{"id":"https://openalex.org/W40881502","doi":"https://doi.org/10.21437/interspeech.2013-631","title":"Speaker adaptation of an acoustic-articulatory inversion model using cascaded Gaussian mixture regressions","display_name":"Speaker adaptation of an acoustic-articulatory inversion model using cascaded Gaussian mixture regressions","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W40881502","doi":"https://doi.org/10.21437/interspeech.2013-631","mag":"40881502"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-631","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","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":true,"raw_author_name":"Thomas Hueber","raw_affiliation_strings":["GIPSA -  Machines parlantes, Gestes oro-faciaux, Interaction Face-\u00e0-face, Communication augment\u00e9e"],"affiliations":[{"raw_affiliation_string":"GIPSA -  Machines parlantes, Gestes oro-faciaux, Interaction Face-\u00e0-face, Communication augment\u00e9e","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071432574","display_name":"G\u00e9rard Bailly","orcid":"https://orcid.org/0000-0002-6053-0818"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G\u00e9rard Bailly","raw_affiliation_strings":["GIPSA -  Machines parlantes, Gestes oro-faciaux, Interaction Face-\u00e0-face, Communication augment\u00e9e"],"affiliations":[{"raw_affiliation_string":"GIPSA -  Machines parlantes, Gestes oro-faciaux, Interaction Face-\u00e0-face, Communication augment\u00e9e","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058305510","display_name":"Pierre Badin","orcid":"https://orcid.org/0000-0001-7440-820X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pierre Badin","raw_affiliation_strings":["GIPSA -  Machines parlantes, Gestes oro-faciaux, Interaction Face-\u00e0-face, Communication augment\u00e9e"],"affiliations":[{"raw_affiliation_string":"GIPSA -  Machines parlantes, Gestes oro-faciaux, Interaction Face-\u00e0-face, Communication augment\u00e9e","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068848480","display_name":"Fr\u00e9d\u00e9ric Elisei","orcid":"https://orcid.org/0000-0002-1295-3445"},"institutions":[{"id":"https://openalex.org/I2800493309","display_name":"Grain Inspection, Packers and Stockyards Administration","ror":"https://ror.org/056mcm922","country_code":"US","type":"government","lineage":["https://openalex.org/I1336096307","https://openalex.org/I2800493309"]},{"id":"https://openalex.org/I4210124956","display_name":"Grenoble Images Parole Signal Automatique","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","US"],"is_corresponding":false,"raw_author_name":"Fr\u00e9d\u00e9ric Elisei","raw_affiliation_strings":["GIPSA-Services"],"affiliations":[{"raw_affiliation_string":"GIPSA-Services","institution_ids":["https://openalex.org/I4210124956","https://openalex.org/I2800493309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5060372031"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8855,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.90939223,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2753","last_page":"2757"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9988999962806702,"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":0.7408655881881714},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7252753973007202},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.63907790184021},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5069808959960938},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5002539157867432},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.48648354411125183},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.4745270311832428},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.4665016531944275},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.4536074101924896},{"id":"https://openalex.org/keywords/acoustic-space","display_name":"Acoustic space","score":0.4421387016773224},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.4307924211025238},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.42319077253341675},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39521101117134094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37123993039131165},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.3403717279434204},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.27285462617874146},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15071576833724976},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1493721902370453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7408655881881714},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7252753973007202},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.63907790184021},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5069808959960938},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5002539157867432},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.48648354411125183},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.4745270311832428},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.4665016531944275},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.4536074101924896},{"id":"https://openalex.org/C108250783","wikidata":"https://www.wikidata.org/wiki/Q4674710","display_name":"Acoustic space","level":3,"score":0.4421387016773224},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.4307924211025238},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.42319077253341675},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39521101117134094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37123993039131165},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.3403717279434204},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.27285462617874146},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15071576833724976},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1493721902370453},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C204723758","wikidata":"https://www.wikidata.org/wiki/Q3882459","display_name":"Acoustic wave","level":2,"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/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2013-631","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W60202269","https://openalex.org/W1505583828","https://openalex.org/W1514234570","https://openalex.org/W1525414018","https://openalex.org/W1607802755","https://openalex.org/W1965392255","https://openalex.org/W1982854652","https://openalex.org/W2034829178","https://openalex.org/W2062125287","https://openalex.org/W2064234620","https://openalex.org/W2069618035","https://openalex.org/W2100969003","https://openalex.org/W2101307193","https://openalex.org/W2106058739","https://openalex.org/W2116257577","https://openalex.org/W2120605154","https://openalex.org/W2124555689","https://openalex.org/W2134539847","https://openalex.org/W2146871184","https://openalex.org/W2154920538","https://openalex.org/W2295705173","https://openalex.org/W2403459132"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"The":[0,20,169],"article":[1],"presents":[2],"a":[3,7,14,33,52,64,74],"method":[4,45],"for":[5,88],"adapting":[6],"GMM-based":[8,85],"acoustic-articulatory":[9],"inversion":[10],"model":[11],"trained":[12],"on":[13,161,182],"reference":[15,34,117,131],"speaker":[16,35,65,89,107,118,132,177],"to":[17,23,83,145,174],"another":[18,42],"speaker.":[19,43],"goal":[21],"is":[22,46,172],"estimate":[24],"the":[25,29,37,49,101,105,109,116,124,130,134,151],"articulatory":[26,127],"trajectories":[27,103,114,128],"in":[28,48,95],"geometrical":[30],"space":[31],"of":[32,41,51,54,104,115,129],"from":[36,133],"speech":[38],"audio":[39],"signal":[40],"This":[44,61],"developed":[47],"context":[50],"system":[53,62,110],"visual":[55,67],"biofeedback,":[56],"aimed":[57],"at":[58],"pronunciation":[59],"training.":[60],"provides":[63],"with":[66],"information":[68],"about":[69],"his/her":[70],"own":[71],"articulation,":[72],"via":[73],"3D":[75],"orofacial":[76],"clone.":[77],"In":[78,140],"previous":[79],"work,":[80,142],"we":[81,143],"proposed":[82,170],"use":[84],"voice":[86],"conversion":[87],"adaptation.":[90],"Acoustic-articulatory":[91],"mapping":[92,154],"was":[93],"achieved":[94],"2":[96],"consecutive":[97],"steps:":[98],"1)":[99],"converting":[100],"spectral":[102,113,136],"target":[106],"(i.e.":[108],"user)":[111],"into":[112,150],"(voice":[119],"conversion),":[120],"and":[121,164,184],"2)":[122],"estimating":[123],"most":[125],"likely":[126],"converted":[135],"features":[137],"(acoustic-articulatory":[138],"inversion).":[139],"this":[141],"propose":[144],"combine":[146],"these":[147],"two":[148,175],"steps":[149],"same":[152],"statistical":[153],"framework,":[155],"by":[156],"fusing":[157],"multiple":[158],"regressions":[159],"based":[160,180],"trajectory":[162],"GMM":[163],"maximum":[165],"likelihood":[166],"criterion":[167],"(MLE).":[168],"technique":[171],"compared":[173],"standard":[176],"adaptation":[178],"techniques":[179],"respectively":[181],"MAP":[183],"MLLR.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}