{"id":"https://openalex.org/W3047902412","doi":"https://doi.org/10.21437/interspeech.2020-1031","title":"Ultrasound-Based Articulatory-to-Acoustic Mapping with WaveGlow Speech Synthesis","display_name":"Ultrasound-Based Articulatory-to-Acoustic Mapping with WaveGlow Speech Synthesis","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3047902412","doi":"https://doi.org/10.21437/interspeech.2020-1031","mag":"3047902412"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1031","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"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"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Tam\u00e1s G\u00e1bor Csap\u00f3","raw_affiliation_strings":["E\u00f6tv\u00f6s Lor\u00e1nd University, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"E\u00f6tv\u00f6s Lor\u00e1nd University, Budapest, Hungary","institution_ids":["https://openalex.org/I106118109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031237235","display_name":"Csaba Zaink\u00f3","orcid":null},"institutions":[{"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":false,"raw_author_name":"Csaba Zaink\u00f3","raw_affiliation_strings":["Budapest University of Technology and Economics, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"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/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":"L\u00e1szl\u00f3 T\u00f3th","raw_affiliation_strings":["University of Szeged, Szeged, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Szeged, 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"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"G\u00e1bor Gosztolya","raw_affiliation_strings":["University of Szeged, Szeged, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Szeged, Szeged, Hungary","institution_ids":["https://openalex.org/I227486990"]}]},{"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"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Alexandra Mark\u00f3","raw_affiliation_strings":["E\u00f6tv\u00f6s Lor\u00e1nd University, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4063,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69699008,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9991000294685364,"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":0.9965000152587891,"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/spectrogram","display_name":"Spectrogram","score":0.8870139122009277},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7311480045318604},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7133181095123291},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.584152340888977},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5463578701019287},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5333820581436157},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5057985782623291},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.4677486717700958},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.4611760377883911},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4428649842739105},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.430704265832901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39796310663223267},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3520597219467163},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3426344692707062}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8870139122009277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7311480045318604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7133181095123291},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.584152340888977},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5463578701019287},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5333820581436157},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5057985782623291},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.4677486717700958},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.4611760377883911},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4428649842739105},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.430704265832901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39796310663223267},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3520597219467163},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3426344692707062},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2020-1031","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:publicatio.bibl.u-szeged.hu:19937","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400436","display_name":"SZTE Publicatio Repozit\u00f3rium (University of Szeged)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I227486990","host_organization_name":"University of Szeged","host_organization_lineage":["https://openalex.org/I227486990"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"K\u00f6nyv r\u00e9sze"},{"id":"pmh:oai:arXiv.org:2008.03152","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.03152","pdf_url":"https://arxiv.org/pdf/2008.03152","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":"mag:3047902412","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2008.03152.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2008.03152","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.03152","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:publicatio.bibl.u-szeged.hu:19937","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400436","display_name":"SZTE Publicatio Repozit\u00f3rium (University of Szeged)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I227486990","host_organization_name":"University of Szeged","host_organization_lineage":["https://openalex.org/I227486990"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"K\u00f6nyv r\u00e9sze"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.699999988079071}],"awards":[{"id":"https://openalex.org/G1530658115","display_name":null,"funder_award_id":"\u00daNKP-20-5","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4140855681","display_name":"A European AI On Demand Platform and Ecosystem","funder_award_id":"825619","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7596222748","display_name":null,"funder_award_id":"\u00daNKP-20-5","funder_id":"https://openalex.org/F4320322192","funder_display_name":"Magyar Tudom\u00e1nyos Akad\u00e9mia"},{"id":"https://openalex.org/G807110274","display_name":null,"funder_award_id":"TUDFO/47138-1/2019-ITM","funder_id":"https://openalex.org/F4320322192","funder_display_name":"Magyar Tudom\u00e1nyos Akad\u00e9mia"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320322192","display_name":"Magyar Tudom\u00e1nyos Akad\u00e9mia","ror":"https://ror.org/02ks8qq67"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1980988001","https://openalex.org/W1995735739","https://openalex.org/W2008120082","https://openalex.org/W2021914964","https://openalex.org/W2107860279","https://openalex.org/W2145442746","https://openalex.org/W2145892079","https://openalex.org/W2294901616","https://openalex.org/W2296650368","https://openalex.org/W2419247625","https://openalex.org/W2482033662","https://openalex.org/W2515755543","https://openalex.org/W2519091744","https://openalex.org/W2566785804","https://openalex.org/W2585227925","https://openalex.org/W2585824449","https://openalex.org/W2603597171","https://openalex.org/W2746109435","https://openalex.org/W2746648261","https://openalex.org/W2765833400","https://openalex.org/W2768153200","https://openalex.org/W2770785043","https://openalex.org/W2888796252","https://openalex.org/W2888815552","https://openalex.org/W2888917702","https://openalex.org/W2889853672","https://openalex.org/W2897318954","https://openalex.org/W2955236751","https://openalex.org/W2963300588","https://openalex.org/W2972959620","https://openalex.org/W2978506536","https://openalex.org/W3013952251"],"related_works":["https://openalex.org/W3095801312","https://openalex.org/W2949893096","https://openalex.org/W3094025065","https://openalex.org/W3097264669","https://openalex.org/W2086949317","https://openalex.org/W2973085046","https://openalex.org/W2482033662","https://openalex.org/W3197273793","https://openalex.org/W2417163358","https://openalex.org/W1498609987","https://openalex.org/W2599218332","https://openalex.org/W3176280627","https://openalex.org/W2127832144","https://openalex.org/W115937626","https://openalex.org/W2048831533","https://openalex.org/W2534037053","https://openalex.org/W2145482206","https://openalex.org/W2131663003","https://openalex.org/W1837137761","https://openalex.org/W2542848502"],"abstract_inverted_index":{"For":[0],"articulatory-to-acoustic":[1,38,130],"mapping":[2,131],"using":[3],"deep":[4],"neural":[5,44,63,135],"networks,":[6],"typically":[7],"spectral":[8,82],"and":[9,27,54,161],"excitation":[10,169],"parameters":[11],"of":[12,52,60,94,150],"vocoders":[13],"have":[14],"been":[15],"used":[16,87],"as":[17],"the":[18,61,73,85,92,95,106,129,133,144,148,158,168],"training":[19,70],"targets.":[20],"However,":[21],"vocoding":[22],"often":[23],"results":[24,77,100,125],"in":[25,33,78,101,157],"buzzy":[26],"muffled":[28],"final":[29],"speech":[30,56,142],"quality.":[31],"Therefore,":[32],"this":[34],"paper":[35],"on":[36,48],"ultrasound-based":[37],"conversion,":[39],"we":[40],"use":[41,117],"a":[42,49,79,111],"flow-based":[43],"vocoder":[45,113,136],"(WaveGlow)":[46],"pre-trained":[47],"large":[50],"amount":[51],"English":[53],"Hungarian":[55],"data.":[57],"The":[58,69,124],"inputs":[59],"convolutional":[62],"network":[64],"are":[65],"ultrasound":[66],"tongue":[67],"images.":[68],"target":[71],"is":[72,152,155,163],"80-dimensional":[74],"mel-spectrogram,":[75],"which":[76,114],"finer":[80],"detailed":[81],"representation":[83],"than":[84,143],"previously":[86],"25-dimensional":[88],"Mel-Generalized":[89],"Cepstrum.":[90],"From":[91],"output":[93],"ultrasound-to-mel-spectrogram":[96],"prediction,":[97],"WaveGlow":[98,134,151],"inference":[99],"synthesized":[102,141],"speech.":[103],"We":[104],"compare":[105],"proposed":[107],"WaveGlow-based":[108],"system":[109],"with":[110],"continuous":[112],"does":[115],"not":[116,164],"strict":[118],"voiced/unvoiced":[119],"decision":[120],"when":[121],"predicting":[122],"F0.":[123],"demonstrate":[126],"that":[127,153],"during":[128],"experiments,":[132],"produces":[137],"significantly":[138],"more":[139],"natural":[140],"baseline":[145],"system.":[146],"Besides,":[147],"advantage":[149],"F0":[154],"included":[156],"mel-spectrogram":[159],"representation,":[160],"it":[162],"necessary":[165],"to":[166],"predict":[167],"separately.":[170]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2022-07-26T00:00:00"}