{"id":"https://openalex.org/W2285079731","doi":null,"title":"Head-pose and illumination invariant three-dimensional audio-visual speech recognition","display_name":"Head-pose and illumination invariant three-dimensional audio-visual speech recognition","alternate_titles":[],"publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2285079731","mag":"2285079731"},"language":"en","primary_location":{"id":"mag:2285079731","doi":null,"is_oa":false,"landing_page_url":"http://dl.acm.org/citation.cfm?id=1269693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"parent_works":[],"lineage":["https://openalex.org/W2285079731"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":[],"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/A5033151214","display_name":"Michael I. Miller","orcid":"https://orcid.org/0000-0003-4689-3855","observed_orcids":["https://orcid.org/0000-0003-4689-3855"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael I. Miller","raw_affiliation_strings":["The Johns hopkins University"],"raw_orcid":"https://orcid.org/0000-0003-4689-3855","affiliations":[{"raw_affiliation_string":"The Johns hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079631251","display_name":"Dmitri Bitouk","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dmitri Bitouk","raw_affiliation_strings":["The Johns hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Johns hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.6976,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75919225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9570000171661377,"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":0.9570000171661377,"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":0.01549999974668026,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.012299999594688416,"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/audio-visual-speech-recognition","display_name":"audio-visual speech recognition","score":0.9980000257492065},{"id":"https://openalex.org/keywords/head-pose-estimation","display_name":"head pose estimation","score":0.8360000252723694},{"id":"https://openalex.org/keywords/illumination-invariance","display_name":"illumination invariance","score":0.9789999723434448},{"id":"https://openalex.org/keywords/speaker-independent-speech-recognition","display_name":"speaker-independent recognition","score":0.7049999833106995},{"id":"https://openalex.org/keywords/large-vocabulary-speech-recognition","display_name":"large vocabulary speech recognition","score":0.890999972820282},{"id":"https://openalex.org/keywords/visual-feature-extraction","display_name":"visual feature extraction","score":0.7509999871253967}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7247751355171204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6930529475212097},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6154483556747437},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5936400890350342},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.5060333609580994},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4367876648902893},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4112514853477478},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4101041555404663},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2861548662185669},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.22468364238739014},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2285079731","doi":null,"is_oa":false,"landing_page_url":"http://dl.acm.org/citation.cfm?id=1269693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2541607918","https://openalex.org/W2405713570","https://openalex.org/W182684292","https://openalex.org/W2105768392","https://openalex.org/W4288043122","https://openalex.org/W2141939292","https://openalex.org/W2074905202","https://openalex.org/W1608493013","https://openalex.org/W98577832","https://openalex.org/W2184549941"],"abstract_inverted_index":{"Speech":[0],"perception":[1],"is":[2,88,119,138,148,219],"bimodal,":[3],"employing":[4],"not":[5],"only":[6],"the":[7,20,53,72,75,82,125,129,144,171,230,236],"acoustic":[8,254],"signal,":[9],"but":[10],"also":[11],"visual":[12,29,42,67,203,227,237],"cues.":[13],"Audio-visual":[14],"speech":[15,25,207,217,222,246],"recognition":[16,26,218,223,247],"aims":[17,61],"to":[18,32,47,62,214],"improve":[19,245],"performance":[21,248],"of":[22,77,85,95,108,131,143,156,182,211,253],"conventional":[23],"automated":[24],"by":[27,90,121,160],"incorporating":[28],"information.":[30],"Due":[31],"a":[33,91,96,100,109,176,250],"fundamentally":[34],"limited":[35],"two-dimensional":[36],"representation":[37],"employed,":[38],"current":[39],"approaches":[40],"for":[41,66,180],"feature":[43,68],"extraction":[44,69],"lack":[45],"invariance":[46],"speaker's":[48,86,183],"pose":[49],"and":[50,99,117,127,133,147,188,226],"illumination":[51,118,157,189],"in":[52,58,104,170,205],"environment.":[54],"The":[55,102,154,195],"research":[56],"presented":[57],"this":[59],"thesis":[60],"develop":[63],"three-dimensional":[64],"methods":[65],"that":[70,166,235],"alleviate":[71],"above-mentioned":[73],"limitation.\r\nFollowing":[74],"concepts":[76],"Grenander's":[78],"General":[79],"Pattern":[80],"Theory,":[81],"prior":[83],"knowledge":[84],"face":[87,172],"described":[89,139],"prototype,":[92],"which":[93],"consists":[94],"3-D":[97,242],"surface":[98,146,163,173],"texture.":[101],"variability":[103],"observed":[105],"video":[106,193],"images":[107],"speaker":[110],"associated":[111],"with":[112],"pose,":[113,184],"articulatory":[114,185],"facial":[115,186,197],"motion,":[116],"represented":[120],"transformations":[122],"acting":[123],"on":[124],"prototype":[126,145],"forming":[128],"group":[130],"geometric":[132],"photometric":[134],"variability.":[135],"Facial":[136],"motion":[137,151,187,198],"as":[140,202],"smooth":[141],"deformations":[142],"learned":[149],"from":[150,190],"capture":[152],"data.":[153],"effects":[155],"are":[158,200],"accommodated":[159],"analytically":[161],"constructing":[162],"scalar":[164],"fields":[165],"express":[167],"relative":[168],"changes":[169],"irradiance.\r\nWe":[174],"derive":[175],"multi-resolution":[177],"tracking":[178],"algorithm":[179],"estimation":[181],"uncalibrated":[191],"monocular":[192],"sequences.":[194],"inferred":[196],"parameters":[199],"utilized":[201],"features":[204,238],"audio-visual":[206,216],"recognition.":[208],"An":[209],"application":[210],"our":[212,241],"approach":[213,243],"large-vocabulary":[215],"presented.":[220],"Speaker-independent":[221],"combines":[224],"audio":[225],"models":[228],"at":[229],"utterance":[231],"level.":[232],"We":[233],"demonstrate":[234],"derived":[239],"using":[240],"significantly":[244],"across":[249],"wide":[251],"range":[252],"signal-to-noise":[255],"ratios.":[256]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2285079731","counts_by_year":[],"updated_date":"2025-11-06T04:12:42.849631","created_date":"2016-06-24T00:00:00"}
