{"id":"https://openalex.org/W2154951003","doi":"https://doi.org/10.1109/icpr.2002.1048371","title":"Integrated analysis of speech and images as a probabilistic decoding process","display_name":"Integrated analysis of speech and images as a probabilistic decoding process","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W2154951003","doi":"https://doi.org/10.1109/icpr.2002.1048371","mag":"2154951003"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2002.1048371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2002.1048371","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Object recognition supported by user interaction for service robots","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/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":true,"raw_author_name":"S. Wachsmuth","raw_affiliation_strings":["Faculty of Technology, Bielefeld University, Bielefeld, Germany"],"affiliations":[{"raw_affiliation_string":"Faculty of Technology, 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":["Faculty of Technology, Bielefeld University, Bielefeld, Germany"],"affiliations":[{"raw_affiliation_string":"Faculty of Technology, Bielefeld University, Bielefeld, Germany","institution_ids":["https://openalex.org/I20121455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029209441"],"corresponding_institution_ids":["https://openalex.org/I20121455"],"apc_list":null,"apc_paid":null,"fwci":0.8889,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76681741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"588","last_page":"592"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9973999857902527,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9973999857902527,"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/T12031","display_name":"Speech and dialogue systems","score":0.9965000152587891,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7995204329490662},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7530122995376587},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.747905969619751},{"id":"https://openalex.org/keywords/emulation","display_name":"Emulation","score":0.7073756456375122},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5887967348098755},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5849120020866394},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.567616879940033},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5307885408401489},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.4971034824848175},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4854336380958557},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4637957215309143},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3407120108604431},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3306678831577301},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2270534634590149},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06924813985824585}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7995204329490662},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7530122995376587},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.747905969619751},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.7073756456375122},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5887967348098755},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5849120020866394},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.567616879940033},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5307885408401489},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.4971034824848175},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4854336380958557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4637957215309143},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3407120108604431},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3306678831577301},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2270534634590149},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06924813985824585},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icpr.2002.1048371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2002.1048371","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Object recognition supported by user interaction for service robots","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.689.3918","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.689.3918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hci.iwr.uni-heidelberg.de/publications/dip/2002/ICPR2002/DATA/06_1_08.PDF","raw_type":"text"},{"id":"pmh:oai:pub.librecat.org:2618720","is_oa":false,"landing_page_url":"https://pub.uni-bielefeld.de/record/2618720","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":"Wachsmuth S, Sagerer G. Integrated Analysis of Speech and Images as a Probabilistic Decoding Process. In:  <em>Proc. of 16th Int. Conf. on Pattern Recognition (ICPR\u20192002)</em>. Qu\u00e9bec City, Qu\u00e9bec, Canada: IEEE;  2002: 588-592.","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W88010277","https://openalex.org/W152045702","https://openalex.org/W1544444076","https://openalex.org/W1549782497","https://openalex.org/W1550791608","https://openalex.org/W1552416990","https://openalex.org/W1565032492","https://openalex.org/W1577211289","https://openalex.org/W1587808007","https://openalex.org/W1622726500","https://openalex.org/W1787850985","https://openalex.org/W1815594279","https://openalex.org/W1839778843","https://openalex.org/W1969228515","https://openalex.org/W2025713029","https://openalex.org/W2043254070","https://openalex.org/W2079344866","https://openalex.org/W2091428895","https://openalex.org/W2131193678","https://openalex.org/W2134841707","https://openalex.org/W2147810005","https://openalex.org/W2153543869","https://openalex.org/W2156430594","https://openalex.org/W2164018153","https://openalex.org/W2165604538","https://openalex.org/W2167953274","https://openalex.org/W2949437261","https://openalex.org/W4238313768","https://openalex.org/W4250143236","https://openalex.org/W6632384879","https://openalex.org/W6633274295","https://openalex.org/W6636586397","https://openalex.org/W6661463667","https://openalex.org/W6681884492","https://openalex.org/W7046484810"],"related_works":["https://openalex.org/W2154523322","https://openalex.org/W2083200807","https://openalex.org/W2364195017","https://openalex.org/W2049983405","https://openalex.org/W2355430452","https://openalex.org/W1603137082","https://openalex.org/W2392315374","https://openalex.org/W1951195060","https://openalex.org/W2351776620","https://openalex.org/W2352195574"],"abstract_inverted_index":{"Speech":[0],"understanding":[1],"and":[2,40,65],"vision":[3],"are":[4,50],"the":[5,14,44,60],"two":[6],"most":[7],"important":[8],"modalities":[9],"in":[10,100],"human-human":[11],"communication.":[12],"However,":[13],"emulation":[15],"of":[16,62],"these":[17],"by":[18],"a":[19,56,69],"computer":[20],"faces":[21],"fundamental":[22],"difficulties":[23],"due":[24],"to":[25,106],"noisy":[26],"data,":[27],"vague":[28],"meanings,":[29],"previously":[30],"unseen":[31],"objects":[32],"or":[33,85],"unheard":[34],"words,":[35],"occlusions,":[36],"spontaneous":[37],"speech":[38,64],"effects,":[39],"context":[41],"dependence.":[42],"Thus,":[43],"interpretation":[45],"processes":[46],"on":[47,59],"both":[48],"channels":[49],"highly":[51],"error-prone.":[52],"This":[53],"paper":[54],"presents":[55],"new":[57],"perspective":[58],"problem":[61],"relating":[63],"image":[66],"interpretations":[67],"as":[68],"probabilistic":[70,102],"decoding":[71],"process.":[72],"It":[73],"is":[74,81,90],"shown":[75,91],"that":[76,92,104],"such":[77],"an":[78],"integration":[79],"scheme":[80],"robust":[82],"regarding":[83],"partial":[84],"erroneous":[86],"interpretations.":[87],"Furthermore,":[88],"it":[89],"implicit":[93],"error":[94],"correction":[95],"strategies":[96],"can":[97],"be":[98],"formulated":[99],"this":[101],"framework":[103],"lead":[105],"improved":[107],"scene":[108],"interpretation.":[109]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}