{"id":"https://openalex.org/W2106904816","doi":"https://doi.org/10.1007/11922162_3","title":"DBN Based Models for Audio-Visual Speech Analysis and Recognition","display_name":"DBN Based Models for Audio-Visual Speech Analysis and Recognition","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2106904816","doi":"https://doi.org/10.1007/11922162_3","mag":"2106904816"},"language":"en","primary_location":{"id":"doi:10.1007/11922162_3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/11922162_3","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5090286698","display_name":"Ilse Ravyse","orcid":null},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Ilse Ravyse","raw_affiliation_strings":["Department ETRO, Joint Research Group on Audio Visual Signal Processing (AVSP), Vrije Universiteit Brussel, Pleinlaan 2, 1050, Brussel"],"affiliations":[{"raw_affiliation_string":"Department ETRO, Joint Research Group on Audio Visual Signal Processing (AVSP), Vrije Universiteit Brussel, Pleinlaan 2, 1050, Brussel","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102021514","display_name":"Dongmei Jiang","orcid":"https://orcid.org/0000-0002-6238-8499"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongmei Jiang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, 127 Youyi Xilu, Xi\u2019an, 710072, P.R. China","School of Computer Science, Northwestern Polytechnical University, 127 Youyi Xilu, Xi'an, 710072, P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, 127 Youyi Xilu, Xi\u2019an, 710072, P.R. China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, 127 Youyi Xilu, Xi'an, 710072, P.R. China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051764820","display_name":"Zetao Jiang","orcid":"https://orcid.org/0000-0002-0914-2131"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyue Jiang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, 127 Youyi Xilu, Xi\u2019an, 710072, P.R. China","School of Computer Science, Northwestern Polytechnical University, 127 Youyi Xilu, Xi'an, 710072, P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, 127 Youyi Xilu, Xi\u2019an, 710072, P.R. China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, 127 Youyi Xilu, Xi'an, 710072, P.R. China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072820861","display_name":"Guoyun Lv","orcid":"https://orcid.org/0000-0003-2262-3236"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoyun Lv","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, 127 Youyi Xilu, Xi\u2019an, 710072, P.R. China","School of Computer Science, Northwestern Polytechnical University, 127 Youyi Xilu, Xi'an, 710072, P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, 127 Youyi Xilu, Xi\u2019an, 710072, P.R. China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, 127 Youyi Xilu, Xi'an, 710072, P.R. China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100518779","display_name":"Yunshu Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunshu Hou","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, 127 Youyi Xilu, Xi\u2019an, 710072, P.R. China","School of Computer Science, Northwestern Polytechnical University, 127 Youyi Xilu, Xi'an, 710072, P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, 127 Youyi Xilu, Xi\u2019an, 710072, P.R. China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, 127 Youyi Xilu, Xi'an, 710072, P.R. China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073820422","display_name":"Hichem Sahli","orcid":"https://orcid.org/0000-0002-1774-2970"},"institutions":[{"id":"https://openalex.org/I196972281","display_name":"Imec the Netherlands","ror":"https://ror.org/01ezq2j76","country_code":"NL","type":"facility","lineage":["https://openalex.org/I196972281"]},{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE","NL"],"is_corresponding":false,"raw_author_name":"Hichem Sahli","raw_affiliation_strings":["Department ETRO, Joint Research Group on Audio Visual Signal Processing (AVSP), Vrije Universiteit Brussel, Pleinlaan 2, 1050, Brussel","IMEC, Kapeldreef 75, 3001, Leuven"],"affiliations":[{"raw_affiliation_string":"Department ETRO, Joint Research Group on Audio Visual Signal Processing (AVSP), Vrije Universiteit Brussel, Pleinlaan 2, 1050, Brussel","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"IMEC, Kapeldreef 75, 3001, Leuven","institution_ids":["https://openalex.org/I196972281"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114015531","display_name":"Rongchun Zhao","orcid":"https://orcid.org/0009-0005-7003-5422"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongchun Zhao","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, 127 Youyi Xilu, Xi\u2019an, 710072, P.R. China","School of Computer Science, Northwestern Polytechnical University, 127 Youyi Xilu, Xi'an, 710072, P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, 127 Youyi Xilu, Xi\u2019an, 710072, P.R. China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, 127 Youyi Xilu, Xi'an, 710072, P.R. China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5090286698"],"corresponding_institution_ids":["https://openalex.org/I13469542"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.988,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88061466,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"30"},"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":0.9998999834060669,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9977999925613403,"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/computer-science","display_name":"Computer science","score":0.8709940910339355},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7711442708969116},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6868963837623596},{"id":"https://openalex.org/keywords/dynamic-bayesian-network","display_name":"Dynamic Bayesian network","score":0.6080264449119568},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5648906826972961},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5453512072563171},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5271463394165039},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.515370786190033},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.47584104537963867},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46569857001304626},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41872429847717285},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.41689401865005493},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39611518383026123},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.38658612966537476},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36029207706451416},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3200419247150421},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.25471949577331543},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08178624510765076}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8709940910339355},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7711442708969116},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6868963837623596},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.6080264449119568},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5648906826972961},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5453512072563171},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5271463394165039},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.515370786190033},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.47584104537963867},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46569857001304626},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41872429847717285},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.41689401865005493},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39611518383026123},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.38658612966537476},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36029207706451416},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3200419247150421},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.25471949577331543},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08178624510765076}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/11922162_3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/11922162_3","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:39892","is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/dbn-based-models-for-audiovisual-speech-analysis-and-recognition(d28df82e-b8c0-4bb8-8b0a-41daeb505b20).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"bookitem"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W135040384","https://openalex.org/W1660019029","https://openalex.org/W1670311576","https://openalex.org/W1960653181","https://openalex.org/W2117172387","https://openalex.org/W2120242139","https://openalex.org/W2122678358","https://openalex.org/W2129671742","https://openalex.org/W2139425821","https://openalex.org/W2148154194","https://openalex.org/W2148491550","https://openalex.org/W2157827878","https://openalex.org/W2170960573","https://openalex.org/W2793908218","https://openalex.org/W3165053832","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2787035864","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W1556565948","https://openalex.org/W2074132948","https://openalex.org/W2160511961"],"abstract_inverted_index":null,"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}