{"id":"https://openalex.org/W3163599377","doi":"https://doi.org/10.1109/icassp39728.2021.9414614","title":"Multi-Task Transformer with Input Feature Reconstruction for Dysarthric Speech Recognition","display_name":"Multi-Task Transformer with Input Feature Reconstruction for Dysarthric Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163599377","doi":"https://doi.org/10.1109/icassp39728.2021.9414614","mag":"3163599377"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5032101339","display_name":"Chaoyue Ding","orcid":"https://orcid.org/0009-0000-0161-4838"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chaoyue Ding","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047846625","display_name":"Shiliang Sun","orcid":"https://orcid.org/0000-0001-7069-3752"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiliang Sun","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065846668","display_name":"Jing Zhao","orcid":"https://orcid.org/0000-0003-0158-5330"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhao","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032101339"],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":0.56,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.72646621,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7318","last_page":"7322"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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/dysarthria","display_name":"Dysarthria","score":0.8629679679870605},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7749661207199097},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.696772575378418},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6531303524971008},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5730912089347839},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.505364716053009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42182695865631104},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.4158397912979126},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09908166527748108},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09146496653556824}],"concepts":[{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.8629679679870605},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7749661207199097},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.696772575378418},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6531303524971008},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5730912089347839},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.505364716053009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42182695865631104},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4158397912979126},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09908166527748108},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09146496653556824},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321659","display_name":"Shanghai Education Development Foundation","ror":"https://ror.org/02kq92y46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W180052447","https://openalex.org/W1494198834","https://openalex.org/W2018363392","https://openalex.org/W2087891313","https://openalex.org/W2547793174","https://openalex.org/W2624871570","https://openalex.org/W2627092829","https://openalex.org/W2749128330","https://openalex.org/W2792759062","https://openalex.org/W2888789389","https://openalex.org/W2889162002","https://openalex.org/W2889469831","https://openalex.org/W2892009249","https://openalex.org/W2936123380","https://openalex.org/W2945078028","https://openalex.org/W2952711665","https://openalex.org/W2962780374","https://openalex.org/W2963403868","https://openalex.org/W2964243274","https://openalex.org/W2972389417","https://openalex.org/W2973016613","https://openalex.org/W3013783381","https://openalex.org/W3015337486","https://openalex.org/W4385245566","https://openalex.org/W6739365718","https://openalex.org/W6739901393","https://openalex.org/W6754299077","https://openalex.org/W6762242920","https://openalex.org/W6775988622"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W2011227383","https://openalex.org/W2065606036","https://openalex.org/W3016124757","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W3034520363","https://openalex.org/W4307784074"],"abstract_inverted_index":{"Dysarthria":[0],"is":[1],"a":[2,47],"motor":[3],"speech":[4,31,81,85],"disorder":[5],"caused":[6],"by":[7],"damage":[8],"to":[9,35,78,95,111],"the":[10,13,18,36,59,65,70,97,113,124],"part":[11],"of":[12,21,62,86,100,117,136],"nervous":[14],"system":[15],"that":[16,123],"controls":[17],"physical":[19],"production":[20],"speech.":[22,119],"It":[23],"poses":[24],"great":[25],"challenges":[26],"in":[27],"building":[28],"robust":[29],"dysarthric":[30,91,118],"recognition":[32],"(DSR)":[33],"due":[34],"high":[37],"inter-":[38],"and":[39,64],"intra-speaker":[40],"variability.":[41],"To":[42],"this":[43],"end,":[44],"we":[45,104],"propose":[46],"multi-task":[48],"Transformer":[49],"with":[50,133],"input":[51],"feature":[52],"reconstruction":[53,67],"as":[54],"an":[55,106],"auxiliary":[56,66,75],"task,":[57],"where":[58],"main":[60],"task":[61,68,76],"DSR":[63],"share":[69],"same":[71],"encoder":[72],"network.":[73],"The":[74],"aims":[77],"reconstruct":[79],"clear":[80],"features":[82],"from":[83],"corrupted":[84],"healthy":[87],"speakers":[88,92,132],"(intra-domain)":[89],"or":[90],"(cross-domain).":[93],"Further,":[94],"alleviate":[96],"imbalanced":[98],"distribution":[99],"dysarthria":[101],"data":[102],"sets,":[103],"devise":[105],"adaptive":[107],"rebalance":[108],"sampling":[109,115],"scheme":[110],"improve":[112],"utterance":[114],"frequency":[116],"Experimental":[120],"results":[121],"show":[122],"proposed":[125],"model":[126],"considerably":[127],"outperforms":[128],"other":[129],"baselines":[130],"across":[131],"varying":[134],"severity":[135],"dysarthria.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
