"Ding Ma","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":"Ding Ma","raw_affiliation_strings":["Nagoya University"],"raw_orcid":"https://orcid.org/0009-0002-6564-4571","affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136496960","display_name":"Jinyi Mi","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":"Jinyi Mi","raw_affiliation_strings":["Nagoya University"],"raw_orcid":"https://orcid.org/0009-0007-8554-0987","affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136476457","display_name":"Fengji Li","orcid":null},"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"],"raw_orcid":"https://orcid.org/0009-0002-0426-7223","affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"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"],"raw_orcid":"https://orcid.org/0000-0001-9118-2994","affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136466287","display_name":"Jiajun He","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":"Jiajun He","raw_affiliation_strings":["Nagoya University"],"raw_orcid":"https://orcid.org/0009-0006-6489-5220","affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100904914","display_name":"Huang WenChin","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":"Wenchin Huang","raw_affiliation_strings":["Nagoya University"],"raw_orcid":"https://orcid.org/0000-0003-3172-3335","affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136476529","display_name":"Kazuhiro Kobayashi","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":"Kazuhiro Kobayashi","raw_affiliation_strings":["Nagoya University"],"raw_orcid":"https://orcid.org/0000-0001-5047-4165","affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136495195","display_name":"Tomoki Toda","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":"Tomoki Toda","raw_affiliation_strings":["Nagoya University"],"raw_orcid":"https://orcid.org/0000-0001-8146-1279","affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.49233654,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"73","issue":"8","first_page":"2861","last_page":"2875"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.3264000117778778,"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":0.3264000117778778,"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":0.18469999730587006,"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/T12031","display_name":"Speech and dialogue systems","score":0.050700001418590546,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6789000034332275},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4878999888896942},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34040001034736633},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.3003999888896942},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.2962000072002411}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6901999711990356},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6789000034332275},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48969998955726624},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4878999888896942},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4334000051021576},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.310699999332428},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3003999888896942},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.28450000286102295}],"mesh":[{"descriptor_ui":"D000098409","descriptor_name":"Representation Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098409","descriptor_name":"Representation Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098446","descriptor_name":"Autoencoder","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098446","descriptor_name":"Autoencoder","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":"D012815","descriptor_name":"Signal Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012815","descriptor_name":"Signal Processing, Computer-Assisted","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":"D049250","descriptor_name":"Speech Recognition Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D049250","descriptor_name":"Speech Recognition Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1109/tbme.2026.3694703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbme.2026.3694703","pdf_url":null,"source":{"id":"https://openalex.org/S5240358","display_name":"IEEE Transactions on Biomedical Engineering","issn_l":"0018-9294","issn":["0018-9294","1558-2531"],"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 Transactions on Biomedical Engineering","raw_type":"journal-article"},{"id":"pmid:42154697","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42154697","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":"IEEE transactions on bio-medical engineering","raw_type":"Journal Article"},{"id":"pmh:oai:arXiv.org:2606.01905","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.01905","pdf_url":"https://arxiv.org/pdf/2606.01905","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,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2606.01905","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.01905","pdf_url":"https://arxiv.org/pdf/2606.01905","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,"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":[],"awards":[{"id":"https://openalex.org/G7857875618","display_name":"\u9769\u65b0\u7684\u97f3\u58f0\u5909\u63db\u6280\u8853\u304c\u62d3\u304f\u65b0\u898f\u4ee3\u7528\u97f3\u58f0\u306e\u958b\u767a","funder_award_id":"25K02788","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320321474","display_name":"Cabinet Office, Government of Japan","ror":"https://ror.org/007f5s288"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7161675290.pdf","grobid_xml":"https://content.openalex.org/works/W7161675290.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"OBJECTIVE:":[0],"laryngectomees":[1],"depend":[2],"on":[3,175,204],"an":[4,126,171,231],"electromechanical":[5],"device":[6],"to":[7,79,120,133,181],"generate":[8],"electrolaryngeal":[9],"(EL)":[10],"speech":[11,20,55,75,205,238],"for":[12,236],"verbal":[13],"communication.":[14],"Compared":[15],"with":[16,117,197,216],"normal":[17,54],"speech,":[18],"EL":[19,52,237],"suffers":[21],"from":[22],"severe":[23],"distortion,":[24],"limited":[25],"phonetic":[26],"variation,":[27],"unnatural":[28],"prosody,":[29],"and":[30,35,53,76,82,100,102,157,211,233,240],"temporal":[31],"shifts,":[32],"degrading":[33],"naturalness":[34],"intelligibility.":[36,212],"Although":[37],"sequence-to-sequence":[38],"(seq2seq)":[39],"voice":[40],"conversion":[41,45,209],"(VC)":[42],"based":[43],"EL-speech-to-normal-speech":[44],"(EL2SP)":[46],"is":[47,114,179],"promising,":[48],"substantial":[49],"mismatches":[50],"between":[51],"inevitably":[56],"cause":[57],"cumulative":[58],"mapping":[59,81],"errors":[60],"that":[61,161,193],"limit":[62],"performance.":[63],"To":[64],"address":[65],"this,":[66],"we":[67],"describe":[68],"a":[69,86],"novel":[70],"representation":[71,98,178,183],"learning":[72],"framework":[73],"integrating":[74],"text":[77,112],"representations":[78,136,206],"improve":[80],"reconstruction":[83,104,128,173],"quality":[84,210],"within":[85],"seq2seq":[87,168],"VC":[88,169],"model.":[89],"METHODS:":[90],"our":[91,194,224],"methodology":[92,235],"comprises":[93],"two":[94],"main":[95],"stages:":[96],"1)":[97],"integration":[99],"learning,":[101],"2)":[103],"training.":[105],"A":[106],"network":[107],"capable":[108],"of":[109,223],"incorporating":[110],"auxiliary":[111],"information":[113],"first":[115],"constructed":[116],"pretrained":[118],"modules":[119],"learn":[121],"speech-text-based":[122],"integrated":[123,177],"representations.":[124],"Then,":[125],"autoencoder-style":[127],"strategy":[129],"finalizes":[130],"EL2SP":[131,189],"model":[132,139],"inherit":[134],"these":[135,147],"without":[137],"increasing":[138],"complexity.":[140],"Additional":[141],"optimization":[142],"designs":[143],"are":[144],"performed":[145],"across":[146],"stages.":[148],"We":[149],"introduce":[150],"three":[151],"fusion":[152,159],"strategies":[153,160],"including":[154],"middle-,":[155],"input-,":[156],"hybrid-level":[158],"progressively":[162],"enhance":[163],"learning.":[164],"Moreover,":[165],"besides":[166],"standard":[167],"objectives,":[170],"additional":[172],"loss":[174],"the":[176,221,227],"introduced":[180],"refine":[182],"transfer.":[184],"RESULTS:":[185],"experiments":[186],"under":[187],"different":[188],"datasets":[190],"consistently":[191],"demonstrate":[192],"methods,":[195],"combined":[196],"data":[198],"augmentations,":[199],"outperform":[200],"baselines":[201],"relying":[202],"solely":[203],"regarding":[207],"both":[208],"Furthermore,":[213],"progressive":[214],"improvements":[215],"system":[217],"design":[218],"depth":[219],"validate":[220],"effectiveness":[222],"methods.":[225],"SIGNIFICANCE:":[226],"proposed":[228],"methods":[229],"provide":[230],"extensible":[232],"practical":[234],"enhancement":[239],"assistive":[241],"communication":[242],"technologies.":[243]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2026-05-20T00:00:00"}