{"id":"https://openalex.org/W2408520046","doi":"https://doi.org/10.21437/interspeech.2011-688","title":"Method for speech inversion with large scale statistical evaluation","display_name":"Method for speech inversion with large scale statistical evaluation","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2408520046","doi":"https://doi.org/10.21437/interspeech.2011-688","mag":"2408520046"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-688","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-688","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5020980125","display_name":"Heikki Rasilo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heikki Rasilo","raw_affiliation_strings":["Informatics and Applied Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informatics and Applied Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040512120","display_name":"Unto K. Laine","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Unto K. Laine","raw_affiliation_strings":["Aalto Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto Univ","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016518233","display_name":"Okko R\u00e4s\u00e4nen","orcid":"https://orcid.org/0000-0002-0537-0946"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Okko R\u00e4s\u00e4nen","raw_affiliation_strings":["Aalto Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto Univ","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071511165","display_name":"Toomas Altosaar","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Toomas Altosaar","raw_affiliation_strings":["Aalto Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto Univ","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0135,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.79797441,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2693","last_page":"2696"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"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":0.9948999881744385,"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":0.7159822583198547},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.6860104203224182},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6814664006233215},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6349154114723206},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.5789708495140076},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.48655763268470764},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.46971458196640015},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4132898449897766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24446287751197815},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18238556385040283},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.0974145233631134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7159822583198547},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.6860104203224182},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6814664006233215},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6349154114723206},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.5789708495140076},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.48655763268470764},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.46971458196640015},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4132898449897766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24446287751197815},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18238556385040283},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0974145233631134},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2011-688","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-688","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:91488","is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/method-for-speech-inversion-with-large-scale-statistical-evaluation(eb067a6f-7467-421b-a874-d3850742f695).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"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":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W116416030","https://openalex.org/W123135133","https://openalex.org/W1490506669","https://openalex.org/W1970242389","https://openalex.org/W1977591085","https://openalex.org/W1984689963","https://openalex.org/W2006775235","https://openalex.org/W2054159638","https://openalex.org/W2069618035","https://openalex.org/W2088492089","https://openalex.org/W2088792641","https://openalex.org/W2143493821","https://openalex.org/W2150423550","https://openalex.org/W2166469361","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2046073792","https://openalex.org/W4254341835","https://openalex.org/W1748856376","https://openalex.org/W2086580720","https://openalex.org/W1909584822","https://openalex.org/W2001425423","https://openalex.org/W2061217898","https://openalex.org/W2894697037","https://openalex.org/W2131046383","https://openalex.org/W2021612972"],"abstract_inverted_index":{"Abstract":[0],"An":[1],"articulatory":[2,40,91,122,131,176,205,227,249,274,317],"model":[3,275,318],"of":[4,12,54,67,90,147,154,163,167,172,183,204,279],"speech":[5,17,26,113,148,164,173,217,243],"production":[6,18,162,218],"is":[7,100],"created":[8,314],"for":[9,25,51,58,106,216,238],"the":[10,14,52,78,85,95,107,151,161,168,170,184,189,192,197,202,209,242,265,277,282],"purpose":[11],"studying":[13,241],"links":[15],"between":[16],"and":[19,140,212,289,298,304,311],"perception.":[20],"A":[21,72],"computationally":[22],"effective":[23],"method":[24],"inversion":[27,55],"in":[28,35,130,160,191,261,281,327],"proposed,":[29],"using":[30,84,256],"a":[31,103,315],"two-pole":[32],"predictor":[33],"structure":[34],"order":[36,262],"to":[37,44,121,144,180,226,263,269,324],"maintain":[38],"better":[39],"dynamics":[41],"when":[42,142,208,240],"compared":[43,143],"conventional":[45],"dynamic":[46],"programming":[47],"methods.":[48],"Preliminary":[49],"tests":[50],"effect":[53],"are":[56,80,126,291],"performed":[57],"2500":[59],"Finnish":[60],"syllables":[61,79],"extracted":[62],"from":[63,188,253],"continuous":[64],"speech,":[65],"consisting":[66],"125":[68],"different":[69,155],"syllable":[70],"classes.":[71],"cluster":[73],"selectivity":[74],"test":[75],"shows":[76],"that":[77,99,186],"more":[81,127,300],"reliably":[82],"clustered":[83],"automatically":[86],"obtained":[87],"parametric":[88],"representation":[89,98],"gestures":[92],"rather":[93,138,158],"than":[94,132],"original":[96],"formant":[97],"used":[101,320],"as":[102,293],"starting":[104],"point":[105],"inversion.":[108],"Index":[109],"Terms:":[110],"Articulatory":[111],"model,":[112],"inversion,":[114],"motor":[115],"theory,":[116],"vocal":[117,302],"tract":[118,303],"1.":[119],"Introduction":[120],"modeling":[123,171,177,206],"Speech":[124],"events":[125],"conveniently":[128],"described":[129],"acoustic":[133,194],"sense.":[134],"Individual":[135],"articulators":[136,156,280],"move":[137],"slowly":[139],"smoothly":[141],"spectral":[145],"characteristics":[146],"signals.":[149],"Since":[150],"relative":[152],"trajectories":[153],"remain":[157],"similar":[159],"sounds":[165],"regardless":[166],"speaker,":[169],"perception":[174],"with":[175],"may":[178],"help":[179],"overcome":[181],"many":[182],"problems":[185],"arise":[187],"ambiguity":[190],"purely":[193],"domain.":[195],"In":[196,296],"19th":[198],"century":[199],"research":[200],"on":[201],"area":[203],"boomed":[207],"first":[210],"electrical":[211],"then":[213],"digital":[214],"models":[215,228,306],"could":[219],"be":[220],"implemented.":[221],"Researchers":[222],"have":[223,264,313],"often":[224],"referred":[225],"developed":[229],"by":[230],"Coker":[231],"[1],":[232],"Mermelstein":[233],"[2]":[234],"or":[235],"Maeda":[236],"[3],":[237],"example":[239],"inverse":[244],"problem.":[245],"Maeda\u2019s":[246],"model\u2019s":[247],"seven":[248],"parameters":[250,266],"were":[251,307],"estimated":[252],"x-ray":[254],"tracings":[255],"so-called":[257],"arbitrary":[258],"factor":[259],"analysis":[260],"maximally":[267],"uncorrelated":[268],"each":[270],"other.":[271],"Mermelstein\u2019s":[272],"geometrical":[273],"depicts":[276],"positions":[278],"midsagittal":[283],"plane.":[284],"Lips,":[285],"jaw,":[286],"tongue,":[287],"velum":[288],"hyoid":[290],"considered":[292],"movable":[294],"structures.":[295],"1990\u2019s":[297],"2000\u2019s":[299],"complex":[301],"tongue":[305],"developed.":[308],"E.g.":[309],"Dang":[310],"Honda":[312],"3D":[316],"which":[319],"physiological":[321],"constraints":[322],"typical":[323],"human":[325],"articulation":[326],"inverting":[328],"vowel-to-vowel":[329],"sequences":[330],"[4].":[331]},"counts_by_year":[{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
