{"id":"https://openalex.org/W3196511136","doi":"https://doi.org/10.21437/interspeech.2021-60","title":"Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognition","display_name":"Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognition","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196511136","doi":"https://doi.org/10.21437/interspeech.2021-60","mag":"3196511136"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-60","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-60","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2201.05554","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003895235","display_name":"Mengzhe Geng","orcid":"https://orcid.org/0000-0002-7886-439X"},"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":"Mengzhe Geng","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066070154","display_name":"Shansong Liu","orcid":"https://orcid.org/0000-0001-6202-5615"},"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":"Shansong Liu","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004643540","display_name":"Jianwei Yu","orcid":"https://orcid.org/0000-0002-2449-1436"},"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":"Jianwei Yu","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113476082","display_name":"Xurong Xie","orcid":"https://orcid.org/0009-0007-6729-2879"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xurong Xie","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045355404","display_name":"Shoukang Hu","orcid":"https://orcid.org/0000-0002-3345-6923"},"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":"Shoukang Hu","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341722","display_name":"Zi Ye","orcid":"https://orcid.org/0000-0003-1002-0315"},"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":"Zi Ye","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075023049","display_name":"Zengrui Jin","orcid":"https://orcid.org/0000-0002-2637-7880"},"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":"Zengrui Jin","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4793","last_page":"4797"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991999864578247,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9966999888420105,"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/speech-recognition","display_name":"Speech recognition","score":0.8023568987846375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6520988345146179},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5706942081451416},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5605209469795227},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4679967761039734},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.447039932012558},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44189009070396423},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3639184236526489}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8023568987846375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6520988345146179},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5706942081451416},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5605209469795227},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4679967761039734},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.447039932012558},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44189009070396423},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3639184236526489},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"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:10.21437/interspeech.2021-60","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-60","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2201.05554","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.05554","pdf_url":"https://arxiv.org/pdf/2201.05554","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:2201.05554","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.05554","pdf_url":"https://arxiv.org/pdf/2201.05554","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"score":0.44999998807907104,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W36841680","https://openalex.org/W116902681","https://openalex.org/W180052447","https://openalex.org/W1524333225","https://openalex.org/W1592672653","https://openalex.org/W1599512239","https://openalex.org/W1877570817","https://openalex.org/W1979651826","https://openalex.org/W1985371235","https://openalex.org/W1989674786","https://openalex.org/W1993409002","https://openalex.org/W2002342963","https://openalex.org/W2009815309","https://openalex.org/W2039844283","https://openalex.org/W2075060370","https://openalex.org/W2079623482","https://openalex.org/W2099621636","https://openalex.org/W2109848220","https://openalex.org/W2127141656","https://openalex.org/W2130739159","https://openalex.org/W2139913691","https://openalex.org/W2143612262","https://openalex.org/W2150907703","https://openalex.org/W2239847623","https://openalex.org/W2250686550","https://openalex.org/W2293992264","https://openalex.org/W2327501763","https://openalex.org/W2396944218","https://openalex.org/W2401277329","https://openalex.org/W2402146185","https://openalex.org/W2403170434","https://openalex.org/W2405176157","https://openalex.org/W2407080277","https://openalex.org/W2512988127","https://openalex.org/W2595767284","https://openalex.org/W2888789389","https://openalex.org/W2888807255","https://openalex.org/W2889334015","https://openalex.org/W2913340405","https://openalex.org/W2936861580","https://openalex.org/W2954911682","https://openalex.org/W2964525587","https://openalex.org/W2981857663","https://openalex.org/W3014690389","https://openalex.org/W3022249883","https://openalex.org/W3095123370","https://openalex.org/W3097909406","https://openalex.org/W3110715635","https://openalex.org/W3111319138","https://openalex.org/W3134043075","https://openalex.org/W3140501190","https://openalex.org/W4292660797","https://openalex.org/W4302557958","https://openalex.org/W4304109163"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W2499802997","https://openalex.org/W2112059504"],"abstract_inverted_index":{"Automatic":[0],"recognition":[1,57,123],"of":[2,13,32,97,115,189,196],"disordered":[3,66,121],"speech":[4,19,33,56,69,98,106,122],"remains":[5],"a":[6,51],"highly":[7],"challenging":[8],"task":[9],"to":[10,102,146],"date.":[11],"Sources":[12],"variability":[14],"commonly":[15],"found":[16],"in":[17,54,73,152],"normal":[18,68],"including":[20],"accent,":[21],"age":[22],"or":[23,158],"gender,":[24],"when":[25],"further":[26,171],"compounded":[27],"with":[28,157],"the":[29,61,128,132,179,192],"underlying":[30],"causes":[31],"impairment":[34],"and":[35,67,78,83,109,119],"varying":[36],"severity":[37],"levels,":[38],"create":[39],"large":[40],"diversity":[41],"among":[42],"speakers.":[43],"To":[44],"this":[45],"end,":[46],"speaker":[47,113,168,175],"adaptation":[48,114,143,169],"techniques":[49],"play":[50],"vital":[52],"role":[53],"current":[55],"systems.":[58,124],"Motivated":[59],"by":[60,94,144],"spectro-temporal":[62,87,134],"level":[63],"differences":[64],"between":[65],"that":[70],"systematically":[71],"manifest":[72],"articulatory":[74],"imprecision,":[75],"decreased":[76],"volume":[77],"clarity,":[79],"slower":[80],"speaking":[81],"rates":[82],"increased":[84],"dysfluencies,":[85],"novel":[86],"subspace":[88],"basis":[89,182],"embedding":[90,183],"deep":[91,135],"features":[92,184],"derived":[93],"SVD":[95],"decomposition":[96],"spectrum":[99],"are":[100],"proposed":[101,133,180],"facilitate":[103],"both":[104],"accurate":[105],"intelligibility":[107],"assessment":[108],"auxiliary":[110],"feature":[111,136],"based":[112,167],"state-of-the-art":[116],"hybrid":[117],"DNN":[118],"end-to-end":[120],"Experiments":[125],"conducted":[126],"on":[127,191],"UASpeech":[129,193],"corpus":[130],"suggest":[131],"adapted":[137,176],"systems":[138],"consistently":[139],"outperformed":[140],"baseline":[141],"i-Vector":[142],"up":[145],"2.63%":[147],"absolute":[148],"(8.6%":[149],"relative)":[150],"reduction":[151],"word":[153],"error":[154],"rate":[155],"(WER)":[156],"without":[159],"data":[160],"augmentation.":[161],"Learning":[162],"hidden":[163],"unit":[164],"contribution":[165],"(LHUC)":[166],"was":[170],"applied.":[172],"The":[173],"final":[174],"system":[177],"using":[178],"spectral":[181],"gave":[185],"an":[186],"overall":[187],"WER":[188],"25.6%":[190],"test":[194],"set":[195],"16":[197],"dysarthric":[198],"speakers":[199]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2021-09-13T00:00:00"}