{"id":"https://openalex.org/W4416798553","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249129","title":"DARS: Dysarthria-Aware Rhythm-Style Synthesis for ASR Enhancement","display_name":"DARS: Dysarthria-Aware Rhythm-Style Synthesis for ASR Enhancement","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798553","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249129"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249129","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/2603.01369","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/A5100640673","display_name":"Xueling Liu","orcid":"https://orcid.org/0000-0001-6478-202X"},"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":"Xueling Liu","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/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/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"]},{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyong Zhang","raw_affiliation_strings":["Huawei Technology,China","University of Science and Technology of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technology,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109297822","display_name":"Yue Zhang","orcid":null},"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"]},{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Zhang","raw_affiliation_strings":["Huawei Technology,China","University of Science and Technology of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technology,China","institution_ids":["https://openalex.org/I2250955327"]},{"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":3,"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":0.41397435,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1104","last_page":"1109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9452000260353088,"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":0.9452000260353088,"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":0.012799999676644802,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.01119999960064888,"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/prosody","display_name":"Prosody","score":0.6014999747276306},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5842000246047974},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.5687000155448914},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5066999793052673},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.453900009393692},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.42590001225471497},{"id":"https://openalex.org/keywords/dysarthria","display_name":"Dysarthria","score":0.4187999963760376},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.38909998536109924}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7843000292778015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.613099992275238},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6014999747276306},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5842000246047974},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.5687000155448914},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5066999793052673},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.453900009393692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43619999289512634},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.42590001225471497},{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.3287000060081482},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.2732999920845032}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249129","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:2603.01369","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.01369","pdf_url":"https://arxiv.org/pdf/2603.01369","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:2603.01369","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.01369","pdf_url":"https://arxiv.org/pdf/2603.01369","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/W4416798553.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2000428399","https://openalex.org/W2016661008","https://openalex.org/W2018363392","https://openalex.org/W2052791563","https://openalex.org/W2137373451","https://openalex.org/W2747874407","https://openalex.org/W2888807255","https://openalex.org/W4223646484","https://openalex.org/W4224931267","https://openalex.org/W4304099317","https://openalex.org/W4312933868","https://openalex.org/W4385245566","https://openalex.org/W4387672817","https://openalex.org/W4387968164","https://openalex.org/W4392904451","https://openalex.org/W4392931276","https://openalex.org/W4399265137","https://openalex.org/W4402111804","https://openalex.org/W4406385914","https://openalex.org/W4410771268","https://openalex.org/W4415432852"],"related_works":[],"abstract_inverted_index":{"Dysarthric":[0],"speech":[1,14,119],"exhibits":[2],"abnormal":[3],"prosody":[4],"and":[5,35,69,85],"significant":[6],"speaker":[7],"variability,":[8],"presenting":[9],"persistent":[10],"challenges":[11],"for":[12],"automatic":[13],"recognition":[15,143],"(ASR).":[16],"While":[17],"text-to-speech":[18],"(TTS)based":[19],"data":[20],"augmentation":[21],"has":[22],"shown":[23],"potential,":[24],"existing":[25],"methods":[26],"often":[27],"fail":[28],"to":[29,134],"accurately":[30],"model":[31],"the":[32,54,92,138],"pathological":[33,86],"rhythm":[34,61,83],"acoustic":[36,87],"style":[37,88],"of":[38,104],"dysarthric":[39,70,109,118],"speech.":[40,110],"To":[41],"address":[42],"this,":[43],"we":[44],"propose":[45],"DARS,":[46],"a":[47,59,74,99,112,123],"dysarthria-aware":[48],"rhythm-style":[49],"synthesis":[50],"framework":[51],"based":[52],"on":[53,91],"Matcha-TTS":[55],"architecture.":[56],"DARS":[57,97,121],"incorporates":[58],"multi-stage":[60],"predictor":[62],"optimized":[63],"by":[64],"contrastive":[65],"preferences":[66],"between":[67],"normal":[68],"speech,":[71],"along":[72],"with":[73,116],"dysarthric-style":[75],"conditional":[76],"flow":[77],"matching":[78],"mechanism,":[79],"jointly":[80],"enhancing":[81,142],"temporal":[82],"reconstruction":[84],"simulation.":[89],"Experiments":[90],"TORGO":[93],"dataset":[94],"demonstrate":[95],"that":[96],"achieves":[98,122],"Mean":[100],"Cepstral":[101],"Distortion":[102],"(MCD)":[103],"4.29,":[105],"closely":[106],"approximating":[107],"real":[108],"Adapting":[111],"Whisper-based":[113],"ASR":[114],"system":[115],"synthetic":[117],"from":[120],"54.22":[124],"%":[125],"relative":[126],"reduction":[127],"in":[128,141],"word":[129],"error":[130],"rate":[131],"(WER)":[132],"compared":[133],"state-of-the-art":[135],"methods,":[136],"demonstrating":[137],"framework's":[139],"effectiveness":[140],"performance.":[144]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-11-28T00:00:00"}