{"id":"https://openalex.org/W4319862479","doi":"https://doi.org/10.1109/slt54892.2023.10023428","title":"Exploration of a Self-Supervised Speech Model: A Study on Emotional Corpora","display_name":"Exploration of a Self-Supervised Speech Model: A Study on Emotional Corpora","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862479","doi":"https://doi.org/10.1109/slt54892.2023.10023428"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023428","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/7fdf9f70-6908-4f69-a6e5-7b3097e46fc4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077749078","display_name":"Yuanchao Li","orcid":"https://orcid.org/0000-0002-8005-947X"},"institutions":[{"id":"https://openalex.org/I4210159188","display_name":"SpeechTech (Czechia)","ror":"https://ror.org/05fsqes40","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210159188"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["CZ","GB"],"is_corresponding":false,"raw_author_name":"Yuanchao Li","raw_affiliation_strings":["University of Edinburgh,Centre for Speech Technology Research","Centre for Speech Technology Research, University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Centre for Speech Technology Research","institution_ids":["https://openalex.org/I4210159188","https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076680086","display_name":"Yumnah Mohamied","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159188","display_name":"SpeechTech (Czechia)","ror":"https://ror.org/05fsqes40","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210159188"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["CZ","GB"],"is_corresponding":false,"raw_author_name":"Yumnah Mohamied","raw_affiliation_strings":["University of Edinburgh,Centre for Speech Technology Research","Centre for Speech Technology Research, University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Centre for Speech Technology Research","institution_ids":["https://openalex.org/I4210159188","https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"institutions":[{"id":"https://openalex.org/I4210159188","display_name":"SpeechTech (Czechia)","ror":"https://ror.org/05fsqes40","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210159188"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["CZ","GB"],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":["University of Edinburgh,Centre for Speech Technology Research","Centre for Speech Technology Research, University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Centre for Speech Technology Research","institution_ids":["https://openalex.org/I4210159188","https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058881584","display_name":"Catherine Lai","orcid":"https://orcid.org/0000-0003-2411-8954"},"institutions":[{"id":"https://openalex.org/I4210159188","display_name":"SpeechTech (Czechia)","ror":"https://ror.org/05fsqes40","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210159188"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["CZ","GB"],"is_corresponding":false,"raw_author_name":"Catherine Lai","raw_affiliation_strings":["University of Edinburgh,Centre for Speech Technology Research","Centre for Speech Technology Research, University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Centre for Speech Technology Research","institution_ids":["https://openalex.org/I4210159188","https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.8361,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.97691069,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"868","last_page":"875"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9994000196456909,"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/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":0.8913646340370178},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7777502536773682},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.6033940315246582},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5855664014816284},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5365357995033264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5058850646018982},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5012085437774658},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4890316426753998},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4606698751449585},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.43115562200546265},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1016981303691864},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08901822566986084}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.8913646340370178},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777502536773682},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6033940315246582},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5855664014816284},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5365357995033264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5058850646018982},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5012085437774658},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4890316426753998},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4606698751449585},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.43115562200546265},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1016981303691864},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08901822566986084},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/slt54892.2023.10023428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023428","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/7fdf9f70-6908-4f69-a6e5-7b3097e46fc4","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/7fdf9f70-6908-4f69-a6e5-7b3097e46fc4","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Li, Y, Mohamied, Y, Bell, P & Lai, C 2023, Exploration of A Self-Supervised Speech Model: A Study on Emotional Corpora. in Proceedings of the 2022 IEEE Spoken Language Technology Workshop. Institute of Electrical and Electronics Engineers, pp. 868-875, 2022 IEEE Spoken Language Technology Workshop, Doha, Qatar, 9/01/23. https://doi.org/10.1109/SLT54892.2023.10023428","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.ed.ac.uk:publications/7fdf9f70-6908-4f69-a6e5-7b3097e46fc4","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/305860313/SLT_2022_final.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Li, Y, Mohamied, Y, Bell, P & Lai, C 2023, Exploration of A Self-Supervised Speech Model: A Study on Emotional Corpora. in Proceedings of the 2022 IEEE Spoken Language Technology Workshop. Institute of Electrical and Electronics Engineers, pp. 868-875, 2022 IEEE Spoken Language Technology Workshop, Doha, Qatar, 9/01/23. https://doi.org/10.1109/SLT54892.2023.10023428","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/7fdf9f70-6908-4f69-a6e5-7b3097e46fc4","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/7fdf9f70-6908-4f69-a6e5-7b3097e46fc4","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Li, Y, Mohamied, Y, Bell, P & Lai, C 2023, Exploration of A Self-Supervised Speech Model: A Study on Emotional Corpora. in Proceedings of the 2022 IEEE Spoken Language Technology Workshop. Institute of Electrical and Electronics Engineers, pp. 868-875, 2022 IEEE Spoken Language Technology Workshop, Doha, Qatar, 9/01/23. https://doi.org/10.1109/SLT54892.2023.10023428","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1505035441","https://openalex.org/W1573035800","https://openalex.org/W1969386661","https://openalex.org/W1987759408","https://openalex.org/W2054941444","https://openalex.org/W2084582948","https://openalex.org/W2090861223","https://openalex.org/W2100235303","https://openalex.org/W2102113734","https://openalex.org/W2104773730","https://openalex.org/W2146334809","https://openalex.org/W2148154194","https://openalex.org/W2168045655","https://openalex.org/W2239141610","https://openalex.org/W2484663467","https://openalex.org/W2587150483","https://openalex.org/W2803193013","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2962739339","https://openalex.org/W2972602947","https://openalex.org/W2972943112","https://openalex.org/W3036601975","https://openalex.org/W3096919670","https://openalex.org/W3097286738","https://openalex.org/W3122100772","https://openalex.org/W3197580070","https://openalex.org/W3197642003","https://openalex.org/W3198275944","https://openalex.org/W3198528147","https://openalex.org/W3198858531","https://openalex.org/W3206192140","https://openalex.org/W3208480086","https://openalex.org/W3209059054","https://openalex.org/W4210849719","https://openalex.org/W4221162874","https://openalex.org/W4224918181","https://openalex.org/W4225096077","https://openalex.org/W4226380987","https://openalex.org/W4297808394","https://openalex.org/W4390911710","https://openalex.org/W6675365184","https://openalex.org/W6755207826","https://openalex.org/W6767906889","https://openalex.org/W6780218876","https://openalex.org/W6782524110","https://openalex.org/W6784776607","https://openalex.org/W6787335539","https://openalex.org/W6802546489","https://openalex.org/W6860024833"],"related_works":["https://openalex.org/W2064370490","https://openalex.org/W3166813893","https://openalex.org/W2910013580","https://openalex.org/W2391900574","https://openalex.org/W3200958703","https://openalex.org/W1990078780","https://openalex.org/W2778981579","https://openalex.org/W2376619307","https://openalex.org/W4250647969","https://openalex.org/W3108667266"],"abstract_inverted_index":{"Self-supervised":[0],"speech":[1],"models":[2,121],"have":[3,12,37],"grown":[4],"fast":[5],"during":[6],"the":[7,29,93,107,112,125,154],"past":[8],"few":[9],"years":[10],"and":[11,150],"proven":[13],"feasible":[14],"for":[15,83,88,128,153],"use":[16,133,155],"in":[17,111,115,147],"various":[18],"downstream":[19,129],"tasks.":[20],"Some":[21],"recent":[22],"work":[23,138],"has":[24],"started":[25],"to":[26,52,75],"look":[27],"at":[28],"characteristics":[30],"of":[31,64,134,156],"these":[32],"models,":[33],"yet":[34],"many":[35],"concerns":[36],"not":[38,123],"been":[39],"fully":[40],"addressed.":[41],"In":[42],"this":[43,148],"work,":[44],"we":[45,67],"conduct":[46],"a":[47,54,62],"study":[48],"on":[49],"emotional":[50],"corpora":[51],"explore":[53],"popular":[55],"self-supervised":[56,120],"model":[57],"-":[58],"wav2vec":[59,72],"2.0.":[60],"Via":[61],"set":[63],"quantitative":[65],"analysis,":[66],"mainly":[68],"demonstrate":[69],"that:":[70],"1)":[71],"2.0":[73],"appears":[74],"discard":[76],"paralinguistic":[77],"information":[78],"that":[79,131,142],"is":[80],"less":[81],"useful":[82],"word":[84],"recognition":[85],"purposes;":[86],"2)":[87],"emotion":[89],"recognition,":[90],"representations":[91],"from":[92,103],"middle":[94],"layer":[95,104,109],"alone":[96],"perform":[97],"as":[98,100],"well":[99],"those":[101],"derived":[102],"averaging,":[105],"while":[106],"final":[108],"results":[110],"worst":[113],"performance":[114],"some":[116],"cases;":[117],"3)":[118],"current":[119],"may":[122],"be":[124],"optimal":[126],"solution":[127],"tasks":[130],"make":[132],"non-lexical":[135],"features.":[136],"Our":[137],"provides":[139],"novel":[140],"findings":[141],"will":[143],"aid":[144],"future":[145],"research":[146],"area":[149],"theoretical":[151],"basis":[152],"existing":[157],"models.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":9}],"updated_date":"2026-08-27T14:10:00.468798","created_date":"2025-10-10T00:00:00"}