{"id":"https://openalex.org/W2137938204","doi":"https://doi.org/10.1109/amfg.2003.1240826","title":"Boosted audio-visual HMM for speech reading","display_name":"Boosted audio-visual HMM for speech reading","publication_year":2004,"publication_date":"2004-04-23","ids":{"openalex":"https://openalex.org/W2137938204","doi":"https://doi.org/10.1109/amfg.2003.1240826","mag":"2137938204"},"language":"en","primary_location":{"id":"doi:10.1109/amfg.2003.1240826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/amfg.2003.1240826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443)","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/A5100688994","display_name":"Peihao Yin","orcid":"https://orcid.org/0009-0001-1496-1107"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pei Yin","raw_affiliation_strings":["GVU Center College of Computing, Georgia Institute of Technology, Atlanta, GA, USA","[Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA]"],"affiliations":[{"raw_affiliation_string":"GVU Center College of Computing, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA]","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070348998","display_name":"Irfan Essa","orcid":"https://orcid.org/0000-0002-6236-2969"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I. Essa","raw_affiliation_strings":["GVU Center College of Computing, Georgia Institute of Technology, Atlanta, GA, USA","[Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA]"],"affiliations":[{"raw_affiliation_string":"GVU Center College of Computing, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA]","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002228469","display_name":"James M. Rehg","orcid":"https://orcid.org/0000-0003-1793-5462"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J.M. Rehg","raw_affiliation_strings":["GVU Center College of Computing, Georgia Institute of Technology, Atlanta, GA, USA","[Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA]"],"affiliations":[{"raw_affiliation_string":"GVU Center College of Computing, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA]","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100688994"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.8413,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74382483,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"68","last_page":"73"},"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/T11309","display_name":"Music and Audio Processing","score":0.9955000281333923,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9943000078201294,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.869400680065155},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7854182124137878},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7530160546302795},{"id":"https://openalex.org/keywords/adaboost","display_name":"AdaBoost","score":0.6846450567245483},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5710142850875854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5505648851394653},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4909673035144806},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.43205612897872925},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.43034863471984863},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.15688791871070862},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07807204127311707}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.869400680065155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7854182124137878},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7530160546302795},{"id":"https://openalex.org/C141404830","wikidata":"https://www.wikidata.org/wiki/Q2823869","display_name":"AdaBoost","level":3,"score":0.6846450567245483},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5710142850875854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5505648851394653},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4909673035144806},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.43205612897872925},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.43034863471984863},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.15688791871070862},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07807204127311707},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/amfg.2003.1240826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/amfg.2003.1240826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W586860715","https://openalex.org/W1486915487","https://openalex.org/W1527102103","https://openalex.org/W1549965231","https://openalex.org/W1560013842","https://openalex.org/W1966280301","https://openalex.org/W1988790447","https://openalex.org/W2033419168","https://openalex.org/W2093677674","https://openalex.org/W2128022812","https://openalex.org/W2133067194","https://openalex.org/W2140020980","https://openalex.org/W2150652745","https://openalex.org/W2168020168","https://openalex.org/W2487271655","https://openalex.org/W3097096317","https://openalex.org/W3214102110","https://openalex.org/W4245134515","https://openalex.org/W6684338786"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W1591475660","https://openalex.org/W2001275470","https://openalex.org/W2073996508","https://openalex.org/W3145575561","https://openalex.org/W2164162849"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,18],"new":[3],"approach":[4],"for":[5],"combining":[6],"acoustic":[7,38],"and":[8,40,86],"visual":[9,46],"measurements":[10],"to":[11,33,44,75,80,90],"aid":[12],"in":[13,95],"recognizing":[14],"lip":[15],"shapes":[16],"of":[17,29,66,72],"person":[19],"speaking.":[20],"Our":[21],"method":[22],"relies":[23],"on":[24,63],"computing":[25],"the":[26,37,55,64,82,96],"maximum":[27],"likelihoods":[28],"(a)":[30],"HMM":[31,42,89],"used":[32,43],"model":[34,45],"phonemes":[35],"from":[36,49],"signal,":[39],"(b)":[41],"features":[47,59,84],"motions":[48],"video.":[50],"One":[51],"significant":[52],"addition":[53],"is":[54],"dynamic":[56,92],"analysis":[57],"with":[58],"selected":[60],"by":[61],"AdaBoost,":[62],"basis":[65],"their":[67],"discriminant":[68],"ability.":[69],"This":[70],"form":[71],"integration,":[73],"leading":[74],"boosted":[76],"HMM,":[77],"permits":[78],"AdaBoost":[79],"find":[81],"best":[83],"first,":[85],"then":[87],"uses":[88],"exploit":[91],"information":[93],"inherent":[94],"signal.":[97]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
