{"id":"https://openalex.org/W4414990885","doi":"https://doi.org/10.21437/interspeech.2025-2451","title":"Multimodal Fusion with Semi-Supervised Learning Minimizes Annotation Quantity for Modeling Videoconference Conversation Experience","display_name":"Multimodal Fusion with Semi-Supervised Learning Minimizes Annotation Quantity for Modeling Videoconference Conversation Experience","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4414990885","doi":"https://doi.org/10.21437/interspeech.2025-2451"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-2451","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2451","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.13971","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102881477","display_name":"Andrew Chang","orcid":"https://orcid.org/0009-0003-1441-1310"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Chang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073944287","display_name":"Chenkai Hu","orcid":"https://orcid.org/0000-0001-6136-8712"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenkai Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102993435","display_name":"Ji Qi","orcid":"https://orcid.org/0000-0003-3324-5269"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhuojian Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuojian Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100459344","display_name":"Kexin Zhang","orcid":"https://orcid.org/0000-0003-1968-8004"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kexin Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115792754","display_name":"Viswadruth Akkaraju","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Viswadruth Akkaraju","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033417964","display_name":"David Poeppel","orcid":"https://orcid.org/0000-0003-0184-163X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Poeppel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5035737956","display_name":"Dustin Freeman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dustin Freeman","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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4313","last_page":"4317"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12214","display_name":"Media Influence and Health","score":0.9836999773979187,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12214","display_name":"Media Influence and Health","score":0.9836999773979187,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9721999764442444,"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/T12593","display_name":"Communication in Education and Healthcare","score":0.9430000185966492,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/conversation","display_name":"Conversation","score":0.728600025177002},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7023000121116638},{"id":"https://openalex.org/keywords/videoconferencing","display_name":"Videoconferencing","score":0.6833999752998352},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6403999924659729},{"id":"https://openalex.org/keywords/teleconference","display_name":"Teleconference","score":0.46790000796318054},{"id":"https://openalex.org/keywords/clips","display_name":"CLIPS","score":0.3806999921798706}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.728600025177002},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7023000121116638},{"id":"https://openalex.org/C22561748","wikidata":"https://www.wikidata.org/wiki/Q854954","display_name":"Videoconferencing","level":2,"score":0.6833999752998352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6628999710083008},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6403999924659729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5293999910354614},{"id":"https://openalex.org/C126669455","wikidata":"https://www.wikidata.org/wiki/Q1630941","display_name":"Teleconference","level":2,"score":0.46790000796318054},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4352000057697296},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4092999994754791},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.3806999921798706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.357699990272522},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.31470000743865967},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C2780829048","wikidata":"https://www.wikidata.org/wiki/Q1624720","display_name":"Conversation analysis","level":3,"score":0.25940001010894775}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-2451","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2451","pdf_url":null,"source":null,"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:2506.13971","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.13971","pdf_url":"https://arxiv.org/pdf/2506.13971","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.13971","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.13971","pdf_url":"https://arxiv.org/pdf/2506.13971","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Group":[0],"conversations":[1],"over":[2],"videoconferencing":[3],"are":[4,27],"a":[5,35],"complex":[6],"social":[7],"behavior.":[8],"However,":[9],"the":[10,17,98,105,117],"subjective":[11],"moments":[12,26,70],"of":[13,82,88,101,116],"negative":[14],"experience,":[15],"where":[16],"conversation":[18],"loses":[19],"fluidity":[20],"or":[21,68],"enjoyment":[22],"remain":[23],"understudied.":[24],"These":[25],"infrequent":[28],"in":[29,71],"naturalistic":[30],"data,":[31],"and":[32,54,84],"thus":[33],"training":[34,58],"supervised":[36],"learning":[37,48],"(SL)":[38],"model":[39,108],"requires":[40],"costly":[41],"manual":[42],"data":[43,113],"annotation.":[44],"We":[45],"applied":[46],"semi-supervised":[47],"(SSL)":[49],"to":[50,65,95],"leverage":[51],"targeted":[52],"labeled":[53,102,112],"unlabeled":[55],"clips":[56],"for":[57,127],"multimodal":[59],"(audio,":[60],"facial,":[61],"text)":[62],"deep":[63],"features":[64],"predict":[66],"non-fluid":[67],"unenjoyable":[69],"holdout":[72],"videoconference":[73,129],"sessions.":[74],"The":[75],"modality-fused":[76],"co-training":[77],"SSL":[78,107],"achieved":[79],"an":[80,85,124],"ROC-AUC":[81],"0.9":[83],"F1":[86],"score":[87],"0.6,":[89],"outperforming":[90],"SL":[91,118],"models":[92],"by":[93],"up":[94],"4%":[96],"with":[97,109],"same":[99],"amount":[100],"data.":[103],"Remarkably,":[104],"best":[106],"just":[110],"8%":[111],"matched":[114],"96%":[115],"model's":[119],"full-data":[120],"performance.":[121],"This":[122],"shows":[123],"annotation-efficient":[125],"framework":[126],"modeling":[128],"experience.":[130]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}