{"id":"https://openalex.org/W341711312","doi":"https://doi.org/10.21437/interspeech.2009-226","title":"Visuo-phonetic decoding using multi-stream and context-dependent models for an ultrasound-based silent speech interface","display_name":"Visuo-phonetic decoding using multi-stream and context-dependent models for an ultrasound-based silent speech interface","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W341711312","doi":"https://doi.org/10.21437/interspeech.2009-226","mag":"341711312"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-226","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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/A5003116633","display_name":"Elie-Laurent Benaroya","orcid":null},"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":"Elie-Laurent Benaroya","raw_affiliation_strings":["ESPCI Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ESPCI Paris","institution_ids":["https://openalex.org/I98910050"]}]},{"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":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.929,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.9336292,"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":"640","last_page":"643"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9969000220298767,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9926000237464905,"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":0.8305444717407227},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.8230503797531128},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7620156407356262},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6979737281799316},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6342462301254272},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5482913255691528},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.5402948260307312},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5118829011917114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.496794730424881},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3473342955112457},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3390958905220032},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.06863406300544739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8305444717407227},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.8230503797531128},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7620156407356262},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6979737281799316},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6342462301254272},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5482913255691528},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.5402948260307312},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5118829011917114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.496794730424881},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3473342955112457},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3390958905220032},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.06863406300544739},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","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/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"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/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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2009-226","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.602.2491","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.602.2491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://biblio.telecom-paristech.fr/cgi-bin/download.cgi?id=9908","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.605.9225","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.605.9225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.neurones.espci.fr/Articles_PS/INTERSPEECH 2009.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W36439550","https://openalex.org/W143765690","https://openalex.org/W161739902","https://openalex.org/W1922557984","https://openalex.org/W1974688490","https://openalex.org/W2004143321","https://openalex.org/W2006820723","https://openalex.org/W2039640471","https://openalex.org/W2106125881","https://openalex.org/W2117193121","https://openalex.org/W2129160496","https://openalex.org/W2130094715","https://openalex.org/W2144855640","https://openalex.org/W2158069733","https://openalex.org/W2276283915","https://openalex.org/W4285719527","https://openalex.org/W4320342197"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W3145575561","https://openalex.org/W2001275470","https://openalex.org/W2073996508","https://openalex.org/W1591475660","https://openalex.org/W2164162849"],"abstract_inverted_index":{"Recent":[0],"improvements":[1],"are":[2,36,46,77],"presented":[3],"for":[4],"phonetic":[5,101],"decoding":[6,102,119],"of":[7,14,96,112],"continuous-speech":[8],"from":[9],"ultrasound":[10],"and":[11,17,55,74,108],"optical":[12],"observations":[13],"the":[15,33,94,97,110],"tongue":[16],"lips":[18],"in":[19],"a":[20,26,49,56,66,117],"silent":[21,123],"speech":[22,71,86,124,127],"interface":[23],"application.":[24],"In":[25],"new":[27],"approach":[28],"to":[29,48,92],"this":[30],"critical":[31],"step,":[32],"visual":[34,57,98,126],"streams":[35],"modeled":[37],"by":[38],"context-dependent":[39],"multi-stream":[40,129],"Hidden":[41],"Markov":[42],"Models":[43],"(CD-MSHMM).":[44],"Results":[45],"compared":[47],"baseline":[50],"system":[51],"using":[52,79],"context-independent":[53],"modeling":[54,130],"feature":[58,81],"fusion":[59],"strategy,":[60],"with":[61,107],"both":[62],"systems":[63],"evaluated":[64,105],"on":[65],"one-hour,":[67],"phonetically":[68],"balanced":[69],"English":[70],"database.":[72],"Tongue":[73],"lip":[75],"images":[76],"coded":[78],"PCA-based":[80],"extraction":[82],"techniques.":[83],"The":[84],"uttered":[85],"signal,":[87],"also":[88],"recorded,":[89],"is":[90,104],"used":[91],"initialize":[93],"training":[95],"HMMs.":[99],"Visual":[100],"performance":[103],"successively":[106],"without":[109],"help":[111],"linguistic":[113],"constraints":[114],"introduced":[115],"via":[116],"2.5k-word":[118],"dictionary.":[120],"Index":[121],"Terms:":[122],"interface,":[125],"recognition,":[128],"1.":[131]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}