{"id":"https://openalex.org/W3081363221","doi":"https://doi.org/10.1145/3382507.3418842","title":"Dyadic Speech-based Affect Recognition using DAMI-P2C Parent-child Multimodal Interaction Dataset","display_name":"Dyadic Speech-based Affect Recognition using DAMI-P2C Parent-child Multimodal Interaction Dataset","publication_year":2020,"publication_date":"2020-10-21","ids":{"openalex":"https://openalex.org/W3081363221","doi":"https://doi.org/10.1145/3382507.3418842","mag":"3081363221"},"language":"en","primary_location":{"id":"doi:10.1145/3382507.3418842","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3382507.3418842","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3382507.3418842","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3382507.3418842","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Huili Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huili Chen","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yue Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Zhang","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Felix Weninger","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Felix Weninger","raw_affiliation_strings":["Nuance Communications, Burlington, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications, Burlington, MA, USA","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rosalind Picard","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rosalind Picard","raw_affiliation_strings":["Massachusetts Institute of Techology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Techology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cynthia Breazeal","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cynthia Breazeal","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":null,"display_name":"Hae Won Park","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hae Won Park","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9994999766349792,"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":0.9994999766349792,"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/T13289","display_name":"Infant Health and Development","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9787999987602234,"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/pooling","display_name":"Pooling","score":0.6909000277519226},{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.6528000235557556},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.4514999985694885},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4189000129699707},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.41190001368522644},{"id":"https://openalex.org/keywords/affective-computing","display_name":"Affective computing","score":0.40799999237060547},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.3917999863624573},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.3490000069141388}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6909000277519226},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.6528000235557556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6295999884605408},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.4514999985694885},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4189000129699707},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4047999978065491},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.3917999863624573},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34880000352859497},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32089999318122864},{"id":"https://openalex.org/C36951298","wikidata":"https://www.wikidata.org/wiki/Q379784","display_name":"Arousal","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29490000009536743},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2603999972343445},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3382507.3418842","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3382507.3418842","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3382507.3418842","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.09207","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.09207","pdf_url":"https://arxiv.org/pdf/2008.09207","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":"doi:10.1145/3382507.3418842","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3382507.3418842","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3382507.3418842","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3081363221.pdf","grobid_xml":"https://content.openalex.org/works/W3081363221.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W194074817","https://openalex.org/W1495623570","https://openalex.org/W1559045878","https://openalex.org/W1973023835","https://openalex.org/W2019906816","https://openalex.org/W2029505355","https://openalex.org/W2063085086","https://openalex.org/W2090777335","https://openalex.org/W2097915124","https://openalex.org/W2125189926","https://openalex.org/W2141403362","https://openalex.org/W2143612262","https://openalex.org/W2146334809","https://openalex.org/W2156639694","https://openalex.org/W2165345255","https://openalex.org/W2167277498","https://openalex.org/W2169629169","https://openalex.org/W2296609965","https://openalex.org/W2345356450","https://openalex.org/W2461731879","https://openalex.org/W2610961739","https://openalex.org/W2625297138","https://openalex.org/W2632394526","https://openalex.org/W2750666523","https://openalex.org/W2889374687","https://openalex.org/W2889462515","https://openalex.org/W2896520210","https://openalex.org/W2937977583","https://openalex.org/W2967042165","https://openalex.org/W2970737019","https://openalex.org/W3004720641","https://openalex.org/W3010090216"],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"speech-based":[1],"affect":[2,135,173,189,203,221],"recognition":[3],"of":[4,16,32,83,149,201,216,227,233],"individuals":[5],"in":[6,13,50,136,146,162,180],"dyadic":[7],"conversation":[8],"is":[9,184],"a":[10,71,133,147,153,156,224],"challenging":[11,199],"task,":[12],"part":[14],"because":[15],"its":[17],"heavy":[18],"reliance":[19],"on":[20,111,197],"manual":[21],"pre-processing.":[22],"Traditional":[23],"approaches":[24],"frequently":[25],"require":[26],"hand-crafted":[27],"speech":[28],"features":[29,59,215],"and":[30,60,79,91,119,125,131,155,223,230],"segmentation":[31],"speaker":[33],"turns.":[34],"In":[35,166],"this":[36],"work,":[37],"we":[38,129,205],"design":[39],"end-to-end":[40,77],"deep":[41],"learning":[42],"methods":[43],"to":[44,64,107,109,141,168],"recognize":[45],"each":[46,175,234],"person's":[47],"affective":[48,117],"expression":[49],"an":[51],"audio":[52],"stream":[53],"with":[54],"two":[55,92],"speakers,":[56],"automatically":[57],"discovering":[58],"time":[61],"regions":[62,113],"relevant":[63],"the":[65,76,81,100,112,122,181,187,198,207,217],"target":[66,115],"speaker's":[67,116],"affect.":[68],"We":[69],"integrate":[70],"local":[72],"attention":[73,85,103],"mechanism":[74],"into":[75],"architecture":[78],"compare":[80],"performance":[82],"three":[84,191],"implementations":[86],"-":[87,139],"one":[88],"mean":[89],"pooling":[90,94],"weighted":[93],"methods.":[95],"Our":[96],"results":[97],"show":[98],"that":[99],"proposed":[101],"weighted-pooling":[102],"solutions":[104],"are":[105],"able":[106],"learn":[108],"focus":[110],"containing":[114],"information":[118],"successfully":[120],"extract":[121],"individual's":[123],"valence":[124],"arousal":[126],"intensity.":[127],"Here":[128],"introduce":[130],"use":[132],"\"dyadic":[134],"multimodal":[137],"interaction":[138],"parent":[140,154],"child\"":[142],"(DAMI-P2C)":[143],"dataset":[144,183,210],"collected":[145],"study":[148],"34":[150],"families,":[151],"where":[152],"child":[157],"(3-7":[158],"years":[159],"old)":[160],"engage":[161],"reading":[163],"storybooks":[164],"together.":[165],"contrast":[167],"existing":[169],"public":[170],"datasets":[171],"for":[172,177,186],"recognition,":[174],"instance":[176],"both":[178],"speakers":[179],"DAMI-P2C":[182,209],"annotated":[185,208],"perceived":[188],"by":[190],"labelers.":[192],"To":[193],"encourage":[194],"more":[195],"research":[196],"task":[200],"multi-speaker":[202],"sensing,":[204],"make":[206],"publicly":[211],"available,":[212],"including":[213],"acoustic":[214],"dyads'":[218],"raw":[219],"audios,":[220],"annotations,":[222],"diverse":[225],"set":[226],"developmental,":[228],"social,":[229],"demographic":[231],"profiles":[232],"dyad.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2020-09-01T00:00:00"}