{"id":"https://openalex.org/W4392909766","doi":"https://doi.org/10.1109/icassp48485.2024.10446614","title":"Neural2speech: A Transfer Learning Framework for Neural-Driven Speech Reconstruction","display_name":"Neural2speech: A Transfer Learning Framework for Neural-Driven Speech Reconstruction","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909766","doi":"https://doi.org/10.1109/icassp48485.2024.10446614"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5108050442","display_name":"Jiawei Li","orcid":"https://orcid.org/0000-0003-3873-8003"},"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":true,"raw_author_name":"Jiawei Li","raw_affiliation_strings":["ShanghaiTech University,School of Biomedical Engineering,Shanghai,China","School of Biomedical Engineering, ShanghaiTech University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,School of Biomedical Engineering,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"School of Biomedical Engineering, ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031372474","display_name":"Chunxu Guo","orcid":null},"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":["ShanghaiTech University,School of Biomedical Engineering,Shanghai,China","School of Biomedical Engineering, ShanghaiTech University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,School of Biomedical Engineering,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"School of Biomedical Engineering, ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101865288","display_name":"Li Fu","orcid":"https://orcid.org/0000-0002-7533-692X"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Fu","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371061","display_name":"Lu Fan","orcid":"https://orcid.org/0009-0002-9253-0019"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Fan","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091099837","display_name":"Edward F. Chang","orcid":"https://orcid.org/0000-0003-2480-4700"},"institutions":[{"id":"https://openalex.org/I4210157890","display_name":"Neurological Surgery","ror":"https://ror.org/04r0gp612","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210157890"]},{"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":["University of California,Department of Neurological Surgery,San Francisco,CA,USA","Department of Neurological Surgery, University of California, San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California,Department of Neurological Surgery,San Francisco,CA,USA","institution_ids":["https://openalex.org/I4210157890"]},{"raw_affiliation_string":"Department of Neurological Surgery, University of California, San Francisco, CA, USA","institution_ids":["https://openalex.org/I4210157890","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"},"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":"Yuanning Li","raw_affiliation_strings":["ShanghaiTech University,School of Biomedical Engineering,Shanghai,China","School of Biomedical Engineering, ShanghaiTech University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,School of Biomedical Engineering,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"School of Biomedical Engineering, ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5108050442"],"corresponding_institution_ids":["https://openalex.org/I30809798"],"apc_list":null,"apc_paid":null,"fwci":1.1002,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79665862,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2200","last_page":"2204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9959999918937683,"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":0.9959999918937683,"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":0.9907000064849854,"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/T11309","display_name":"Music and Audio Processing","score":0.9574000239372253,"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":0.754950761795044},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6270931959152222},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4561847746372223},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42564651370048523}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.754950761795044},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6270931959152222},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4561847746372223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42564651370048523}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1635512741","https://openalex.org/W2005066437","https://openalex.org/W2010495159","https://openalex.org/W2074086085","https://openalex.org/W2106006415","https://openalex.org/W2151544568","https://openalex.org/W2516001803","https://openalex.org/W2913144232","https://openalex.org/W2951670472","https://openalex.org/W2997091249","https://openalex.org/W3013691153","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3179826751","https://openalex.org/W3180220247","https://openalex.org/W4224926216","https://openalex.org/W4385834631","https://openalex.org/W4386100600","https://openalex.org/W4388034436","https://openalex.org/W6631190155","https://openalex.org/W6780218876","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3123837699"],"abstract_inverted_index":{"Reconstructing":[0],"natural":[1],"speech":[2,25,52,66,86,99,106,110,115,135,148,167],"from":[3,53,112],"neural":[4,22,29,36,55,70,126,131],"activity":[5,132],"is":[6,40,101,121],"vital":[7],"for":[8,84,137],"enabling":[9],"direct":[10],"communication":[11],"via":[12],"brain-computer":[13],"interfaces.":[14],"Previous":[15],"efforts":[16],"have":[17],"explored":[18],"the":[19,63,69,113,124,130,134,144],"conversion":[20],"of":[21,65,92,146,155,166],"recordings":[23,56,127],"into":[24],"using":[26],"complex":[27],"deep":[28],"network":[30],"(DNN)":[31],"models":[32],"trained":[33,122],"on":[34,103,123],"extensive":[35],"recording":[37],"data,":[38,157],"which":[39,90,158],"resource-intensive":[41],"under":[42],"regular":[43],"clinical":[44],"constraints.":[45,72],"However,":[46],"achieving":[47],"satisfactory":[48],"performance":[49],"in":[50,164],"reconstructing":[51],"limited-scale":[54],"has":[57],"been":[58],"challenging,":[59],"mainly":[60],"due":[61],"to":[62,108,128],"complexity":[64],"representations":[67],"and":[68,133,169],"data":[71],"To":[73],"overcome":[74],"these":[75],"challenges,":[76],"we":[77],"propose":[78],"a":[79,98,118],"novel":[80],"transfer":[81],"learning":[82],"framework":[83],"neural-driven":[85,147],"reconstruction,":[87],"called":[88],"Neural2Speech,":[89],"consists":[91],"two":[93],"distinct":[94],"training":[95],"phases.":[96],"First,":[97],"autoencoder":[100],"pre-trained":[102],"readily":[104],"available":[105],"corpora":[107],"decode":[109],"waveforms":[111],"encoded":[114],"representations.":[116],"Second,":[117],"lightweight":[119],"adaptor":[120],"small-scale":[125],"align":[129],"representation":[136],"decoding.":[138],"Remarkably,":[139],"our":[140],"proposed":[141],"Neural2Speech":[142],"demonstrates":[143],"feasibility":[145],"reconstruction":[149],"even":[150],"with":[151],"only":[152],"20":[153],"minutes":[154],"intracranial":[156],"significantly":[159],"outperforms":[160],"existing":[161],"baseline":[162],"methods":[163],"terms":[165],"fidelity":[168],"intelligibility.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}