{"id":"https://openalex.org/W2396919411","doi":"https://doi.org/10.1109/icassp.2016.7472181","title":"Lightly-supervised utterance-level emotion identification using latent topic modeling of multimodal words","display_name":"Lightly-supervised utterance-level emotion identification using latent topic modeling of multimodal words","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2396919411","doi":"https://doi.org/10.1109/icassp.2016.7472181","mag":"2396919411"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5101951509","display_name":"Zhaojun Yang","orcid":"https://orcid.org/0000-0002-5966-9636"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhaojun Yang","raw_affiliation_strings":["Signal Analysis and Interpretation Lab (SAIL), University of Southern California, Los Angeles, CA"],"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Lab (SAIL), University of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["Signal Analysis and Interpretation Lab (SAIL), University of Southern California, Los Angeles, CA"],"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Lab (SAIL), University of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101951509"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.9072,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.78230765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"16","issue":null,"first_page":"2767","last_page":"2771"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9977999925613403,"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":0.9977999925613403,"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/T11439","display_name":"Video Analysis and Summarization","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9865000247955322,"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/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.7632389664649963},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7200003862380981},{"id":"https://openalex.org/keywords/canonical-correlation","display_name":"Canonical correlation","score":0.601372480392456},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.5941981077194214},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.5738601088523865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5636575818061829},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.5448501110076904},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.511499285697937},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.45845359563827515},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44520822167396545},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4245312809944153},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.4211121201515198},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10236740112304688}],"concepts":[{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.7632389664649963},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7200003862380981},{"id":"https://openalex.org/C153874254","wikidata":"https://www.wikidata.org/wiki/Q115542","display_name":"Canonical correlation","level":2,"score":0.601372480392456},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.5941981077194214},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.5738601088523865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5636575818061829},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.5448501110076904},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.511499285697937},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.45845359563827515},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44520822167396545},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4245312809944153},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.4211121201515198},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10236740112304688},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W172155968","https://openalex.org/W1261896931","https://openalex.org/W1548558438","https://openalex.org/W1778065289","https://openalex.org/W1964287530","https://openalex.org/W1964716415","https://openalex.org/W1985625293","https://openalex.org/W1994616049","https://openalex.org/W2016839396","https://openalex.org/W2028899742","https://openalex.org/W2034136097","https://openalex.org/W2053101950","https://openalex.org/W2095797119","https://openalex.org/W2103658758","https://openalex.org/W2104084893","https://openalex.org/W2106964106","https://openalex.org/W2107743791","https://openalex.org/W2130013064","https://openalex.org/W2143350951","https://openalex.org/W2145598468","https://openalex.org/W2151539117","https://openalex.org/W2158169396","https://openalex.org/W2159856586","https://openalex.org/W2164186291","https://openalex.org/W2184188583","https://openalex.org/W2400346398","https://openalex.org/W2405732242","https://openalex.org/W4214544731","https://openalex.org/W4233135949","https://openalex.org/W6654409765","https://openalex.org/W6676173584","https://openalex.org/W6686207219","https://openalex.org/W6713704110"],"related_works":["https://openalex.org/W2242083226","https://openalex.org/W2884410131","https://openalex.org/W3093803775","https://openalex.org/W1603253275","https://openalex.org/W120501756","https://openalex.org/W111011176","https://openalex.org/W2138996412","https://openalex.org/W2763292376","https://openalex.org/W2097596242","https://openalex.org/W3041425257"],"abstract_inverted_index":{"Research":[0],"on":[1,58],"multimodal":[2,18,44,114,135,153],"emotion":[3,33,45,71,79],"recognition":[4],"has":[5,24,139],"drawn":[6],"much":[7],"attention":[8],"recently":[9],"in":[10,35,107],"diverse":[11],"disciplines.":[12],"With":[13],"the":[14,66,70,75,88,104,118,148,151,160],"increasing":[15],"amount":[16,51],"of":[17,32,52,113,134,150],"data,":[19],"unsupervised":[20],"or":[21],"semi-supervised":[22],"learning":[23,46],"become":[25],"highly":[26],"desirable":[27],"to":[28],"automatically":[29],"discover":[30],"expression":[31],"patterns":[34],"behavioral":[36],"data.":[37],"We":[38,144],"present":[39],"a":[40,49,82,111,127],"novel":[41],"approach":[42,55,138],"for":[43],"using":[47],"only":[48],"small":[50],"labels.":[53],"Our":[54,137],"is":[56],"hinging":[57],"probabilistic":[59],"latent":[60,67,83],"semantic":[61],"analysis":[62,130],"(pLSA)":[63],"that":[64,77,86],"defines":[65],"variable":[68,85],"as":[69,81,93,110],"class,":[72],"motivated":[73],"by":[74],"conceptualization":[76],"human":[78],"acts":[80],"control":[84],"regulates":[87],"external":[89],"behavior":[90],"manifestations,":[91],"such":[92],"through":[94],"speech":[95,121],"and":[96,122],"body":[97],"gesture.":[98],"In":[99],"our":[100],"approach,":[101],"we":[102,125],"represent":[103],"audio-visual":[105],"information":[106],"an":[108],"utterance":[109],"bag":[112],"words.":[115,136],"To":[116],"exploit":[117],"interrelation":[119],"between":[120],"gesture":[123],"modalities,":[124],"propose":[126],"canonical":[128],"correlation":[129],"(CCA)":[131],"based":[132],"vocabulary":[133],"achieved":[140],"promising":[141],"experimental":[142],"results.":[143],"have":[145],"also":[146],"demonstrated":[147],"superiority":[149],"CCA-based":[152],"words":[154],"over":[155],"those":[156],"derived":[157],"directly":[158],"from":[159],"original":[161],"cues.":[162]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}