{"id":"https://openalex.org/W143765690","doi":"https://doi.org/10.21437/interspeech.2008-527","title":"Towards a segmental vocoder driven by ultrasound and optical images of the tongue and lips","display_name":"Towards a segmental vocoder driven by ultrasound and optical images of the tongue and lips","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W143765690","doi":"https://doi.org/10.21437/interspeech.2008-527","mag":"143765690"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-527","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-527","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":3.4221,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.9202346,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2028","last_page":"2031"},"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":0.9990000128746033,"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":0.9987999796867371,"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":0.8104393482208252},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7973716259002686},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7667316198348999},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6146535873413086},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4811452627182007},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4759383201599121},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4500633776187897},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44873765110969543},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3432953357696533},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20457255840301514},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07321420311927795}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8104393482208252},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7973716259002686},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7667316198348999},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6146535873413086},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4811452627182007},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4759383201599121},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4500633776187897},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44873765110969543},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3432953357696533},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20457255840301514},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07321420311927795},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2008-527","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-527","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":[{"display_name":"Quality Education","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W71082305","https://openalex.org/W91932436","https://openalex.org/W135040384","https://openalex.org/W1211067074","https://openalex.org/W1974688490","https://openalex.org/W2006820723","https://openalex.org/W2117193121","https://openalex.org/W2129160496","https://openalex.org/W2130094715","https://openalex.org/W2142384583","https://openalex.org/W2150658333","https://openalex.org/W3127686677"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W4387678054","https://openalex.org/W3095575180","https://openalex.org/W2389596151","https://openalex.org/W4221148444","https://openalex.org/W4226054107","https://openalex.org/W4306784355","https://openalex.org/W2510951244","https://openalex.org/W4246226292","https://openalex.org/W2153098279"],"abstract_inverted_index":{"This":[0],"article":[1],"presents":[2],"a":[3,6,21,43,73,99],"framework":[4],"for":[5,20,54],"phonetic":[7,40,49],"vocoder":[8],"driven":[9],"by":[10],"ultrasound":[11,106],"and":[12,18,111,114],"optical":[13],"images":[14,107],"of":[15,58,108,117],"the":[16,52,55,64,78,109,118],"tongue":[17,110],"lips":[19],"\u201csilent":[22],"speech":[23,83,102],"interface\u201d":[24],"application.":[25],"The":[26,48,81],"system":[27],"is":[28,85],"built":[29],"around":[30],"an":[31],"HMM-based":[32],"visual":[33,45,69],"phone":[34],"recognition":[35],"step":[36],"which":[37],"provides":[38],"target":[39,50],"sequences":[41],"from":[42],"continuous":[44,101],"observation":[46],"stream.":[47],"constrains":[51],"search":[53],"optimal":[56],"sequence":[57],"diphones":[59],"that":[60],"maximizes":[61],"similarity":[62],"to":[63,72],"input":[65],"test":[66],"data":[67],"in":[68,77],"space":[70],"subject":[71],"unit":[74],"concatenation":[75],"cost":[76],"acoustic":[79],"domain.":[80],"final":[82],"waveform":[84],"generated":[86],"using":[87],"\u201cHarmonic":[88],"plus":[89],"Noise":[90],"Model\u201d":[91],"synthesis":[92],"techniques.":[93],"Experimental":[94],"results":[95],"are":[96],"based":[97],"on":[98],"onehour":[100],"audiovisual":[103],"database":[104],"comprising":[105],"both":[112],"frontal":[113],"lateral":[115],"view":[116],"speaker\u2019s":[119],"lips.":[120]},"counts_by_year":[{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
