{"id":"https://openalex.org/W2972425221","doi":"https://doi.org/10.21437/interspeech.2019-2526","title":"A Phonetic-Level Analysis of Different Input Features for Articulatory Inversion","display_name":"A Phonetic-Level Analysis of Different Input Features for Articulatory Inversion","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972425221","doi":"https://doi.org/10.21437/interspeech.2019-2526","mag":"2972425221"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2526","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/A5032571112","display_name":"Abdolreza Sabzi Shahrebabaki","orcid":"https://orcid.org/0000-0002-0877-9456"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Abdolreza Sabzi Shahrebabaki","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054931657","display_name":"Negar Olfati","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Negar Olfati","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044015235","display_name":"Ali Shariq Imran","orcid":"https://orcid.org/0000-0002-2416-2878"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ali Shariq Imran","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055323428","display_name":"Torbj\u00f8rn Svendsen","orcid":"https://orcid.org/0000-0003-0578-7941"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Torbj\u00f8rn Svendsen","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5032571112"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7001,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78134104,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3775","last_page":"3779"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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":0.7249122858047485},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.7082513570785522},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5258128046989441},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3274557590484619},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3247523903846741},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.14975878596305847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7249122858047485},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.7082513570785522},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5258128046989441},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3274557590484619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3247523903846741},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.14975878596305847},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2019-2526","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unipa.it:10447/636677","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/636677","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1525807100","https://openalex.org/W1531956331","https://openalex.org/W1982854652","https://openalex.org/W2049686551","https://openalex.org/W2052382192","https://openalex.org/W2060630096","https://openalex.org/W2066381494","https://openalex.org/W2077804127","https://openalex.org/W2102152293","https://openalex.org/W2105478683","https://openalex.org/W2231075402","https://openalex.org/W2395955767","https://openalex.org/W2507804770","https://openalex.org/W2529309347","https://openalex.org/W2622158094","https://openalex.org/W2888815947","https://openalex.org/W2889371465"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0,35],"challenge":[1],"of":[2,12,32,38,89,179,186],"articulatory":[3,65],"inversion":[4,66],"is":[5,41],"to":[6,77,83,173],"determine":[7],"the":[8,13,16,29,33,39,62,73,84,90,136,187],"tem-":[9],"poral":[10],"movement":[11],"articulators":[14,40],"from":[15,20,25,44,72],"speech":[17,118],"waveform,":[18],"or":[19],"acoustic-phonetic":[21],"knowledge,":[22],"e.g.":[23],"derived":[24,71],"infor-":[26],"mation":[27],"about":[28],"linguistic":[30,111,169],"content":[31],"utterance.":[34,91],"actual":[36],"position":[37,50],"typically":[42],"obtained":[43,52,164],"measured":[45],"data,":[46],"in":[47],"our":[48],"case":[49],"measurements":[51],"using":[53,69,78],"EMA":[54,123],"(Electromagnetic":[55],"articulography).":[56],"In":[57],"this":[58],"paper,":[59],"we":[60],"investigate":[61],"impact":[63],"on":[64,116],"problem":[67],"by":[68,165],"features":[70,81,141],"acoustic":[74,98],"waveform":[75],"relative":[76,176,184],"linguis-":[79],"tic":[80],"related":[82],"time":[85],"aligned":[86],"phone":[87],"sequence":[88],"Filterbank":[92],"energies":[93],"(FBE)":[94],"are":[95,108,114],"used":[96,109],"as":[97,110],"fea-":[99,148],"tures,":[100],"while":[101],"phoneme":[102],"identities":[103],"and":[104,126,155,168,181],"(binary)":[105],"phonetic":[106],"attributes":[107],"features.":[112],"Experiments":[113],"performed":[115,142],"a":[117,128,182],"corpus":[119],"with":[120],"synchronously":[121],"recorded":[122],"measure-":[124],"ments":[125],"employing":[127],"bidirectional":[129],"long":[130],"short-term":[131],"memory":[132],"(BLSTM)":[133],"that":[134],"estimates":[135],"articulators\u2019":[137],"position.":[138],"Acoustic":[139],"FBE":[140,167],"better":[143,151],"for":[144,153,159],"vowel":[145],"sounds.":[146],"Phonetic":[147],"tures":[149],"attained":[150],"results":[152],"nasal":[154],"fricative":[156],"sounds":[157],"except":[158],"/h/.":[160],"Further":[161],"improvements":[162],"were":[163],"combining":[166],"features,":[170],"which":[171],"led":[172],"an":[174],"average":[175],"RMSE":[177],"reduction":[178],"9.8%,":[180],"3%":[183],"improvement":[185],"Pearson":[188],"correlation":[189],"coefficient.":[190]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}