{"id":"https://openalex.org/W4372267510","doi":"https://doi.org/10.1109/icassp49357.2023.10096552","title":"Evaluating Variants of wav2vec 2.0 on Affective Vocal Burst Tasks","display_name":"Evaluating Variants of wav2vec 2.0 on Affective Vocal Burst Tasks","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267510","doi":"https://doi.org/10.1109/icassp49357.2023.10096552"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5065879041","display_name":"Bagus Tris Atmaja","orcid":"https://orcid.org/0000-0003-1560-2824"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Bagus Tris Atmaja","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology,Tsukuba,Japan","National Institute of Advanced Industrial Science and Technology, Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology,Tsukuba,Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046057045","display_name":"Akira Sasou","orcid":"https://orcid.org/0000-0003-1700-0325"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akira Sasou","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology,Tsukuba,Japan","National Institute of Advanced Industrial Science and Technology, Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology,Tsukuba,Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1086,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77120218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9986000061035156,"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/embedding","display_name":"Embedding","score":0.6962603330612183},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6825417280197144},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6412477493286133},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6263840198516846},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.46156755089759827},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37625691294670105}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6962603330612183},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6825417280197144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6412477493286133},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6263840198516846},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.46156755089759827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37625691294670105},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1412878278","https://openalex.org/W1494198834","https://openalex.org/W1976725440","https://openalex.org/W2008710632","https://openalex.org/W2060691228","https://openalex.org/W2092206588","https://openalex.org/W2094274886","https://openalex.org/W2144005487","https://openalex.org/W2146334809","https://openalex.org/W2239141610","https://openalex.org/W2586291442","https://openalex.org/W2742542661","https://openalex.org/W2905841571","https://openalex.org/W2908510526","https://openalex.org/W2973049979","https://openalex.org/W3036601975","https://openalex.org/W3104763483","https://openalex.org/W3157722160","https://openalex.org/W3158775612","https://openalex.org/W3162538529","https://openalex.org/W3197642003","https://openalex.org/W3198771897","https://openalex.org/W4229039499","https://openalex.org/W4297697709","https://openalex.org/W4304098636","https://openalex.org/W4312097115","https://openalex.org/W4361994820","https://openalex.org/W4362650921","https://openalex.org/W6747784922","https://openalex.org/W6757817989","https://openalex.org/W6780218876","https://openalex.org/W6780226713","https://openalex.org/W6794235820","https://openalex.org/W6809829207","https://openalex.org/W6810693714","https://openalex.org/W6931421704"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2183306018","https://openalex.org/W2549990292","https://openalex.org/W2345479200","https://openalex.org/W2951819827","https://openalex.org/W2342291550","https://openalex.org/W2252747487","https://openalex.org/W4307413935","https://openalex.org/W3158697290","https://openalex.org/W4318718858"],"abstract_inverted_index":{"The":[0],"search":[1],"for":[2,51,66,131,139],"emotional":[3],"biomarkers":[4],"within":[5],"the":[6,33,69,75,83,103,112,122,135,140,145],"human":[7],"voice":[8],"is":[9],"a":[10,63],"challenging":[11],"research":[12],"area.":[13],"Previous":[14],"studies":[15,150],"focused":[16],"on":[17,28,102],"predicting":[18],"affective":[19,29,53,88],"state":[20],"from":[21,128],"speech;":[22],"this":[23],"study":[24],"explores":[25],"various":[26],"tasks":[27,133],"vocal":[30,54,89],"bursts.":[31],"Borrowing":[32],"success":[34],"of":[35,48,71,78,106,137],"self-supervised":[36],"learning":[37],"in":[38,87,121],"automatic":[39],"speech":[40],"recognition,":[41],"we":[42],"extracted":[43],"acoustic":[44,72,85,96,100],"embedding":[45],"using":[46],"variants":[47,81],"wav2vec":[49,79],"2.0":[50,80],"four":[52],"bursts":[55,90],"tasks:":[56],"High,":[57],"Two,":[58],"Culture,":[59],"and":[60,98,110,114,151],"Type.":[61],"Using":[62],"similar":[64],"architecture":[65],"all":[67,132],"tasks,":[68],"evaluation":[70,109],"embeddings":[73,101],"reveals":[74],"potential":[76],"use":[77],"over":[82],"conventional":[84,95],"features":[86,97],"tasks.":[91],"We":[92,143],"evaluated":[93],"both":[94],"these":[99,129],"different":[104],"number":[105],"twenty":[107],"seeds":[108],"reported":[111],"maximum":[113],"average":[115],"scores":[116,127,147],"with":[117,148],"their":[118],"standard":[119],"deviations":[120],"validation":[123],"set.":[124,142],"Three":[125],"high":[126],"validations":[130],"assist":[134],"generation":[136],"predictions":[138],"test":[141,146],"compared":[144],"previous":[149],"obtained":[152],"remarkable":[153],"improvements.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}