{"id":"https://openalex.org/W4297841602","doi":"https://doi.org/10.21437/interspeech.2022-11307","title":"Interactive Co-Learning with Cross-Modal Transformer for Audio-Visual Emotion Recognition","display_name":"Interactive Co-Learning with Cross-Modal Transformer for Audio-Visual Emotion Recognition","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841602","doi":"https://doi.org/10.21437/interspeech.2022-11307"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11307","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11307","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5103213652","display_name":"Akihiko Takashima","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akihiko Takashima","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090978027","display_name":"Atsushi Ando","orcid":"https://orcid.org/0000-0002-0389-5001"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atsushi Ando","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037013625","display_name":"Yoshihiro Yamazaki","orcid":"https://orcid.org/0000-0002-6404-0031"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoshihiro Yamazaki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008141813","display_name":"Mihiro Uchida","orcid":"https://orcid.org/0009-0002-1350-6038"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mihiro Uchida","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5013009514","display_name":"Shota Orihashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shota Orihashi","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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4740","last_page":"4744"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9192000031471252,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9192000031471252,"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":0.6849699020385742},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6465535163879395},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6390734910964966},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.615315854549408},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6021525263786316},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4571431279182434},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37332212924957275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3239307999610901},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32359611988067627},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11821776628494263},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07923880219459534},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06738889217376709},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.0643499493598938}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6849699020385742},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6465535163879395},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6390734910964966},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.615315854549408},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6021525263786316},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4571431279182434},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37332212924957275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3239307999610901},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32359611988067627},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11821776628494263},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07923880219459534},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06738889217376709},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0643499493598938},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11307","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11307","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3105646692","https://openalex.org/W4387914125","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}