{"id":"https://openalex.org/W2074417845","doi":"https://doi.org/10.1145/1027933.1027960","title":"Articulatory features for robust visual speech recognition","display_name":"Articulatory features for robust visual speech recognition","publication_year":2004,"publication_date":"2004-10-13","ids":{"openalex":"https://openalex.org/W2074417845","doi":"https://doi.org/10.1145/1027933.1027960","mag":"2074417845"},"language":"en","primary_location":{"id":"doi:10.1145/1027933.1027960","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1027933.1027960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th international conference on Multimodal interfaces","raw_type":"proceedings-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/A5075906727","display_name":"Kate Saenko","orcid":"https://orcid.org/0000-0002-7564-7218"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kate Saenko","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA","MIT, Computer Science and Artificial Intelligence Laboratory, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"MIT, Computer Science and Artificial Intelligence Laboratory, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029105520","display_name":"Trevor Darrell","orcid":"https://orcid.org/0000-0001-5453-8533"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevor Darrell","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA","MIT, Computer Science and Artificial Intelligence Laboratory, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"MIT, Computer Science and Artificial Intelligence Laboratory, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James R. Glass","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA","MIT, Computer Science and Artificial Intelligence Laboratory, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"MIT, Computer Science and Artificial Intelligence Laboratory, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5075906727"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":3.4291,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.92588334,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"152","last_page":"158"},"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":0.9984999895095825,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.9322097301483154},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8171513676643372},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7755669355392456},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5354205965995789},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5211955904960632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5063751935958862},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46112698316574097},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3975818157196045},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3948819041252136},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3423471450805664},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2095385491847992},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.07099485397338867}],"concepts":[{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.9322097301483154},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8171513676643372},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7755669355392456},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5354205965995789},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5211955904960632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5063751935958862},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46112698316574097},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3975818157196045},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3948819041252136},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3423471450805664},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2095385491847992},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.07099485397338867},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1027933.1027960","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1027933.1027960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th international conference on Multimodal interfaces","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W14023614","https://openalex.org/W22517275","https://openalex.org/W124434589","https://openalex.org/W161516627","https://openalex.org/W181056519","https://openalex.org/W196476531","https://openalex.org/W573069471","https://openalex.org/W1529401398","https://openalex.org/W1549662771","https://openalex.org/W1554901277","https://openalex.org/W1598851216","https://openalex.org/W1939950554","https://openalex.org/W1970533835","https://openalex.org/W1970996882","https://openalex.org/W1986174057","https://openalex.org/W2014621385","https://openalex.org/W2038952578","https://openalex.org/W2096391593","https://openalex.org/W2104095591","https://openalex.org/W2106125881","https://openalex.org/W2113814270","https://openalex.org/W2118977726","https://openalex.org/W2121430128","https://openalex.org/W2121486117","https://openalex.org/W2148603752","https://openalex.org/W2151043030","https://openalex.org/W2153635508","https://openalex.org/W2155471382","https://openalex.org/W2156203418","https://openalex.org/W2156909104","https://openalex.org/W2157190406","https://openalex.org/W2170308399","https://openalex.org/W2172803778","https://openalex.org/W2399865636","https://openalex.org/W3120421331","https://openalex.org/W6682634897","https://openalex.org/W6683365042"],"related_works":["https://openalex.org/W4253235840","https://openalex.org/W2488941600","https://openalex.org/W2044408773","https://openalex.org/W2116497041","https://openalex.org/W2591964346","https://openalex.org/W2130717063","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2131711534","https://openalex.org/W1560013842"],"abstract_inverted_index":{"Visual":[0],"information":[1],"has":[2,45],"been":[3],"shown":[4],"to":[5,36,55,62,76,106],"improve":[6],"the":[7,68,107],"performance":[8],"of":[9,59],"speech":[10,20,38],"recognition":[11],"systems":[12],"in":[13,89],"noisy":[14],"acoustic":[15],"environments.":[16],"However,":[17],"most":[18],"audio-visual":[19,96],"recognizers":[21],"rely":[22],"on":[23,41,93],"a":[24,33,57,90,94],"clean":[25],"visual":[26,37],"signal.":[27],"In":[28],"this":[29],"paper,":[30],"we":[31],"explore":[32],"novel":[34],"approach":[35,88],"modeling,":[39],"based":[40],"articulatory":[42,65],"features,":[43],"which":[44],"potential":[46],"benefits":[47],"under":[48],"visually":[49],"challenging":[50],"conditions.":[51],"The":[52],"idea":[53],"is":[54],"use":[56],"set":[58],"parallel":[60],"classifiers":[61],"extract":[63],"different":[64],"attributes":[66],"from":[67],"input":[69],"images,":[70],"and":[71,103],"then":[72],"combine":[73],"their":[74],"decisions":[75],"obtain":[77],"higher-level":[78],"units,":[79],"such":[80],"as":[81],"visemes":[82],"or":[83],"words.":[84],"We":[85],"evaluate":[86],"our":[87],"preliminary":[91],"experiment":[92],"small":[95],"database,":[97],"using":[98],"several":[99],"image":[100],"noise":[101],"conditions,":[102],"compare":[104],"it":[105],"standard":[108],"viseme-based":[109],"modeling":[110],"approach.":[111]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
