{"id":"https://openalex.org/W3198806843","doi":"https://doi.org/10.21437/interspeech.2021-168","title":"Adversarial Data Augmentation for Disordered Speech Recognition","display_name":"Adversarial Data Augmentation for Disordered Speech Recognition","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198806843","doi":"https://doi.org/10.21437/interspeech.2021-168","mag":"3198806843"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-168","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-168","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":["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/A5075023049","display_name":"Zengrui Jin","orcid":"https://orcid.org/0000-0002-2637-7880"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zengrui Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003895235","display_name":"Mengzhe Geng","orcid":"https://orcid.org/0000-0002-7886-439X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengzhe Geng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113476082","display_name":"Xurong Xie","orcid":"https://orcid.org/0009-0007-6729-2879"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xurong Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004643540","display_name":"Jianwei Yu","orcid":"https://orcid.org/0000-0002-2449-1436"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianwei Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066070154","display_name":"Shansong Liu","orcid":"https://orcid.org/0000-0001-6202-5615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shansong Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4803","last_page":"4807"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9986000061035156,"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":0.9943000078201294,"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/adversarial-system","display_name":"Adversarial system","score":0.7837315797805786},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.733465313911438},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5635170340538025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3593268394470215}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7837315797805786},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733465313911438},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5635170340538025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3593268394470215}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-168","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-168","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7799999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2903917280","https://openalex.org/W4205705013","https://openalex.org/W2901368259","https://openalex.org/W3198184493","https://openalex.org/W1858327386","https://openalex.org/W4295850094","https://openalex.org/W2368779261","https://openalex.org/W4304891817","https://openalex.org/W3156291593","https://openalex.org/W4386716251"],"abstract_inverted_index":{"Automatic":[0],"recognition":[1,52],"of":[2,30,69,175,182],"disordered":[3,50,76,101],"speech":[4,32,51,79,95],"remains":[5],"a":[6,45,128],"highly":[7],"challenging":[8],"task":[9],"to":[10,23,56,92,100,141],"date.":[11],"The":[12,155],"underlying":[13],"neuro-motor":[14],"conditions,":[15],"often":[16],"compounded":[17],"with":[18],"co-occurring":[19],"physical":[20],"disabilities,":[21],"lead":[22],"the":[24,63,106,110,118,148,166,178],"difficulty":[25],"in":[26,48],"collecting":[27],"large":[28],"quantities":[29],"impaired":[31],"required":[33],"for":[34],"ASR":[35],"system":[36,150,164],"development.":[37],"To":[38],"this":[39],"end,":[40],"data":[41,58,90,113,153],"augmentation":[42,59,91,114,120,169],"techniques":[43,60],"play":[44],"vital":[46],"role":[47],"current":[49],"systems.":[53],"In":[54],"contrast":[55],"existing":[57],"only":[61],"modifying":[62],"speaking":[64],"rate":[65,137],"or":[66,124],"overall":[67,134,173],"shape":[68],"spectral":[70],"contour,":[71],"fine-grained":[72],"spectro-temporal":[73],"differences":[74],"between":[75],"and":[77],"normal":[78,94],"are":[80],"modelled":[81],"using":[82,122,151,165],"deep":[83],"convolutional":[84],"generative":[85],"adversarial":[86,112,168],"networks":[87],"(DCGAN)":[88],"during":[89],"modify":[93],"spectra":[96],"into":[97],"those":[98],"closer":[99],"speech.":[102],"Experiments":[103],"conducted":[104],"on":[105,127,177],"UASpeech":[107,179],"corpus":[108],"suggest":[109],"proposed":[111],"approach":[115,170],"consistently":[116],"outperformed":[117],"baseline":[119,149],"methods":[121],"tempo":[123],"speed":[125],"perturbation":[126],"state-of-the-art":[129],"hybrid":[130],"DNN":[131],"system.":[132],"An":[133],"word":[135],"error":[136],"(WER)":[138],"reduction":[139],"up":[140],"3.05\\%":[142],"(9.7\\%":[143],"relative)":[144],"was":[145],"obtained":[146],"over":[147],"no":[152],"augmentation.":[154],"final":[156],"learning":[157],"hidden":[158],"unit":[159],"contribution":[160],"(LHUC)":[161],"speaker":[162],"adapted":[163],"best":[167],"gives":[171],"an":[172],"WER":[174],"25.89%":[176],"test":[180],"set":[181],"16":[183],"dysarthric":[184],"speakers.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}