{"id":"https://openalex.org/W2291998724","doi":"https://doi.org/10.21437/interspeech.2012-225","title":"Continuous articulatory-to-acoustic mapping using phone-based trajectory HMM for a silent speech interface","display_name":"Continuous articulatory-to-acoustic mapping using phone-based trajectory HMM for a silent speech interface","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2291998724","doi":"https://doi.org/10.21437/interspeech.2012-225","mag":"2291998724"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-225","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},"type":"conference-paper","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":[{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thomas Hueber","raw_affiliation_strings":["GIPSA-MAGIC - GIPSA -  Machines parlantes, Gestes oro-faciaux, Interaction Face-\u00e0-face, Communication augment\u00e9e (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA-MAGIC - GIPSA -  Machines parlantes, Gestes oro-faciaux, Interaction Face-\u00e0-face, Communication augment\u00e9e (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)","institution_ids":["https://openalex.org/I4210124956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071432574","display_name":"G\u00e9rard Bailly","orcid":"https://orcid.org/0000-0002-6053-0818"},"institutions":[{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"G\u00e9rard Bailly","raw_affiliation_strings":["GIPSA-MAGIC - GIPSA -  Machines parlantes, Gestes oro-faciaux, Interaction Face-\u00e0-face, Communication augment\u00e9e (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA-MAGIC - GIPSA -  Machines parlantes, Gestes oro-faciaux, Interaction Face-\u00e0-face, Communication augment\u00e9e (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)","institution_ids":["https://openalex.org/I4210124956"]}]},{"author_position":"last","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":["SIGMA - Laboratoire Signaux, Mod\u00e8les et Apprentissage Statistique (ESPCI, 10 rue Vauquelin, 75231 Paris cedex 05 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SIGMA - Laboratoire Signaux, Mod\u00e8les et Apprentissage Statistique (ESPCI, 10 rue Vauquelin, 75231 Paris cedex 05 - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.464,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.84785021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"723","last_page":"726"},"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":0.9993000030517578,"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":0.9988999962806702,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.9028605818748474},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7766421437263489},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7323881387710571},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5760653018951416},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.49978041648864746},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4837665557861328},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4292314648628235},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42717570066452026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42691460251808167},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4260631799697876},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.42346712946891785},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.415925532579422},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19589421153068542}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9028605818748474},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7766421437263489},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7323881387710571},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5760653018951416},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.49978041648864746},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4837665557861328},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4292314648628235},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42717570066452026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42691460251808167},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4260631799697876},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.42346712946891785},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.415925532579422},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19589421153068542},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2012-225","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","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":17,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W144370208","https://openalex.org/W1965392255","https://openalex.org/W1982854652","https://openalex.org/W1995735739","https://openalex.org/W2008120082","https://openalex.org/W2023249208","https://openalex.org/W2038697827","https://openalex.org/W2059169992","https://openalex.org/W2095026407","https://openalex.org/W2116257577","https://openalex.org/W2129160496","https://openalex.org/W2131062138","https://openalex.org/W2154920538","https://openalex.org/W2294901616","https://openalex.org/W2613113958","https://openalex.org/W2943553228"],"related_works":["https://openalex.org/W2079194684","https://openalex.org/W2617269004","https://openalex.org/W35292311","https://openalex.org/W1748856376","https://openalex.org/W2803166627","https://openalex.org/W2046073792","https://openalex.org/W2053269318","https://openalex.org/W2546021431","https://openalex.org/W2581127593","https://openalex.org/W2153098279"],"abstract_inverted_index":{"The":[0,28,59,94],"article":[1],"presents":[2],"an":[3,18],"HMM-based":[4],"mapping":[5,61],"approach":[6,133],"for":[7,22,42,112],"converting":[8],"ultrasound":[9],"and":[10,39,51,90,126],"video":[11],"images":[12],"of":[13,37,115,139],"the":[14,34,69,76,81,86,91,106,113,116,121,140],"vocal":[15],"tract":[16],"into":[17],"audible":[19],"speech":[20,25],"signal,":[21],"a":[23,136],"silent":[24],"interface":[26],"application.":[27],"proposed":[29,95],"technique":[30,96],"is":[31,62,97],"based":[32],"on":[33],"joint":[35],"modeling":[36],"articulatory":[38,77,92,122],"spectral":[40,82,117,141],"features,":[41],"each":[43],"phonetic":[44],"class,":[45],"using":[46],"Hidden":[47],"Markov":[48],"Models":[49],"(HMM)":[50],"multivariate":[52],"Gaussian":[53],"distributions":[54],"with":[55],"full":[56],"covariance":[57],"matrices.":[58],"articulatory-toacoustic":[60],"achieved":[63],"in":[64,103],"2":[65],"steps:":[66],"1)":[67],"finding":[68],"most":[70],"likely":[71],"HMM":[72],"state":[73,88,108],"sequence":[74,89,109],"from":[75,84,120],"observations;":[78],"2)":[79],"inferring":[80],"trajectories":[83],"both":[85],"decoded":[87,107],"observations.":[93,123],"compared":[98],"to":[99,135],"our":[100],"previous":[101],"approach,":[102],"which":[104],"only":[105],"was":[110],"used":[111],"inference":[114],"trajectories,":[118],"independently":[119],"Both":[124],"objective":[125],"perceptual":[127],"evaluations":[128],"show":[129],"that":[130],"this":[131],"new":[132],"leads":[134],"better":[137],"estimation":[138],"trajectories.":[142]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}