{"id":"https://openalex.org/W3132874366","doi":"https://doi.org/10.1109/icassp39728.2021.9413520","title":"SEP-28k: A Dataset for Stuttering Event Detection from Podcasts with People Who Stutter","display_name":"SEP-28k: A Dataset for Stuttering Event Detection from Podcasts with People Who Stutter","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3132874366","doi":"https://doi.org/10.1109/icassp39728.2021.9413520","mag":"3132874366"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413520","doi":"https://doi.org/10.1109/icassp39728.2021.9413520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413520","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.12394","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088537496","display_name":"Colin Lea","orcid":"https://orcid.org/0000-0001-7068-3351","observed_orcids":["https://orcid.org/0000-0001-7068-3351"]},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Colin Lea","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091201226","display_name":"Vikramjit Mitra","orcid":"https://orcid.org/0000-0002-2721-3976","observed_orcids":["https://orcid.org/0000-0002-2721-3976"]},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikramjit Mitra","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108136438","display_name":"Aparna Joshi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aparna Joshi","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065814281","display_name":"Sachin S. Kajarekar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sachin Kajarekar","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082603621","display_name":"Jeffrey P. Bigham","orcid":"https://orcid.org/0000-0002-2072-0625","observed_orcids":["https://orcid.org/0000-0002-2072-0625"]},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey P. Bigham","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210153776"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210153776"],"apc_list":null,"apc_paid":null,"fwci":140.6179,"has_fulltext":true,"cited_by_count":113,"citation_normalized_percentile":{"value":0.99927167,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6798","last_page":"6802"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12684","display_name":"Stuttering Research and Treatment","score":0.8817999958992004,"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":0.8817999958992004,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.11249999701976776,"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/T10860","display_name":"Speech and Audio Processing","score":0.00139999995008111,"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/stuttering","display_name":"stuttering","score":0.7400000095367432},{"id":"https://openalex.org/keywords/podcasts","display_name":"podcasts","score":0.6320000290870667},{"id":"https://openalex.org/keywords/speech-annotation","display_name":"speech annotation","score":0.4950000047683716},{"id":"https://openalex.org/keywords/prolongation","display_name":"prolongation","score":0.7390000224113464},{"id":"https://openalex.org/keywords/sound-repetition","display_name":"sound repetition","score":0.8849999904632568},{"id":"https://openalex.org/keywords/word-repetition","display_name":"word repetition","score":0.9779999852180481},{"id":"https://openalex.org/keywords/interjections","display_name":"interjections","score":0.984000027179718},{"id":"https://openalex.org/keywords/training-set-size","display_name":"training data size","score":0.7269999980926514}],"concepts":[{"id":"https://openalex.org/C2781371259","wikidata":"https://www.wikidata.org/wiki/Q186676","display_name":"Stuttering","level":2,"score":0.9022178053855896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6658263802528381},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.6523566842079163},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.637145459651947},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6132514476776123},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5562663674354553},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5538333654403687},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.49451062083244324},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3606451749801636},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35785502195358276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30127352476119995},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.10220226645469666},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.08109483122825623},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413520","doi":"https://doi.org/10.1109/icassp39728.2021.9413520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413520","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.12394","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.12394","pdf_url":"https://arxiv.org/pdf/2102.12394","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,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3132874366","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.12394.pdf","pdf_url":null,"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,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2102.12394","doi":"https://doi.org/10.48550/arxiv.2102.12394","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.12394","pdf_url":null,"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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/w7yw-g732","doi":"https://doi.org/10.17023/w7yw-g732","is_oa":true,"landing_page_url":"https://doi.org/10.17023/w7yw-g732","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.12394","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.12394","pdf_url":"https://arxiv.org/pdf/2102.12394","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,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3132874366.pdf","grobid_xml":"https://content.openalex.org/works/W3132874366.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1482738118","https://openalex.org/W1494198834","https://openalex.org/W1525176859","https://openalex.org/W2079075205","https://openalex.org/W2154074091","https://openalex.org/W2470954754","https://openalex.org/W2511489569","https://openalex.org/W2768920018","https://openalex.org/W2794511405","https://openalex.org/W2888826281","https://openalex.org/W2889371465","https://openalex.org/W2898689885","https://openalex.org/W2902233571","https://openalex.org/W2905960593","https://openalex.org/W2926063217","https://openalex.org/W2953737218","https://openalex.org/W2963351448","https://openalex.org/W2981902467","https://openalex.org/W3009893473","https://openalex.org/W3033127073","https://openalex.org/W3034933717","https://openalex.org/W3043178498","https://openalex.org/W3045297130"],"related_works":["https://openalex.org/W4404386343","https://openalex.org/W4281620586","https://openalex.org/W3198298452","https://openalex.org/W4281909602","https://openalex.org/W4224932945","https://openalex.org/W4402111964","https://openalex.org/W4307784937","https://openalex.org/W7159680656","https://openalex.org/W4403209863","https://openalex.org/W4226439395"],"abstract_inverted_index":{"The":[0],"ability":[1],"to":[2,43],"automatically":[3],"detect":[4],"stuttering":[5],"events":[6],"in":[7,34,60],"speech":[8,11,22,29],"could":[9],"help":[10,20],"pathologists":[12],"track":[13],"an":[14],"individual\u2019s":[15],"fluency":[16],"over":[17,66,136],"time":[18],"or":[19],"improve":[21],"recognition":[23],"systems":[24,48],"for":[25],"people":[26,91,96],"with":[27,70],"atypical":[28],"patterns.":[30],"Despite":[31],"increasing":[32,117],"interest":[33],"this":[35,54],"area,":[36],"existing":[37],"public":[38,86,110],"datasets":[39,141],"are":[40],"too":[41],"small":[42],"build":[44],"generalizable":[45],"dysfluency":[46],"detection":[47,125],"and":[49,81,108,113,129],"lack":[50],"sufficient":[51],"annotations.":[52],"In":[53],"work,":[55],"we":[56],"introduce":[57],"Stuttering":[58],"Events":[59],"Podcasts":[61],"(SEP-28k),":[62],"a":[63,101],"dataset":[64,112],"containing":[65],"28k":[67],"clips":[68,138],"labeled":[69],"five":[71],"event":[72],"types":[73],"including":[74],"blocks,":[75],"prolongations,":[76],"sound":[77],"repetitions,":[78,80],"word":[79],"interjections.":[82],"Audio":[83],"comes":[84],"from":[85,135],"podcasts":[87],"largely":[88],"consisting":[89],"of":[90,103,120],"who":[92,97],"stutter":[93],"interviewing":[94],"other":[95],"stutter.":[98],"We":[99],"benchmark":[100],"set":[102],"acoustic":[104],"models":[105],"on":[106,132],"SEP-28k":[107],"the":[109,118],"FluencyBank":[111],"highlight":[114],"how":[115],"simply":[116],"amount":[119],"training":[121],"data":[122],"improves":[123],"relative":[124],"performance":[126],"by":[127],"28%":[128],"24%":[130],"F1":[131],"each.":[133],"Annotations":[134],"32k":[137],"across":[139],"both":[140],"will":[142],"be":[143],"publicly":[144],"released.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":2}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2021-03-01T00:00:00"}