{"id":"https://openalex.org/W4392902750","doi":"https://doi.org/10.1109/icassp48485.2024.10447197","title":"Electrolaryngeal Speech Intelligibility Enhancement through Robust Linguistic Encoders","display_name":"Electrolaryngeal Speech Intelligibility Enhancement through Robust Linguistic Encoders","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902750","doi":"https://doi.org/10.1109/icassp48485.2024.10447197"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447197","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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/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/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/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":["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","TARVO, Inc., 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"]},{"raw_affiliation_string":"TARVO, Inc., Japan","institution_ids":[]}]},{"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":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10961","last_page":"10965"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9979000091552734,"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/T13289","display_name":"Infant Health and Development","score":0.9811000227928162,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7859022617340088},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7756137847900391},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7315638065338135},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6741099953651428},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6222840547561646},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5824384093284607},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.46409741044044495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38809722661972046}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7859022617340088},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7756137847900391},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7315638065338135},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6741099953651428},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6222840547561646},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5824384093284607},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.46409741044044495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38809722661972046},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447197","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G2576085165","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320311405","funder_display_name":"Japan Agency for Medical Research and Development"},{"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/G8892501299","display_name":null,"funder_award_id":"JPMJCR19A3","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320311405","display_name":"Japan Agency for Medical Research and Development","ror":"https://ror.org/004rtk039"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2012122078","https://openalex.org/W2526425061","https://openalex.org/W2765486990","https://openalex.org/W2964525587","https://openalex.org/W2969049672","https://openalex.org/W2972970915","https://openalex.org/W2998572311","https://openalex.org/W3083423753","https://openalex.org/W3097777922","https://openalex.org/W3098557217","https://openalex.org/W3118753411","https://openalex.org/W3158762648","https://openalex.org/W3161018648","https://openalex.org/W3161109662","https://openalex.org/W3161669994","https://openalex.org/W3165478005","https://openalex.org/W3194248215","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/W4319862397","https://openalex.org/W4320459320","https://openalex.org/W4385245566","https://openalex.org/W4388820620","https://openalex.org/W6779823529","https://openalex.org/W6783867762","https://openalex.org/W6840815571","https://openalex.org/W6846304340"],"related_works":["https://openalex.org/W2081919107","https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W4252942110","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W4403759994","https://openalex.org/W4400309480","https://openalex.org/W2549308614"],"abstract_inverted_index":{"We":[0,132],"propose":[1,68],"a":[2,45,69,96,126,164],"novel":[3],"framework":[4,114,139,149],"for":[5,115],"electrolaryngeal":[6],"speech":[7,38,80,102],"intelligibility":[8],"enhancement":[9],"through":[10],"the":[11,37,49,57,82,101,112,117,137,147,151],"use":[12,125],"of":[13,60],"robust":[14,72],"linguistic":[15,70,93],"encoders.":[16],"Pretraining":[17],"and":[18,78,143,157,172],"fine-tuning":[19],"approaches":[20],"have":[21],"proven":[22],"to":[23,74,90,99,111,123,136,153],"work":[24],"well":[25],"in":[26,30,52,81,168,175],"this":[27,61,65],"task,":[28],"but":[29],"most":[31],"cases,":[32],"various":[33],"mismatches,":[34],"such":[35],"as":[36,161],"type":[39,103],"mismatch":[40,47],"(electrolaryngeal":[41],"vs.":[42],"typical)":[43],"or":[44],"speaker":[46,118],"between":[48],"datasets":[50],"used":[51],"each":[53],"stage,":[54],"can":[55],"deteriorate":[56],"conversion":[58],"performance":[59],"framework.":[62],"To":[63],"resolve":[64],"issue,":[66],"we":[67,106],"encoder":[71],"enough":[73],"project":[75],"both":[76],"EL":[77],"typical":[79],"same":[83],"latent":[84],"space,":[85],"while":[86],"still":[87],"being":[88],"able":[89],"extract":[91],"accurate":[92],"information,":[94],"creating":[95],"unified":[97],"representation":[98],"reduce":[100],"mismatch.":[104],"Furthermore,":[105],"introduce":[107],"HuBERT":[108],"output":[109,144],"features":[110],"proposed":[113,148],"reducing":[116],"mismatch,":[119],"making":[120],"it":[121],"possible":[122],"effectively":[124],"large-scale":[127],"parallel":[128],"dataset":[129],"during":[130],"pretraining.":[131],"show":[133],"that":[134],"compared":[135],"conventional":[138],"using":[140,146],"mel-spectrogram":[141],"input":[142],"features,":[145],"enables":[150],"model":[152],"synthesize":[154],"more":[155],"intelligible":[156],"naturally":[158],"sounding":[159],"speech,":[160],"shown":[162],"by":[163],"significant":[165],"16%":[166],"improvement":[167,174],"character":[169],"error":[170],"rate":[171],"0.83":[173],"naturalness":[176],"score.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}