{"id":"https://openalex.org/W4417400095","doi":"https://doi.org/10.7554/elife.109400.1","title":"High-Fidelity Neural Speech Reconstruction through an Efficient Acoustic-Linguistic Dual-Pathway Framework","display_name":"High-Fidelity Neural Speech Reconstruction through an Efficient Acoustic-Linguistic Dual-Pathway Framework","publication_year":2025,"publication_date":"2025-12-16","ids":{"openalex":"https://openalex.org/W4417400095","doi":"https://doi.org/10.7554/elife.109400.1"},"language":"en","primary_location":{"id":"doi:10.7554/elife.109400.1","doi":"https://doi.org/10.7554/elife.109400.1","is_oa":true,"landing_page_url":"https://doi.org/10.7554/elife.109400.1","pdf_url":"https://elifesciences.org/reviewed-preprints/109400v1.pdf","source":{"id":"https://openalex.org/S1336409049","display_name":"eLife","issn_l":"2050-084X","issn":["2050-084X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","jufo-2","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311710","host_organization_name":"eLife Sciences Publications Ltd","host_organization_lineage":["https://openalex.org/P4310311710"],"host_organization_lineage_names":["eLife Sciences Publications Ltd"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"eLife","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://elifesciences.org/reviewed-preprints/109400v1.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108050442","display_name":"Jiawei Li","orcid":"https://orcid.org/0000-0003-3873-8003","observed_orcids":["https://orcid.org/0000-0003-3873-8003","https://orcid.org/0000-0002-4018-0830"]},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Li","raw_affiliation_strings":["School of Biomedical Engineering, ShanghaiTech University","State Key Laboratory of Advanced Medical Materials and Devices, ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biomedical Engineering, ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"State Key Laboratory of Advanced Medical Materials and Devices, ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031372474","display_name":"Chunxu Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunxu Guo","raw_affiliation_strings":["School of Biomedical Engineering, ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biomedical Engineering, ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460206","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-7730-5131","observed_orcids":["https://orcid.org/0000-0002-7730-5131"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University","Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091099837","display_name":"Edward F. Chang","orcid":"https://orcid.org/0000-0003-2480-4700","observed_orcids":["https://orcid.org/0000-0003-2480-4700"]},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward F Chang","raw_affiliation_strings":["Department of Neurological Surgery, University of California, San Francisco"],"raw_orcid":"https://orcid.org/0000-0003-2480-4700","affiliations":[{"raw_affiliation_string":"Department of Neurological Surgery, University of California, San Francisco","institution_ids":["https://openalex.org/I180670191"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101397818","display_name":"Yuanning Li","orcid":"https://orcid.org/0000-0003-3277-0600","observed_orcids":["https://orcid.org/0000-0003-3277-0600"]},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanning Li","raw_affiliation_strings":["Lingang Laboratory","School of Biomedical Engineering, ShanghaiTech University","Shanghai Artificial Intelligence Laboratory","Shanghai Clinical Research and Trial Center","State Key Laboratory of Advanced Medical Materials and Devices, ShanghaiTech University"],"raw_orcid":"https://orcid.org/0000-0003-3277-0600","affiliations":[{"raw_affiliation_string":"Lingang Laboratory","institution_ids":[]},{"raw_affiliation_string":"School of Biomedical Engineering, ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai Clinical Research and Trial Center","institution_ids":[]},{"raw_affiliation_string":"State Key Laboratory of Advanced Medical Materials and Devices, ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3000,"currency":"USD","value_usd":2500},"apc_paid":{"value":3000,"currency":"USD","value_usd":2500},"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9624000191688538,"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":0.9624000191688538,"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":0.026799999177455902,"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/T10863","display_name":"Voice and Speech Disorders","score":0.0026000000070780516,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology (medical)"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/electrocorticography","display_name":"electrocorticography","score":0.9049999713897705},{"id":"https://openalex.org/keywords/brain-computer-interface","display_name":"brain-computer interface","score":0.9129999876022339},{"id":"https://openalex.org/keywords/voice-cloning","display_name":"voice cloning","score":0.5899999737739563},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.6840000152587891},{"id":"https://openalex.org/keywords/hifi-gan","display_name":"HiFi-GAN","score":0.8429999947547913},{"id":"https://openalex.org/keywords/lstm-decoder","display_name":"LSTM decoder","score":0.6499999761581421},{"id":"https://openalex.org/keywords/speech-intelligibility","display_name":"speech intelligibility","score":0.7639999985694885},{"id":"https://openalex.org/keywords/prosody","display_name":"prosody","score":0.4009999930858612},{"id":"https://openalex.org/keywords/speech-coding","display_name":"speech coding","score":0.5440000295639038}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7243000268936157},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7146999835968018},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4456000030040741},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4397999942302704},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3889000117778778},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3398999869823456},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2757999897003174},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.2653000056743622},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7554/elife.109400.1","doi":"https://doi.org/10.7554/elife.109400.1","is_oa":true,"landing_page_url":"https://doi.org/10.7554/elife.109400.1","pdf_url":"https://elifesciences.org/reviewed-preprints/109400v1.pdf","source":{"id":"https://openalex.org/S1336409049","display_name":"eLife","issn_l":"2050-084X","issn":["2050-084X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","jufo-2","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311710","host_organization_name":"eLife Sciences Publications Ltd","host_organization_lineage":["https://openalex.org/P4310311710"],"host_organization_lineage_names":["eLife Sciences Publications Ltd"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"eLife","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.7554/elife.109400.1","doi":"https://doi.org/10.7554/elife.109400.1","is_oa":true,"landing_page_url":"https://doi.org/10.7554/elife.109400.1","pdf_url":"https://elifesciences.org/reviewed-preprints/109400v1.pdf","source":{"id":"https://openalex.org/S1336409049","display_name":"eLife","issn_l":"2050-084X","issn":["2050-084X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","jufo-2","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311710","host_organization_name":"eLife Sciences Publications Ltd","host_organization_lineage":["https://openalex.org/P4310311710"],"host_organization_lineage_names":["eLife Sciences Publications Ltd"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"eLife","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1595344975","display_name":null,"funder_award_id":"22PJ1410500","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G3093801524","display_name":null,"funder_award_id":"32371154","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4684966088","display_name":null,"funder_award_id":"24QA2705500","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320327675","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786"},{"id":"https://openalex.org/F4320327803","display_name":"Shanghai Rising-Star Program","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417400095.pdf","grobid_xml":"https://content.openalex.org/works/W4417400095.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1965248225","https://openalex.org/W2005066437","https://openalex.org/W2079207700","https://openalex.org/W2110015077","https://openalex.org/W2344975321","https://openalex.org/W2913144232","https://openalex.org/W2940585064","https://openalex.org/W3169320628","https://openalex.org/W3193706553","https://openalex.org/W3205578964","https://openalex.org/W3210923133","https://openalex.org/W4220949944","https://openalex.org/W4367609927","https://openalex.org/W4385834631","https://openalex.org/W4386091044","https://openalex.org/W4386100600","https://openalex.org/W4387378260","https://openalex.org/W4388034436","https://openalex.org/W4391591803","https://openalex.org/W4392303387","https://openalex.org/W4394577281","https://openalex.org/W4395661358","https://openalex.org/W4396547417","https://openalex.org/W4396905256","https://openalex.org/W4403963746","https://openalex.org/W4405433404","https://openalex.org/W4406018375","https://openalex.org/W4406026111","https://openalex.org/W4406449927","https://openalex.org/W4408684073","https://openalex.org/W4411240941","https://openalex.org/W7117471448"],"related_works":["https://openalex.org/W4405673928","https://openalex.org/W7167251978","https://openalex.org/W7150390616","https://openalex.org/W4394577281","https://openalex.org/W7163066310","https://openalex.org/W4388674325","https://openalex.org/W2913144232","https://openalex.org/W4401827074","https://openalex.org/W7167455010","https://openalex.org/W4416964706"],"abstract_inverted_index":{"Reconstructing":[0],"speech":[1,9,111,129],"from":[2,130],"neural":[3],"recordings":[4],"is":[5],"crucial":[6],"for":[7,25,78],"understanding":[8],"coding":[10],"and":[11,43,56,74,92,127],"developing":[12],"brain-computer":[13],"interfaces":[14],"(BCIs).":[15],"However,":[16],"existing":[17],"methods":[18],"trade":[19],"off":[20],"acoustic":[21,42,47,91],"richness":[22],"(pitch,":[23],"prosody)":[24],"linguistic":[26,44,68,93],"intelligibility":[27],"(words,":[28],"phonemes).":[29],"To":[30],"overcome":[31],"this":[32],"limitation,":[33],"we":[34],"propose":[35],"a":[36,50,57,71],"dual-path":[37,123],"framework":[38,124],"to":[39,63,88],"concurrently":[40],"decode":[41],"representations.":[45],"The":[46,67],"pathway":[48,69],"uses":[49],"long-short":[51],"term":[52],"memory":[53],"(LSTM)":[54],"decoder":[55],"high-fidelity":[58],"generative":[59],"adversarial":[60],"network":[61],"(HiFi-GAN)":[62],"reconstruct":[64],"spectrotemporal":[65],"features.":[66],"employs":[70],"transformer":[72],"adaptor":[73],"text-to-speech":[75],"(TTS)":[76],"generator":[77],"word":[79,117],"tokens.":[80],"These":[81],"two":[82],"pathways":[83],"merge":[84],"via":[85],"voice":[86],"cloning":[87],"combine":[89],"both":[90],"validity.":[94],"Using":[95],"only":[96],"20":[97],"minutes":[98],"of":[99],"electrocorticography":[100],"(ECoG)":[101],"data":[102],"per":[103],"subject,":[104],"our":[105],"approach":[106],"achieves":[107],"highly":[108],"intelligible":[109,128],"synthesized":[110],"(mean":[112],"opinion":[113],"score":[114],"=":[115,120],"4.0/5.0,":[116],"error":[118],"rate":[119],"18.9%).":[121],"Our":[122],"reconstructs":[125],"natural":[126],"ECoG,":[131],"resolving":[132],"the":[133],"acoustic-linguistic":[134],"trade-off.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-12-16T00:00:00"}