{"id":"https://openalex.org/W4319862700","doi":"https://doi.org/10.1109/slt54892.2023.10023345","title":"Extracting Speaker and Emotion Information from Self-Supervised Speech Models via Channel-Wise Correlations","display_name":"Extracting Speaker and Emotion Information from Self-Supervised Speech Models via Channel-Wise Correlations","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862700","doi":"https://doi.org/10.1109/slt54892.2023.10023345"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023345","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10023345","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061939508","display_name":"Themos Stafylakis","orcid":"https://orcid.org/0000-0002-9227-3588"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Themos Stafylakis","raw_affiliation_strings":["Omilia - Conversational Intelligence,Athens,Greece","Omilia - Conversational Intelligence, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Omilia - Conversational Intelligence,Athens,Greece","institution_ids":[]},{"raw_affiliation_string":"Omilia - Conversational Intelligence, Athens, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055201620","display_name":"Ladislav Mo\u0161ner","orcid":"https://orcid.org/0000-0001-8175-2244"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ladislav Mosner","raw_affiliation_strings":["Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063704331","display_name":"Sofoklis Kakouros","orcid":"https://orcid.org/0000-0001-8996-0793"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Sofoklis Kakouros","raw_affiliation_strings":["University of Helsinki,Finland","University of Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Helsinki,Finland","institution_ids":["https://openalex.org/I133731052"]},{"raw_affiliation_string":"University of Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064238041","display_name":"Old\u0159ich Plchot","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Oldrich Plchot","raw_affiliation_strings":["Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Cernocky","raw_affiliation_strings":["Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.086,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77722359,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1136","last_page":"1143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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/pooling","display_name":"Pooling","score":0.9110168218612671},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7276045680046082},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6099235415458679},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5837007164955139},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5586905479431152},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5404790639877319},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44118767976760864},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38433295488357544},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3797031342983246},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13716498017311096}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.9110168218612671},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7276045680046082},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6099235415458679},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5837007164955139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5586905479431152},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5404790639877319},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44118767976760864},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38433295488357544},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3797031342983246},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13716498017311096},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023345","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10023345","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1040906508","display_name":"Computational modelling of prosody in speech","funder_award_id":"340125","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2475287302","https://openalex.org/W2602034649","https://openalex.org/W2726515241","https://openalex.org/W2784163702","https://openalex.org/W2808631503","https://openalex.org/W2810637193","https://openalex.org/W2890964092","https://openalex.org/W2962739339","https://openalex.org/W2963804033","https://openalex.org/W2982474723","https://openalex.org/W3103152812","https://openalex.org/W3135006803","https://openalex.org/W3178795096","https://openalex.org/W3194763370","https://openalex.org/W3197392277","https://openalex.org/W3197580070","https://openalex.org/W3197642003","https://openalex.org/W3198275944","https://openalex.org/W3202370288","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3210530853","https://openalex.org/W4221161148","https://openalex.org/W4236965008","https://openalex.org/W4283078310","https://openalex.org/W4385245566","https://openalex.org/W6771667380","https://openalex.org/W6800175519","https://openalex.org/W6810126160"],"related_works":["https://openalex.org/W2951391129","https://openalex.org/W2944724518","https://openalex.org/W4225258897","https://openalex.org/W2613736958","https://openalex.org/W2758063741","https://openalex.org/W4226125296","https://openalex.org/W2969680539","https://openalex.org/W3097056957","https://openalex.org/W1789705271","https://openalex.org/W3202266780"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"of":[2,8,43,54,71],"speech":[3,17,22],"representations":[4,23,73],"from":[5,60],"large":[6],"amounts":[7],"unlabeled":[9],"data":[10],"has":[11],"enabled":[12],"state-of-the-art":[13],"results":[14],"in":[15,34],"several":[16],"processing":[18],"tasks.":[19],"Aggregating":[20],"these":[21],"across":[24],"time":[25],"is":[26,96],"typically":[27],"approached":[28],"by":[29],"using":[30,36],"descriptive":[31],"statistics,":[32],"and":[33,40,57,83],"particular,":[35],"the":[37,66,69,72,87],"first":[38],"-":[39,74],"second-order":[41],"statistics":[42],"representation":[44],"coefficients.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49],"examine":[50],"an":[51],"alternative":[52],"way":[53],"extracting":[55],"speaker":[56],"emotion":[58],"information":[59],"self-supervised":[61],"trained":[62],"models,":[63],"based":[64],"on":[65],"correlations":[67],"between":[68],"coefficients":[70],"correlation":[75],"pooling.":[76],"We":[77],"show":[78],"improvements":[79],"over":[80],"mean":[81],"pooling":[82,88],"further":[84],"gains":[85],"when":[86],"methods":[89],"are":[90],"combined":[91],"via":[92],"fusion.":[93],"The":[94],"code":[95],"available":[97],"at":[98],"github.com/Lamomal/s3prl_correlation.":[99]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}