{"id":"https://openalex.org/W4385823265","doi":"https://doi.org/10.21437/interspeech.2023-497","title":"Towards Paralinguistic-Only Speech Representations for End-to-End Speech Emotion Recognition","display_name":"Towards Paralinguistic-Only Speech Representations for End-to-End Speech Emotion Recognition","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823265","doi":"https://doi.org/10.21437/interspeech.2023-497"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-497","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5073370625","display_name":"\u0393\u03b5\u03ce\u03c1\u03b3\u03b9\u03bf\u03c2 \u0399\u03c9\u03b1\u03bd\u03bd\u03af\u03b4\u03b7\u03c2","orcid":"https://orcid.org/0000-0003-3922-8080"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Georgios Ioannides","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026352442","display_name":"Michael J. Owen","orcid":"https://orcid.org/0000-0003-4798-0862"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Owen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000608564","display_name":"Andrew Fletcher","orcid":"https://orcid.org/0000-0003-4111-2968"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Fletcher","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091009689","display_name":"Viktor Rozgi\u0107","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Viktor Rozgic","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5115076700","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0003-4887-923X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5073370625"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.049,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81211175,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1853","last_page":"1857"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9768999814987183,"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":0.9768999814987183,"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":0.9517999887466431,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9146999716758728,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/paralanguage","display_name":"Paralanguage","score":0.9615167379379272},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6904705762863159},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6728061437606812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6348888874053955},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4383573532104492},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4250567555427551},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3582002520561218},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.23849773406982422},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.22438755631446838},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2010158896446228}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.9615167379379272},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6904705762863159},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6728061437606812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6348888874053955},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4383573532104492},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4250567555427551},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3582002520561218},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.23849773406982422},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22438755631446838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2010158896446228}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-497","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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":0,"referenced_works":[],"related_works":["https://openalex.org/W1838628832","https://openalex.org/W2099475353","https://openalex.org/W1966028611","https://openalex.org/W2568050604","https://openalex.org/W3195200850","https://openalex.org/W2744347949","https://openalex.org/W2048673468","https://openalex.org/W3107456284","https://openalex.org/W642007152","https://openalex.org/W3110551121"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
