{"id":"https://openalex.org/W4415433368","doi":"https://doi.org/10.21437/interspeech.2025-1198","title":"EmotionRankCLAP: Bridging Natural Language Speaking Styles and Ordinal Speech Emotion via Rank-N-Contrast","display_name":"EmotionRankCLAP: Bridging Natural Language Speaking Styles and Ordinal Speech Emotion via Rank-N-Contrast","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433368","doi":"https://doi.org/10.21437/interspeech.2025-1198"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1198","doi":"https://doi.org/10.21437/interspeech.2025-1198","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1198","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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 2025","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.23732","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101375042","display_name":"Shreeram Suresh Chandra","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shreeram Suresh Chandra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017966455","display_name":"Lucas Goncalves","orcid":"https://orcid.org/0000-0001-9613-1002","observed_orcids":["https://orcid.org/0000-0001-9613-1002"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lucas Goncalves","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067107105","display_name":"Junchen Lu","orcid":"https://orcid.org/0000-0003-1668-7743","observed_orcids":["https://orcid.org/0000-0003-1668-7743"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junchen Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040793194","display_name":"Carlos Busso","orcid":"https://orcid.org/0000-0002-4075-4072","observed_orcids":["https://orcid.org/0000-0002-4075-4072"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carlos Busso","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001303929","display_name":"Berrak \u015ei\u015fman","orcid":"https://orcid.org/0000-0001-8078-3305","observed_orcids":["https://orcid.org/0000-0001-8078-3305"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Berrak Sisman","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":1.7919,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86029803,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3000","last_page":"3004"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9761000275611877,"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":0.9761000275611877,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.01119999960064888,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.007300000172108412,"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/speech-emotion-recognition","display_name":"speech emotion recognition","score":0.8109999895095825},{"id":"https://openalex.org/keywords/speech-style","display_name":"speech style","score":0.5619999766349792},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.7639999985694885},{"id":"https://openalex.org/keywords/clap","display_name":"CLAP","score":0.6809999942779541}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6639000177383423},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.6155999898910522},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.54830002784729},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43860000371932983},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43149998784065247},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4212999939918518},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.36970001459121704},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.32839998602867126},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.29490000009536743},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.289900004863739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2851000130176544},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2025-1198","doi":"https://doi.org/10.21437/interspeech.2025-1198","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1198","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.23732","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.23732","pdf_url":"https://arxiv.org/pdf/2505.23732","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"doi:10.48550/arxiv.2505.23732","doi":"https://doi.org/10.48550/arxiv.2505.23732","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.23732","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.23732","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.23732","pdf_url":"https://arxiv.org/pdf/2505.23732","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415433368.pdf","grobid_xml":"https://content.openalex.org/works/W4415433368.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7125127790","https://openalex.org/W4392903074","https://openalex.org/W4415433583","https://openalex.org/W7165804654","https://openalex.org/W4415433432","https://openalex.org/W4402112338","https://openalex.org/W4392903888","https://openalex.org/W4415433700","https://openalex.org/W7203626346","https://openalex.org/W7107862394"],"abstract_inverted_index":{"Current":[0],"emotion-based":[1],"contrastive":[2,59],"language-audio":[3],"pretraining":[4],"(CLAP)":[5],"methods":[6,108],"typically":[7],"learn":[8,90],"by":[9,93],"na\u00efvely":[10],"aligning":[11],"audio":[12,42],"samples":[13,95],"with":[14],"corresponding":[15],"text":[16,44],"prompts.":[17],"Consequently,":[18],"this":[19],"approach":[20,61,84],"fails":[21],"to":[22,47,73,89],"capture":[23,75],"the":[24,41,101],"ordinal":[25],"nature":[26],"of":[27,66],"emotions,":[28],"hindering":[29],"inter-emotion":[30],"understanding":[31],"and":[32,43,69,79],"often":[33],"resulting":[34],"in":[35,100,109],"a":[36,57,86,117],"wide":[37],"modality":[38],"gap":[39],"between":[40],"embeddings":[45],"due":[46],"insufficient":[48],"alignment.":[49,82],"To":[50],"handle":[51],"these":[52],"drawbacks,":[53],"we":[54],"introduce":[55],"EmotionRankCLAP,":[56],"supervised":[58],"learning":[60],"that":[62],"uses":[63],"dimensional":[64],"attributes":[65],"emotional":[67],"speech":[68],"natural":[70],"language":[71],"prompts":[72],"jointly":[74],"fine-grained":[76],"emotion":[77,111],"variations":[78],"improve":[80],"cross-modal":[81,118],"Our":[83],"utilizes":[85],"Rank-N-Contrast":[87],"objective":[88],"ordered":[91],"relationships":[92],"contrasting":[94],"based":[96],"on":[97],"their":[98],"rankings":[99],"valence-arousal":[102],"space.":[103],"EmotionRankCLAP":[104],"outperforms":[105],"existing":[106],"emotion-CLAP":[107],"modeling":[110],"ordinality":[112],"across":[113],"modalities,":[114],"measured":[115],"via":[116],"retrieval":[119],"task.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-24T00:00:00"}
