{"id":"https://openalex.org/W3157356148","doi":"https://doi.org/10.23919/eusipco54536.2021.9616153","title":"Reconstructing Speech from Real-Time Articulatory MRI Using Neural Vocoders","display_name":"Reconstructing Speech from Real-Time Articulatory MRI Using Neural Vocoders","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3157356148","doi":"https://doi.org/10.23919/eusipco54536.2021.9616153","mag":"3157356148"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616153","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616153","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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/A5053839372","display_name":"Yide Yu","orcid":"https://orcid.org/0000-0002-5549-2925"},"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":true,"raw_author_name":"Yide Yu","raw_affiliation_strings":["Institute of Informatics, University of Szeged, Szeged, Hungary"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics, University of Szeged, Szeged, Hungary","institution_ids":["https://openalex.org/I227486990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026493983","display_name":"Amin Honarmandi Shandiz","orcid":"https://orcid.org/0000-0002-8561-7629"},"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":"Amin Honarmandi Shandiz","raw_affiliation_strings":["Institute of Informatics, University of Szeged, Szeged, Hungary"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics, University of Szeged, Szeged, Hungary","institution_ids":["https://openalex.org/I227486990"]}]},{"author_position":"last","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":"Laszlo Toth","raw_affiliation_strings":["Institute of Informatics, University of Szeged, Szeged, Hungary"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics, University of Szeged, Szeged, Hungary","institution_ids":["https://openalex.org/I227486990"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053839372"],"corresponding_institution_ids":["https://openalex.org/I227486990"],"apc_list":null,"apc_paid":null,"fwci":1.7204,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.90799194,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"945","last_page":"949"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9976000189781189,"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":0.8081527948379517},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.7065982818603516},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6856635808944702},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5989629030227661},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5414692163467407},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4836362600326538},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.44304922223091125},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4349654018878937},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42044389247894287},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4152890145778656},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.36264467239379883},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.09612751007080078},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.08844727277755737}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8081527948379517},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.7065982818603516},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6856635808944702},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5989629030227661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5414692163467407},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4836362600326538},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.44304922223091125},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4349654018878937},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42044389247894287},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4152890145778656},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.36264467239379883},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.09612751007080078},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.08844727277755737},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616153","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616153","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1499800345","https://openalex.org/W1663785051","https://openalex.org/W2008120082","https://openalex.org/W2039640471","https://openalex.org/W2064675550","https://openalex.org/W2066381494","https://openalex.org/W2107860279","https://openalex.org/W2109272898","https://openalex.org/W2141998673","https://openalex.org/W2143929858","https://openalex.org/W2150448558","https://openalex.org/W2294901616","https://openalex.org/W2322064186","https://openalex.org/W2394855416","https://openalex.org/W2395719637","https://openalex.org/W2509285937","https://openalex.org/W2515755543","https://openalex.org/W2554625447","https://openalex.org/W2603597171","https://openalex.org/W2623570296","https://openalex.org/W2746109435","https://openalex.org/W2765833400","https://openalex.org/W2769402512","https://openalex.org/W2769531941","https://openalex.org/W2801248077","https://openalex.org/W2803054199","https://openalex.org/W2884768626","https://openalex.org/W2888815552","https://openalex.org/W2889007195","https://openalex.org/W2892110446","https://openalex.org/W2892356933","https://openalex.org/W2924343001","https://openalex.org/W2963155035","https://openalex.org/W2963300588","https://openalex.org/W2964058413","https://openalex.org/W2970006822","https://openalex.org/W2971417062","https://openalex.org/W2972882294","https://openalex.org/W3046440749","https://openalex.org/W3094463005","https://openalex.org/W3095801312","https://openalex.org/W3096158177","https://openalex.org/W3097071316","https://openalex.org/W3098606562","https://openalex.org/W6745378982","https://openalex.org/W6767111847"],"related_works":["https://openalex.org/W3016109656","https://openalex.org/W2342810974","https://openalex.org/W2058482658","https://openalex.org/W2513767140","https://openalex.org/W1973895194","https://openalex.org/W3135613579","https://openalex.org/W4388016426","https://openalex.org/W1980687383","https://openalex.org/W4386746628","https://openalex.org/W2037635165"],"abstract_inverted_index":{"Several":[0],"approaches":[1],"exist":[2],"for":[3,109],"the":[4,31,34,42,49,59,62,92,96,102,110,122,137,148,176,187],"recording":[5,43,69],"of":[6,44,48,61,75,104,127,159],"articulatory":[7],"movements,":[8],"such":[9],"as":[10],"eletromagnetic":[11],"and":[12,19,116,163],"permanent":[13],"magnetic":[14,23],"articulagraphy,":[15],"ultrasound":[16],"tongue":[17],"imaging":[18,25],"surface":[20],"electromyography.":[21],"Although":[22],"resonance":[24],"(MRI)":[26],"is":[27],"more":[28,181],"costly":[29],"than":[30],"above":[32],"approaches,":[33],"recent":[35],"developments":[36],"in":[37],"this":[38],"area":[39],"now":[40],"allow":[41],"real-time":[45,67],"MRI":[46,68],"videos":[47],"articulators":[50],"with":[51,58],"an":[52],"acceptable":[53],"resolution.":[54],"Here,":[55],"we":[56,90,130],"experiment":[57],"reconstruction":[60],"speech":[63,77,93,138,144],"signal":[64,94],"from":[65,88],"a":[66,85],"using":[70,95,141],"deep":[71,106],"neural":[72,98,107,119],"networks.":[73],"Instead":[74],"estimating":[76],"directly,":[78],"our":[79,128,133,171],"networks":[80],"are":[81,183],"trained":[82],"to":[83,185],"output":[84],"spectral":[86,178,189],"vector,":[87],"which":[89],"reconstruct":[91,175],"WaveGlow":[97],"vocoder.":[99],"We":[100],"compare":[101],"performance":[103],"three":[105],"architectures":[108],"estimation":[111],"task,":[112],"combining":[113],"convolutional":[114],"(CNN)":[115],"recurrence-based":[117],"(LSTM)":[118],"layers.":[120],"Besides":[121],"mean":[123,149],"absolute":[124],"error":[125],"(MAE)":[126],"networks,":[129],"also":[131],"evaluate":[132],"models":[134],"by":[135],"comparing":[136],"signals":[139],"obtained":[140],"several":[142],"objective":[143],"quality":[145],"metrics":[146],"like":[147],"cepstral":[150],"distortion":[151],"(MCD),":[152],"Short-Time":[153],"Objective":[154],"Intelligibility":[155],"(STOI),":[156],"Perceptual":[157],"Evaluation":[158],"Speech":[160],"Quality":[161],"(PESQ)":[162],"Signal-to-Distortion":[164],"Ratio":[165],"(SDR).":[166],"The":[167],"results":[168],"indicate":[169],"that":[170],"approach":[172],"can":[173],"successfully":[174],"gross":[177],"shape,":[179],"but":[180],"improvements":[182],"needed":[184],"reproduce":[186],"fine":[188],"details.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}