{"id":"https://openalex.org/W4304098255","doi":"https://doi.org/10.1145/3503161.3551588","title":"End-to-End and Self-Supervised Learning for ComParE 2022 Stuttering Sub-Challenge","display_name":"End-to-End and Self-Supervised Learning for ComParE 2022 Stuttering Sub-Challenge","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304098255","doi":"https://doi.org/10.1145/3503161.3551588"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3551588","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3551588","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5064868877","display_name":"Shakeel A. Sheikh","orcid":"https://orcid.org/0000-0001-9822-8422"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Shakeel A. Sheikh","raw_affiliation_strings":["Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079693142","display_name":"Md Sahidullah","orcid":"https://orcid.org/0000-0002-0624-2903"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Md Sahidullah","raw_affiliation_strings":["Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044130608","display_name":"Slim Ouni","orcid":"https://orcid.org/0000-0001-5286-7368"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Slim Ouni","raw_affiliation_strings":["Universit\u00e9 De Lorraine, CNRS, Inria, LORIA, Nancy, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 De Lorraine, CNRS, Inria, LORIA, Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055076003","display_name":"Fabrice Hirsch","orcid":"https://orcid.org/0000-0002-5646-4651"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210095130","display_name":"Universit\u00e9 Paul-Val\u00e9ry Montpellier","ror":null,"country_code":"FR","type":null,"lineage":["https://openalex.org/I4210095130"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fabrice Hirsch","raw_affiliation_strings":["Universit\u00e9 de Paul-Val\u00e9ry, CNRS, Montpellier, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Paul-Val\u00e9ry, CNRS, Montpellier, France","institution_ids":["https://openalex.org/I4210095130","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064868877"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838","https://openalex.org/I90183372"],"apc_list":null,"apc_paid":null,"fwci":0.3118,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.51222797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7104","last_page":"7108"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962999820709229,"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":0.9962999820709229,"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/T12684","display_name":"Stuttering Research and Treatment","score":0.9912999868392944,"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":0.9878000020980835,"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/computer-science","display_name":"Computer science","score":0.7025095224380493},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6918689012527466},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6570513844490051},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6283719539642334},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.6124669909477234},{"id":"https://openalex.org/keywords/stuttering","display_name":"Stuttering","score":0.5884420871734619},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5765098333358765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5572935938835144},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5415407419204712},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5077953934669495},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.44392716884613037},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.39503368735313416},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3830738663673401},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3027940094470978}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7025095224380493},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6918689012527466},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6570513844490051},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6283719539642334},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.6124669909477234},{"id":"https://openalex.org/C2781371259","wikidata":"https://www.wikidata.org/wiki/Q186676","display_name":"Stuttering","level":2,"score":0.5884420871734619},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5765098333358765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5572935938835144},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5415407419204712},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5077953934669495},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.44392716884613037},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.39503368735313416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3830738663673401},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3027940094470978},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3551588","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3551588","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger"}],"awards":[{"id":"https://openalex.org/G1459882349","display_name":null,"funder_award_id":"18-CE36-0008-03","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1483627603","https://openalex.org/W1503398984","https://openalex.org/W1545884232","https://openalex.org/W2117671523","https://openalex.org/W2166659155","https://openalex.org/W2402146185","https://openalex.org/W2746419079","https://openalex.org/W2746963436","https://openalex.org/W2973049979","https://openalex.org/W2997399314","https://openalex.org/W2997591727","https://openalex.org/W3023212902","https://openalex.org/W3137249133","https://openalex.org/W3207924272","https://openalex.org/W3212886388","https://openalex.org/W4304098636"],"related_works":["https://openalex.org/W2348937403","https://openalex.org/W2088087094","https://openalex.org/W2043322848","https://openalex.org/W604959964","https://openalex.org/W1483627603","https://openalex.org/W2163543546","https://openalex.org/W2103044274","https://openalex.org/W1877441159","https://openalex.org/W1968127204","https://openalex.org/W2122095792"],"abstract_inverted_index":{"In":[0,29],"this":[1],"paper,":[2],"we":[3,31,51,95,125],"present":[4],"end-to-end":[5],"and":[6,69,73,82,113,117,146,150],"speech":[7],"embedding":[8,49],"based":[9,61],"systems":[10],"trained":[11],"in":[12,18],"a":[13,65,141],"self-supervised":[14,60],"fashion":[15],"to":[16],"participate":[17],"the":[19,26,33,36,45,88,109,122,128,133,138],"ACM":[20],"Multimedia":[21],"2022":[22],"ComParE":[23],"Challenge,":[24],"specifically":[25],"stuttering":[27,41],"sub-challenge.":[28],"particular,":[30],"exploit":[32],"embeddings":[34,100],"from":[35],"pre-trained":[37],"Wav2Vec2.0":[38,136],"model":[39],"for":[40,56],"detection":[42],"(SD)":[43],"on":[44,71,115,148],"KSoF":[46],"dataset.":[47],"After":[48],"extraction,":[50],"benchmark":[52],"with":[53,101],"several":[54],"methods":[55],"SD.":[57],"Our":[58],"proposed":[59],"SD":[62],"system":[63],"achieves":[64],"UAR":[66,110],"of":[67,111,135,144],"36.9%":[68],"41.0%":[70],"validation":[72,116,149],"test":[74,118,151],"sets":[75,119,152],"respectively,":[76],"which":[77],"is":[78],"31.32%":[79],"(validation":[80],"set)":[81,85],"1.49%":[83],"(test":[84],"higher":[86],"than":[87],"best":[89],"(DeepSpectrum)":[90],"challenge":[91],"baseline":[92],"(CBL).":[93],"Moreover,":[94],"show":[96],"that":[97,127],"concatenating":[98],"layer":[99],"Mel-frequency":[102],"cepstral":[103],"coefficients":[104],"(MFCCs)":[105],"features":[106],"further":[107],"improves":[108],"33.81%":[112],"5.45%":[114],"respectively":[120],"over":[121],"CBL.":[123],"Finally,":[124],"demonstrate":[126],"summing":[129],"information":[130],"across":[131],"all":[132],"layers":[134],"surpasses":[137],"CBL":[139],"by":[140],"relative":[142],"margin":[143],"45.91%":[145],"5.69%":[147],"respectively.":[153]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}