{"id":"https://openalex.org/W2049155405","doi":"https://doi.org/10.1142/s021821309900004x","title":"DISCRIMINATIVE LEARNING OF VISUAL DATA FOR AUDIOVISUAL SPEECH RECOGNITION","display_name":"DISCRIMINATIVE LEARNING OF VISUAL DATA FOR AUDIOVISUAL SPEECH RECOGNITION","publication_year":1999,"publication_date":"1999-03-01","ids":{"openalex":"https://openalex.org/W2049155405","doi":"https://doi.org/10.1142/s021821309900004x","mag":"2049155405"},"language":"en","primary_location":{"id":"doi:10.1142/s021821309900004x","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s021821309900004x","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","raw_type":"journal-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/A5041948708","display_name":"Alexandrina Rogozan","orcid":"https://orcid.org/0000-0002-7931-9633"},"institutions":[{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"ALEXANDRINA ROGOZAN","raw_affiliation_strings":["Laboratoire d'Informatique de l'Universit\u00e9 du Maine, 72085 Le Mans Cedex 9, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire d'Informatique de l'Universit\u00e9 du Maine, 72085 Le Mans Cedex 9, France","institution_ids":["https://openalex.org/I4210108471"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5041948708"],"corresponding_institution_ids":["https://openalex.org/I4210108471"],"apc_list":null,"apc_paid":null,"fwci":0.7259,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.72916667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":"08","issue":"01","first_page":"43","last_page":"52"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9936000108718872,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9908999800682068,"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":0.8975646495819092},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8450378179550171},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7755271196365356},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.737815260887146},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5400576591491699},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5328887701034546},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.46498697996139526},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4541832506656647},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.451568603515625},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44295722246170044},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43920138478279114},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4274751543998718},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13157925009727478}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8975646495819092},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8450378179550171},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7755271196365356},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.737815260887146},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5400576591491699},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5328887701034546},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.46498697996139526},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4541832506656647},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.451568603515625},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44295722246170044},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43920138478279114},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4274751543998718},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13157925009727478},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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":3,"locations":[{"id":"doi:10.1142/s021821309900004x","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s021821309900004x","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.26.4431","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.26.4431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.clsp.jhu.edu/ws2000/groups/av_speech/./papers/rogozan_ijiat.ps","raw_type":"text"},{"id":"pmh:oai:HAL:hal-01434712v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01434712","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal on Artificial Intelligence Tools, 1999, 8 (1), pp.43--52","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W633999132","https://openalex.org/W1527102103","https://openalex.org/W1991133427","https://openalex.org/W2036205336","https://openalex.org/W2169507824","https://openalex.org/W4301623764"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W3148366653","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W2611678594","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149"],"abstract_inverted_index":{"In":[0],"recent":[1],"years":[2],"a":[3,93,100,107,119],"number":[4],"of":[5,17,51,84,103,130],"techniques":[6],"have":[7,46],"been":[8,40],"proposed":[9],"to":[10,42,63],"improve":[11],"the":[12,15,27,49,77,82,131],"accuracy":[13],"and":[14,66],"robustness":[16],"automatic":[18],"speech":[19,60,79,112,121],"recognition":[20,80,113,122],"in":[21,81],"noisy":[22],"environments.":[23],"Among":[24],"these,":[25],"suplementing":[26],"acoustic":[28],"information":[29],"with":[30,106],"visual":[31,53],"data,":[32],"mostly":[33],"extracted":[34],"from":[35],"speaker's":[36],"lip":[37],"shapes,":[38],"has":[39],"proved":[41],"be":[43],"successful.":[44],"We":[45],"already":[47],"demonstrated":[48],"effectiveness":[50],"integrating":[52],"data":[54],"at":[55],"two":[56],"different":[57],"levels":[58],"during":[59],"decoding":[61],"according":[62],"both":[64],"direct":[65],"separate":[67,85],"identification":[68],"strategies":[69],"(DI+SI).":[70],"This":[71],"paper":[72],"outlines":[73],"methods":[74,127],"for":[75,111],"reinforcing":[76],"visible":[78],"framework":[83],"identification.":[86],"First,":[87],"we":[88,98,116],"define":[89],"visual-specific":[90],"units":[91,105],"using":[92,125],"self-organizing":[94],"mapping":[95],"technique.":[96],"Second,":[97],"complete":[99],"stochastic":[101],"learning":[102],"these":[104,126],"discriminative":[108],"neural-network-based":[109],"technique":[110],"purposes.":[114],"Finally,":[115],"show":[117],"on":[118],"connected-letter":[120],"task":[123],"that":[124],"improves":[128],"performances":[129],"DI+SI":[132],"based":[133],"system":[134],"under":[135],"varying":[136],"noise-level":[137],"conditions.":[138]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}