{"id":"https://openalex.org/W2056030034","doi":"https://doi.org/10.1145/1322192.1322201","title":"Audiovisual recognition of spontaneous interest within conversations","display_name":"Audiovisual recognition of spontaneous interest within conversations","publication_year":2007,"publication_date":"2007-11-12","ids":{"openalex":"https://openalex.org/W2056030034","doi":"https://doi.org/10.1145/1322192.1322201","mag":"2056030034"},"language":"en","primary_location":{"id":"doi:10.1145/1322192.1322201","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1322192.1322201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th international conference on Multimodal interfaces","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":null,"display_name":"Bj\u00f6ern Schuller","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bj\u00f6ern Schuller","raw_affiliation_strings":["Technische Universitaet Muenchen, Muenchen, Germany","[Technische Universitaet Muenchen, Muenchen, Germany]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universitaet Muenchen, Muenchen, Germany","institution_ids":[]},{"raw_affiliation_string":"[Technische Universitaet Muenchen, Muenchen, Germany]","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059235993","display_name":"Ronald M\u00fceller","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ronald M\u00fceller","raw_affiliation_strings":["Technische Universitaet Muenchen, Muenchen, Germany","[Technische Universitaet Muenchen, Muenchen, Germany]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universitaet Muenchen, Muenchen, Germany","institution_ids":[]},{"raw_affiliation_string":"[Technische Universitaet Muenchen, Muenchen, Germany]","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000196362","display_name":"Benedikt H\u00f6ernler","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Benedikt H\u00f6ernler","raw_affiliation_strings":["Technische Universitaet Muenchen, Muenchen, Germany","[Technische Universitaet Muenchen, Muenchen, Germany]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universitaet Muenchen, Muenchen, Germany","institution_ids":[]},{"raw_affiliation_string":"[Technische Universitaet Muenchen, Muenchen, Germany]","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003239991","display_name":"A. Hoethker","orcid":null},"institutions":[{"id":"https://openalex.org/I1293612202","display_name":"Toyota Motor Corporation (Switzerland)","ror":"https://ror.org/05p0pbv75","country_code":"CH","type":"company","lineage":["https://openalex.org/I1293612202","https://openalex.org/I4210125472","https://openalex.org/I4210137853"]},{"id":"https://openalex.org/I4210120547","display_name":"Toyota Motor Corporation (Belgium)","ror":"https://ror.org/023g86t37","country_code":"BE","type":"company","lineage":["https://openalex.org/I4210120547","https://openalex.org/I4210125472","https://openalex.org/I4210137853"]}],"countries":["BE","CH"],"is_corresponding":false,"raw_author_name":"Anja H\u00f6ethker","raw_affiliation_strings":["Toyota Motor Europe, Zaventem, Belgium","Toyota Motor Europe, Zaventem, Belgium#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Motor Europe, Zaventem, Belgium","institution_ids":["https://openalex.org/I4210120547"]},{"raw_affiliation_string":"Toyota Motor Europe, Zaventem, Belgium#TAB#","institution_ids":["https://openalex.org/I1293612202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024267790","display_name":"Hitoshi Konosu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137853","display_name":"Toyota Motor Corporation (Japan)","ror":"https://ror.org/02zqm6r10","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4210137853"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hitoshi Konosu","raw_affiliation_strings":["Toyota Motor Corporation, Toyota City, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Motor Corporation, Toyota City, Japan","institution_ids":["https://openalex.org/I4210137853"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039092855","display_name":"Gerhard Rigoll","orcid":"https://orcid.org/0000-0003-1096-1596"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Rigoll","raw_affiliation_strings":["Technische Universitaet Muenchen, Muenchen, Germany","[Technische Universitaet Muenchen, Muenchen, Germany]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universitaet Muenchen, Muenchen, Germany","institution_ids":[]},{"raw_affiliation_string":"[Technische Universitaet Muenchen, Muenchen, Germany]","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.6685,"has_fulltext":false,"cited_by_count":83,"citation_normalized_percentile":{"value":0.96221794,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"30","last_page":"37"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9973999857902527,"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":0.9973999857902527,"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/T10860","display_name":"Speech and Audio Processing","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12032","display_name":"Multisensory perception and integration","score":0.9958000183105469,"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":0.7902512550354004},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7165172100067139},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.608020544052124},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5841773748397827},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5337997674942017},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.4488525390625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40965455770492554},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3405100107192993}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7902512550354004},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7165172100067139},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.608020544052124},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5841773748397827},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5337997674942017},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.4488525390625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40965455770492554},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3405100107192993},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1322192.1322201","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1322192.1322201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th international conference on Multimodal interfaces","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.44999998807907104,"display_name":"Quality Education"},{"id":"https://metadata.un.org/sdg/5","score":0.4099999964237213,"display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1548328233","https://openalex.org/W1570448133","https://openalex.org/W1587972688","https://openalex.org/W2032254851","https://openalex.org/W2085714685","https://openalex.org/W2111573508","https://openalex.org/W2123864036","https://openalex.org/W2149684865","https://openalex.org/W2161299247","https://openalex.org/W2171939880","https://openalex.org/W2172803778","https://openalex.org/W2224025406","https://openalex.org/W2966207845"],"related_works":["https://openalex.org/W1968552888","https://openalex.org/W2374116601","https://openalex.org/W3093134843","https://openalex.org/W2772323916","https://openalex.org/W1511346092","https://openalex.org/W1527532029","https://openalex.org/W2378167147","https://openalex.org/W3210777354","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"In":[0],"this":[1],"work":[2],"we":[3],"present":[4],"an":[5,148],"audiovisual":[6],"approach":[7],"to":[8,42,122],"the":[9,57,78,85,165],"recognition":[10],"of":[11,60,77,84,96,98,131,168],"spontaneous":[12,99],"interest":[13,132],"in":[14,105,151],"human":[15],"conversations.":[16],"For":[17],"a":[18,29,47,94,114,136,145,157,170],"most":[19],"robust":[20],"estimate,":[21],"information":[22,142],"from":[23],"four":[24],"sources":[25],"is":[26,38],"combined":[27],"by":[28,63,81,88],"synergistic":[30],"and":[31,51,65,83,107,118,126,144,163],"individual":[32],"failure":[33],"tolerant":[34],"fusion.":[35],"Firstly,":[36],"speech":[37],"analyzed":[39],"with":[40,113],"respect":[41],"acoustic":[43],"properties":[44],"based":[45,175],"on":[46,93,147,176],"high-dimensional":[48],"prosodic,":[49],"articulatory,":[50],"voice":[52],"quality":[53],"feature":[54],"space":[55,68],"plus":[56],"linguistic":[58],"analysis":[59,74],"spoken":[61],"content":[62],"LVCSR":[64],"bag-of-words":[66],"vector":[67],"modeling":[69],"including":[70],"non-verbals.":[71],"Secondly,":[72],"visual":[73],"provides":[75],"patterns":[76],"facial":[79],"expression":[80],"AAMs,":[82],"movement":[86],"activity":[87],"eye":[89],"tracking.":[90],"Experiments":[91],"base":[92],"database":[95],"10.5h":[97],"human-to-human":[100],"conversation":[101],"containing":[102],"20":[103],"subjects":[104],"gender":[106],"age-class":[108],"balance.":[109],"Recordings":[110],"are":[111,181],"fulfilled":[112],"room":[115],"microphone,":[116],"camera,":[117],"headsets":[119],"for":[120,160],"close-talk":[121],"consider":[123],"diverse":[124],"comfort":[125],"noise":[127],"conditions.":[128],"Three":[129],"levels":[130],"were":[133],"annotated":[134],"within":[135],"rich":[137],"transcription.":[138],"We":[139],"describe":[140],"each":[141],"stream":[143],"fusion":[146],"early":[149],"level":[150],"detail.":[152],"Our":[153],"experiments":[154],"aim":[155],"at":[156],"person-independent":[158],"system":[159],"real-life":[161],"usage":[162],"show":[164],"high":[166],"potential":[167],"such":[169],"multimodal":[171],"approach.":[172],"Benchmark":[173],"results":[174],"transcription":[177],"versus":[178],"automatic":[179],"processing":[180],"also":[182],"provided.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}