{"id":"https://openalex.org/W2890669918","doi":"https://doi.org/10.1109/slt.2018.8639537","title":"Improving Generalization of Vocal Tract Feature Reconstruction: From Augmented Acoustic Inversion to Articulatory Feature Reconstruction without Articulatory Data","display_name":"Improving Generalization of Vocal Tract Feature Reconstruction: From Augmented Acoustic Inversion to Articulatory Feature Reconstruction without Articulatory Data","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2890669918","doi":"https://doi.org/10.1109/slt.2018.8639537","mag":"2890669918"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1809.00938","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041990349","display_name":"Rosanna Turrisi","orcid":null},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]},{"id":"https://openalex.org/I4210133238","display_name":"Center for Translational Neurophysiology of Speech and Communication","ror":"https://ror.org/02nzxcb82","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210133238"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Rosanna Turrisi","raw_affiliation_strings":["CTNSC, Istituto Italiano di Tecnologia, Ferrara, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CTNSC, Istituto Italiano di Tecnologia, Ferrara, Italy","institution_ids":["https://openalex.org/I4210133238","https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090996481","display_name":"Raffaele Tavarone","orcid":null},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]},{"id":"https://openalex.org/I4210133238","display_name":"Center for Translational Neurophysiology of Speech and Communication","ror":"https://ror.org/02nzxcb82","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210133238"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Raffaele Tavarone","raw_affiliation_strings":["CTNSC, Istituto Italiano di Tecnologia, Ferrara, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CTNSC, Istituto Italiano di Tecnologia, Ferrara, Italy","institution_ids":["https://openalex.org/I4210133238","https://openalex.org/I30771326"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063165262","display_name":"Leonardo Badino","orcid":"https://orcid.org/0000-0001-7037-5914"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]},{"id":"https://openalex.org/I4210133238","display_name":"Center for Translational Neurophysiology of Speech and Communication","ror":"https://ror.org/02nzxcb82","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210133238"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Leonardo Badino","raw_affiliation_strings":["CTNSC, Istituto Italiano di Tecnologia, Ferrara, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CTNSC, Istituto Italiano di Tecnologia, Ferrara, Italy","institution_ids":["https://openalex.org/I4210133238","https://openalex.org/I30771326"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3379,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68954496,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"71","issue":null,"first_page":"159","last_page":"166"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.8817217946052551},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.736207127571106},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6806524991989136},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5867674946784973},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5091583132743835},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.4934665262699127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4601363241672516},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44464531540870667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40336787700653076},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15745946764945984}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.8817217946052551},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.736207127571106},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6806524991989136},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5867674946784973},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5091583132743835},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.4934665262699127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4601363241672516},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44464531540870667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40336787700653076},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15745946764945984},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/slt.2018.8639537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1809.00938","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.00938","pdf_url":"https://arxiv.org/pdf/1809.00938","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:sfera.unife.it:11392/2573913","is_oa":false,"landing_page_url":"https://hdl.handle.net/11392/2573913","pdf_url":null,"source":{"id":"https://openalex.org/S4306400369","display_name":"Institutional Research Information System University of Ferrara (University of Ferrara)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I201324441","host_organization_name":"University of Ferrara","host_organization_lineage":["https://openalex.org/I201324441"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1809.00938","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.00938","pdf_url":"https://arxiv.org/pdf/1809.00938","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W40881502","https://openalex.org/W900447646","https://openalex.org/W1496997718","https://openalex.org/W1522301498","https://openalex.org/W1531883353","https://openalex.org/W1533861849","https://openalex.org/W1959608418","https://openalex.org/W1980837758","https://openalex.org/W1990394889","https://openalex.org/W2025877346","https://openalex.org/W2053757129","https://openalex.org/W2064675550","https://openalex.org/W2068447135","https://openalex.org/W2075948878","https://openalex.org/W2091288983","https://openalex.org/W2116082100","https://openalex.org/W2134539847","https://openalex.org/W2194775991","https://openalex.org/W2395955767","https://openalex.org/W2403459132","https://openalex.org/W2507804770","https://openalex.org/W2746549158","https://openalex.org/W2951004968","https://openalex.org/W2964121744","https://openalex.org/W6713069414"],"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/W1591384192","https://openalex.org/W2099204336","https://openalex.org/W4254341835","https://openalex.org/W4200300343"],"abstract_inverted_index":{"We":[0,35,50],"address":[1],"the":[2,38],"problem":[3],"of":[4,16],"reconstructing":[5],"articulatory":[6,18,43,65,95,99,119,124,140],"movements,":[7],"given":[8],"audio":[9],"and/or":[10],"phonetic":[11,46,53,103],"labels.":[12,104],"The":[13],"scarce":[14],"availability":[15],"multi-speaker":[17],"data":[19],"makes":[20],"it":[21],"difficult":[22],"to":[23,29,58,93,133],"learn":[24],"a":[25,83,88],"reconstruction":[26],"that":[27,52,63,91,123],"generalizes":[28],"new":[30],"speakers":[31],"and":[32,45,78],"across":[33],"datasets.":[34],"first":[36],"consider":[37],"XRMB":[39],"dataset":[40,115],"where":[41],"audio,":[42],"measurements":[44],"transcriptions":[47],"are":[48,67],"available.":[49],"show":[51,122],"labels,":[54],"used":[55],"as":[56],"input":[57],"deep":[59],"recurrent":[60],"neural":[61],"networks":[62],"reconstruct":[64],"features,":[66],"in":[68,75],"general":[69],"more":[70],"helpful":[71],"than":[72],"acoustic":[73],"features":[74,96,125],"both":[76],"matched":[77],"mismatched":[79],"training-testing":[80],"conditions.":[81],"In":[82],"second":[84],"experiment,":[85],"we":[86],"test":[87],"novel":[89],"approach":[90,106,129],"attempts":[92],"build":[94],"from":[97,102,112],"prior":[98],"information":[100],"extracted":[101],"Such":[105],"recovers":[107],"vocal":[108],"tract":[109],"movements":[110],"directly":[111],"an":[113],"acoustic-only":[114],"without":[116],"using":[117],"any":[118],"measurement.":[120],"Results":[121],"generated":[126],"by":[127],"this":[128],"can":[130],"correlate":[131],"up":[132],"0.59":[134],"Pearson's":[135],"product-moment":[136],"correlation":[137],"with":[138],"measured":[139],"features.":[141]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2018-09-27T00:00:00"}
