{"id":"https://openalex.org/W4408355494","doi":"https://doi.org/10.1109/icassp49660.2025.10889480","title":"Multimodal Machine Learning Can Predict Videoconference Fluidity and Enjoyment","display_name":"Multimodal Machine Learning Can Predict Videoconference Fluidity and Enjoyment","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355494","doi":"https://doi.org/10.1109/icassp49660.2025.10889480"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5102881477","display_name":"Andrew Chang","orcid":"https://orcid.org/0009-0003-1441-1310"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrew Chang","raw_affiliation_strings":["New York University,New York,USA"],"affiliations":[{"raw_affiliation_string":"New York University,New York,USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115792754","display_name":"Viswadruth Akkaraju","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viswadruth Akkaraju","raw_affiliation_strings":["New York University,New York,USA"],"affiliations":[{"raw_affiliation_string":"New York University,New York,USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115792755","display_name":"Ray McFadden Cogliano","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ray McFadden Cogliano","raw_affiliation_strings":["New York University,New York,USA"],"affiliations":[{"raw_affiliation_string":"New York University,New York,USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033417964","display_name":"David Poeppel","orcid":"https://orcid.org/0000-0003-0184-163X"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Poeppel","raw_affiliation_strings":["New York University,New York,USA"],"affiliations":[{"raw_affiliation_string":"New York University,New York,USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035737956","display_name":"Dustin Freeman","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dustin Freeman","raw_affiliation_strings":["New York University,New York,USA"],"affiliations":[{"raw_affiliation_string":"New York University,New York,USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102881477"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04365973,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9577999711036682,"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"}},"topics":[{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9577999711036682,"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/computer-science","display_name":"Computer science","score":0.6737943887710571},{"id":"https://openalex.org/keywords/videoconferencing","display_name":"Videoconferencing","score":0.6254103779792786},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.45427262783050537},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4152563512325287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36287373304367065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6737943887710571},{"id":"https://openalex.org/C22561748","wikidata":"https://www.wikidata.org/wiki/Q854954","display_name":"Videoconferencing","level":2,"score":0.6254103779792786},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.45427262783050537},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4152563512325287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36287373304367065}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1967043959","https://openalex.org/W2116031726","https://openalex.org/W2395639500","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2613941748","https://openalex.org/W2910670902","https://openalex.org/W3011043904","https://openalex.org/W3044476465","https://openalex.org/W3094618205","https://openalex.org/W3126233671","https://openalex.org/W3136944856","https://openalex.org/W3211732462","https://openalex.org/W4226071457","https://openalex.org/W4285019489","https://openalex.org/W4375869341","https://openalex.org/W4390051549","https://openalex.org/W4399583435","https://openalex.org/W6764045775","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2142127558","https://openalex.org/W1546632383","https://openalex.org/W4313257994","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2309250577"],"abstract_inverted_index":{"Videoconferencing":[0],"is":[1,115],"now":[2],"a":[3,116],"frequent":[4],"mode":[5],"of":[6,22,34,42,83,137],"communication":[7],"in":[8,37],"both":[9],"professional":[10],"and":[11,20,55,69],"informal":[12],"settings,":[13],"yet":[14],"it":[15],"often":[16],"lacks":[17],"the":[18,46],"fluidity":[19],"enjoyment":[21],"in-person":[23],"conversation.":[24],"This":[25,98],"study":[26,143],"leverages":[27],"multimodal":[28,102,127],"machine":[29,128],"learning":[30,129],"to":[31,59,85,118,133],"predict":[32,107],"moments":[33,136],"negative":[35,138],"experience":[36,123,140],"videoconferencing.":[38],"We":[39],"sampled":[40],"thousands":[41],"short":[43],"clips":[44],"from":[45],"RoomReader":[47],"corpus":[48],"[1],":[49],"extracting":[50],"audio":[51,93],"embeddings,":[52],"facial":[53],"actions,":[54],"body":[56],"motion":[57],"features":[58,94],"train":[60],"models":[61,79],"for":[62,141],"identifying":[63],"low":[64,67],"conversational":[65,71,110],"fluidity,":[66],"enjoyment,":[68],"classifying":[70],"events":[72],"(backchanneling,":[73],"interruption,":[74],"or":[75,144],"gap).":[76],"Our":[77],"best":[78],"achieved":[80],"an":[81],"ROC-AUC":[82],"up":[84],"0.87":[86],"on":[87,120],"hold-out":[88],"videoconference":[89],"sessions,":[90],"with":[91],"domain-general":[92],"proving":[95],"most":[96],"critical.":[97],"work":[99],"demonstrates":[100],"that":[101,126],"audio-video":[103],"signals":[104],"can":[105,130],"effectively":[106],"high-level":[108],"subjective":[109],"outcomes.":[111],"In":[112],"addition,":[113],"this":[114],"contribution":[117],"research":[119],"videoconferencing":[121],"user":[122,139],"by":[124],"showing":[125],"be":[131],"used":[132],"identify":[134],"rare":[135],"further":[142],"mitigation.":[145]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}