{"id":"https://openalex.org/W4375868876","doi":"https://doi.org/10.1109/icassp49357.2023.10095598","title":"Towards Dialogue Modeling Beyond Text","display_name":"Towards Dialogue Modeling Beyond Text","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868876","doi":"https://doi.org/10.1109/icassp49357.2023.10095598"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095598","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5073235752","display_name":"Tongzi Wu","orcid":"https://orcid.org/0000-0001-5292-9469"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210125326","display_name":"Public Health Ontario","ror":"https://ror.org/025z8ah66","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I4210125326"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Tongzi Wu","raw_affiliation_strings":["Talka AI,Toronto,ON,Canada","University of Toronto, Toronto, ON, Canada","Talka AI, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Talka AI,Toronto,ON,Canada","institution_ids":["https://openalex.org/I4210125326"]},{"raw_affiliation_string":"University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Talka AI, Toronto, ON, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053105889","display_name":"Yuhao Zhou","orcid":"https://orcid.org/0000-0001-8074-6416"},"institutions":[{"id":"https://openalex.org/I4210125326","display_name":"Public Health Ontario","ror":"https://ror.org/025z8ah66","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I4210125326"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yuhao Zhou","raw_affiliation_strings":["Talka AI,Toronto,ON,Canada","Talka AI, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Talka AI,Toronto,ON,Canada","institution_ids":["https://openalex.org/I4210125326"]},{"raw_affiliation_string":"Talka AI, Toronto, ON, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103679471","display_name":"Wang Ling","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125326","display_name":"Public Health Ontario","ror":"https://ror.org/025z8ah66","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I4210125326"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Wang Ling","raw_affiliation_strings":["Talka AI,Toronto,ON,Canada","Talka AI, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Talka AI,Toronto,ON,Canada","institution_ids":["https://openalex.org/I4210125326"]},{"raw_affiliation_string":"Talka AI, Toronto, ON, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012352599","display_name":"Hojin Yang","orcid":"https://orcid.org/0000-0001-7645-6774"},"institutions":[{"id":"https://openalex.org/I4210125326","display_name":"Public Health Ontario","ror":"https://ror.org/025z8ah66","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I4210125326"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hojin Yang","raw_affiliation_strings":["Talka AI,Toronto,ON,Canada","Talka AI, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Talka AI,Toronto,ON,Canada","institution_ids":["https://openalex.org/I4210125326"]},{"raw_affiliation_string":"Talka AI, Toronto, ON, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108308820","display_name":"J. A. F. Veloso","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125326","display_name":"Public Health Ontario","ror":"https://ror.org/025z8ah66","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I4210125326"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Joana Veloso","raw_affiliation_strings":["Talka AI,Toronto,ON,Canada","Talka AI, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Talka AI,Toronto,ON,Canada","institution_ids":["https://openalex.org/I4210125326"]},{"raw_affiliation_string":"Talka AI, Toronto, ON, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018668652","display_name":"Lin Sun","orcid":"https://orcid.org/0000-0001-9607-9232"},"institutions":[{"id":"https://openalex.org/I4210125326","display_name":"Public Health Ontario","ror":"https://ror.org/025z8ah66","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I4210125326"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Lin Sun","raw_affiliation_strings":["Talka AI,Toronto,ON,Canada","Talka AI, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Talka AI,Toronto,ON,Canada","institution_ids":["https://openalex.org/I4210125326"]},{"raw_affiliation_string":"Talka AI, Toronto, ON, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109375071","display_name":"Ruixin Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125326","display_name":"Public Health Ontario","ror":"https://ror.org/025z8ah66","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I4210125326"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ruixin Huang","raw_affiliation_strings":["Talka AI,Toronto,ON,Canada","Talka AI, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Talka AI,Toronto,ON,Canada","institution_ids":["https://openalex.org/I4210125326"]},{"raw_affiliation_string":"Talka AI, Toronto, ON, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102511249","display_name":"Norberto Guimaraes","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125326","display_name":"Public Health Ontario","ror":"https://ror.org/025z8ah66","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I4210125326"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Norberto Guimaraes","raw_affiliation_strings":["Talka AI,Toronto,ON,Canada","Talka AI, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Talka AI,Toronto,ON,Canada","institution_ids":["https://openalex.org/I4210125326"]},{"raw_affiliation_string":"Talka AI, Toronto, ON, Canada","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028174137","display_name":"Scott Sanner","orcid":"https://orcid.org/0000-0001-7984-8394"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Scott Sanner","raw_affiliation_strings":["University of Toronto,Toronto,ON,Canada","University of Toronto, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto,Toronto,ON,Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5073235752"],"corresponding_institution_ids":["https://openalex.org/I185261750","https://openalex.org/I4210125326"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0386604,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9998000264167786,"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/T12031","display_name":"Speech and dialogue systems","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9961000084877014,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.8940364122390747},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.812612771987915},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7328495979309082},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.7258775234222412},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.7228796482086182},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.699760377407074},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5174142122268677},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.4926777482032776},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46627169847488403},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.41414546966552734},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3755854666233063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36893177032470703},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22205385565757751},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15277817845344543},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.10483530163764954},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07013270258903503}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.8940364122390747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.812612771987915},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7328495979309082},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.7258775234222412},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.7228796482086182},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.699760377407074},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5174142122268677},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.4926777482032776},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46627169847488403},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41414546966552734},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3755854666233063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36893177032470703},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22205385565757751},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15277817845344543},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.10483530163764954},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07013270258903503},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095598","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2017746714","https://openalex.org/W2073762424","https://openalex.org/W2106078370","https://openalex.org/W2167702024","https://openalex.org/W2168708019","https://openalex.org/W2742542661","https://openalex.org/W2798491816","https://openalex.org/W2896457183","https://openalex.org/W2944828972","https://openalex.org/W2962960500","https://openalex.org/W2990640172","https://openalex.org/W2997646412","https://openalex.org/W3003875515","https://openalex.org/W3015746570","https://openalex.org/W3035044096","https://openalex.org/W3035524453","https://openalex.org/W3039444588","https://openalex.org/W3145385912","https://openalex.org/W3157506437","https://openalex.org/W3161411634","https://openalex.org/W3166396011","https://openalex.org/W3214685499","https://openalex.org/W4256401083","https://openalex.org/W4312864639","https://openalex.org/W4312960652","https://openalex.org/W4381786045","https://openalex.org/W6684552912","https://openalex.org/W6755207826","https://openalex.org/W6770717842","https://openalex.org/W6771883515","https://openalex.org/W6777640276","https://openalex.org/W6781217715","https://openalex.org/W6791353385","https://openalex.org/W6795140394","https://openalex.org/W6804095316","https://openalex.org/W6843330092"],"related_works":["https://openalex.org/W2248852396","https://openalex.org/W73545470","https://openalex.org/W2366755249","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W199123384","https://openalex.org/W4239305747"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,15],"model":[4],"aspects":[5],"of":[6,77,81],"communication":[7],"beyond":[8],"the":[9,57,59,62,75,78,82],"words":[10],"that":[11,45,55,67],"are":[12,25],"said.":[13],"Specifically,":[14],"aim":[16],"to":[17,90],"detect":[18],"interruptions":[19],"and":[20,41,61],"active":[21],"listening":[22],"events,":[23],"which":[24],"important":[26],"elements":[27],"in":[28,51,73],"any":[29],"dialogue.":[30],"We":[31],"build":[32],"a":[33,52,70],"dataset":[34],"with":[35],"fine-grained":[36],"annotations":[37],"for":[38],"each":[39],"category":[40],"train":[42],"multimodal":[43],"models":[44],"take":[46],"into":[47],"account":[48],"all":[49],"channels":[50],"digital":[53],"conversation,":[54],"is,":[56],"video,":[58],"audio,":[60],"text.":[63],"Our":[64],"experiments":[65],"show":[66],"multimodality":[68],"is":[69],"necessary":[71],"component":[72],"modeling":[74],"complexity":[76],"non-textual":[79],"components":[80],"conversation":[83],"as":[84],"different":[85,88],"artifacts":[86],"require":[87],"modalities":[89],"capture":[91],"effectively.":[92]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}