{"id":"https://openalex.org/W4385823339","doi":"https://doi.org/10.21437/interspeech.2023-1595","title":"Learning Emotional Representations from Imbalanced Speech Data for Speech Emotion Recognition and Emotional Text-to-Speech","display_name":"Learning Emotional Representations from Imbalanced Speech Data for Speech Emotion Recognition and Emotional Text-to-Speech","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823339","doi":"https://doi.org/10.21437/interspeech.2023-1595"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1595","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1595","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":"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/A5100627209","display_name":"Shijun Wang","orcid":"https://orcid.org/0000-0001-7290-412X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shijun Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079762083","display_name":"J\u00f3n Gu\u00f0nason","orcid":"https://orcid.org/0000-0001-6560-5543"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J\u00f3n Gu\u00f0nason","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5065722787","display_name":"Damian Borth","orcid":"https://orcid.org/0000-0002-4660-2627"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Damian Borth","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"351","last_page":"355"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9575999975204468,"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":0.9575999975204468,"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":0.9229000210762024,"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/speech-recognition","display_name":"Speech recognition","score":0.7221261262893677},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6718301773071289},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6637330055236816},{"id":"https://openalex.org/keywords/motor-theory-of-speech-perception","display_name":"Motor theory of speech perception","score":0.44763195514678955},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4376629590988159},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4269663989543915},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4213064908981323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36439383029937744},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.33654356002807617},{"id":"https://openalex.org/keywords/speech-perception","display_name":"Speech perception","score":0.2922113239765167},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.264174222946167},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.12665769457817078}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7221261262893677},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6718301773071289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6637330055236816},{"id":"https://openalex.org/C186393131","wikidata":"https://www.wikidata.org/wiki/Q1949774","display_name":"Motor theory of speech perception","level":4,"score":0.44763195514678955},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4376629590988159},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4269663989543915},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4213064908981323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36439383029937744},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.33654356002807617},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.2922113239765167},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.264174222946167},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.12665769457817078},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-1595","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1595","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2016090750","https://openalex.org/W2537969829","https://openalex.org/W2111751477","https://openalex.org/W2022789108","https://openalex.org/W2185554451","https://openalex.org/W2166366223","https://openalex.org/W2567495185","https://openalex.org/W2389353568","https://openalex.org/W2153664791","https://openalex.org/W90720583"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
