{"id":"https://openalex.org/W4224932945","doi":"https://doi.org/10.1109/icassp43922.2022.9746638","title":"Dysfluency Classification in Stuttered Speech Using Deep Learning for Real-Time Applications","display_name":"Dysfluency Classification in Stuttered Speech Using Deep Learning for Real-Time Applications","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224932945","doi":"https://doi.org/10.1109/icassp43922.2022.9746638"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746638","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5050326510","display_name":"M\u00e9lanie Jouaiti","orcid":"https://orcid.org/0000-0001-6402-0623"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Melanie Jouaiti","raw_affiliation_strings":["University of Waterloo,Department of Electrical and Computer Engineering,Waterloo,ON,Canada,N2L3G5"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo,Department of Electrical and Computer Engineering,Waterloo,ON,Canada,N2L3G5","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059371010","display_name":"Kerstin Dautenhahn","orcid":"https://orcid.org/0000-0002-9263-3897"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kerstin Dautenhahn","raw_affiliation_strings":["University of Waterloo,Department of Electrical and Computer Engineering,Waterloo,ON,Canada,N2L3G5"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo,Department of Electrical and Computer Engineering,Waterloo,ON,Canada,N2L3G5","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6482","last_page":"6486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12684","display_name":"Stuttering Research and Treatment","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12684","display_name":"Stuttering Research and Treatment","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9984999895095825,"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"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9948999881744385,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stuttering","display_name":"Stuttering","score":0.9306595325469971},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.687725841999054},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6626244187355042},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49861979484558105},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.498079776763916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4718962609767914},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3655303418636322},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.23358342051506042},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.1344914734363556},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.0642123818397522}],"concepts":[{"id":"https://openalex.org/C2781371259","wikidata":"https://www.wikidata.org/wiki/Q186676","display_name":"Stuttering","level":2,"score":0.9306595325469971},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.687725841999054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6626244187355042},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49861979484558105},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.498079776763916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4718962609767914},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3655303418636322},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.23358342051506042},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.1344914734363556},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0642123818397522}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746638","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/30766a1b-9830-4631-9e24-2d24d7bc3fde","is_oa":false,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/30766a1b-9830-4631-9e24-2d24d7bc3fde","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"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":"contributionToPeriodical"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7900000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1573786402","https://openalex.org/W1979702444","https://openalex.org/W2074946384","https://openalex.org/W2079075205","https://openalex.org/W2089364955","https://openalex.org/W2215531496","https://openalex.org/W2220261269","https://openalex.org/W2251474395","https://openalex.org/W2794511405","https://openalex.org/W2963729456","https://openalex.org/W2972797781","https://openalex.org/W3015764649","https://openalex.org/W3120691648","https://openalex.org/W3161639065","https://openalex.org/W3168391820","https://openalex.org/W3176579494","https://openalex.org/W3178537356","https://openalex.org/W4287662461","https://openalex.org/W6688856415","https://openalex.org/W6784262730","https://openalex.org/W6797548469","https://openalex.org/W6804597511"],"related_works":["https://openalex.org/W2038216521","https://openalex.org/W2736574136","https://openalex.org/W2565286512","https://openalex.org/W2399955410","https://openalex.org/W2097377227","https://openalex.org/W3126677997","https://openalex.org/W2933782699","https://openalex.org/W1996938627","https://openalex.org/W2365953267","https://openalex.org/W142440765"],"abstract_inverted_index":{"Stuttering":[0],"detection":[1,47],"and":[2,37,48,62,65,72],"classification":[3,49],"are":[4],"important":[5,25],"issues":[6],"in":[7],"speech":[8,29],"therapy":[9],"as":[10],"they":[11],"could":[12],"help":[13],"therapists":[14],"track":[15],"the":[16,59],"progression":[17],"of":[18,50],"patients\u2019":[19],"dysfluencies.":[20],"This":[21],"is":[22,70],"also":[23],"an":[24],"tool":[26],"for":[27,45,74],"technology-assisted":[28],"therapy.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34],"combine":[35],"MFCC":[36],"phoneme":[38],"probabilities":[39],"to":[40],"train":[41],"a":[42],"neural":[43],"network":[44],"stuttering":[46],"four":[51],"dysfluency":[52],"types.":[53],"We":[54],"evaluate":[55],"our":[56,68],"system":[57,69],"on":[58],"UCLASS,":[60],"FluencyBank":[61],"SEP-28K":[63],"datasets":[64],"show":[66],"that":[67],"effective":[71],"suitable":[73],"real-time":[75],"applications.":[76]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}