{"id":"https://openalex.org/W2092572762","doi":"https://doi.org/10.1109/mmsp.2010.5662066","title":"Overcoming asynchrony in Audio-Visual Speech Recognition","display_name":"Overcoming asynchrony in Audio-Visual Speech Recognition","publication_year":2010,"publication_date":"2010-10-01","ids":{"openalex":"https://openalex.org/W2092572762","doi":"https://doi.org/10.1109/mmsp.2010.5662066","mag":"2092572762"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2010.5662066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2010.5662066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Workshop on Multimedia Signal Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/149405","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026933333","display_name":"Virginia Estellers","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Virginia Estellers","raw_affiliation_strings":["Signal Processing Laboratory 5 (LTS5, Ecole Polytechnique Federale de Lausanne, Lausanne, Switzerland","Signal Processing Laboratory 5 (LTS5), Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Station 11, 1015 Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Signal Processing Laboratory 5 (LTS5, Ecole Polytechnique Federale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Signal Processing Laboratory 5 (LTS5), Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Station 11, 1015 Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067782007","display_name":"Jean\u2010Philippe Thiran","orcid":"https://orcid.org/0000-0003-2938-9657"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jean-Philippe Thiran","raw_affiliation_strings":["Signal Processing Laboratory 5 (LTS5, Ecole Polytechnique Federale de Lausanne, Lausanne, Switzerland","Signal Processing Laboratory 5 (LTS5), Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Station 11, 1015 Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Signal Processing Laboratory 5 (LTS5, Ecole Polytechnique Federale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Signal Processing Laboratory 5 (LTS5), Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Station 11, 1015 Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5026933333"],"corresponding_institution_ids":["https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.16924933,"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":"466","last_page":"471"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9976000189781189,"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/asynchrony","display_name":"Asynchrony (computer programming)","score":0.9390710592269897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8318261504173279},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6840278506278992},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6603326201438904},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5162692070007324},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5104088187217712},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49463245272636414},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.475210040807724},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4576505720615387},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.39972925186157227},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37180909514427185},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3205724060535431},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.18260183930397034}],"concepts":[{"id":"https://openalex.org/C2779019669","wikidata":"https://www.wikidata.org/wiki/Q25203946","display_name":"Asynchrony (computer programming)","level":3,"score":0.9390710592269897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8318261504173279},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6840278506278992},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6603326201438904},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5162692070007324},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5104088187217712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49463245272636414},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.475210040807724},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4576505720615387},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.39972925186157227},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37180909514427185},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3205724060535431},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.18260183930397034},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/mmsp.2010.5662066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2010.5662066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Workshop on Multimedia Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.352.2823","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.352.2823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:infoscience.tind.io:149405","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/149405","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:149405","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/149405","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference proceedings"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W135040384","https://openalex.org/W175821084","https://openalex.org/W196476531","https://openalex.org/W1978380426","https://openalex.org/W2098923380","https://openalex.org/W2110575115","https://openalex.org/W2121486117","https://openalex.org/W2122678358","https://openalex.org/W2125838338","https://openalex.org/W2134764753","https://openalex.org/W2148226542","https://openalex.org/W2157190406","https://openalex.org/W2157827878","https://openalex.org/W2165712214","https://openalex.org/W2793908218","https://openalex.org/W4285719527","https://openalex.org/W6607219637","https://openalex.org/W6608045302","https://openalex.org/W6676404962","https://openalex.org/W6684249834"],"related_works":["https://openalex.org/W2944915449","https://openalex.org/W2102266661","https://openalex.org/W2122229220","https://openalex.org/W4297966918","https://openalex.org/W1541180262","https://openalex.org/W2092572762","https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W4243125559","https://openalex.org/W4241778367"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,103],"propose":[4],"two":[5],"alternatives":[6],"to":[7,56,124],"overcome":[8],"the":[9,21,57,64,75,79,92,107,111,115],"natural":[10],"asynchrony":[11,44],"of":[12,23,35,63,78,86,94],"modalities":[13],"in":[14,84],"Audio-Visual":[15],"Speech":[16],"Recognition.":[17],"We":[18,37],"first":[19],"investigate":[20],"use":[22,93],"asynchronous":[24,117],"statistical":[25,96],"models":[26,41,97],"based":[27],"on":[28],"Dynamic":[29],"Bayesian":[30],"Networks":[31],"with":[32,106,114],"different":[33],"levels":[34],"asynchrony.":[36],"show":[38],"that":[39],"audio-visual":[40],"should":[42],"consider":[43],"within":[45],"word":[46],"boundaries":[47],"and":[48,81,90,119],"not":[49],"at":[50],"phoneme":[51],"level.":[52],"The":[53,71],"second":[54],"approach":[55],"problem":[58],"includes":[59],"an":[60],"additional":[61],"processing":[62,121],"features":[65],"before":[66],"being":[67],"used":[68],"for":[69,98],"recognition.":[70],"proposed":[72,116],"technique":[73,122],"aligns":[74],"temporal":[76],"evolution":[77],"audio":[80],"video":[82],"streams":[83],"terms":[85],"a":[87],"speech-recognition":[88],"system":[89],"enables":[91],"simpler":[95],"classification.":[99],"On":[100],"both":[101],"cases":[102],"report":[104],"experiments":[105],"CUAVE":[108],"database,":[109],"showing":[110],"improvements":[112],"obtained":[113],"model":[118],"feature":[120],"compared":[123],"traditional":[125],"systems.":[126]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}