{"id":"https://openalex.org/W2746109435","doi":"https://doi.org/10.21437/interspeech.2017-939","title":"DNN-Based Ultrasound-to-Speech Conversion for a Silent Speech Interface","display_name":"DNN-Based Ultrasound-to-Speech Conversion for a Silent Speech Interface","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2746109435","doi":"https://doi.org/10.21437/interspeech.2017-939","mag":"2746109435"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-939","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/A5016031960","display_name":"Tam\u00e1s G\u00e1bor Csap\u00f3","orcid":"https://orcid.org/0000-0003-4375-7524"},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]},{"id":"https://openalex.org/I2802350943","display_name":"ELTE Hungarian Research Centre for Linguistics","ror":"https://ror.org/005cqsz63","country_code":"HU","type":"facility","lineage":["https://openalex.org/I2802350943"]},{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Tam\u00e1s G\u00e1bor Csap\u00f3","raw_affiliation_strings":["Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary","MTA-ELTE Lend\u00fclet Lingual Articulation Research Group, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"MTA-ELTE Lend\u00fclet Lingual Articulation Research Group, Budapest, Hungary","institution_ids":["https://openalex.org/I2802350943","https://openalex.org/I106118109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058277119","display_name":"Tam\u00e1s Gr\u00f3sz","orcid":"https://orcid.org/0000-0001-7918-9579"},"institutions":[{"id":"https://openalex.org/I227486990","display_name":"University of Szeged","ror":"https://ror.org/01pnej532","country_code":"HU","type":"education","lineage":["https://openalex.org/I227486990"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Tam\u00e1s Gr\u00f3sz","raw_affiliation_strings":["Institute of Informatics, University of Szeged, Hungary"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics, University of Szeged, Hungary","institution_ids":["https://openalex.org/I227486990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088559776","display_name":"G\u00e1bor Gosztolya","orcid":"https://orcid.org/0000-0002-2864-6466"},"institutions":[{"id":"https://openalex.org/I227486990","display_name":"University of Szeged","ror":"https://ror.org/01pnej532","country_code":"HU","type":"education","lineage":["https://openalex.org/I227486990"]},{"id":"https://openalex.org/I4210152167","display_name":"MTA-SZTE Research Group on Artificial Intelligence","ror":"https://ror.org/0507fk326","country_code":"HU","type":"facility","lineage":["https://openalex.org/I227486990","https://openalex.org/I4210152167","https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"G\u00e1bor Gosztolya","raw_affiliation_strings":["Institute of Informatics, University of Szeged, Hungary","MTA-SZTE Research Group on Artificial Intelligence, Szeged, Hungary"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics, University of Szeged, Hungary","institution_ids":["https://openalex.org/I227486990"]},{"raw_affiliation_string":"MTA-SZTE Research Group on Artificial Intelligence, Szeged, Hungary","institution_ids":["https://openalex.org/I4210152167"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020608163","display_name":"L\u00e1szl\u00f3 T\u00f3th","orcid":"https://orcid.org/0000-0003-0161-1375"},"institutions":[{"id":"https://openalex.org/I4210152167","display_name":"MTA-SZTE Research Group on Artificial Intelligence","ror":"https://ror.org/0507fk326","country_code":"HU","type":"facility","lineage":["https://openalex.org/I227486990","https://openalex.org/I4210152167","https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"L\u00e1szl\u00f3 T\u00f3th","raw_affiliation_strings":["MTA-SZTE Research Group on Artificial Intelligence, Szeged, Hungary"],"affiliations":[{"raw_affiliation_string":"MTA-SZTE Research Group on Artificial Intelligence, Szeged, Hungary","institution_ids":["https://openalex.org/I4210152167"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085147054","display_name":"Alexandra Mark\u00f3","orcid":"https://orcid.org/0000-0003-0301-7134"},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]},{"id":"https://openalex.org/I2802350943","display_name":"ELTE Hungarian Research Centre for Linguistics","ror":"https://ror.org/005cqsz63","country_code":"HU","type":"facility","lineage":["https://openalex.org/I2802350943"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Alexandra Mark\u00f3","raw_affiliation_strings":["MTA-ELTE Lend\u00fclet Lingual Articulation Research Group, Budapest, Hungary","Department of Phonetics, E\u00f6tv\u00f6s Lor\u00e1nd University, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"MTA-ELTE Lend\u00fclet Lingual Articulation Research Group, Budapest, Hungary","institution_ids":["https://openalex.org/I2802350943","https://openalex.org/I106118109"]},{"raw_affiliation_string":"Department of Phonetics, E\u00f6tv\u00f6s Lor\u00e1nd University, Budapest, Hungary","institution_ids":["https://openalex.org/I106118109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5016031960"],"corresponding_institution_ids":["https://openalex.org/I106118109","https://openalex.org/I2802350943","https://openalex.org/I29770179"],"apc_list":null,"apc_paid":null,"fwci":4.7811,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.95926732,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3672","last_page":"3676"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9990000128746033,"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/T12031","display_name":"Speech and dialogue systems","score":0.9593999981880188,"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/speech-recognition","display_name":"Speech recognition","score":0.7507146596908569},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7294809818267822},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.5692938566207886},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5467679500579834},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.511921763420105},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4812181293964386}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7507146596908569},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7294809818267822},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.5692938566207886},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5467679500579834},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.511921763420105},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4812181293964386},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2017-939","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:real.mtak.hu:90672","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400081","display_name":"Repository of the Academy's Library (Library of the Hungarian Academy of Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210140733","host_organization_name":"Library and Information Centre of the Hungarian Academy of Sciences","host_organization_lineage":["https://openalex.org/I4210140733"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2283631711","display_name":null,"funder_award_id":"\u00daNKP-16","funder_id":"https://openalex.org/F4320323476","funder_display_name":"Emberi Eroforr\u00e1sok Miniszt\u00e9riuma"}],"funders":[{"id":"https://openalex.org/F4320323476","display_name":"Emberi Eroforr\u00e1sok Miniszt\u00e9riuma","ror":"https://ror.org/00rb16m44"},{"id":"https://openalex.org/F4320338388","display_name":"Eurostars","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W845365781","https://openalex.org/W1663785051","https://openalex.org/W1975079546","https://openalex.org/W1995735739","https://openalex.org/W2008120082","https://openalex.org/W2068056889","https://openalex.org/W2129160496","https://openalex.org/W2138451337","https://openalex.org/W2143929858","https://openalex.org/W2145442746","https://openalex.org/W2145892079","https://openalex.org/W2163605009","https://openalex.org/W2291998724","https://openalex.org/W2294901616","https://openalex.org/W2295969124","https://openalex.org/W2296704011","https://openalex.org/W2322064186","https://openalex.org/W2402091997","https://openalex.org/W2482033662","https://openalex.org/W2515755543","https://openalex.org/W2554625447","https://openalex.org/W2607333215"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2536333783","https://openalex.org/W3002577753","https://openalex.org/W1658560081","https://openalex.org/W1547849677","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340","https://openalex.org/W2120019655","https://openalex.org/W2069501481"],"abstract_inverted_index":{"In":[0],"this":[1,40],"paper":[2],"we":[3,42,55,100],"present":[4],"our":[5],"initial":[6],"results":[7,175],"in":[8,147,162,167,185],"articulatory-toacoustic":[9],"conversion":[10],"based":[11],"on":[12],"tongue":[13],"movement":[14],"recordings":[15],"using":[16,129],"Deep":[17],"Neural":[18],"Networks":[19],"(DNNs).Despite":[20],"the":[21,53,66,91,111,114,122,139,158,163,170,186],"fact":[22],"that":[23,138,141],"deep":[24],"learning":[25],"has":[26],"revolutionized":[27],"several":[28,143],"fields,":[29],"so":[30],"far":[31],"only":[32],"a":[33,84,96,133,150],"few":[34],"researchers":[35],"have":[36,95],"applied":[37],"DNNs":[38],"for":[39,88,179],"task.Here,":[41],"compare":[43],"various":[44,103,123],"possible":[45],"feature":[46,104,115,151],"representation":[47,140],"approaches":[48,108],"combined":[49],"with":[50,102,149],"DNN-based":[51],"regression.As":[52],"input,":[54],"recorded":[56],"synchronized":[57],"2D":[58],"ultrasound":[59,93],"images":[60,94],"and":[61,106,132,166],"speech":[62,89,118],"signals.The":[63],"task":[64],"of":[65,113,169],"DNN":[67,124],"was":[68,154],"to":[69,83,109],"estimate":[70],"Mel-Generalized":[71],"Cepstrum-based":[72],"Line":[73],"Spectral":[74],"Pair":[75],"(MGC-LSP)":[76],"coefficients,":[77],"which":[78],"then":[79],"served":[80],"as":[81],"input":[82],"standard":[85],"pulse-noise":[86],"vocoder":[87],"synthesis.As":[90],"raw":[92],"relatively":[97],"high":[98],"resolution,":[99],"experimented":[101],"selection":[105,152],"transformation":[107],"reduce":[110],"size":[112],"vectors.The":[116],"synthetic":[117],"signals":[119],"resulting":[120],"from":[121],"configurations":[125],"were":[126],"evaluated":[127],"both":[128,156],"objective":[130],"measures":[131],"subjective":[134],"listening":[135,164],"test.We":[136],"found":[137],"used":[142],"neighboring":[144],"image":[145],"frames":[146],"combination":[148],"method":[153],"preferred":[155],"by":[157],"subjects":[159],"taking":[160],"part":[161],"experiments,":[165],"terms":[168],"Normalized":[171],"Mean":[172],"Squared":[173],"Error.Our":[174],"may":[176],"be":[177],"useful":[178],"creating":[180],"Silent":[181],"Speech":[182],"Interface":[183],"applications":[184],"future.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-14T06:02:45.956762","created_date":"2025-10-10T00:00:00"}