{"id":"https://openalex.org/W2171456773","doi":"https://doi.org/10.1109/isspa.2010.5605429","title":"Lip detection for audio-visual speech recognition in-car environment","display_name":"Lip detection for audio-visual speech recognition in-car environment","publication_year":2010,"publication_date":"2010-05-01","ids":{"openalex":"https://openalex.org/W2171456773","doi":"https://doi.org/10.1109/isspa.2010.5605429","mag":"2171456773"},"language":"en","primary_location":{"id":"doi:10.1109/isspa.2010.5605429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspa.2010.5605429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th International Conference on Information Science, Signal Processing and their Applications (ISSPA 2010)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.qut.edu.au/32879/1/c32879.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085576560","display_name":"Rajitha Navarathna","orcid":"https://orcid.org/0000-0002-0105-4911"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Rajitha Navarathna","raw_affiliation_strings":["Speech, Audio, Image and Video Technology, Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Speech, Audio, Image and Video Technology, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032604032","display_name":"Patrick Lucey","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Patrick Lucey","raw_affiliation_strings":["Speech, Audio, Image and Video Technology, Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Speech, Audio, Image and Video Technology, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000014182","display_name":"David Dean","orcid":"https://orcid.org/0000-0003-1274-9775"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Dean","raw_affiliation_strings":["Speech, Audio, Image and Video Technology, Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Speech, Audio, Image and Video Technology, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034095159","display_name":"Clinton Fookes","orcid":"https://orcid.org/0000-0002-8515-6324"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Clinton Fookes","raw_affiliation_strings":["Speech, Audio, Image and Video Technology, Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Speech, Audio, Image and Video Technology, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055128383","display_name":"Sridha Sridharan","orcid":"https://orcid.org/0000-0003-4316-9001"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sridha Sridharan","raw_affiliation_strings":["Speech, Audio, Image and Video Technology, Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Speech, Audio, Image and Video Technology, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5085576560"],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":null,"apc_paid":null,"fwci":2.7067,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.91281433,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"1","issue":null,"first_page":"598","last_page":"601"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9936000108718872,"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/T13289","display_name":"Infant Health and Development","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7828848361968994},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7557456493377686},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7209770083427429},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.6721820831298828},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6337589621543884},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3456169366836548},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.19001469016075134}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7828848361968994},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7557456493377686},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7209770083427429},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.6721820831298828},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6337589621543884},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3456169366836548},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.19001469016075134}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/isspa.2010.5605429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspa.2010.5605429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th International Conference on Information Science, Signal Processing and their Applications (ISSPA 2010)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.qut.edu.au:32879","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.qut.edu.au/32879/1/c32879.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010","raw_type":"Chapter in Book, Report or Conference volume"}],"best_oa_location":{"id":"pmh:oai:eprints.qut.edu.au:32879","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.qut.edu.au/32879/1/c32879.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010","raw_type":"Chapter in Book, Report or Conference volume"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2171456773.pdf","grobid_xml":"https://content.openalex.org/works/W2171456773.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W142803501","https://openalex.org/W142945732","https://openalex.org/W1988790447","https://openalex.org/W2004143321","https://openalex.org/W2024082079","https://openalex.org/W2074796660","https://openalex.org/W2098923380","https://openalex.org/W2164598857","https://openalex.org/W4285719527","https://openalex.org/W6605737493","https://openalex.org/W6605769872"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351","https://openalex.org/W1911859126","https://openalex.org/W642007152","https://openalex.org/W2184127972","https://openalex.org/W2343205865","https://openalex.org/W2341426843","https://openalex.org/W2009814707"],"abstract_inverted_index":{"Acoustically,":[0],"car":[1],"cabins":[2],"are":[3],"extremely":[4],"noisy":[5],"and":[6,63,68,104,115],"as":[7,36],"a":[8,37,56,99],"consequence":[9],"audio-only,":[10],"in-car":[11,89],"voice":[12],"recognition":[13,50,121],"systems":[14],"perform":[15],"poorly.":[16],"As":[17],"the":[18,27,32,65,82,86,94,106,110],"visual":[19,28,47,111],"modality":[20],"is":[21,34,98],"immune":[22],"to":[23,60],"acoustic":[24],"noise,":[25],"using":[26,45,81],"lip":[29,69],"information":[30],"from":[31],"driver":[33],"seen":[35],"viable":[38],"strategy":[39],"in":[40,71],"circumventing":[41],"this":[42,74],"problem":[43],"by":[44],"audio":[46],"automatic":[48],"speech":[49,120],"(AVASR).":[51],"However,":[52],"implementing":[53],"AVASR":[54],"requires":[55],"system":[57],"being":[58],"able":[59],"accurately":[61],"locate":[62],"track":[64],"drivers":[66],"face":[67],"area":[70],"real-time.":[72],"In":[73],"paper":[75],"we":[76,91],"present":[77],"such":[78],"an":[79],"approach":[80,97],"Viola-Jones":[83],"algorithm.":[84],"Using":[85],"AVICAR":[87],"[1]":[88],"database,":[90],"show":[92],"that":[93],"Viola-":[95],"Jones":[96],"suitable":[100],"method":[101],"of":[102,113],"locating":[103],"tracking":[105],"driver's":[107],"lips":[108],"despite":[109],"variability":[112],"illumination":[114],"head":[116],"pose":[117],"for":[118],"audio-visual":[119],"system.":[122]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
