{"id":"https://openalex.org/W1978380426","doi":"https://doi.org/10.1155/s1110865702206083","title":"Dynamic Bayesian Networks for Audio-Visual Speech Recognition","display_name":"Dynamic Bayesian Networks for Audio-Visual Speech Recognition","publication_year":2002,"publication_date":"2002-11-28","ids":{"openalex":"https://openalex.org/W1978380426","doi":"https://doi.org/10.1155/s1110865702206083","mag":"1978380426"},"language":"en","primary_location":{"id":"doi:10.1155/s1110865702206083","is_oa":true,"landing_page_url":"https://doi.org/10.1155/s1110865702206083","pdf_url":"https://asp-eurasipjournals.springeropen.com/counter/pdf/10.1155/S1110865702206083","source":{"id":"https://openalex.org/S35920007","display_name":"EURASIP Journal on Advances in Signal Processing","issn_l":"1687-6172","issn":["1687-6172","1687-6180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asp-eurasipjournals.springeropen.com/counter/pdf/10.1155/S1110865702206083","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113481101","display_name":"Ara Nefian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128612","display_name":"Mission College","ror":"https://ror.org/035fpgr29","country_code":"US","type":"education","lineage":["https://openalex.org/I4210128612"]},{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ara V. Nefian","raw_affiliation_strings":["Intel Corporation, Microprocessor Research Labs, 2200 Mission College Blvd., Santa Clara, CA, 95052-8119, USA","Intel Corporation, Microprocessor Research Labs, Santa Clara, CA"],"affiliations":[{"raw_affiliation_string":"Intel Corporation, Microprocessor Research Labs, 2200 Mission College Blvd., Santa Clara, CA, 95052-8119, USA","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4210128612"]},{"raw_affiliation_string":"Intel Corporation, Microprocessor Research Labs, Santa Clara, CA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052554057","display_name":"Luhong Liang","orcid":"https://orcid.org/0009-0001-4190-006X"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luhong Liang","raw_affiliation_strings":["Intel Corporation, Microcomputer Research Labs, Guanghua Road, 100020, Chaoyang District, Beijing, China","Intel Corporation, Microprocessor Research Labs, Chaoyang District, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Intel Corporation, Microcomputer Research Labs, Guanghua Road, 100020, Chaoyang District, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Intel Corporation, Microprocessor Research Labs, Chaoyang District, Beijing, China#TAB#","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027964715","display_name":"Xiaobo Pi","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaobo Pi","raw_affiliation_strings":["Intel Corporation, Microcomputer Research Labs, Guanghua Road, 100020, Chaoyang District, Beijing, China","Intel Corporation, Microprocessor Research Labs, Chaoyang District, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Intel Corporation, Microcomputer Research Labs, Guanghua Road, 100020, Chaoyang District, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Intel Corporation, Microprocessor Research Labs, Chaoyang District, Beijing, China#TAB#","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100783771","display_name":"Xiaoxing Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoxing Liu","raw_affiliation_strings":["Intel Corporation, Microcomputer Research Labs, Guanghua Road, 100020, Chaoyang District, Beijing, China","Intel Corporation, Microprocessor Research Labs, Chaoyang District, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Intel Corporation, Microcomputer Research Labs, Guanghua Road, 100020, Chaoyang District, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Intel Corporation, Microprocessor Research Labs, Chaoyang District, Beijing, China#TAB#","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103280100","display_name":"Kevin J. Murphy","orcid":"https://orcid.org/0009-0006-9681-3285"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Murphy","raw_affiliation_strings":["Computer Science Division, University of California, Berkeley, Berkeley, CA, 94720-1776, USA","Computer Science Division, University of California-Berkeley, Berkeley, CA"],"affiliations":[{"raw_affiliation_string":"Computer Science Division, University of California, Berkeley, Berkeley, CA, 94720-1776, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Computer Science Division, University of California-Berkeley, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113481101"],"corresponding_institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4210128612"],"apc_list":{"value":1140,"currency":"GBP","value_usd":1398},"apc_paid":{"value":1140,"currency":"GBP","value_usd":1398},"fwci":9.2487,"has_fulltext":true,"cited_by_count":319,"citation_normalized_percentile":{"value":0.98518991,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"2002","issue":"11","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.9912999868392944,"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/speech-recognition","display_name":"Speech recognition","score":0.8287925720214844},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7572180032730103},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6645058393478394},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4560726284980774},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43354836106300354},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37051740288734436}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8287925720214844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7572180032730103},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6645058393478394},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4560726284980774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43354836106300354},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37051740288734436}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1155/s1110865702206083","is_oa":true,"landing_page_url":"https://doi.org/10.1155/s1110865702206083","pdf_url":"https://asp-eurasipjournals.springeropen.com/counter/pdf/10.1155/S1110865702206083","source":{"id":"https://openalex.org/S35920007","display_name":"EURASIP Journal on Advances in Signal Processing","issn_l":"1687-6172","issn":["1687-6172","1687-6180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1155/s1110865702206083","is_oa":true,"landing_page_url":"https://doi.org/10.1155/s1110865702206083","pdf_url":"https://asp-eurasipjournals.springeropen.com/counter/pdf/10.1155/S1110865702206083","source":{"id":"https://openalex.org/S35920007","display_name":"EURASIP Journal on Advances in Signal Processing","issn_l":"1687-6172","issn":["1687-6172","1687-6180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1978380426.pdf","grobid_xml":"https://content.openalex.org/works/W1978380426.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W87942418","https://openalex.org/W124434589","https://openalex.org/W135040384","https://openalex.org/W162646390","https://openalex.org/W1523010034","https://openalex.org/W1528056001","https://openalex.org/W1560013842","https://openalex.org/W1565763124","https://openalex.org/W1568586930","https://openalex.org/W1576996184","https://openalex.org/W1595108906","https://openalex.org/W1755360231","https://openalex.org/W1929897159","https://openalex.org/W2010318909","https://openalex.org/W2015394094","https://openalex.org/W2020294948","https://openalex.org/W2083792893","https://openalex.org/W2099947851","https://openalex.org/W2110575115","https://openalex.org/W2112348857","https://openalex.org/W2116418373","https://openalex.org/W2121430128","https://openalex.org/W2121486117","https://openalex.org/W2124174353","https://openalex.org/W2129571380","https://openalex.org/W2132217089","https://openalex.org/W2152239535","https://openalex.org/W2159080219","https://openalex.org/W2164450870","https://openalex.org/W2492805573","https://openalex.org/W2793908218","https://openalex.org/W2799061466","https://openalex.org/W4205944311","https://openalex.org/W4230946174","https://openalex.org/W4244018879","https://openalex.org/W4245655784","https://openalex.org/W4299670631","https://openalex.org/W4300145996","https://openalex.org/W6632282560","https://openalex.org/W6671432306","https://openalex.org/W6684209796"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W3184123547","https://openalex.org/W2160030256","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W2488941600","https://openalex.org/W2033914206"],"abstract_inverted_index":{"The":[0,98],"use":[1,62],"of":[2,63,83,101,113],"visual":[3,25,117],"features":[4,32],"in":[5,22,50,91],"audio-visual":[6,68,94],"speech":[7,15],"recognition":[8],"(AVSR)":[9],"is":[10,19],"justified":[11],"by":[12,28,53],"both":[13,102],"the":[14,29,61,70,75,81,87,103,110,114,130,137,141],"generation":[16],"mechanism,":[17],"which":[18],"essentially":[20],"bimodal":[21],"audio":[23,115],"and":[24,27,74,79,105,116,140],"representation,":[26],"need":[30],"for":[31,67],"that":[33],"are":[34],"invariant":[35],"to":[36,108],"acoustic":[37,54],"noise":[38],"perturbation.":[39],"As":[40],"a":[41],"result,":[42],"current":[43],"AVSR":[44],"systems":[45],"demonstrate":[46],"significant":[47],"accuracy":[48],"improvements":[49],"environments":[51],"affected":[52],"noise.":[55],"In":[56,127],"this":[57],"paper,":[58],"we":[59],"describe":[60],"two":[64],"statistical":[65,99],"models":[66,85,89,139],"integration,":[69],"coupled":[71],"HMM":[72,77],"(CHMM)":[73],"factorial":[76],"(FHMM),":[78],"compare":[80],"performance":[82],"these":[84],"with":[86],"existing":[88,138],"used":[90],"speaker":[92],"dependent":[93],"isolated":[95],"word":[96],"recognition.":[97],"properties":[100],"CHMM":[104,131],"FHMM":[106],"allow":[107],"model":[109],"state":[111],"asynchrony":[112],"observation":[118],"sequences":[119],"while":[120],"preserving":[121],"their":[122],"natural":[123],"correlation":[124],"over":[125],"time.":[126],"our":[128],"experiments,":[129],"performs":[132],"best":[133],"overall,":[134],"outperforming":[135],"all":[136],"FHMM.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":20},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":13}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}