{"id":"https://openalex.org/W2099446004","doi":"https://doi.org/10.21437/interspeech.2010-426","title":"HMM-based automatic visual speech segmentation using facial data","display_name":"HMM-based automatic visual speech segmentation using facial data","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W2099446004","doi":"https://doi.org/10.21437/interspeech.2010-426","mag":"2099446004"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-426","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/inria-00526776","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020473453","display_name":"Utpala Musti","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Utpala Musti","raw_affiliation_strings":["Analysis, perception and recognition of speech"],"affiliations":[{"raw_affiliation_string":"Analysis, perception and recognition of speech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030228191","display_name":"Asterios Toutios","orcid":"https://orcid.org/0000-0003-3193-2241"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Asterios Toutios","raw_affiliation_strings":["Analysis, perception and recognition of speech"],"affiliations":[{"raw_affiliation_string":"Analysis, perception and recognition of speech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044130608","display_name":"Slim Ouni","orcid":"https://orcid.org/0000-0001-5286-7368"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Slim Ouni","raw_affiliation_strings":["Analysis, perception and recognition of speech"],"affiliations":[{"raw_affiliation_string":"Analysis, perception and recognition of speech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039712983","display_name":"Vincent Colotte","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent Colotte","raw_affiliation_strings":["Analysis, perception and recognition of speech"],"affiliations":[{"raw_affiliation_string":"Analysis, perception and recognition of speech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046710569","display_name":"Brigitte Wrobel-Dautcourt","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brigitte Wrobel-Dautcourt","raw_affiliation_strings":["Visual Augmentation of Complex Environments"],"affiliations":[{"raw_affiliation_string":"Visual Augmentation of Complex Environments","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027151885","display_name":"Marie\u2010Odile Berger","orcid":"https://orcid.org/0000-0002-9371-1367"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marie-Odile Berger","raw_affiliation_strings":["Visual Augmentation of Complex Environments"],"affiliations":[{"raw_affiliation_string":"Visual Augmentation of Complex Environments","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5020473453"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6764,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70583005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1401","last_page":"1404"},"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/T11448","display_name":"Face recognition and analysis","score":0.9891999959945679,"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"}},{"id":"https://openalex.org/T12032","display_name":"Multisensory perception and integration","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/coarticulation","display_name":"Coarticulation","score":0.9428601264953613},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7971124649047852},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.756587028503418},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6623553037643433},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.621597409248352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5847957134246826},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.5360342264175415},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.46744927763938904},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4327370226383209},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3359105587005615},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.288719117641449},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.09036624431610107}],"concepts":[{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.9428601264953613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7971124649047852},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.756587028503418},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6623553037643433},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.621597409248352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5847957134246826},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.5360342264175415},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.46744927763938904},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4327370226383209},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3359105587005615},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.288719117641449},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.09036624431610107}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2010-426","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.722.9929","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.722.9929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sipi.usc.edu/%7Etoutios/papers/musti_interspeech2010.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:inria-00526776v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00526776","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech 2010, ISCA, Sep 2010, Makuhari, Chiba, Japan. pp.1401-1404","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:inria-00526776v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00526776","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech 2010, ISCA, Sep 2010, Makuhari, Chiba, Japan. pp.1401-1404","raw_type":"Conference papers"},"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W87280800","https://openalex.org/W88081813","https://openalex.org/W1503703342","https://openalex.org/W1550599496","https://openalex.org/W1569375693","https://openalex.org/W2014621385","https://openalex.org/W2075316843","https://openalex.org/W2076228207","https://openalex.org/W2127211243","https://openalex.org/W2406132719","https://openalex.org/W2620587884","https://openalex.org/W2990152011"],"related_works":["https://openalex.org/W2142233983","https://openalex.org/W1514850790","https://openalex.org/W2044479749","https://openalex.org/W4232484596","https://openalex.org/W1497083033","https://openalex.org/W2121472286","https://openalex.org/W4253235840","https://openalex.org/W2488941600","https://openalex.org/W1950150365","https://openalex.org/W2006482757"],"abstract_inverted_index":{"We":[0],"describe":[1],"automatic":[2,27],"visual":[3,39,61,98],"speech":[4,28,40,55,64,99,110],"segmentation":[5,15],"using":[6,18,38],"facial":[7,52,108],"data":[8,41],"captured":[9],"by":[10],"a":[11,83],"stereo-vision":[12],"technique.":[13],"The":[14,30],"is":[16,32],"performed":[17],"an":[19],"HMM-based":[20],"forced":[21,112],"alignment":[22],"mecha-nism":[23],"widely":[24],"used":[25],"in":[26,50,60,95],"recognition.":[29],"idea":[31],"based":[33,101],"on":[34,102],"the":[35,44,48,51,79,97],"assumption":[36],"that":[37,75],"alone":[42],"for":[43],"training":[45],"might":[46],"capture":[47],"uniqueness":[49],"compo-nent":[53],"of":[54],"articulation,":[56],"asynchrony":[57],"(time":[58],"lags)":[59],"and":[62,66],"acoustic":[63],"segments":[65,100],"significant":[67],"coarticulation":[68],"effects.":[69],"This":[70,90],"should":[71,91],"provide":[72,92],"valuable":[73,94],"information":[74,93],"helps":[76],"to":[77,81],"show":[78],"extent":[80],"which":[82],"phoneme":[84],"may":[85],"affect":[86],"surrounding":[87],"phonemes":[88],"visually.":[89],"labeling":[96],"dominant":[103],"coarticulatory":[104],"contexts.":[105],"Index":[106],"Terms:":[107],"speech,":[109],"segmentation,":[111],"align-ment,":[113],"coarticulation.":[114]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}