{"id":"https://openalex.org/W91932436","doi":"https://doi.org/10.21437/interspeech.2007-283","title":"Continuous-speech phone recognition from ultrasound and optical images of the tongue and lips","display_name":"Continuous-speech phone recognition from ultrasound and optical images of the tongue and lips","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W91932436","doi":"https://doi.org/10.21437/interspeech.2007-283","mag":"91932436"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-283","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","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":4.8825,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.95598227,"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":"658","last_page":"661"},"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":0.9944000244140625,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.986299991607666,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.810808539390564},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7946590185165405},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6851567029953003},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6306797862052917},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5482786297798157},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5431655049324036},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5186290144920349},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4962320923805237},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4772729277610779},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4685220420360565},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.46390220522880554}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.810808539390564},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7946590185165405},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6851567029953003},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6306797862052917},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5482786297798157},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5431655049324036},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5186290144920349},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4962320923805237},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4772729277610779},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4685220420360565},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46390220522880554},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2007-283","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1974688490","https://openalex.org/W2006820723","https://openalex.org/W2083932711","https://openalex.org/W2098693229","https://openalex.org/W2114720268","https://openalex.org/W2117193121","https://openalex.org/W2129160496","https://openalex.org/W2131722136","https://openalex.org/W2144855640","https://openalex.org/W3127686677"],"related_works":["https://openalex.org/W2153098279","https://openalex.org/W2121652828","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2092406870","https://openalex.org/W2052688117","https://openalex.org/W642007152","https://openalex.org/W2341426843","https://openalex.org/W2131711534"],"abstract_inverted_index":{"The":[0,55],"article":[1],"describes":[2],"a":[3,9,66],"video-only":[4],"speech":[5,11,26,34,60],"recognition":[6,61],"system":[7,62],"for":[8],"\u201csilent":[10],"interface\u201d":[12],"application,":[13],"using":[14,31],"ultrasound":[15],"and":[16,37,52],"optical":[17],"images":[18],"of":[19,57],"the":[20,50,58],"voice":[21],"organ.":[22],"A":[23],"one-hour":[24],"audiovisual":[25],"corpus":[27],"was":[28],"phonetically":[29],"labeled":[30],"an":[32],"automatic":[33],"alignment":[35],"procedure":[36],"robust":[38],"visual":[39,51,59],"feature":[40],"extraction":[41],"techniques.":[42],"HMM-based":[43],"stochastic":[44],"models":[45],"were":[46],"estimated":[47],"separately":[48],"on":[49],"acoustic":[53],"corpus.":[54],"performance":[56],"is":[63],"compared":[64],"to":[65],"traditional":[67],"acoustic-based":[68],"recognizer.":[69]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
