{"id":"https://openalex.org/W4304087162","doi":"https://doi.org/10.1145/3503161.3551572","title":"Wav2vec2-based Paralinguistic Systems to Recognise Vocalised Emotions and Stuttering","display_name":"Wav2vec2-based Paralinguistic Systems to Recognise Vocalised Emotions and Stuttering","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304087162","doi":"https://doi.org/10.1145/3503161.3551572"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3551572","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3551572","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3551572","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3551572","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058277119","display_name":"Tam\u00e1s Gr\u00f3sz","orcid":"https://orcid.org/0000-0001-7918-9579"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tam\u00e1s Gr\u00f3sz","raw_affiliation_strings":["Aalto University, Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052292328","display_name":"Dejan Porjazovski","orcid":"https://orcid.org/0000-0002-7219-9042"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Dejan Porjazovski","raw_affiliation_strings":["Aalto University, Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082953089","display_name":"Yaroslav Getman","orcid":"https://orcid.org/0000-0003-4680-8294"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Yaroslav Getman","raw_affiliation_strings":["Aalto University, Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080870546","display_name":"Sudarsana Reddy Kadiri","orcid":"https://orcid.org/0000-0001-5806-3053"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Sudarsana Kadiri","raw_affiliation_strings":["Aalto University, Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043424064","display_name":"Mikko Kurimo","orcid":"https://orcid.org/0000-0001-5278-7974"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Mikko Kurimo","raw_affiliation_strings":["Aalto University, Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":4.2173,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.95489942,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7026","last_page":"7029"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9991999864578247,"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/T12031","display_name":"Speech and dialogue systems","score":0.9991999864578247,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9969000220298767,"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/paralanguage","display_name":"Paralanguage","score":0.9409739971160889},{"id":"https://openalex.org/keywords/stuttering","display_name":"Stuttering","score":0.7802804708480835},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.7216439843177795},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7173393964767456},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5699779391288757},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5587185025215149},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5531121492385864},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48969414830207825},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.447518527507782},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4388887584209442},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35016918182373047},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22924846410751343},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.2186858355998993},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.18867117166519165},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09370845556259155},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.0767831802368164}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.9409739971160889},{"id":"https://openalex.org/C2781371259","wikidata":"https://www.wikidata.org/wiki/Q186676","display_name":"Stuttering","level":2,"score":0.7802804708480835},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.7216439843177795},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7173393964767456},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5699779391288757},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5587185025215149},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5531121492385864},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48969414830207825},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.447518527507782},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4388887584209442},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35016918182373047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22924846410751343},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2186858355998993},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18867117166519165},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09370845556259155},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0767831802368164},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3503161.3551572","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3551572","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3551572","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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:aaltodoc.aalto.fi:123456789/118886","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/72c5bd61-bd3e-43b3-affe-c06ee805500b","pdf_url":"https://research.aalto.fi/files/96487217/Wav2Vec2_Stuttering.pdf","source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1145/3503161.3551572","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3551572","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3551572","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7154773589","display_name":null,"funder_award_id":"345790","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G7231237868","display_name":null,"funder_award_id":"103893","funder_id":"https://openalex.org/F4320322885","funder_display_name":"NordForsk"},{"id":"https://openalex.org/G8267031437","display_name":"Understanding speech and scene with ears and eyes","funder_award_id":"345790","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"},{"id":"https://openalex.org/F4320322885","display_name":"NordForsk","ror":"https://ror.org/05bqzfg94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4304087162.pdf","grobid_xml":"https://content.openalex.org/works/W4304087162.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2746419079","https://openalex.org/W2916113431","https://openalex.org/W2972824267","https://openalex.org/W3082964898","https://openalex.org/W3096383643","https://openalex.org/W3138521398","https://openalex.org/W3152531055","https://openalex.org/W3197642003","https://openalex.org/W3198275944","https://openalex.org/W3198446739","https://openalex.org/W4210836801","https://openalex.org/W4297841770"],"related_works":["https://openalex.org/W1973603352","https://openalex.org/W2348937403","https://openalex.org/W2064370490","https://openalex.org/W2088087094","https://openalex.org/W3166813893","https://openalex.org/W604959964","https://openalex.org/W1483627603","https://openalex.org/W2910013580","https://openalex.org/W2321134590","https://openalex.org/W2163543546"],"abstract_inverted_index":{"With":[0],"the":[1,19,65,103,124,136],"rapid":[2],"advancement":[3],"in":[4],"automatic":[5],"speech":[6],"recognition":[7],"and":[8,69,127],"natural":[9],"language":[10],"understanding,":[11],"a":[12,107],"complementary":[13],"field":[14],"(paralinguistics)":[15],"emerged,":[16],"focusing":[17],"on":[18,43,80,123,135],"non-verbal":[20],"content":[21],"of":[22,35,73,115,119,131],"speech.":[23],"The":[24],"ACM":[25],"Multimedia":[26],"2022":[27],"Computational":[28],"Paralinguistics":[29],"Challenge":[30],"introduced":[31],"several":[32],"exciting":[33],"tasks":[34],"this":[36,39],"field.":[37],"In":[38],"work,":[40],"we":[41],"focus":[42],"tackling":[44],"two":[45],"Sub-Challenges":[46],"using":[47],"modern,":[48],"pre-trained":[49],"models":[50],"called":[51],"wav2vec2.":[52],"Our":[53,99],"experimental":[54],"results":[55,79,84],"demonstrated":[56,85],"that":[57,86],"wav2vec2":[58],"is":[59],"an":[60,111],"excellent":[61],"tool":[62],"for":[63],"detecting":[64],"emotions":[66],"behind":[67],"vocalisations":[68],"recognising":[70],"different":[71],"types":[72],"stutterings.":[74],"Albeit":[75],"they":[76],"achieve":[77],"outstanding":[78],"their":[81],"own,":[82],"our":[83],"wav2vec2-based":[87],"systems":[88,101],"could":[89],"be":[90],"further":[91],"improved":[92],"by":[93,106],"ensembling":[94],"them":[95],"with":[96],"other":[97],"models.":[98],"best":[100],"outperformed":[102],"competition":[104],"baselines":[105],"considerable":[108],"margin,":[109],"achieving":[110],"unweighted":[112],"average":[113],"recall":[114],"44.0":[116],"(absolute":[117,129],"improvement":[118,130],"6.6%":[120],"over":[121,133],"baseline)":[122,134],"Vocalisation":[125],"Sub-Challenge":[126],"62.1":[128],"21.7%":[132],"Stuttering":[137],"Sub-Challenge.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":12}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
