{"id":"https://openalex.org/W4385485018","doi":"https://doi.org/10.1109/icasspw59220.2023.10193018","title":"Deep Investigation of Intermediate Representations in Self-Supervised Learning Models for Speech Emotion Recognition","display_name":"Deep Investigation of Intermediate Representations in Self-Supervised Learning Models for Speech Emotion Recognition","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4385485018","doi":"https://doi.org/10.1109/icasspw59220.2023.10193018"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw59220.2023.10193018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5089591444","display_name":"Zhi Zhu","orcid":"https://orcid.org/0000-0002-1525-9395"},"institutions":[{"id":"https://openalex.org/I4210106389","display_name":"Physical Devices (United States)","ror":"https://ror.org/01nsm8h24","country_code":"US","type":"company","lineage":["https://openalex.org/I4210106389"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhi Zhu","raw_affiliation_strings":["Fairy Devices Inc,Japan","Fairy Devices Inc, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fairy Devices Inc,Japan","institution_ids":["https://openalex.org/I4210106389"]},{"raw_affiliation_string":"Fairy Devices Inc, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054596832","display_name":"Yoshinao Sato","orcid":"https://orcid.org/0000-0003-0657-0269"},"institutions":[{"id":"https://openalex.org/I4210106389","display_name":"Physical Devices (United States)","ror":"https://ror.org/01nsm8h24","country_code":"US","type":"company","lineage":["https://openalex.org/I4210106389"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yoshinao Sato","raw_affiliation_strings":["Fairy Devices Inc,Japan","Fairy Devices Inc, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fairy Devices Inc,Japan","institution_ids":["https://openalex.org/I4210106389"]},{"raw_affiliation_string":"Fairy Devices Inc, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210106389"],"apc_list":null,"apc_paid":null,"fwci":2.465,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.91150442,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9997000098228455,"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":0.9988999962806702,"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/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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/paralanguage","display_name":"Paralanguage","score":0.9703264832496643},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.7406539916992188},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.6877619028091431},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6664212942123413},{"id":"https://openalex.org/keywords/upstream","display_name":"Upstream (networking)","score":0.6043455600738525},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5664635896682739},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5644738674163818},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4898628890514374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4865395128726959},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4787806272506714},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41852355003356934},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35051238536834717},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.09374132752418518},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08759114146232605},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08306306600570679},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07812091708183289}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.9703264832496643},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7406539916992188},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.6877619028091431},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6664212942123413},{"id":"https://openalex.org/C191172861","wikidata":"https://www.wikidata.org/wiki/Q7899321","display_name":"Upstream (networking)","level":2,"score":0.6043455600738525},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5664635896682739},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5644738674163818},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4898628890514374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4865395128726959},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4787806272506714},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41852355003356934},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35051238536834717},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.09374132752418518},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08759114146232605},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08306306600570679},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07812091708183289},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw59220.2023.10193018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2803193013","https://openalex.org/W3036601975","https://openalex.org/W3197580070","https://openalex.org/W3197642003","https://openalex.org/W3197994565","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221162793","https://openalex.org/W4221162872","https://openalex.org/W4225635674","https://openalex.org/W4281492411","https://openalex.org/W4284960025","https://openalex.org/W4319862442","https://openalex.org/W4319862479","https://openalex.org/W4319862658","https://openalex.org/W4319862700","https://openalex.org/W6780218876","https://openalex.org/W6845718520","https://openalex.org/W6845853456","https://openalex.org/W6846177407","https://openalex.org/W6846336121"],"related_works":["https://openalex.org/W3113528484","https://openalex.org/W2241146542","https://openalex.org/W3124058258","https://openalex.org/W2209220924","https://openalex.org/W4214653257","https://openalex.org/W1499733765","https://openalex.org/W3125376000","https://openalex.org/W2031986320","https://openalex.org/W4362671650","https://openalex.org/W2117453324"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"(SSL)":[2],"for":[3,7,14,101],"speech":[4,43],"is":[5,50,106,117],"effective":[6,129],"various":[8],"downstream":[9,30,86],"tasks.":[10],"However,":[11],"the":[12,54,75,85,92,109,112,133,143],"strategies":[13],"selecting":[15],"upstream":[16,26,76,145],"models,":[17],"layer":[18,72,126],"depths":[19,73],"where":[20,47],"intermediate":[21],"representations":[22],"are":[23,96],"passed":[24],"from":[25],"to":[27,42,115],"downstream,":[28],"and":[29,58,66,78,81,123],"model":[31,77,138],"structures":[32],"should":[33],"be":[34],"clarified.":[35],"In":[36],"this":[37],"study,":[38],"SSL":[39],"was":[40],"applied":[41],"emotion":[44],"recognition":[45],"(SER),":[46],"paralinguistic":[48,102,104],"information":[49,105,113,130],"relevant.":[51],"We":[52],"investigated":[53],"wav2vec":[55],"2.0,":[56],"HuBERT,":[57],"WavLM":[59],"models":[60,95,100,141],"on":[61],"two":[62],"SER":[63,116],"datasets:":[64],"IEMOCAP":[65],"RAVDESS.":[67],"Moreover,":[68],"we":[69],"compared":[70,131],"different":[71],"in":[74,84,108,121,142],"examined":[79],"mean":[80],"attention":[82],"pooling":[83],"model.":[87],"Our":[88,136],"experimental":[89],"results":[90],"revealed":[91],"following:":[93],"predictive":[94],"preferred":[97],"over":[98],"contrastive":[99],"tasks;":[103],"incorporated":[107],"middle":[110],"layers;":[111],"relevant":[114],"not":[118],"extremely":[119],"localized":[120],"time;":[122],"a":[124],"single":[125],"includes":[127],"sufficiently":[128],"with":[132],"weighted":[134],"sum.":[135],"best":[137],"outperformed":[139],"previous":[140],"frozen":[144],"condition.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}