{"id":"https://openalex.org/W4399794377","doi":"https://doi.org/10.21437/odyssey.2024-38","title":"Double Multi-Head Attention Multimodal System for Odyssey 2024 Speech Emotion Recognition Challenge","display_name":"Double Multi-Head Attention Multimodal System for Odyssey 2024 Speech Emotion Recognition Challenge","publication_year":2024,"publication_date":"2024-06-18","ids":{"openalex":"https://openalex.org/W4399794377","doi":"https://doi.org/10.21437/odyssey.2024-38"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2024-38","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2024-38","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2024)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.10598","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103232154","display_name":"Federico Costa","orcid":"https://orcid.org/0000-0002-1389-3595"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Federico Costa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085739769","display_name":"Miquel India","orcid":"https://orcid.org/0000-0002-3107-3662"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miquel India","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5025633053","display_name":"Javier Hernando","orcid":"https://orcid.org/0000-0002-1730-8154"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Javier Hernando","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3052,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80563615,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"266","last_page":"273"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.7530999779701233,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.7530999779701233,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.7351999878883362,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.6812639236450195},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5776277780532837},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5540183186531067},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4486600458621979},{"id":"https://openalex.org/keywords/multimodal-therapy","display_name":"Multimodal therapy","score":0.41536960005760193},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3741547167301178},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3613775372505188},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.07643133401870728},{"id":"https://openalex.org/keywords/psychotherapist","display_name":"Psychotherapist","score":0.0637560486793518}],"concepts":[{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.6812639236450195},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5776277780532837},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5540183186531067},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4486600458621979},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.41536960005760193},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3741547167301178},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3613775372505188},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.07643133401870728},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0637560486793518},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/odyssey.2024-38","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2024-38","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2024)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2406.10598","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.10598","pdf_url":"https://arxiv.org/pdf/2406.10598","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"pmh:oai:upcommons.upc.edu:2117/442389","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/442389","pdf_url":"https://upcommons.upc.edu/bitstreams/53cb6231-df1c-452f-8b9c-325c2d940d6c/download","source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.10598","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.10598","pdf_url":"https://arxiv.org/pdf/2406.10598","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7300000190734863,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2954395134","display_name":null,"funder_award_id":"PID2019-107579RB-I00","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G3690828678","display_name":null,"funder_award_id":"PID2019","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G7425137858","display_name":null,"funder_award_id":"PID2019","funder_id":"https://openalex.org/F4320321505","funder_display_name":"Generalitat de Catalunya"}],"funders":[{"id":"https://openalex.org/F4320321505","display_name":"Generalitat de Catalunya","ror":"https://ror.org/01bg62x04"},{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399794377.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3097502728","https://openalex.org/W2113206756","https://openalex.org/W2358901620","https://openalex.org/W4306253668","https://openalex.org/W3032782782","https://openalex.org/W3009949491","https://openalex.org/W1927475415","https://openalex.org/W2613352840","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"As":[0],"computer-based":[1],"applications":[2],"are":[3],"becoming":[4],"more":[5],"integrated":[6],"into":[7,90,105],"our":[8],"daily":[9],"lives,":[10],"the":[11,28,40,53,113,117],"importance":[12],"of":[13,39],"Speech":[14,31],"Emotion":[15,32],"Recognition":[16,33,46],"(SER)":[17],"has":[18],"increased":[19],"significantly.":[20],"Promoting":[21],"research":[22],"with":[23,121],"innovative":[24],"approaches":[25],"in":[26,116,130],"SER,":[27],"Odyssey":[29,41],"2024":[30,42],"Challenge":[34],"was":[35,79],"organized":[36],"as":[37],"part":[38],"Speaker":[43],"and":[44,72],"Language":[45],"Workshop.":[47],"In":[48],"this":[49,61],"paper":[50],"we":[51],"describe":[52],"Double":[54],"Multi-Head":[55,83],"Attention":[56,84],"Multimodal":[57],"System":[58],"developed":[59],"for":[60],"challenge.":[62],"Pre-trained":[63],"self-supervised":[64],"models":[65],"were":[66],"used":[67],"to":[68,101],"extract":[69],"informative":[70],"acoustic":[71],"text":[73],"features.":[74],"An":[75],"early":[76],"fusion":[77],"strategy":[78],"adopted,":[80],"where":[81,126],"a":[82,122],"layer":[85],"transforms":[86],"these":[87,103],"mixed":[88],"features":[89],"complementary":[91],"contextualized":[92],"representations.":[93],"A":[94],"second":[95],"attention":[96],"mechanism":[97],"is":[98],"then":[99],"applied":[100],"pool":[102],"representations":[104],"an":[106],"utterance-level":[107],"vector.":[108],"Our":[109],"proposed":[110],"system":[111],"achieved":[112],"third":[114],"position":[115],"categorical":[118],"task":[119],"ranking":[120],"34.41%":[123],"Macro-F1":[124],"score,":[125],"31":[127],"teams":[128],"participated":[129],"total.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2025-10-10T00:00:00"}
