{"id":"https://openalex.org/W4408352429","doi":"https://doi.org/10.1109/icassp49660.2025.10889032","title":"Phone-purity Guided Discrete Tokens for Dysarthric Speech Recognition","display_name":"Phone-purity Guided Discrete Tokens for Dysarthric Speech Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352429","doi":"https://doi.org/10.1109/icassp49660.2025.10889032"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5000600118","display_name":"Huimeng Wang","orcid":"https://orcid.org/0000-0002-4280-503X"},"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":"Huimeng Wang","raw_affiliation_strings":["The Chinese University of Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035857878","display_name":"Xurong Xie","orcid":"https://orcid.org/0000-0002-6714-6296"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xurong Xie","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Software,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Software,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003895235","display_name":"Mengzhe Geng","orcid":"https://orcid.org/0000-0002-7886-439X"},"institutions":[{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mengzhe Geng","raw_affiliation_strings":["National Research Council Canada,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Research Council Canada,Canada","institution_ids":["https://openalex.org/I4210159778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026334377","display_name":"Shujie Hu","orcid":"https://orcid.org/0000-0002-8475-4912"},"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":"Shujie Hu","raw_affiliation_strings":["The Chinese University of Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063907750","display_name":"Haoning Xu","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":"Haoning Xu","raw_affiliation_strings":["The Chinese University of Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113020902","display_name":"Youjun Chen","orcid":"https://orcid.org/0000-0002-6484-2325"},"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":"Youjun Chen","raw_affiliation_strings":["The Chinese University of Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101675941","display_name":"Zhaoqing Li","orcid":"https://orcid.org/0000-0001-8649-4934"},"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":"Zhaoqing Li","raw_affiliation_strings":["The Chinese University of Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106406454","display_name":"Jiajun Deng","orcid":"https://orcid.org/0000-0001-8874-4167"},"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":"Jiajun Deng","raw_affiliation_strings":["The Chinese University of Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"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":"Xunying Liu","raw_affiliation_strings":["The Chinese University of Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9919999837875366,"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":0.9919999837875366,"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":0.9830999970436096,"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":0.9739000201225281,"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":0.7718868255615234},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7641031742095947},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7290104031562805},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07088899612426758}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7718868255615234},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7641031742095947},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7290104031562805},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07088899612426758},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:cisti-icist.nrc-cnrc.ca:cistinparc:0457618b-9591-4752-97df-27ce17c1dca2","is_oa":false,"landing_page_url":"https://nrc-publications.canada.ca/eng/view/object/?id=0457618b-9591-4752-97df-27ce17c1dca2","pdf_url":null,"source":{"id":"https://openalex.org/S7407055245","display_name":"NPARC","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":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W180052447","https://openalex.org/W1932968309","https://openalex.org/W2139913691","https://openalex.org/W2396944218","https://openalex.org/W2402146185","https://openalex.org/W2514741789","https://openalex.org/W2936861580","https://openalex.org/W2962780374","https://openalex.org/W3014690389","https://openalex.org/W3095123370","https://openalex.org/W3174329270","https://openalex.org/W3198806843","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221162789","https://openalex.org/W4226132755","https://openalex.org/W4283461667","https://openalex.org/W4297841331","https://openalex.org/W4297841875","https://openalex.org/W4360993686","https://openalex.org/W4362696744","https://openalex.org/W4372263660","https://openalex.org/W4372341972","https://openalex.org/W4385822683","https://openalex.org/W4385822796","https://openalex.org/W4385822966","https://openalex.org/W4385823120","https://openalex.org/W4385823130","https://openalex.org/W4392903673","https://openalex.org/W4392909068","https://openalex.org/W4392909075","https://openalex.org/W4392909760","https://openalex.org/W4393147067","https://openalex.org/W4400275735","https://openalex.org/W4402111644","https://openalex.org/W6668990524","https://openalex.org/W6727249380","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2061937230"],"abstract_inverted_index":{"Discrete":[0],"tokens":[1,39,87],"provide":[2],"compact":[3],"and":[4,20,67,74,95,114,118,156],"domain-adaptable":[5],"representations":[6],"of":[7,54,110,137,169],"speech":[8],"features.":[9,56,147],"However,":[10],"their":[11],"application":[12],"to":[13,40,62,112],"disordered":[14],"speech,":[15],"characterized":[16],"by":[17,141],"articulation":[18],"imprecision":[19],"significant":[21,104],"mismatch":[22],"with":[23,166],"normal":[24],"voice,":[25],"remains":[26],"unexplored.":[27],"To":[28],"this":[29,31],"end,":[30],"paper":[32],"proposes":[33],"novel":[34],"phone-purity":[35,170],"guided":[36],"(PPG)":[37],"discrete":[38,86],"address":[41],"the":[42,64,80,128,167],"weakened":[43],"phonetic":[44],"discrimination":[45],"arising":[46],"during":[47],"unsupervised":[48],"K-means":[49,73],"clustering":[50],"or":[51],"vector":[52],"quantization":[53],"continuous":[55],"Phonetic":[57],"label":[58],"supervision":[59],"is":[60,139],"incorporated":[61],"regularize":[63],"maximum":[65],"likelihood":[66],"reconstruction":[68],"error":[69,106],"costs":[70],"in":[71,153],"standard":[72],"VAE-VQ-based":[75],"token":[76,146],"extraction.":[77],"Experiments":[78],"on":[79],"UASpeech":[81,130],"corpus":[82],"show":[83],"that":[84],"PPG-based":[85],"extracted":[88],"from":[89],"HuBERT":[90],"consistently":[91],"outperform":[92],"hybrid":[93],"TDNN":[94],"End-to-End":[96],"(E2E)":[97],"Conformer":[98],"systems":[99,143],"using":[100,144],"non-PPG":[101],"tokens.":[102],"Statistically":[103],"word":[105],"rate":[107],"(WER)":[108],"reductions":[109],"up":[111],"0.99%":[113],"1.77%":[115],"absolute":[116],"(3.21%":[117],"4.82%":[119],"relative)":[120],"are":[121,150],"achieved":[122],"across":[123],"varying":[124],"codebook":[125],"sizes":[126],"for":[127],"16":[129],"test":[131],"dysarthric":[132],"speakers.":[133],"The":[134],"lowest":[135],"WER":[136],"23.25%":[138],"obtained":[140],"combining":[142],"complementary":[145],"Consistent":[148],"improvements":[149],"also":[151],"observed":[152],"phone":[154],"purity,":[155],"t-SNE":[157],"visualizations":[158],"demonstrate":[159],"sharper":[160],"decision":[161],"boundaries":[162],"between":[163],"K-means/VAE-VQ":[164],"clusters":[165],"introduction":[168],"guidance.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
