{"id":"https://openalex.org/W4397026467","doi":"https://doi.org/10.1109/taslp.2024.3402557","title":"Pretraining and Adaptation Techniques for Electrolaryngeal Speech Recognition","display_name":"Pretraining and Adaptation Techniques for Electrolaryngeal Speech Recognition","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4397026467","doi":"https://doi.org/10.1109/taslp.2024.3402557"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3402557","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3402557","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10533680.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10533680.pdf","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":["Graduate School of Informatics, Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9118-2994","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, 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":["Graduate School of Informatics, Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0009-0002-6564-4571","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, 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":["Graduate School of Informatics, Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3172-3335","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, 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":["Information Technology Center, Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8146-1279","affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Nagoya, 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":0.8335,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75976453,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"32","issue":null,"first_page":"2777","last_page":"2789"},"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":0.9995999932289124,"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":0.9934999942779541,"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/computer-science","display_name":"Computer science","score":0.7787036895751953},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6890400648117065},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6410032510757446},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5211513042449951},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5108311176300049},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4917026162147522},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4537515938282013},{"id":"https://openalex.org/keywords/negative-transfer","display_name":"Negative transfer","score":0.4285416603088379},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35787737369537354},{"id":"https://openalex.org/keywords/first-language","display_name":"First language","score":0.16837769746780396},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08457714319229126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7787036895751953},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6890400648117065},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6410032510757446},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5211513042449951},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5108311176300049},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4917026162147522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4537515938282013},{"id":"https://openalex.org/C2779178101","wikidata":"https://www.wikidata.org/wiki/Q6987274","display_name":"Negative transfer","level":3,"score":0.4285416603088379},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35787737369537354},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.16837769746780396},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08457714319229126},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3402557","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3402557","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10533680.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2024.3402557","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3402557","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10533680.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"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"}],"funders":[{"id":"https://openalex.org/F4320311405","display_name":"Japan Agency for Medical Research and Development","ror":"https://ror.org/004rtk039"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4397026467.pdf"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W180052447","https://openalex.org/W811578723","https://openalex.org/W1974487811","https://openalex.org/W1990005915","https://openalex.org/W2012122078","https://openalex.org/W2101632997","https://openalex.org/W2127141656","https://openalex.org/W2134315375","https://openalex.org/W2143612262","https://openalex.org/W2187089797","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2627092829","https://openalex.org/W2677089859","https://openalex.org/W2741920812","https://openalex.org/W2765486990","https://openalex.org/W2887280559","https://openalex.org/W2896457183","https://openalex.org/W2903739847","https://openalex.org/W2951099770","https://openalex.org/W2962780374","https://openalex.org/W2964525587","https://openalex.org/W2973213910","https://openalex.org/W2995181338","https://openalex.org/W2997090102","https://openalex.org/W3015338123","https://openalex.org/W3096567388","https://openalex.org/W3097777922","https://openalex.org/W3104570641","https://openalex.org/W3161669994","https://openalex.org/W3163725792","https://openalex.org/W3163793923","https://openalex.org/W3196321886","https://openalex.org/W3197580070","https://openalex.org/W3197712601","https://openalex.org/W3198429080","https://openalex.org/W3198771897","https://openalex.org/W3198802556","https://openalex.org/W3198806843","https://openalex.org/W3207399576","https://openalex.org/W3209059054","https://openalex.org/W4224931267","https://openalex.org/W4226074601","https://openalex.org/W4226089239","https://openalex.org/W4322614701","https://openalex.org/W4375868803","https://openalex.org/W4385245566","https://openalex.org/W4388820620","https://openalex.org/W6675365184","https://openalex.org/W6745289305","https://openalex.org/W6755862295","https://openalex.org/W6779469704","https://openalex.org/W6780218876","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2379014936","https://openalex.org/W2901328199","https://openalex.org/W2348786013","https://openalex.org/W2350461028","https://openalex.org/W2382190840","https://openalex.org/W2309273277","https://openalex.org/W2354314391","https://openalex.org/W2061937230","https://openalex.org/W1187351618","https://openalex.org/W1574295218"],"abstract_inverted_index":{"We":[0,54],"investigate":[1],"state-of-the-art":[2],"automatic":[3],"speech":[4,89,194],"recognition":[5],"(ASR)":[6],"systems":[7],"and":[8,42,70,135,139,171,192],"provide":[9],"thorough":[10],"investigations":[11],"on":[12,146],"training":[13],"methods":[14],"to":[15,18,28,48,107,110],"adapt":[16],"them":[17],"low-resourced":[19,30],"electrolaryngeal":[20],"(EL)":[21],"datasets.":[22],"Transfer":[23],"learning":[24,66],"is":[25,45,90],"often":[26],"sufficient":[27],"resolve":[29],"problems;":[31],"however,":[32],"in":[33,130],"EL":[34,71,83,153,164,169,175,182,191],"speech,":[35],"the":[36,40,51,60,68,94,101,111,120,126,142,148,152,159,185],"domain":[37,61,187],"shift":[38,62],"between":[39,67,161,189],"pretraining":[41],"fine-tuning":[43,77,144],"data":[44,176],"too":[46],"large":[47],"overcome,":[49],"limiting":[50],"ASR":[52],"performance.":[53],"propose":[55],"a":[56,162,167],"method":[57,98],"of":[58,96,151],"reducing":[59],"gap":[63,188],"during":[64],"transfer":[65,115],"healthy":[69],"datasets":[72],"by":[73,99,105],"conducting":[74],"an":[75],"intermediate":[76,143],"task":[78,132],"that":[79,141,173],"uses":[80],"imperfectly":[81],"synthesized":[82],"speech.":[84],"Although":[85],"using":[86,113],"imperfect":[87],"synthetic":[88],"non-intuitive,":[91],"we":[92,123,156],"proved":[93],"effectiveness":[95],"this":[97],"decreasing":[100],"character":[102],"error":[103],"rate":[104],"up":[106],"6.1%":[108],"compared":[109],"baselines":[112],"naive":[114],"learning.":[116],"To":[117],"further":[118,124],"understand":[119],"model's":[121],"behavior,":[122],"analyze":[125],"produced":[127],"latent":[128],"spaces":[129],"each":[131],"through":[133],"linguistic":[134],"identity":[136],"proxy":[137],"tasks":[138],"find":[140,172],"focuses":[145],"identifying":[147],"voicing":[149],"characteristics":[150],"speakers.":[154],"Moreover,":[155],"also":[157],"show":[158],"differences":[160,179],"simulated":[163,174],"speaker":[165,170],"from":[166,180],"real":[168,181,190],"has":[177],"pronunciation":[178],"data,":[183],"showing":[184],"huge":[186],"other":[193],"data.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}