{"id":"https://openalex.org/W4375868803","doi":"https://doi.org/10.1109/icassp49357.2023.10095931","title":"Intermediate Fine-Tuning Using Imperfect Synthetic Speech for Improving Electrolaryngeal Speech Recognition","display_name":"Intermediate Fine-Tuning Using Imperfect Synthetic Speech for Improving Electrolaryngeal Speech Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868803","doi":"https://doi.org/10.1109/icassp49357.2023.10095931"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095931","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095931","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/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/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":"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":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9991999864578247,"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":0.9897000193595886,"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/computer-science","display_name":"Computer science","score":0.7903502583503723},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.7224349975585938},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"Fine-tuning","score":0.709496796131134},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6933421492576599},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.621852457523346},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.584236204624176},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.48535099625587463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47354811429977417},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.46079808473587036},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4135548770427704},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06624063849449158}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7903502583503723},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.7224349975585938},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.709496796131134},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6933421492576599},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.621852457523346},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.584236204624176},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.48535099625587463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47354811429977417},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.46079808473587036},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4135548770427704},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06624063849449158},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095931","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095931","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2143612262","https://openalex.org/W2187089797","https://openalex.org/W2627092829","https://openalex.org/W2677089859","https://openalex.org/W2903739847","https://openalex.org/W2907121074","https://openalex.org/W2964525587","https://openalex.org/W2995181338","https://openalex.org/W3096567388","https://openalex.org/W3097777922","https://openalex.org/W3104570641","https://openalex.org/W3161018648","https://openalex.org/W3161669994","https://openalex.org/W3163725792","https://openalex.org/W3196321886","https://openalex.org/W3197712601","https://openalex.org/W3198771897","https://openalex.org/W3198802556","https://openalex.org/W3198806843","https://openalex.org/W3207399576","https://openalex.org/W3209059054","https://openalex.org/W4226074601","https://openalex.org/W4226089239","https://openalex.org/W4385245566","https://openalex.org/W6779469704"],"related_works":["https://openalex.org/W2130553454","https://openalex.org/W3022007134","https://openalex.org/W4317548404","https://openalex.org/W2087783760","https://openalex.org/W4312659495","https://openalex.org/W4380558612","https://openalex.org/W1509924131","https://openalex.org/W3101007570","https://openalex.org/W4387910575","https://openalex.org/W3163689946"],"abstract_inverted_index":{"Research":[0],"on":[1,102,128],"automatic":[2],"speech":[3,78,104],"recognition":[4,38,63],"(ASR)":[5],"systems":[6],"for":[7],"electrolaryngeal":[8,42,103],"speakers":[9],"has":[10],"been":[11],"relatively":[12],"unexplored":[13],"due":[14],"to":[15,35,56,79],"small":[16],"datasets.":[17],"When":[18],"training":[19],"data":[20,52,138],"is":[21,32,53],"lacking":[22],"in":[23,41],"ASR,":[24],"a":[25],"large-scale":[26],"pre-training":[27],"and":[28,50,88],"fine":[29],"tuning":[30],"framework":[31],"often":[33],"sufficient":[34],"achieve":[36],"high":[37],"rates;":[39],"however,":[40],"speech,":[43],"the":[44,48,59,81,86,92,98,111,123,130,135,141],"domain":[45,82],"shift":[46,83],"between":[47,85],"pretraining":[49,87],"fine-tuning":[51,72,125],"too":[54],"large":[55],"over-come,":[57],"limiting":[58],"maximum":[60],"improvement":[61],"of":[62,100,108,134],"rates.":[64],"To":[65],"resolve":[66],"this,":[67],"we":[68,96],"propose":[69],"an":[70],"intermediate":[71,124],"step":[73],"that":[74,113],"uses":[75],"imperfect":[76,93,117,136],"synthetic":[77,94,118,137],"close":[80],"gap":[84],"target":[89],"data.":[90],"Despite":[91],"data,":[95],"show":[97,121],"effectiveness":[99],"this":[101],"datasets,":[105],"with":[106],"improvements":[107],"6.1%":[109],"over":[110],"baseline":[112],"did":[114],"not":[115],"use":[116],"speech.":[119],"Results":[120],"how":[122],"stage":[126],"focuses":[127],"learning":[129],"high-level":[131],"inherent":[132],"features":[133,143],"rather":[139],"than":[140],"low-level":[142],"such":[144],"as":[145],"intelligibility.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}