{"id":"https://openalex.org/W4388820620","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317318","title":"An Analysis of Personalized Speech Recognition System Development for the Deaf and Hard-of-Hearing","display_name":"An Analysis of Personalized Speech Recognition System Development for the Deaf and Hard-of-Hearing","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388820620","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317318"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":"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":"1862","last_page":"1867"},"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8344653844833374},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7424656748771667},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5569246411323547},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4654195308685303},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4135867953300476},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3266203701496124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2592545747756958}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8344653844833374},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7424656748771667},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5569246411323547},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4654195308685303},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4135867953300476},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3266203701496124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2592545747756958},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W14146365","https://openalex.org/W180052447","https://openalex.org/W811578723","https://openalex.org/W1990005915","https://openalex.org/W2012692872","https://openalex.org/W2018363392","https://openalex.org/W2143612262","https://openalex.org/W2765486990","https://openalex.org/W2765687795","https://openalex.org/W2907121074","https://openalex.org/W2962780374","https://openalex.org/W2964525587","https://openalex.org/W3092028330","https://openalex.org/W3097777922","https://openalex.org/W3161669994","https://openalex.org/W3163793923","https://openalex.org/W3196321886","https://openalex.org/W3197150384","https://openalex.org/W3197712601","https://openalex.org/W3205665014","https://openalex.org/W4226074601","https://openalex.org/W4375868803","https://openalex.org/W4385245566","https://openalex.org/W6745289305","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Deaf":[0],"or":[1],"hard-of-hearing":[2],"(DHH)":[3],"speakers":[4,87],"typically":[5,60],"have":[6],"atypical":[7],"speech":[8,45],"caused":[9],"by":[10,101],"deafness.":[11],"With":[12],"the":[13,40,95,103,124],"growing":[14],"support":[15],"of":[16,42,73,85,97,130],"speech-based":[17],"devices":[18,31],"and":[19,92],"software":[20],"applications,":[21],"more":[22],"work":[23,131],"needs":[24],"to":[25,28,33,137,143,157],"be":[26],"done":[27],"make":[29,144],"these":[30,56],"inclusive":[32],"everyone.":[34],"To":[35],"do":[36,61],"so,":[37],"we":[38,68,134,159],"analyze":[39],"use":[41],"openly-available":[43],"automatic":[44],"recognition":[46],"(ASR)":[47],"tools":[48],"with":[49,127],"a":[50,70,80,117],"DHH":[51,66,82],"Japanese":[52],"speaker":[53,83,119],"dataset.":[54],"As":[55],"out-of-the-box":[57],"ASR":[58,76,148],"models":[59],"not":[62],"perform":[63],"well":[64],"on":[65],"speech,":[67],"provide":[69],"thorough":[71],"analysis":[72],"creating":[74],"personalized":[75,147],"systems.":[77],"We":[78],"collected":[79],"large":[81],"dataset":[84],"four":[86],"totaling":[88],"around":[89],"28.05":[90],"hours":[91],"thoroughly":[93],"analyzed":[94],"performance":[96,126],"different":[98],"training":[99,104],"frameworks":[100],"varying":[102],"data":[105,168],"sizes.":[106],"Our":[107],"findings":[108],"show":[109],"that":[110],"1000":[111,141,153],"utterances":[112,142,154,178],"(or":[113],"1-2":[114],"hours)":[115],"from":[116],"target":[118],"can":[120],"already":[121],"significantly":[122],"improve":[123],"model":[125],"minimal":[128],"amount":[129],"needed,":[132],"thus":[133],"recommend":[135],"researchers":[136],"collect":[138],"at":[139],"least":[140],"an":[145],"efficient":[146],"system.":[149],"In":[150],"cases":[151],"where":[152],"is":[155],"difficult":[156],"collect,":[158],"also":[160],"discover":[161],"significant":[162],"improvements":[163],"in":[164],"using":[165],"previously":[166],"proposed":[167],"augmentation":[169],"techniques":[170],"such":[171],"as":[172],"intermediate":[173],"fine-tuning":[174],"when":[175],"only":[176],"200":[177],"are":[179],"available.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}