{"id":"https://openalex.org/W2167159094","doi":"https://doi.org/10.1109/slt.2006.326841","title":"AN ASYNCHRONOUS DBN FOR AUDIO-VISUAL SPEECH RECOGNITION","display_name":"AN ASYNCHRONOUS DBN FOR AUDIO-VISUAL SPEECH RECOGNITION","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2167159094","doi":"https://doi.org/10.1109/slt.2006.326841","mag":"2167159094"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2006.326841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2006.326841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE Spoken Language Technology Workshop","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/A5075906727","display_name":"Kate Saenko","orcid":"https://orcid.org/0000-0002-7564-7218"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kate Saenko","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015602781","display_name":"Karen Livescu","orcid":"https://orcid.org/0000-0003-4962-946X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karen Livescu","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5075906727"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":1.6121,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.8401514,"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":"154","last_page":"157"},"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":0.9995999932289124,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8368065357208252},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7755433917045593},{"id":"https://openalex.org/keywords/asynchrony","display_name":"Asynchrony (computer programming)","score":0.700714647769928},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.672374963760376},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.6569995880126953},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6210476756095886},{"id":"https://openalex.org/keywords/dynamic-bayesian-network","display_name":"Dynamic Bayesian network","score":0.5219998955726624},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48817235231399536},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4583948850631714},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4293053150177002},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42421677708625793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41470855474472046},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.41169166564941406},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.40838274359703064},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3810495138168335},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.2340570092201233},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.12587332725524902}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8368065357208252},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7755433917045593},{"id":"https://openalex.org/C2779019669","wikidata":"https://www.wikidata.org/wiki/Q25203946","display_name":"Asynchrony (computer programming)","level":3,"score":0.700714647769928},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.672374963760376},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.6569995880126953},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6210476756095886},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.5219998955726624},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48817235231399536},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4583948850631714},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4293053150177002},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42421677708625793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41470855474472046},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.41169166564941406},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.40838274359703064},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3810495138168335},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2340570092201233},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.12587332725524902},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt.2006.326841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2006.326841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE Spoken Language Technology Workshop","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.115.8318","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.115.8318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.csail.mit.edu/saenko/saenko_livescu_slt_06.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W58214371","https://openalex.org/W114725541","https://openalex.org/W135040384","https://openalex.org/W1528056001","https://openalex.org/W1960653181","https://openalex.org/W2049633694","https://openalex.org/W2096391593","https://openalex.org/W2098923380","https://openalex.org/W2106125881","https://openalex.org/W2110575115","https://openalex.org/W2121430128","https://openalex.org/W2122678358","https://openalex.org/W2152239535","https://openalex.org/W2157827878","https://openalex.org/W2163973301","https://openalex.org/W2793908218","https://openalex.org/W3129711340","https://openalex.org/W4245655784","https://openalex.org/W6602408607","https://openalex.org/W6604577772","https://openalex.org/W6641135991","https://openalex.org/W6678195145","https://openalex.org/W6684209112","https://openalex.org/W6828034933"],"related_works":["https://openalex.org/W2378274372","https://openalex.org/W2157598242","https://openalex.org/W2092572762","https://openalex.org/W2620660273","https://openalex.org/W2134807850","https://openalex.org/W2619911963","https://openalex.org/W2014474048","https://openalex.org/W2762879233","https://openalex.org/W1969715806","https://openalex.org/W22517275"],"abstract_inverted_index":{"We":[0,70,104],"investigate":[1],"an":[2,75],"asynchronous":[3,96],"two-stream":[4],"dynamic":[5],"Bayesian":[6],"network-based":[7],"model":[8,14,73,97],"for":[9,51,55],"audio-visual":[10,102],"speech":[11,57,68],"recognition.":[12,69],"The":[13,29,95],"allows":[15],"the":[16,24,72,117,127],"audio":[17,128],"and":[18,54,89,100,114,129],"visual":[19,56,130],"streams":[20,131],"to":[21,66,92,134,138],"de-synchronize":[22,135],"within":[23],"boundaries":[25],"of":[26,31,37,45,78,85,111],"each":[27],"word.":[28],"probability":[30],"de-synchronization":[32],"by":[33,136],"a":[34],"given":[35],"number":[36],"states":[38],"is":[39,62,124],"learned":[40],"during":[41],"training.":[42],"This":[43],"type":[44],"asynchrony":[46,113],"has":[47],"been":[48],"previously":[49],"used":[50],"pronunciation":[52],"modeling":[53],"recognition":[58],"(lipreading);":[59],"however,":[60],"this":[61,122],"its":[63],"first":[64],"application":[65],"audiovisual":[67,76],"evaluate":[71],"on":[74,121],"corpus":[77],"English":[79],"digits":[80],"(CUAVE)":[81],"with":[82,108],"different":[83,109],"levels":[84],"added":[86],"acoustic":[87],"noise,":[88],"compare":[90,106],"it":[91],"several":[93],"baselines.":[94,103],"outperforms":[98],"audio-only":[99],"synchronous":[101],"also":[105],"models":[107],"degrees":[110],"allowed":[112,133],"find":[115],"that":[116],"lowest":[118],"error":[119],"rate":[120],"task":[123],"achieved":[125],"when":[126],"are":[132],"up":[137],"two":[139],"states.":[140]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
