{"id":"https://openalex.org/W4416799494","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248992","title":"End-to-End Simultaneous Dysarthric Speech Reconstruction with Frame-Level Adaptor and Multiple Wait-k Knowledge Distillation","display_name":"End-to-End Simultaneous Dysarthric Speech Reconstruction with Frame-Level Adaptor and Multiple Wait-k Knowledge Distillation","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799494","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248992"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11248992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2603.01382","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101925641","display_name":"Minghui Wu","orcid":"https://orcid.org/0000-0001-8179-7119"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghui Wu","raw_affiliation_strings":["University of Science and Technology of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101089791","display_name":"Haitao Tang","orcid":"https://orcid.org/0000-0002-1507-7890"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitao Tang","raw_affiliation_strings":["iFlytek Co., Ltd.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek Co., Ltd.,China","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101319147","display_name":"Jiahuan Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahuan Fan","raw_affiliation_strings":["iFlytek Co., Ltd.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek Co., Ltd.,China","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114188107","display_name":"Ruizhi Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruizhi Liao","raw_affiliation_strings":["iFlytek Co., Ltd.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek Co., Ltd.,China","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053344541","display_name":"Yanyong Zhang","orcid":"https://orcid.org/0000-0001-6520-255X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyong Zhang","raw_affiliation_strings":["University of Science and Technology of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41405992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1092","last_page":"1097"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.953000009059906,"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"}},"topics":[{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.953000009059906,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.015799999237060547,"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/T12684","display_name":"Stuttering Research and Treatment","score":0.0066999997943639755,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical 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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6328999996185303},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5482000112533569},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.47600001096725464},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.43320000171661377},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.4099000096321106},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.3671000003814697},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.34310001134872437}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7432000041007996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7098000049591064},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6328999996185303},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5482000112533569},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.47600001096725464},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.43320000171661377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43070000410079956},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.4099000096321106},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C2780801066","wikidata":"https://www.wikidata.org/wiki/Q323808","display_name":"Hearing aid","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11248992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2603.01382","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.01382","pdf_url":"https://arxiv.org/pdf/2603.01382","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2603.01382","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.01382","pdf_url":"https://arxiv.org/pdf/2603.01382","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4416799494.pdf"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1995193848","https://openalex.org/W2026653933","https://openalex.org/W2143612262","https://openalex.org/W2319453305","https://openalex.org/W2888789389","https://openalex.org/W2963414781","https://openalex.org/W2964525587","https://openalex.org/W3015194534","https://openalex.org/W3015686596","https://openalex.org/W3015707856","https://openalex.org/W3016010032","https://openalex.org/W3097777922","https://openalex.org/W3161873870","https://openalex.org/W3197407562","https://openalex.org/W4225289116","https://openalex.org/W4226021270","https://openalex.org/W4312602417","https://openalex.org/W4372349408","https://openalex.org/W4375850714","https://openalex.org/W4388008051","https://openalex.org/W4392100823","https://openalex.org/W4392902441","https://openalex.org/W4392909911","https://openalex.org/W4402112045","https://openalex.org/W4402112533","https://openalex.org/W4402402589"],"related_works":[],"abstract_inverted_index":{"Dysarthric":[0],"speech":[1,12,22],"reconstruction":[2],"(DSR)":[3],"typically":[4],"employs":[5],"a":[6,101,203,216],"cascaded":[7],"system":[8,114,169],"that":[9],"combines":[10],"automatic":[11],"recognition":[13],"(ASR)":[14],"and":[15,55,82,129,137,214],"sentence-level":[16],"text-to-speech":[17],"(TTS)":[18],"to":[19,34,100,126,148,160,232],"convert":[20],"dysarthric":[21,27],"into":[23],"normally-prosodied":[24],"speech.":[25,88],"However,":[26,62],"individuals":[28],"often":[29],"speak":[30],"more":[31],"slowly,":[32],"leading":[33],"excessively":[35],"long":[36],"response":[37,173],"times":[38],"in":[39,45,77,226],"such":[40],"systems,":[41],"rendering":[42],"them":[43],"impractical":[44],"long-speech":[46],"scenarios.":[47],"Cascaded":[48],"DSR":[49,113],"systems":[50],"based":[51],"on":[52,182],"streaming":[53],"ASR":[54,81,128,149],"incremental":[56,91],"TTS":[57,92,147,156],"can":[58],"help":[59],"reduce":[60],"latency.":[61],"patients":[63],"with":[64,115,185],"differing":[65],"dysarthria":[66],"severity":[67],"exhibit":[68],"substantial":[69],"pronunciation":[70],"variability":[71],"for":[72],"the":[73,84,143,198,233],"same":[74],"text,":[75],"resulting":[76],"poor":[78,95],"robustness":[79],"of":[80,86,146,175,191,208],"limiting":[83],"intelligibility":[85],"reconstructed":[87],"In":[89,105],"addition,":[90],"suffers":[93],"from":[94],"prosodic":[96,162],"feature":[97],"prediction":[98],"due":[99],"limited":[102],"receptive":[103],"field.":[104],"this":[106],"study,":[107],"we":[108],"propose":[109],"an":[110,171,186],"end-to-end":[111],"simultaneous":[112],"two":[116],"key":[117],"innovations:":[118],"1)":[119],"A":[120,152],"frame-level":[121],"adaptor":[122],"module":[123,139,157],"is":[124,158,237],"introduced":[125],"bridge":[127],"TTS.":[130],"By":[131],"employing":[132],"explicitimplicit":[133],"semantic":[134],"information":[135],"fusion":[136],"joint":[138],"training,":[140],"it":[141,201],"enhances":[142],"error":[144,228],"tolerance":[145],"outputs.":[150],"2)":[151],"multiple":[153],"wait-k":[154],"autoregressive":[155],"designed":[159],"mitigate":[161],"degradation":[163],"via":[164],"multi-view":[165],"knowledge":[166],"distillation.":[167],"Our":[168,235],"has":[170],"average":[172,187],"time":[174],"<tex":[176,192,209,217],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[177,193,210,218],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{1.":[178],"0":[179],"3}$</tex>":[180],"seconds":[181],"Tesla":[183],"A100,":[184],"real-time":[188],"factor":[189],"(RTF)":[190],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{0.":[194],"7":[195],"1}$</tex>.":[196],"On":[197],"UASpeech":[199],"dataset,":[200],"attains":[202],"mean":[204],"opinion":[205],"score":[206],"(MOS)":[207],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{4.":[211],"6":[212],"7}$</tex>":[213],"demonstrates":[215],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{5":[219],"4.":[220],"2":[221],"5":[222],"\\%}$</tex>":[223],"relative":[224],"reduction":[225],"word":[227],"rate":[229],"(WER)":[230],"compared":[231],"state-of-the-art.":[234],"demo":[236],"available":[238],"at:":[239],"https://wflrz123.github.io/":[240]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-11-28T00:00:00"}