{"id":"https://openalex.org/W1211067074","doi":"https://doi.org/10.21437/interspeech.2008-528","title":"Phone recognition from ultrasound and optical video sequences for a silent speech interface","display_name":"Phone recognition from ultrasound and optical video sequences for a silent speech interface","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W1211067074","doi":"https://doi.org/10.21437/interspeech.2008-528","mag":"1211067074"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-528","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","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/A5060372031","display_name":"Thomas Hueber","orcid":"https://orcid.org/0000-0002-8296-5177"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Hueber","raw_affiliation_strings":["Institute of Electrical and Electronics Engineers"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Electronics Engineers","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054175637","display_name":"G\u00e9rard Chollet","orcid":"https://orcid.org/0000-0003-4245-146X"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"G\u00e9rard Chollet","raw_affiliation_strings":["TELECOM-ParisTech,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TELECOM-ParisTech,","institution_ids":["https://openalex.org/I12356871"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108119715","display_name":"Bruce Denby","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bruce Denby","raw_affiliation_strings":["Institute of Electrical and Electronics Engineers"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Electronics Engineers","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034139703","display_name":"G\u00e9rard Dreyfus","orcid":"https://orcid.org/0000-0001-7500-4573"},"institutions":[{"id":"https://openalex.org/I98910050","display_name":"ESPCI Paris","ror":"https://ror.org/03zx86w41","country_code":"FR","type":"education","lineage":["https://openalex.org/I190752583","https://openalex.org/I2746051580","https://openalex.org/I98910050"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"G\u00e9rard Dreyfus","raw_affiliation_strings":["ESPCI Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ESPCI Paris","institution_ids":["https://openalex.org/I98910050"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109307699","display_name":"Maureen Stone","orcid":null},"institutions":[{"id":"https://openalex.org/I126744593","display_name":"University of Maryland, Baltimore","ror":"https://ror.org/04rq5mt64","country_code":"US","type":"education","lineage":["https://openalex.org/I126744593"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maureen Stone","raw_affiliation_strings":["University of Maryland, Baltimore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, Baltimore","institution_ids":["https://openalex.org/I126744593"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.464,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.96898012,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2032","last_page":"2035"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9980999827384949,"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":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.8057205677032471},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7988866567611694},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7620970606803894},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5656628608703613},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.5429801940917969},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4512270987033844},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.41642138361930847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.392118364572525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8057205677032471},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7988866567611694},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7620970606803894},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5656628608703613},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.5429801940917969},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4512270987033844},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.41642138361930847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.392118364572525},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"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/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2008-528","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W91932436","https://openalex.org/W143765690","https://openalex.org/W1974688490","https://openalex.org/W1993996117","https://openalex.org/W2002735326","https://openalex.org/W2004143321","https://openalex.org/W2006820723","https://openalex.org/W2083932711","https://openalex.org/W2098693229","https://openalex.org/W2117193121","https://openalex.org/W2129160496","https://openalex.org/W2130094715","https://openalex.org/W2144855640","https://openalex.org/W3127686677"],"related_works":["https://openalex.org/W2964976023","https://openalex.org/W1982477181","https://openalex.org/W2403083015","https://openalex.org/W4285488523","https://openalex.org/W2011367623","https://openalex.org/W2734065904","https://openalex.org/W2027125286","https://openalex.org/W2049289069","https://openalex.org/W2809078847","https://openalex.org/W2061937230"],"abstract_inverted_index":{"Latest":[0],"results":[1],"on":[2,30],"continuous":[3,98],"speech":[4,24],"phone":[5,106,115,119],"recognition":[6,67,116,120],"from":[7],"video":[8],"observations":[9,90],"of":[10,20,39,50,91,103],"the":[11,18,40,51,101,104],"tongue":[12,41],"and":[13,47,56,68,77,88],"lips":[14],"are":[15,74,95],"described":[16],"in":[17,126],"context":[19],"an":[21],"ultrasound-based":[22],"silent":[23],"interface.":[25],"The":[26,118],"study":[27],"is":[28,63,123],"based":[29],"a":[31,112],"new":[32],"61-minute":[33],"audiovisual":[34],"database":[35,62],"containing":[36],"ultrasound":[37],"sequences":[38,79],"as":[42,44],"well":[43],"both":[45,65],"frontal":[46],"lateral":[48],"view":[49],"speaker\u2019s":[52],"lips.":[53],"Phonetically":[54],"balanced":[55],"exhibiting":[57],"good":[58],"diphone":[59],"coverage,":[60],"this":[61],"designed":[64],"for":[66],"corpus-based":[69],"synthesis":[70],"purposes.":[71],"Acoustic":[72],"waveforms":[73],"phonetically":[75],"labeled,":[76],"visual":[78,105],"coded":[80],"using":[81],"PCA-based":[82],"robust":[83],"feature":[84],"extraction":[85],"techniques.":[86],"Visual":[87],"acoustic":[89],"each":[92],"phonetic":[93],"class":[94],"modeled":[96],"by":[97],"HMMs,":[99],"allowing":[100],"performance":[102],"recognizer":[107],"to":[108,111],"be":[109],"compared":[110],"traditional":[113],"acoustic-based":[114],"experiment.":[117],"confusion":[121],"matrix":[122],"also":[124],"discussed":[125],"detail.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
