{"id":"https://openalex.org/W2765247238","doi":"https://doi.org/10.1145/3136755.3136813","title":"Multimodal analysis of vocal collaborative search: a public corpus and results","display_name":"Multimodal analysis of vocal collaborative search: a public corpus and results","publication_year":2017,"publication_date":"2017-11-03","ids":{"openalex":"https://openalex.org/W2765247238","doi":"https://doi.org/10.1145/3136755.3136813","mag":"2765247238"},"language":"en","primary_location":{"id":"doi:10.1145/3136755.3136813","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3136755.3136813","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100681741","display_name":"Daniel McDuff","orcid":"https://orcid.org/0000-0001-7313-0082"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel McDuff","raw_affiliation_strings":["Microsoft Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046377370","display_name":"Paul Thomas","orcid":"https://orcid.org/0000-0003-2425-3136"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul Thomas","raw_affiliation_strings":["Microsoft Research, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Australia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020340631","display_name":"Mary Czerwinski","orcid":"https://orcid.org/0000-0003-0881-401X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mary Czerwinski","raw_affiliation_strings":["Microsoft Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055132321","display_name":"Nick Craswell","orcid":"https://orcid.org/0000-0002-9351-8137"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nick Craswell","raw_affiliation_strings":["Microsoft Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"456","last_page":"463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13155","display_name":"Digital Communication and Language","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T13155","display_name":"Digital Communication and Language","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9972000122070312,"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/T11148","display_name":"Language, Metaphor, and Cognition","score":0.9966999888420105,"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":0.700421929359436},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44923052191734314},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4444105327129364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38030844926834106}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.700421929359436},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44923052191734314},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4444105327129364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38030844926834106}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3136755.3136813","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3136755.3136813","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6499999761581421,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1595126664","https://openalex.org/W1596947417","https://openalex.org/W1889777305","https://openalex.org/W1976725440","https://openalex.org/W1981231682","https://openalex.org/W1989689139","https://openalex.org/W2009266235","https://openalex.org/W2032139348","https://openalex.org/W2045528981","https://openalex.org/W2090777335","https://openalex.org/W2096131645","https://openalex.org/W2099703387","https://openalex.org/W2114030807","https://openalex.org/W2127429655","https://openalex.org/W2148905283","https://openalex.org/W2157289187","https://openalex.org/W2299275441","https://openalex.org/W2339343773","https://openalex.org/W2395639500","https://openalex.org/W2538496976","https://openalex.org/W2572052422","https://openalex.org/W2740050834","https://openalex.org/W2755063892","https://openalex.org/W2911336608","https://openalex.org/W2951127645","https://openalex.org/W3097102333","https://openalex.org/W4285719527","https://openalex.org/W4290610135","https://openalex.org/W4292994367"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Intelligent":[0],"agents":[1,31],"have":[2],"the":[3,26,96,101,114,129,159,163],"potential":[4],"to":[5,25,36,50],"help":[6],"with":[7,108],"many":[8],"tasks.":[9,71],"Information":[10],"seeking":[11,45,168],"and":[12,34,47,92,111,135,145,183,185],"voice-enabled":[13],"search":[14,70],"assistants":[15],"are":[16,165],"becoming":[17],"very":[18],"common.":[19],"However,":[20],"there":[21],"remain":[22],"questions":[23],"as":[24,139],"extent":[27],"by":[28],"which":[29],"these":[30,104,155],"should":[32],"sense":[33],"respond":[35],"emotional":[37],"signals.":[38],"We":[39,99,116],"designed":[40],"a":[41,54,80,148],"set":[42],"of":[43,65,103,150,180],"information":[44,167],"tasks":[46,164],"recruited":[48],"participants":[49,73],"complete":[51],"them":[52],"using":[53,77],"human":[55],"intermediary.":[56],"In":[57],"total":[58],"we":[59,86],"collected":[60],"data":[61],"from":[62,95,128],"22":[63],"pairs":[64],"individuals,":[66],"each":[67],"completing":[68],"five":[69],"The":[72,170],"could":[74],"communicate":[75],"only":[76],"voice,":[78],"over":[79,177],"VoIP":[81],"service.":[82],"Using":[83],"automated":[84],"methods":[85],"extracted":[87],"facial":[88,133],"action,":[89],"voice":[90],"prosody":[91],"linguistic":[93],"features":[94],"audio-visual":[97],"recordings.":[98],"analyzed":[100],"characteristics":[102],"interactions":[105,156],"that":[106,118,125],"correlated":[107],"successful":[109],"communication":[110,130],"understanding":[112],"between":[113],"pairs.":[115],"found":[117],"those":[119],"who":[120],"were":[121,126,137],"expressive":[122],"in":[123],"channels":[124],"missing":[127],"channel":[131],"(e.g.,":[132],"actions":[134],"gaze)":[136],"rated":[138],"communicating":[140],"poorly,":[141],"being":[142],"less":[143],"helpful":[144],"understanding.":[146],"Having":[147],"way":[149],"reinstating":[151],"nonverbal":[152],"cues":[153],"into":[154],"would":[157],"improve":[158],"experience,":[160],"even":[161],"when":[162],"purely":[166],"exercises.":[169],"dataset":[171],"used":[172],"for":[173,192],"this":[174],"analysis":[175],"contains":[176],"15":[178],"hours":[179],"video,":[181],"audio":[182],"transcripts":[184],"reported":[186],"ratings.":[187],"It":[188],"is":[189],"publicly":[190],"available":[191],"researchers":[193],"at:":[194],"http://aka.ms/MISCv1.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}