{"id":"https://openalex.org/W2147535357","doi":"https://doi.org/10.1109/icmi.2002.1166961","title":"Evaluating integrated speech- and image understanding","display_name":"Evaluating integrated speech- and image understanding","publication_year":2003,"publication_date":"2003-06-26","ids":{"openalex":"https://openalex.org/W2147535357","doi":"https://doi.org/10.1109/icmi.2002.1166961","mag":"2147535357"},"language":"en","primary_location":{"id":"doi:10.1109/icmi.2002.1166961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmi.2002.1166961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. Fourth IEEE International Conference on Multimodal Interfaces","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/A5003875445","display_name":"Christian Bauckhage","orcid":"https://orcid.org/0000-0001-6615-2128"},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"C. Bauckhage","raw_affiliation_strings":["Technical Faculty, Bielefeld University, Bielefeld, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical Faculty, Bielefeld University, Bielefeld, Germany","institution_ids":["https://openalex.org/I20121455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109276040","display_name":"J. Fritsch","orcid":null},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J. Fritsch","raw_affiliation_strings":["Technical Faculty, Bielefeld University, Bielefeld, Germany","Universitat Bielefeld, Bielefeld, Nordrhein-Westfalen, DE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical Faculty, Bielefeld University, Bielefeld, Germany","institution_ids":["https://openalex.org/I20121455"]},{"raw_affiliation_string":"Universitat Bielefeld, Bielefeld, Nordrhein-Westfalen, DE","institution_ids":["https://openalex.org/I20121455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026500995","display_name":"K.J. Rohifing","orcid":null},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"K.J. Rohifing","raw_affiliation_strings":["Tech. Fac., Bielefeld Univ., Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tech. Fac., Bielefeld Univ., Germany","institution_ids":["https://openalex.org/I20121455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029209441","display_name":"Sven Wachsmuth","orcid":"https://orcid.org/0000-0001-5371-7214"},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"S. Wachsmuth","raw_affiliation_strings":["Technical Faculty, Bielefeld University, Bielefeld, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical Faculty, Bielefeld University, Bielefeld, Germany","institution_ids":["https://openalex.org/I20121455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079251562","display_name":"Gerhard Sagerer","orcid":null},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"G. Sagerer","raw_affiliation_strings":["Technical Faculty, Bielefeld University, Bielefeld, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical Faculty, Bielefeld University, Bielefeld, Germany","institution_ids":["https://openalex.org/I20121455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20121455"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"9","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9980999827384949,"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":0.9980999827384949,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9955999851226807,"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":0.989300012588501,"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":0.821142315864563},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.7508897185325623},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.6949586868286133},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.6693897247314453},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6358694434165955},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.480802446603775},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45013606548309326},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.43412578105926514},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"Virtual reality","score":0.4201606512069702},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3431716859340668},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.334264874458313},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3226066529750824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3203744888305664}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.821142315864563},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.7508897185325623},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6949586868286133},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.6693897247314453},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6358694434165955},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.480802446603775},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45013606548309326},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.43412578105926514},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.4201606512069702},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3431716859340668},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.334264874458313},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3226066529750824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3203744888305664},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icmi.2002.1166961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmi.2002.1166961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. Fourth IEEE International Conference on Multimodal Interfaces","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.6.1755","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.6.1755","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.techfak.uni-bielefeld.de/ags/ai/publications/../publications/papers/Bauckhage2002-EIS.pdf","raw_type":"text"},{"id":"pmh:oai:pub.librecat.org:2618707","is_oa":false,"landing_page_url":"https://pub.uni-bielefeld.de/record/2618707","pdf_url":null,"source":{"id":"https://openalex.org/S4306401671","display_name":"PUB \u2013 Publications at Bielefeld University (Bielefeld University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20121455","host_organization_name":"Bielefeld University","host_organization_lineage":["https://openalex.org/I20121455"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bauckhage C, Fritsch J, Rohlfing K, Wachsmuth S, Sagerer G. Evaluating Integrated Speech- and Image Understanding. In: &lt;em&gt;Proc. IEEE International Conference on Multimodal Interfaces (ICMI\u201902)&lt;/em&gt;. Pittsburgh, PA; 2002: 9-14.","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W152045702","https://openalex.org/W1496092147","https://openalex.org/W1550791608","https://openalex.org/W1552416990","https://openalex.org/W1565032492","https://openalex.org/W1587808007","https://openalex.org/W1588460547","https://openalex.org/W1607588461","https://openalex.org/W1815594279","https://openalex.org/W1823369059","https://openalex.org/W1964997805","https://openalex.org/W2002768443","https://openalex.org/W2043254070","https://openalex.org/W2098856147","https://openalex.org/W2105882189","https://openalex.org/W2119171356","https://openalex.org/W2147810005","https://openalex.org/W2154951003","https://openalex.org/W2159080219","https://openalex.org/W2165604538","https://openalex.org/W2250345906","https://openalex.org/W2461659205","https://openalex.org/W2911697622","https://openalex.org/W2975494440","https://openalex.org/W4242494589","https://openalex.org/W4250143236","https://openalex.org/W6633274295","https://openalex.org/W6635149200","https://openalex.org/W6661463667","https://openalex.org/W6691376714","https://openalex.org/W6768127026"],"related_works":["https://openalex.org/W2378994405","https://openalex.org/W2385974820","https://openalex.org/W2373478030","https://openalex.org/W2378679551","https://openalex.org/W3149739944","https://openalex.org/W2392363776","https://openalex.org/W2063051341","https://openalex.org/W2591066345","https://openalex.org/W1494563618","https://openalex.org/W2209079739"],"abstract_inverted_index":{"The":[0],"capability":[1],"to":[2,25],"coordinate":[3],"and":[4,7,16,39,81,84],"interrelate":[5],"speech":[6,38,51],"vision":[8],"is":[9,22,65],"a":[10],"virtual":[11],"prerequisite":[12],"for":[13,36],"adaptive,":[14],"cooperative,":[15],"flexible":[17],"interaction":[18],"among":[19],"people.":[20],"It":[21],"therefore":[23],"fair":[24],"assume":[26],"that":[27,48],"human-machine":[28],"interaction,":[29],"too,":[30],"would":[31],"benefit":[32,76],"from":[33],"intelligent":[34],"interfaces":[35],"integrated":[37],"image":[40,54],"processing.":[41],"We":[42,73],"first":[43],"sketch":[44],"an":[45,66],"interactive":[46],"system":[47,87],"integrates":[49],"automatic":[50],"processing":[52],"with":[53],"understanding.":[55],"Then,":[56],"we":[57,63],"concentrate":[58],"on":[59],"performance":[60],"assessment":[61],"which":[62],"believe":[64],"emerging":[67],"key":[68],"issue":[69],"in":[70],"multimodal":[71],"interaction.":[72],"explain":[74],"the":[75],"of":[77],"time":[78],"scale":[79],"analysis":[80],"usability":[82],"studies":[83],"evaluate":[85],"our":[86],"accordingly.":[88]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}
