{"id":"https://openalex.org/W4226074601","doi":"https://doi.org/10.21437/interspeech.2022-10043","title":"Investigating Self-supervised Pretraining Frameworks for Pathological Speech Recognition","display_name":"Investigating Self-supervised Pretraining Frameworks for Pathological Speech Recognition","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4226074601","doi":"https://doi.org/10.21437/interspeech.2022-10043"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10043","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10043","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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":true,"raw_author_name":"Lester Phillip Violeta","raw_affiliation_strings":["Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000437338","display_name":"Wen\u2010Chin Huang","orcid":"https://orcid.org/0000-0003-2342-9099"},"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"],"raw_orcid":null,"affiliations":[{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5013549148"],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"45"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962999820709229,"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":0.9962999820709229,"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/T10863","display_name":"Voice and Speech Disorders","score":0.992900013923645,"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"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9409000277519226,"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":0.728447675704956},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5502600073814392},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.467567503452301},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42358189821243286}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.728447675704956},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5502600073814392},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.467567503452301},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42358189821243286}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10043","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10043","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4300000071525574}],"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/G7789893098","display_name":null,"funder_award_id":"JP-MJCR19A3","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W46679369","https://openalex.org/W180052447","https://openalex.org/W811578723","https://openalex.org/W1494198834","https://openalex.org/W1990005915","https://openalex.org/W2063971957","https://openalex.org/W2102113734","https://openalex.org/W2143612262","https://openalex.org/W2171590421","https://openalex.org/W2187089797","https://openalex.org/W2327501763","https://openalex.org/W2627092829","https://openalex.org/W2907121074","https://openalex.org/W2962780374","https://openalex.org/W2964525587","https://openalex.org/W2972943112","https://openalex.org/W3015213852","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3161716720","https://openalex.org/W3174329270","https://openalex.org/W3196321886","https://openalex.org/W3196419581","https://openalex.org/W3197580070","https://openalex.org/W3197712601","https://openalex.org/W3198239978","https://openalex.org/W3198429080","https://openalex.org/W3198446739","https://openalex.org/W3205665014","https://openalex.org/W3209984917","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W3192589309"],"abstract_inverted_index":{"We":[0],"investigate":[1,100],"the":[2,50,65,105,155,164],"performance":[3,117],"of":[4,22,24,34,56,126],"self-supervised":[5,73],"pretraining":[6,49,70,121],"frameworks":[7,102],"on":[8,52,64],"pathological":[9,35,66,127,158],"speech":[10,15,36,58,67,81,93,175],"datasets":[11,37,59],"used":[12,97],"for":[13],"automatic":[14],"recognition":[16],"(ASR).Modern":[17],"end-to-end":[18],"models":[19,110],"require":[20],"thousands":[21],"hours":[23],"data":[25,88,94],"to":[26,43,95,153],"train":[27],"well,":[28],"but":[29],"only":[30,80],"a":[31,53,77],"small":[32],"number":[33,55],"are":[38],"publicly":[39],"available.A":[40],"proven":[41],"solution":[42],"this":[44,152],"problem":[45],"is":[46],"by":[47,168],"first":[48],"model":[51],"huge":[54],"healthy":[57,146],"and":[60,90,108,114,132,176],"then":[61],"fine-tuning":[62],"it":[63],"datasets.One":[68],"new":[69],"framework":[71],"called":[72],"learning":[74],"(SSL)":[75],"trains":[76],"network":[78],"using":[79,111,123],"data,":[82],"providing":[83],"more":[84,92],"flexibility":[85],"in":[86,98,173,181],"training":[87],"requirements":[89],"allowing":[91],"be":[96,154],"pretraining.We":[99],"SSL":[101,139,166],"such":[103],"as":[104],"wav2vec":[106],"2.0":[107],"WavLM":[109],"different":[112,119],"setups":[113],"compare":[115],"their":[116],"with":[118,143,157],"supervised":[120,161],"setups,":[122],"two":[124],"types":[125],"speech,":[128,147],"namely,":[129],"Japanese":[130],"electrolaryngeal":[131,174],"English":[133],"dysarthric.Our":[134],"results":[135],"show":[136],"that":[137],"although":[138],"has":[140],"shown":[141],"success":[142],"minimally":[144],"resourced":[145],"we":[148],"do":[149],"not":[150],"find":[151],"case":[156],"speech.The":[159],"best":[160,165],"setup":[162,167],"outperforms":[163],"13.9%":[169],"character":[170],"error":[171,179],"rate":[172,180],"16.8%":[177],"word":[178],"dysarthric":[182],"speech.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":14}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}