{"id":"https://openalex.org/W4388674325","doi":"https://doi.org/10.1109/bhi58575.2023.10313388","title":"BrainTalker: Low-Resource Brain-to-Speech Synthesis with Transfer Learning using Wav2Vec 2.0","display_name":"BrainTalker: Low-Resource Brain-to-Speech Synthesis with Transfer Learning using Wav2Vec 2.0","publication_year":2023,"publication_date":"2023-10-15","ids":{"openalex":"https://openalex.org/W4388674325","doi":"https://doi.org/10.1109/bhi58575.2023.10313388"},"language":"en","primary_location":{"id":"doi:10.1109/bhi58575.2023.10313388","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bhi58575.2023.10313388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI)","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/A5066878875","display_name":"Miseul Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Miseul Kim","raw_affiliation_strings":["Yonsei University,Digital Signal Processing &#x0026; Artificial Intelligence Lab, School of Electrical and Electronic Engineering,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,Digital Signal Processing &#x0026; Artificial Intelligence Lab, School of Electrical and Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010663694","display_name":"Zhenyu Piao","orcid":"https://orcid.org/0009-0008-1801-4343"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Zhenyu Piao","raw_affiliation_strings":["Yonsei University,Digital Signal Processing &#x0026; Artificial Intelligence Lab, School of Electrical and Electronic Engineering,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,Digital Signal Processing &#x0026; Artificial Intelligence Lab, School of Electrical and Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413513","display_name":"Ji\u2010Hyun Lee","orcid":"https://orcid.org/0000-0002-9864-5485"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jihyun Lee","raw_affiliation_strings":["Yonsei University,Digital Signal Processing &#x0026; Artificial Intelligence Lab, School of Electrical and Electronic Engineering,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,Digital Signal Processing &#x0026; Artificial Intelligence Lab, School of Electrical and Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["Yonsei University,Digital Signal Processing &#x0026; Artificial Intelligence Lab, School of Electrical and Electronic Engineering,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,Digital Signal Processing &#x0026; Artificial Intelligence Lab, School of Electrical and Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5066878875"],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":0.3616,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59309476,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.998199999332428,"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/T10860","display_name":"Speech and Audio Processing","score":0.9973999857902527,"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":0.7851184606552124},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6810600757598877},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6434032320976257},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5418773889541626},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.522188127040863},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4971614181995392},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47008800506591797},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4690720736980438},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.46340298652648926},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4631570875644684},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3649762272834778}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7851184606552124},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6810600757598877},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6434032320976257},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5418773889541626},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.522188127040863},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4971614181995392},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47008800506591797},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4690720736980438},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.46340298652648926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4631570875644684},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3649762272834778},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bhi58575.2023.10313388","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bhi58575.2023.10313388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"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":32,"referenced_works":["https://openalex.org/W1488659701","https://openalex.org/W1522301498","https://openalex.org/W1584066751","https://openalex.org/W1973275441","https://openalex.org/W1975163393","https://openalex.org/W2025758384","https://openalex.org/W2049081072","https://openalex.org/W2107860279","https://openalex.org/W2109023847","https://openalex.org/W2194775991","https://openalex.org/W2255466643","https://openalex.org/W2519091744","https://openalex.org/W2922697111","https://openalex.org/W2940585064","https://openalex.org/W2941560734","https://openalex.org/W2952609044","https://openalex.org/W2963446712","https://openalex.org/W3015338123","https://openalex.org/W3082991148","https://openalex.org/W3094253649","https://openalex.org/W3109832790","https://openalex.org/W3177342940","https://openalex.org/W4212774754","https://openalex.org/W4236173595","https://openalex.org/W4372342291","https://openalex.org/W4375868978","https://openalex.org/W4382239589","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6772381481","https://openalex.org/W6780218876","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2016904525"],"abstract_inverted_index":{"Decoding":[0],"spoken":[1,95,138],"speech":[2,96,162],"from":[3,97],"neural":[4,77,158],"activity":[5,40],"in":[6,173],"the":[7,52,70,136],"brain":[8,39],"is":[9,33,72],"a":[10,34,76,106,111,157,181],"fast-emerging":[11],"research":[12],"topic,":[13],"as":[14],"it":[15],"could":[16],"enable":[17],"communication":[18],"for":[19,37,57],"people":[20],"who":[21],"have":[22],"difficulties":[23],"with":[24,41],"producing":[25],"audible":[26],"speech.":[27,139],"For":[28],"this":[29,64,84],"task,":[30],"electrocorticography":[31],"(ECoG)":[32],"common":[35],"method":[36],"recording":[38],"high":[42,46],"temporal":[43],"resolution":[44],"and":[45,69,150,177,189,198],"spatial":[47],"precision.":[48],"However,":[49],"due":[50],"to":[51,74,123,127,160],"risky":[53],"surgical":[54],"procedure":[55],"required":[56],"obtaining":[58],"ECoG":[59,98,125],"recordings,":[60],"relatively":[61],"little":[62],"of":[63,135,175,185],"data":[65],"has":[66],"been":[67],"collected,":[68],"amount":[71],"insufficient":[73],"train":[75,119],"network-based":[78],"Brain-to-Speech":[79],"(BTS)":[80],"system.":[81],"To":[82],"address":[83],"problem,":[85],"we":[86,118],"propose":[87],"BrainTalker\u2014a":[88],"novel":[89],"BTS":[90],"framework":[91,169],"that":[92,130],"generates":[93],"intelligible":[94],"signals":[99,126],"under":[100],"extremely":[101],"low-resource":[102],"scenarios.":[103],"We":[104,193],"apply":[105],"transfer":[107],"learning":[108],"approach":[109],"utilizing":[110],"pre-trained":[112],"self-supervised":[113],"model,":[114],"Wav2Vec":[115,132],"2.0.":[116],"Specifically,":[117],"an":[120],"encoder":[121],"module":[122],"map":[124],"latent":[128],"embeddings":[129,141],"match":[131],"2.0":[133],"representations":[134],"corresponding":[137],"These":[140],"are":[142,154],"then":[143],"transformed":[144],"into":[145,156],"mel-spectrograms":[146],"using":[147],"stacked":[148],"convolutional":[149],"transformer-based":[151],"layers,":[152],"which":[153],"fed":[155],"vocoder":[159],"synthesize":[161],"waveform.":[163],"Experimental":[164],"results":[165],"demonstrate":[166],"our":[167],"proposed":[168],"achieves":[170],"outstanding":[171],"performance":[172],"terms":[174],"subjective":[176],"objective":[178],"metrics,":[179],"including":[180],"Pearson":[182],"correlation":[183],"coefficient":[184],"0.9":[186],"between":[187],"generated":[188],"ground":[190],"truth":[191],"mel-spectrograms.":[192],"share":[194],"publicly":[195],"available":[196],"Demos":[197],"Code":[199],"<sup":[200],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[201],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[202],".":[203]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}