{"id":"https://openalex.org/W2402700212","doi":"https://doi.org/10.21437/eurospeech.1997-532","title":"Real-time lip-tracking for lipreading","display_name":"Real-time lip-tracking for lipreading","publication_year":1997,"publication_date":"1997-09-22","ids":{"openalex":"https://openalex.org/W2402700212","doi":"https://doi.org/10.21437/eurospeech.1997-532","mag":"2402700212"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1997-532","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://publikationen.bibliothek.kit.edu/185597/1863","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087051920","display_name":"Rainer Stiefelhagen","orcid":"https://orcid.org/0000-0001-8046-4945"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rainer Stiefelhagen","raw_affiliation_strings":["Interactive Systems Laboratories University of Karlsruhe | Germany, Carnegie Mellon University | USA"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories University of Karlsruhe | Germany, Carnegie Mellon University | USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065376703","display_name":"Uwe Meier","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Uwe Meier","raw_affiliation_strings":["Interactive Systems Laboratories University of Karlsruhe | Germany, Carnegie Mellon University | USA"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories University of Karlsruhe | Germany, Carnegie Mellon University | USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108358377","display_name":"Jie Yang","orcid":"https://orcid.org/0009-0003-9378-9281"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Yang","raw_affiliation_strings":["Interactive Systems Laboratories University of Karlsruhe | Germany, Carnegie Mellon University | USA"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories University of Karlsruhe | Germany, Carnegie Mellon University | USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087051920"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.8531,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.79038637,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2007","last_page":"2010"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9991999864578247,"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/T11448","display_name":"Face recognition and analysis","score":0.9650999903678894,"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"}},{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9419000148773193,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7035717368125916},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5260372161865234},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5141985416412354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44622698426246643},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43556082248687744},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09848809242248535}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7035717368125916},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5260372161865234},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5141985416412354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44622698426246643},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43556082248687744},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09848809242248535},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/eurospeech.1997-532","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","raw_type":"proceedings-article"},{"id":"pmh:oai:EVASTAR-Karlsruhe.de:185597","is_oa":true,"landing_page_url":"https://publikationen.bibliothek.kit.edu/185597","pdf_url":"https://publikationen.bibliothek.kit.edu/185597/1863","source":{"id":"https://openalex.org/S4306401992","display_name":"Repository KITopen (Karlsruhe Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102335020","host_organization_name":"Karlsruhe Institute of Technology","host_organization_lineage":["https://openalex.org/I102335020"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:bookPart"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.43.8471","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.43.8471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.is.cs.cmu.edu/~wwwadm/papers/speech/EUROSPEECH97/EUROSPEECH97-rainer.ps.gz","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:EVASTAR-Karlsruhe.de:185597","is_oa":true,"landing_page_url":"https://publikationen.bibliothek.kit.edu/185597","pdf_url":"https://publikationen.bibliothek.kit.edu/185597/1863","source":{"id":"https://openalex.org/S4306401992","display_name":"Repository KITopen (Karlsruhe Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102335020","host_organization_name":"Karlsruhe Institute of Technology","host_organization_lineage":["https://openalex.org/I102335020"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:bookPart"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332923","display_name":"U.S. Navy","ror":"https://ror.org/03ar0mv07"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2402700212.pdf","grobid_xml":"https://content.openalex.org/works/W2402700212.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W22517275","https://openalex.org/W124086577","https://openalex.org/W201959675","https://openalex.org/W1573758649","https://openalex.org/W1929733467","https://openalex.org/W1972212822","https://openalex.org/W2023205241","https://openalex.org/W2099400988","https://openalex.org/W2153606381","https://openalex.org/W2163945819","https://openalex.org/W2168824259","https://openalex.org/W3040828298","https://openalex.org/W3041461622"],"related_works":["https://openalex.org/W1891287906","https://openalex.org/W2036807459","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2772917594","https://openalex.org/W2166024367","https://openalex.org/W2755342338","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2058170566"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,44,92,101,166,177],"new":[4,33,62],"approach":[5,63,85],"to":[6,19,124,139,150],"lip":[7,93,118,142],"tracking":[8,13,79,94,174],"for":[9,128,155],"lipreading.Instead":[10],"of":[11,70,78,82,91,108,168,171,179,185,190],"only":[12],"features":[14,26],"on":[15],"lips,":[16],"we":[17,163],"propose":[18],"track":[20],"lips":[21],"along":[22],"with":[23,173],"other":[24],"facial":[25,60],"such":[27],"as":[28],"pupils":[29],"and":[30,51,56,72,76,183],"nostril.In":[31],"the":[32,35,48,59,68,83,121,129,141,152,169,188],"approach,":[34],"face":[36],"is":[37],"rst":[38],"located":[39,55],"in":[40,144,187],"an":[41,156],"image":[42,106,122],"using":[43,181],"stochastic":[45],"skin-color":[46],"model,":[47],"eyes,":[49],"lip-corners":[50],"nostrils":[52],"are":[53],"then":[54],"tracked":[57],"inside":[58],"region.The":[61],"can":[64],"e":[65],"ectively":[66],"improve":[67],"robustness":[69],"lip-tracking":[71],"simplify":[73],"automatic":[74],"detection":[75,182],"recovery":[77],"failure.The":[80],"feasibility":[81],"proposed":[84],"has":[86,97,115,135],"been":[87,98,136],"demonstrated":[88],"by":[89,100,176],"implementation":[90],"system.The":[95,133],"system":[96,114,134],"tested":[99],"database":[102],"that":[103],"contains":[104],"900":[105],"sequences":[107,123,162],"di":[109],"erent":[110],"speakers":[111],"spelling":[112],"words.The":[113],"successfully":[116],"extract":[117,140],"regions":[119],"from":[120,146],"obtain":[125,151],"training":[126],"data":[127],"audio-visual":[130,157],"speech":[131,158],"recognition":[132,159],"also":[137],"applied":[138],"region":[143],"real-time":[145],"live":[147],"video":[148],"images":[149],"visual":[153],"input":[154],"system.On":[160],"test":[161],"have":[164],"achieved":[165],"reduction":[167],"number":[170],"frames":[172],"failures":[175],"factor":[178],"two":[180],"prediction":[184],"outliers":[186],"set":[189],"found":[191],"features.":[192]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}