{"id":"https://openalex.org/W4392909911","doi":"https://doi.org/10.1109/icassp48485.2024.10446921","title":"UNIT-DSR: Dysarthric Speech Reconstruction System Using Speech Unit Normalization","display_name":"UNIT-DSR: Dysarthric Speech Reconstruction System Using Speech Unit Normalization","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909911","doi":"https://doi.org/10.1109/icassp48485.2024.10446921"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5101632921","display_name":"Yuejiao Wang","orcid":"https://orcid.org/0000-0001-5910-9439"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuejiao Wang","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China","Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xixin Wu","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China","Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","Vocal Engineering Technologies Limited, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Vocal Engineering Technologies Limited, Hong Kong SAR, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068726270","display_name":"Disong Wang","orcid":"https://orcid.org/0000-0001-8481-6880"},"institutions":[{"id":"https://openalex.org/I4210156337","display_name":"Voci (United States)","ror":"https://ror.org/05tdgz517","country_code":"US","type":"company","lineage":["https://openalex.org/I4210156337"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Disong Wang","raw_affiliation_strings":["Vocal Engineering Technologies Limited,Hong Kong SAR,China","Vocal Engineering Technologies Limited, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vocal Engineering Technologies Limited,Hong Kong SAR,China","institution_ids":["https://openalex.org/I4210156337"]},{"raw_affiliation_string":"Vocal Engineering Technologies Limited, Hong Kong SAR, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031382920","display_name":"Lingwei Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lingwei Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China","Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China","Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","Vocal Engineering Technologies Limited, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Vocal Engineering Technologies Limited, Hong Kong SAR, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9116,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.9474979,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"12306","last_page":"12310"},"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/T10863","display_name":"Voice and Speech Disorders","score":0.9994000196456909,"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":0.9983999729156494,"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/speech-recognition","display_name":"Speech recognition","score":0.7273269891738892},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7115873098373413},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6162738800048828},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44093799591064453},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4153573215007782},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.41025087237358093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35604336857795715}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7273269891738892},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7115873098373413},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6162738800048828},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44093799591064453},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4153573215007782},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.41025087237358093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35604336857795715},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W180052447","https://openalex.org/W2152637773","https://openalex.org/W2964243274","https://openalex.org/W2972970915","https://openalex.org/W2973215447","https://openalex.org/W3015707856","https://openalex.org/W3036601975","https://openalex.org/W3082218567","https://openalex.org/W3117682035","https://openalex.org/W3119308075","https://openalex.org/W3140429000","https://openalex.org/W3161018648","https://openalex.org/W3194248215","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W4225289116","https://openalex.org/W4285250921","https://openalex.org/W4287854499","https://openalex.org/W4296068414","https://openalex.org/W4372260139","https://openalex.org/W4372263660","https://openalex.org/W4375868953","https://openalex.org/W6780218876","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2127461790","https://openalex.org/W2069324367","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2114688254","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469"],"abstract_inverted_index":{"Dysarthric":[0],"speech":[1,10,42,84,89,110,134],"reconstruction":[2],"(DSR)":[3],"systems":[4,33],"aim":[5],"to":[6,112,179],"automatically":[7],"convert":[8],"dysarthric":[9,115,181],"into":[11],"normal-sounding":[12],"speech.":[13],"The":[14],"technology":[15],"eases":[16],"communication":[17],"with":[18,45,124],"speakers":[19],"affected":[20],"by":[21,57,61,82],"the":[22,37,40,52,62,69,77,98,114,127,154],"neuromotor":[23],"disorder":[24],"and":[25,65,87,108,137,183,189],"enhances":[26],"their":[27],"social":[28],"inclusion.":[29],"NED-based":[30],"(Neural":[31],"Encoder-Decoder)":[32],"have":[34],"significantly":[35],"improved":[36],"intelligibility":[38],"of":[39,68,79,102,132,165],"reconstructed":[41],"as":[43],"compared":[44,178],"GAN-based":[46],"(Generative":[47],"Adversarial":[48],"Network)":[49],"approaches,":[50,126],"but":[51],"approach":[53],"is":[54,143],"still":[55],"limited":[56],"training":[58,105],"inefficiency":[59],"caused":[60],"cascaded":[63,147],"pipeline":[64],"auxiliary":[66,150],"tasks":[67],"content":[70,116,166],"encoder,":[71],"which":[72,96,142],"may":[73],"in":[74,118,163],"turn":[75],"affect":[76],"quality":[78],"reconstruction.":[80],"Inspired":[81],"self-supervised":[83],"representation":[85],"learning":[86],"discrete":[88,120],"units,":[90],"we":[91],"propose":[92],"a":[93,119,133,138,169],"Unit-DSR":[94,128,159],"system,":[95],"harnesses":[97],"powerful":[99],"domain-adaptation":[100],"capacity":[101],"HuBERT":[103],"for":[104],"efficiency":[106],"improvement":[107],"utilizes":[109],"units":[111],"constrain":[113],"restoration":[117],"linguistic":[121],"space.":[122],"Compared":[123],"NED":[125],"system":[129],"only":[130],"consists":[131],"unit":[135],"normalizer":[136],"Unit":[139],"HiFi-GAN":[140],"vocoder,":[141],"considerably":[144],"simpler":[145],"without":[146],"sub-modules":[148],"or":[149],"tasks.":[151],"Results":[152],"on":[153],"UASpeech":[155],"corpus":[156],"indicate":[157],"that":[158],"outperforms":[160],"competitive":[161],"baselines":[162],"terms":[164],"restoration,":[167],"reaching":[168],"28.2%":[170],"relative":[171],"average":[172],"word":[173],"error":[174],"rate":[175],"reduction":[176],"when":[177],"original":[180],"speech,":[182],"shows":[184],"robustness":[185],"against":[186],"speed":[187],"perturbation":[188],"noise1.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}