{"id":"https://openalex.org/W4388692838","doi":"https://doi.org/10.1109/sped59241.2023.10314932","title":"An analysis of large speech models-based representations for speech emotion recognition","display_name":"An analysis of large speech models-based representations for speech emotion recognition","publication_year":2023,"publication_date":"2023-10-25","ids":{"openalex":"https://openalex.org/W4388692838","doi":"https://doi.org/10.1109/sped59241.2023.10314932"},"language":"en","primary_location":{"id":"doi:10.1109/sped59241.2023.10314932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped59241.2023.10314932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","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/A5093266198","display_name":"Adrian Bogdan St\u00e2nea","orcid":null},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Adrian Bogdan St\u00e2nea","raw_affiliation_strings":["Technical University of Cluj-Napoca,Communications Department,Romania","Communications Department, Technical University of Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca,Communications Department,Romania","institution_ids":["https://openalex.org/I158333966"]},{"raw_affiliation_string":"Communications Department, Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093266199","display_name":"Vlad Strile\u021bchi","orcid":null},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Vlad Strile\u021bchi","raw_affiliation_strings":["Technical University of Cluj-Napoca,Communications Department,Romania","Communications Department, Technical University of Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca,Communications Department,Romania","institution_ids":["https://openalex.org/I158333966"]},{"raw_affiliation_string":"Communications Department, Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017426641","display_name":"Cosmin Strile\u0163chi","orcid":"https://orcid.org/0000-0002-5663-9159"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Cosmin Strile\u021bchi","raw_affiliation_strings":["Technical University of Cluj-Napoca,Communications Department,Romania","Communications Department, Technical University of Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca,Communications Department,Romania","institution_ids":["https://openalex.org/I158333966"]},{"raw_affiliation_string":"Communications Department, Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018126799","display_name":"Adriana Stan","orcid":"https://orcid.org/0000-0003-2894-5770"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Adriana Stan","raw_affiliation_strings":["Technical University of Cluj-Napoca,Communications Department,Romania","Communications Department, Technical University of Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca,Communications Department,Romania","institution_ids":["https://openalex.org/I158333966"]},{"raw_affiliation_string":"Communications Department, Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5093266198"],"corresponding_institution_ids":["https://openalex.org/I158333966"],"apc_list":null,"apc_paid":null,"fwci":0.786,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7457406,"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":"100","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":1.0,"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":1.0,"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":0.9994999766349792,"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":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.8042207956314087},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7024951577186584},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6520469188690186},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5256734490394592},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.512766420841217},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4764573872089386},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.45582637190818787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4388333559036255},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4346114993095398},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42938172817230225},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36567234992980957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8042207956314087},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7024951577186584},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6520469188690186},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5256734490394592},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.512766420841217},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4764573872089386},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.45582637190818787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4388333559036255},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4346114993095398},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42938172817230225},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36567234992980957},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped59241.2023.10314932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped59241.2023.10314932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W2030931454","https://openalex.org/W2074788634","https://openalex.org/W2146334809","https://openalex.org/W2889462515","https://openalex.org/W3015265920","https://openalex.org/W3024869864","https://openalex.org/W3081192838","https://openalex.org/W3093573519","https://openalex.org/W3097571315","https://openalex.org/W3197642003","https://openalex.org/W3205878676","https://openalex.org/W3209059054","https://openalex.org/W4212774754","https://openalex.org/W4244693328","https://openalex.org/W4295957212","https://openalex.org/W4323824557","https://openalex.org/W4372269797","https://openalex.org/W6617505242","https://openalex.org/W6780218876","https://openalex.org/W6784200033","https://openalex.org/W6801933569","https://openalex.org/W6811070765","https://openalex.org/W6846420579"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340","https://openalex.org/W4229451372","https://openalex.org/W2113211312"],"abstract_inverted_index":{"Large":[0],"speech":[1,45,87,106],"models-derived":[2,42],"features":[3,11,43],"have":[4],"recently":[5],"shown":[6],"increased":[7],"performance":[8],"over":[9],"signal-based":[10],"across":[12,103],"multiple":[13],"downstream":[14],"tasks,":[15],"even":[16,79,99],"when":[17],"the":[18,24,32,74],"networks":[19],"are":[20,63],"not":[21,68],"fine-tuned":[22],"towards":[23],"target":[25],"task.":[26,75],"In":[27],"this":[28],"paper":[29],"we":[30],"show":[31,77],"results":[33,102],"of":[34,37,58,83],"an":[35],"analysis":[36],"several":[38],"signal-":[39],"and":[40,52,98],"neural":[41,86],"for":[44],"emotion":[46,107],"recognition.":[47],"We":[48,76],"use":[49],"pretrained":[50],"models":[51],"explore":[53],"their":[54],"inherent":[55],"potential":[56],"abstractions":[57],"emotions.":[59],"Simple":[60],"classification":[61],"methods":[62],"used":[64],"so":[65],"as":[66],"to":[67,73],"interfere":[69],"or":[70],"add":[71],"knowledge":[72],"that,":[78],"without":[80],"finetuning,":[81],"some":[82],"these":[84],"large":[85],"models\u2019":[88],"representations":[89],"can":[90],"enclose":[91],"information":[92],"that":[93],"enables":[94],"performances":[95],"close":[96],"to,":[97],"beyond":[100],"state-of-the-art":[101],"six":[104],"standard":[105],"recognition":[108],"datasets.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
