{"id":"https://openalex.org/W4392903920","doi":"https://doi.org/10.1109/icassp48485.2024.10446410","title":"MCM-CSD: Multi-Granularity Context Modeling with Contrastive Speaker Detection for Emotion Recognition in Real-Time Conversation","display_name":"MCM-CSD: Multi-Granularity Context Modeling with Contrastive Speaker Detection for Emotion Recognition in Real-Time Conversation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903920","doi":"https://doi.org/10.1109/icassp48485.2024.10446410"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446410","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5102346489","display_name":"Yuan Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuan Xu","raw_affiliation_strings":["Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,P.R. China,510006"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,P.R. China,510006","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037873810","display_name":"Meng Yang","orcid":"https://orcid.org/0000-0002-0795-3221"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Yang","raw_affiliation_strings":["Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,P.R. China,510006"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,P.R. China,510006","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102346489"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.6982,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72820437,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11956","last_page":"11960"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9994999766349792,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8408495187759399},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.7893074154853821},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6517965197563171},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6053682565689087},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.601555585861206},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5712894797325134},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5405288338661194},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5095982551574707},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.49797844886779785},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48047345876693726},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46337762475013733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45941078662872314},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4333907663822174},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09589278697967529},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.08255079388618469}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8408495187759399},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7893074154853821},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6517965197563171},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6053682565689087},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.601555585861206},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5712894797325134},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5405288338661194},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5095982551574707},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.49797844886779785},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48047345876693726},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46337762475013733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45941078662872314},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4333907663822174},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09589278697967529},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.08255079388618469},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446410","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2016089260","https://openalex.org/W2146334809","https://openalex.org/W2749002090","https://openalex.org/W2908510526","https://openalex.org/W2963101081","https://openalex.org/W2963351448","https://openalex.org/W2963686995","https://openalex.org/W2963873807","https://openalex.org/W2964300796","https://openalex.org/W2965373594","https://openalex.org/W2965453734","https://openalex.org/W2979826702","https://openalex.org/W2985882473","https://openalex.org/W3116016199","https://openalex.org/W3175552668","https://openalex.org/W3176849538","https://openalex.org/W3194998303","https://openalex.org/W3201282015","https://openalex.org/W3212414676","https://openalex.org/W4224320748","https://openalex.org/W4226025958","https://openalex.org/W4287812705","https://openalex.org/W4385245566","https://openalex.org/W4385570970","https://openalex.org/W4385573172","https://openalex.org/W6743333458","https://openalex.org/W6745297980","https://openalex.org/W6757817989","https://openalex.org/W6766673545","https://openalex.org/W6767091845","https://openalex.org/W6776700526","https://openalex.org/W6784350020"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W3133700904"],"abstract_inverted_index":{"Emotion":[0],"recognition":[1,50],"in":[2,13,27,96,125,171],"conversation":[3,25,33],"(ERC)":[4],"has":[5],"received":[6],"extensive":[7],"attention":[8],"for":[9,48,103],"its":[10],"wide":[11],"applications":[12],"recent":[14],"years.":[15],"Considering":[16],"the":[17,23,32,37,45,67,80,92,104,122,135,160,167],"actual":[18],"situation,":[19],"we":[20,57,84,108,150],"focus":[21],"on":[22,131],"real-time":[24],"scenarios,":[26],"which":[28,65],"how":[29,42],"to":[30,43,89,146,158],"model":[31,63,140],"emotion":[34,49],"with":[35,74],"only":[36],"historical":[38],"contextual":[39,94],"information":[40,47,95],"and":[41,99,154,165],"exploit":[44],"speaker":[46,76,124],"have":[51],"not":[52],"been":[53],"well":[54],"studied.":[55],"Therefore,":[56],"propose":[58],"a":[59,86,110,155],"novel":[60],"multi-task":[61],"learning":[62,113],"MCM-CSD,":[64],"combines":[66],"multi-granularity":[68,93],"context":[69],"modeling":[70],"(MCM)":[71],"based":[72],"ERC":[73],"contrastive":[75,112],"detection":[77],"(CSD).":[78],"For":[79],"main":[81],"task":[82,106],"ERC,":[83],"design":[85,109],"bottom-up":[87],"approach":[88],"fully":[90],"extract":[91],"both":[97],"word":[98],"utterance":[100],"levels.":[101],"And":[102],"auxiliary":[105],"CSD,":[107],"supervised":[111],"loss":[114],"that":[115,138],"can":[116,141],"easily":[117],"distinguish":[118],"previous":[119,147],"speakers":[120],"from":[121],"current":[123],"multi-turn":[126],"conversations.":[127],"We":[128],"conduct":[129],"experiments":[130,153],"four":[132],"benchmark":[133],"datasets,":[134],"results":[136],"show":[137],"our":[139],"achieve":[142],"state-of-the-art":[143],"performance":[144],"compared":[145],"methods.":[148],"Furthermore,":[149],"perform":[151],"ablation":[152],"case":[156],"study":[157],"verify":[159],"effectiveness":[161],"of":[162,169],"each":[163],"component":[164],"explain":[166],"significance":[168],"CSD":[170],"MCM-CSD.":[172],"The":[173],"code":[174],"is":[175],"available":[176],"at":[177],"https://github.com/WHOISJENNY/MCM-CSD.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}