{"id":"https://openalex.org/W4304014189","doi":"https://doi.org/10.1145/3503161.3551606","title":"Audio Features from the Wav2Vec 2.0 Embeddings for the ACM Multimedia 2022 Stuttering Challenge","display_name":"Audio Features from the Wav2Vec 2.0 Embeddings for the ACM Multimedia 2022 Stuttering Challenge","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304014189","doi":"https://doi.org/10.1145/3503161.3551606"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3551606","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3551606","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":"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/A5024297346","display_name":"Claude Montaci\u00e9","orcid":"https://orcid.org/0000-0003-1936-8975"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Claude Montaci\u00e9","raw_affiliation_strings":["Sorbonne University, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne University, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054313891","display_name":"Marie-Jos\u00e9 Caraty","orcid":"https://orcid.org/0009-0003-4411-4800"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marie-Jos\u00e9 Caraty","raw_affiliation_strings":["Paris University, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Paris University, Paris, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051772430","display_name":"Nikola Lackovi\u0107","orcid":"https://orcid.org/0000-0003-3739-1220"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikola Lackovic","raw_affiliation_strings":["Malakof Humanis, Paris, France","Malakof Humanis - IA and Data Visualisation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Malakof Humanis, Paris, France","institution_ids":[]},{"raw_affiliation_string":"Malakof Humanis - IA and Data Visualisation","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7981,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.95996333,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7195","last_page":"7199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12684","display_name":"Stuttering Research and Treatment","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9993000030517578,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6628507971763611},{"id":"https://openalex.org/keywords/stuttering","display_name":"Stuttering","score":0.609478771686554},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5770576000213623},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5726317167282104},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4900768995285034},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4267624616622925},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3808048367500305},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35331469774246216},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06915906071662903}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6628507971763611},{"id":"https://openalex.org/C2781371259","wikidata":"https://www.wikidata.org/wiki/Q186676","display_name":"Stuttering","level":2,"score":0.609478771686554},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5770576000213623},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5726317167282104},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4900768995285034},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4267624616622925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3808048367500305},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35331469774246216},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06915906071662903},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3503161.3551606","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3551606","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"},{"id":"pmh:oai:HAL:hal-03945972v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03945972","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MM '22: The 30th ACM International Conference on Multimedia, Oct 2022, Lisboa Portugal, France. pp.7195-7199, ⟨10.1145/3503161.3551606⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.550000011920929},{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2050935816","https://openalex.org/W2062075567","https://openalex.org/W2079075205","https://openalex.org/W2090777335","https://openalex.org/W2101234009","https://openalex.org/W2127726465","https://openalex.org/W2288676002","https://openalex.org/W2519174895","https://openalex.org/W2794511405","https://openalex.org/W2993334576","https://openalex.org/W3015764649","https://openalex.org/W3036601975","https://openalex.org/W3176579494","https://openalex.org/W3197642003","https://openalex.org/W4224932945","https://openalex.org/W4235649620","https://openalex.org/W4297841747","https://openalex.org/W4304098636","https://openalex.org/W6675354045"],"related_works":["https://openalex.org/W2348937403","https://openalex.org/W2088087094","https://openalex.org/W2606084965","https://openalex.org/W604959964","https://openalex.org/W2043322848","https://openalex.org/W1483627603","https://openalex.org/W2103044274","https://openalex.org/W2163543546","https://openalex.org/W2036832189","https://openalex.org/W4388321867"],"abstract_inverted_index":{"The":[0],"ACM":[1],"Multimedia":[2],"2022":[3],"Stuttering":[4],"Challenge":[5,229],"is":[6],"to":[7,38,65,208,223],"determine":[8],"the":[9,32,52,72,84,91,103,114,126,159,209,215,219,224,228],"stuttering-related":[10,19],"class":[11],"of":[12,51,55,87,106,145,206,227],"a":[13,49,143],"speech":[14,181],"segment.":[15],"There":[16],"are":[17],"seven":[18],"classes":[20],"and":[21,90,122,155,185,193,212],"an":[22,204],"eighth":[23],"garbage":[24],"class.":[25],"For":[26],"this":[27],"purpose,":[28],"we":[29,60],"have":[30,139,165,182,202],"investigated":[31],"Wav2Vec":[33],"2.0":[34],"deep":[35],"neural":[36],"network":[37],"extract":[39],"audio":[40,70,136,146,151,162,170,175],"features":[41,152,176],"from":[42,83,102,168],"Transformer":[43,88,107],"embeddings.":[44,108],"Experiments":[45,201],"were":[46],"conducted":[47],"on":[48,218],"part":[50],"Kassel":[53],"State":[54],"Fluency":[56],"Corpus":[57],"(KSoF).":[58],"First,":[59],"introduced":[61],"21":[62],"functionals":[63,110],"allowing":[64],"define":[66],"two":[67,174],"large":[68],"composite":[69,135],"feature:":[71],"first":[73,210],"one":[74,93,211,217],"set":[75,80,98,138,144,190,198,221],"called":[76,94],"W2V2":[77,95,187,194],"Basic":[78],"audio-feature":[79,97,189,197],"(193,536":[81],"features)":[82,101,192],"Base":[85],"version":[86,105],"embeddings":[89],"second":[92,216],"Large":[96,104,195],"(516,":[99],"096":[100],"Some":[109],"aim":[111,124],"at":[112,125],"estimating":[113],"spatial":[115],"variability":[116,128],"(e.g.,":[117,129],"mean,":[118],"standard":[119],"deviation,":[120],"quartiles)":[121],"others":[123],"temporal":[127],"linear":[130],"regression":[131],"slope).":[132],"Then,":[133,158],"each":[134],"feature":[137,147,163,171],"been":[140,166,183],"splitted":[141],"into":[142],"sets":[148,164,177],"by":[149,153,156],"grouping":[150],"functional":[154],"layer.":[157],"most":[160],"discriminant":[161],"selected":[167],"these":[169],"sets.":[172],"Finally,":[173],"specializing":[178],"in":[179],"stuttering":[180],"developed":[184],"assessed:":[186],"Advanced":[188,196],"(9,984":[191],"(15,360":[199],"features).":[200],"shown":[203],"improvement":[205],"9.3%":[207],"11.9%":[213],"for":[214],"Test":[220],"compared":[222],"official":[225],"baseline":[226],"(40.4%).":[230]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}