{"id":"https://openalex.org/W4372342291","doi":"https://doi.org/10.1109/icassp49357.2023.10097004","title":"Synthesizing Speech from ECoG with a Combination of Transformer-Based Encoder and Neural Vocoder","display_name":"Synthesizing Speech from ECoG with a Combination of Transformer-Based Encoder and Neural Vocoder","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372342291","doi":"https://doi.org/10.1109/icassp49357.2023.10097004"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5072330344","display_name":"Kai Shigemi","orcid":null},"institutions":[{"id":"https://openalex.org/I92614990","display_name":"Tokyo University of Agriculture and Technology","ror":"https://ror.org/00qg0kr10","country_code":"JP","type":"education","lineage":["https://openalex.org/I92614990"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kai Shigemi","raw_affiliation_strings":["Tokyo University of Agriculture and Technology,Graduate School of Engineering","Graduate School of Engineering, Tokyo University of Agriculture and Technology"],"affiliations":[{"raw_affiliation_string":"Tokyo University of Agriculture and Technology,Graduate School of Engineering","institution_ids":["https://openalex.org/I92614990"]},{"raw_affiliation_string":"Graduate School of Engineering, Tokyo University of Agriculture and Technology","institution_ids":["https://openalex.org/I92614990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053101464","display_name":"Shuji Komeiji","orcid":null},"institutions":[{"id":"https://openalex.org/I92614990","display_name":"Tokyo University of Agriculture and Technology","ror":"https://ror.org/00qg0kr10","country_code":"JP","type":"education","lineage":["https://openalex.org/I92614990"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shuji Komeiji","raw_affiliation_strings":["Tokyo University of Agriculture and Technology,Graduate School of Engineering","Graduate School of Engineering, Tokyo University of Agriculture and Technology"],"affiliations":[{"raw_affiliation_string":"Tokyo University of Agriculture and Technology,Graduate School of Engineering","institution_ids":["https://openalex.org/I92614990"]},{"raw_affiliation_string":"Graduate School of Engineering, Tokyo University of Agriculture and Technology","institution_ids":["https://openalex.org/I92614990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016286392","display_name":"Takumi Mitsuhashi","orcid":"https://orcid.org/0000-0001-8156-5385"},"institutions":[{"id":"https://openalex.org/I34077901","display_name":"Juntendo University","ror":"https://ror.org/01692sz90","country_code":"JP","type":"education","lineage":["https://openalex.org/I34077901"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takumi Mitsuhashi","raw_affiliation_strings":["Juntendo University School of Medicine,Department of Neurosurgery","Department of Neurosurgery, Juntendo University School of Medicine"],"affiliations":[{"raw_affiliation_string":"Juntendo University School of Medicine,Department of Neurosurgery","institution_ids":["https://openalex.org/I34077901"]},{"raw_affiliation_string":"Department of Neurosurgery, Juntendo University School of Medicine","institution_ids":["https://openalex.org/I34077901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006736245","display_name":"Yasushi Iimura","orcid":"https://orcid.org/0000-0003-4263-5920"},"institutions":[{"id":"https://openalex.org/I34077901","display_name":"Juntendo University","ror":"https://ror.org/01692sz90","country_code":"JP","type":"education","lineage":["https://openalex.org/I34077901"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasushi Iimura","raw_affiliation_strings":["Juntendo University School of Medicine,Department of Neurosurgery","Department of Neurosurgery, Juntendo University School of Medicine"],"affiliations":[{"raw_affiliation_string":"Juntendo University School of Medicine,Department of Neurosurgery","institution_ids":["https://openalex.org/I34077901"]},{"raw_affiliation_string":"Department of Neurosurgery, Juntendo University School of Medicine","institution_ids":["https://openalex.org/I34077901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052263544","display_name":"Hiroharu Suzuki","orcid":"https://orcid.org/0000-0002-9244-8472"},"institutions":[{"id":"https://openalex.org/I34077901","display_name":"Juntendo University","ror":"https://ror.org/01692sz90","country_code":"JP","type":"education","lineage":["https://openalex.org/I34077901"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroharu Suzuki","raw_affiliation_strings":["Juntendo University School of Medicine,Department of Neurosurgery","Department of Neurosurgery, Juntendo University School of Medicine"],"affiliations":[{"raw_affiliation_string":"Juntendo University School of Medicine,Department of Neurosurgery","institution_ids":["https://openalex.org/I34077901"]},{"raw_affiliation_string":"Department of Neurosurgery, Juntendo University School of Medicine","institution_ids":["https://openalex.org/I34077901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045644147","display_name":"Hidenori Sugano","orcid":"https://orcid.org/0000-0002-7836-6585"},"institutions":[{"id":"https://openalex.org/I34077901","display_name":"Juntendo University","ror":"https://ror.org/01692sz90","country_code":"JP","type":"education","lineage":["https://openalex.org/I34077901"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hidenori Sugano","raw_affiliation_strings":["Juntendo University School of Medicine,Department of Neurosurgery","Department of Neurosurgery, Juntendo University School of Medicine"],"affiliations":[{"raw_affiliation_string":"Juntendo University School of Medicine,Department of Neurosurgery","institution_ids":["https://openalex.org/I34077901"]},{"raw_affiliation_string":"Department of Neurosurgery, Juntendo University School of Medicine","institution_ids":["https://openalex.org/I34077901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081629487","display_name":"Koichi Shinoda","orcid":"https://orcid.org/0000-0003-1095-3203"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichi Shinoda","raw_affiliation_strings":["Tokyo Institute of Technology,Department of Computer Science","Department of Computer Science, Tokyo Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology,Department of Computer Science","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034837951","display_name":"Kohei Yatabe","orcid":"https://orcid.org/0000-0002-1345-0663"},"institutions":[{"id":"https://openalex.org/I92614990","display_name":"Tokyo University of Agriculture and Technology","ror":"https://ror.org/00qg0kr10","country_code":"JP","type":"education","lineage":["https://openalex.org/I92614990"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kohei Yatabe","raw_affiliation_strings":["Tokyo University of Agriculture and Technology,Graduate School of Engineering","Graduate School of Engineering, Tokyo University of Agriculture and Technology"],"affiliations":[{"raw_affiliation_string":"Tokyo University of Agriculture and Technology,Graduate School of Engineering","institution_ids":["https://openalex.org/I92614990"]},{"raw_affiliation_string":"Graduate School of Engineering, Tokyo University of Agriculture and Technology","institution_ids":["https://openalex.org/I92614990"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101802085","display_name":"Toshihisa Tanaka","orcid":"https://orcid.org/0000-0002-5056-9508"},"institutions":[{"id":"https://openalex.org/I92614990","display_name":"Tokyo University of Agriculture and Technology","ror":"https://ror.org/00qg0kr10","country_code":"JP","type":"education","lineage":["https://openalex.org/I92614990"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshihisa Tanaka","raw_affiliation_strings":["Tokyo University of Agriculture and Technology,Graduate School of Engineering","Graduate School of Engineering, Tokyo University of Agriculture and Technology"],"affiliations":[{"raw_affiliation_string":"Tokyo University of Agriculture and Technology,Graduate School of Engineering","institution_ids":["https://openalex.org/I92614990"]},{"raw_affiliation_string":"Graduate School of Engineering, Tokyo University of Agriculture and Technology","institution_ids":["https://openalex.org/I92614990"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5072330344"],"corresponding_institution_ids":["https://openalex.org/I92614990"],"apc_list":null,"apc_paid":null,"fwci":2.6248,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.89799184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"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":1.0,"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":1.0,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9926999807357788,"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":0.7682516574859619},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7680702209472656},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7284243106842041},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6254045963287354},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5927499532699585},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5777524709701538},{"id":"https://openalex.org/keywords/wilcoxon-signed-rank-test","display_name":"Wilcoxon signed-rank test","score":0.5433794260025024},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4613838791847229},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44299063086509705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43216705322265625},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.42574185132980347},{"id":"https://openalex.org/keywords/pearson-product-moment-correlation-coefficient","display_name":"Pearson product-moment correlation coefficient","score":0.41506507992744446},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11735287308692932},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0908815860748291}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7682516574859619},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7680702209472656},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7284243106842041},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6254045963287354},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5927499532699585},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5777524709701538},{"id":"https://openalex.org/C206041023","wikidata":"https://www.wikidata.org/wiki/Q1751970","display_name":"Wilcoxon signed-rank test","level":3,"score":0.5433794260025024},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4613838791847229},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44299063086509705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43216705322265625},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.42574185132980347},{"id":"https://openalex.org/C55078378","wikidata":"https://www.wikidata.org/wiki/Q1136628","display_name":"Pearson product-moment correlation coefficient","level":2,"score":0.41506507992744446},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11735287308692932},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0908815860748291},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C12868164","wikidata":"https://www.wikidata.org/wiki/Q1424533","display_name":"Mann\u2013Whitney U test","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50708308","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100921103","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1488659701","https://openalex.org/W2010495159","https://openalex.org/W2079735306","https://openalex.org/W2106006415","https://openalex.org/W2120847449","https://openalex.org/W2138672527","https://openalex.org/W2157331557","https://openalex.org/W2160783467","https://openalex.org/W2481854178","https://openalex.org/W2519091744","https://openalex.org/W2896457183","https://openalex.org/W2940585064","https://openalex.org/W2952609044","https://openalex.org/W2963300588","https://openalex.org/W2963446712","https://openalex.org/W2964982538","https://openalex.org/W2981857663","https://openalex.org/W2991284028","https://openalex.org/W3013691153","https://openalex.org/W3015338123","https://openalex.org/W3198923947","https://openalex.org/W4220904310","https://openalex.org/W4224926216","https://openalex.org/W4311759904","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6810531390"],"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":{"This":[0],"paper":[1],"reports":[2],"on":[3],"a":[4,26,57,64],"novel":[5],"invasive":[6,18],"brain\u2013computer":[7],"interface":[8],"(BCI)":[9],"paradigm":[10],"that":[11,86],"has":[12],"successfully":[13],"reconstructed":[14],"spoken":[15,54],"sentences":[16,55],"from":[17],"electrocorticogram":[19],"(ECoG)":[20],"signals":[21,33],"using":[22,56],"deep-neural-network-based":[23],"encoders":[24],"and":[25,107],"pre-trained":[27],"neural":[28],"vocoder.":[29],"We":[30],"recorded":[31],"ECoG":[32,46],"while":[34],"13":[35],"participants":[36],"were":[37,70],"speaking":[38],"short":[39],"sentences.":[40],"Our":[41],"BCI":[42],"could":[43],"map":[44],"the":[45,49,53,82,87,98],"recording":[47],"to":[48,75],"log-mel":[50,68],"spectrograms":[51,69],"of":[52,81,102],"bidirectional":[58],"long":[59],"short-term":[60],"memory":[61],"(BLSTM)":[62],"or":[63],"Transformer.":[65],"The":[66],"estimated":[67],"used":[71],"in":[72,100],"Parallel":[73],"WaveGAN":[74],"synthesize":[76],"speech":[77],"waveforms.":[78],"An":[79],"evaluation":[80],"model":[83,89],"performance":[84],"revealed":[85],"Transformer":[88],"significantly":[90],"outperformed":[91],"(Wilcoxon":[92],"signed-rank":[93],"test,":[94],"p":[95],"<":[96],"0.001)":[97],"BLSTM":[99],"terms":[101],"mean":[103],"square":[104],"error":[105],"loss":[106],"Pearson":[108],"correlation.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
