{"id":"https://openalex.org/W221422375","doi":"https://doi.org/10.21437/interspeech.2009-640","title":"Acoustic-to-articulatory inversion using speech recognition and trajectory formation based on phoneme hidden Markov models","display_name":"Acoustic-to-articulatory inversion using speech recognition and trajectory formation based on phoneme hidden Markov models","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W221422375","doi":"https://doi.org/10.21437/interspeech.2009-640","mag":"221422375"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-640","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-640","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":null,"display_name":"Atef Ben Youssef","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atef Ben Youssef","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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":[],"raw_orcid":null,"affiliations":[]},{"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":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5029779616","display_name":"Panikos Heracleous","orcid":"https://orcid.org/0000-0002-7709-8195"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Panikos Heracleous","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8119,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.86715788,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2255","last_page":"2258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8949000239372253,"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":0.8949000239372253,"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":0.8207767605781555},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7809714078903198},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7289703488349915},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.5204965472221375},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.48190003633499146},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.46514713764190674},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.45284900069236755},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4284704327583313},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3357076346874237},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3341144323348999},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.1853867769241333},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.09963992238044739},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.054679691791534424}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8207767605781555},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7809714078903198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7289703488349915},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.5204965472221375},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.48190003633499146},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.46514713764190674},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.45284900069236755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4284704327583313},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3357076346874237},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3341144323348999},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.1853867769241333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.09963992238044739},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.054679691791534424},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2009-640","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-640","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W71802542","https://openalex.org/W88081813","https://openalex.org/W198124244","https://openalex.org/W1944976115","https://openalex.org/W1982854652","https://openalex.org/W1990394889","https://openalex.org/W2006775235","https://openalex.org/W2014621385","https://openalex.org/W2034829178","https://openalex.org/W2069618035","https://openalex.org/W2073704877","https://openalex.org/W2115119650","https://openalex.org/W2141477623","https://openalex.org/W2156623121","https://openalex.org/W2395252436","https://openalex.org/W2406017614","https://openalex.org/W2506302005","https://openalex.org/W2620587884","https://openalex.org/W3216401400"],"related_works":["https://openalex.org/W2134386692","https://openalex.org/W1510894296","https://openalex.org/W2316449557","https://openalex.org/W2082284720","https://openalex.org/W2194396582","https://openalex.org/W2116722627","https://openalex.org/W2003247472","https://openalex.org/W2379938888","https://openalex.org/W2537260108","https://openalex.org/W4233405330"],"abstract_inverted_index":{"In":[0],"order":[1],"to":[2,87],"recover":[3],"the":[4,44,53,57,60,81,85,89],"movements":[5,35],"of":[6,56,62,84],"usually":[7],"hidden":[8,115],"articulators":[9],"such":[10],"as":[11],"tongue":[12],"or":[13],"velum,":[14],"we":[15],"have":[16],"developed":[17],"a":[18,27,75],"data-based":[19],"speech":[20,45,48,109],"inversion":[21],"method.":[22],"HMMs":[23,58,86],"are":[24],"trained,":[25],"in":[26],"multistream":[28],"framework,":[29],"from":[30,43],"two":[31],"synchronous":[32],"streams:":[33],"articulatory":[34,82,90],"measured":[36],"by":[37,74],"EMA,":[38],"and":[39,64,99],"MFCC":[40],"+":[41],"energy":[42],"signal.":[46],"A":[47],"recognition":[49],"procedure":[50,78],"based":[51,79],"on":[52,80],"acoustic":[54],"part":[55,83],"delivers":[59],"chain":[61],"phonemes":[63],"together":[65],"with":[66],"their":[67],"durations,":[68],"information":[69],"that":[70],"is":[71],"subsequently":[72],"used":[73],"trajectory":[76,119],"formation":[77],"synthesise":[88],"movements.":[91],"The":[92],"RMS":[93],"reconstruction":[94],"error":[95],"ranged":[96],"between":[97],"1.1":[98],"2.":[100],"mm.":[101],"Index":[102],"Terms:":[103],"Speech":[104],"inversion,":[105],"augmented":[106],"speech,":[107],"automatic":[108],"recognition,":[110],"HTK,":[111],"Electro-Magnetic":[112],"Articulography":[113],"(EMA),":[114],"Markov":[116],"model":[117],"(HMM),":[118],"formation,":[120],"HTS.":[121]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}