{"id":"https://openalex.org/W4402112612","doi":"https://doi.org/10.21437/interspeech.2024-223","title":"Toward Fully-End-to-End Listened Speech Decoding from EEG Signals","display_name":"Toward Fully-End-to-End Listened Speech Decoding from EEG Signals","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112612","doi":"https://doi.org/10.21437/interspeech.2024-223"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-223","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-223","pdf_url":"https://www.isca-archive.org/interspeech_2024/lee24c_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2024/lee24c_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100674127","display_name":"Jihwan Lee","orcid":"https://orcid.org/0000-0001-9380-5470"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jihwan Lee","raw_affiliation_strings":["University of Southern California , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California , USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023844174","display_name":"Aditya Kommineni","orcid":"https://orcid.org/0009-0002-0056-8336"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditya Kommineni","raw_affiliation_strings":["University of Southern California , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California , USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059679122","display_name":"Tiantian Feng","orcid":"https://orcid.org/0000-0002-2053-9068"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tiantian Feng","raw_affiliation_strings":["University of Southern California , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California , USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048302987","display_name":"Kleanthis Avramidis","orcid":"https://orcid.org/0000-0003-0308-795X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kleanthis Avramidis","raw_affiliation_strings":["University of Southern California , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California , USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101907238","display_name":"Xuan Shi","orcid":"https://orcid.org/0000-0002-1387-5418"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuan Shi","raw_affiliation_strings":["University of Southern California , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California , USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080870546","display_name":"Sudarsana Reddy Kadiri","orcid":"https://orcid.org/0000-0001-5806-3053"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sudarsana Reddy Kadiri","raw_affiliation_strings":["University of Southern California , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California , USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104114055","display_name":"Shrikanth Narayanan","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["University of Southern California , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California , USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1500","last_page":"1504"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9185000061988831,"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":0.9185000061988831,"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/decoding-methods","display_name":"Decoding methods","score":0.7322555780410767},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.651110053062439},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6379057765007019},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6267156004905701},{"id":"https://openalex.org/keywords/electroencephalography","display_name":"Electroencephalography","score":0.6146707534790039},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2402927279472351},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20638251304626465},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.17876219749450684},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.09915661811828613}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7322555780410767},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.651110053062439},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6379057765007019},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6267156004905701},{"id":"https://openalex.org/C522805319","wikidata":"https://www.wikidata.org/wiki/Q179965","display_name":"Electroencephalography","level":2,"score":0.6146707534790039},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2402927279472351},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20638251304626465},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.17876219749450684},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.09915661811828613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-223","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-223","pdf_url":"https://www.isca-archive.org/interspeech_2024/lee24c_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2024-223","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-223","pdf_url":"https://www.isca-archive.org/interspeech_2024/lee24c_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4495726782","display_name":null,"funder_award_id":"N660012324006","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332236","display_name":"Annenberg School for Communication and Journalism, University of Southern California","ror":"https://ror.org/03taz7m60"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402112612.pdf","grobid_xml":"https://content.openalex.org/works/W4402112612.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W2922348724","https://openalex.org/W200322357","https://openalex.org/W2390279801","https://openalex.org/W2130428257","https://openalex.org/W4308951944","https://openalex.org/W2358668433","https://openalex.org/W4396701345"],"abstract_inverted_index":{"Speech":[0,28],"decoding":[1],"from":[2,30,83],"EEG":[3,31,42,58,68,74,97],"signals":[4],"is":[5,12,51,102,121,132],"a":[6,23,61,66],"challenging":[7],"task,":[8],"where":[9,44],"brain":[10],"activity":[11],"modeled":[13],"to":[14,35,71,88,123],"estimate":[15],"salient":[16],"characteristics":[17,126],"of":[18,56,92,96,127],"acoustic":[19,47],"stimuli.We":[20],"propose":[21],"FESDE,":[22],"novel":[24],"framework":[25,101],"for":[26],"Fully-End-to-end":[27],"Decoding":[29],"signals.Our":[32],"approach":[33],"aims":[34],"directly":[36],"reconstruct":[37],"listened":[38],"speech":[39,62,78,81,128],"waveforms":[40,82],"given":[41],"signals,":[43,75],"no":[45],"intermediate":[46],"feature":[48],"processing":[49],"step":[50],"required.The":[52],"proposed":[53,100],"method":[54],"consists":[55],"an":[57],"module":[59,63,69,79],"and":[60,98,105,111],"along":[64],"with":[65],"connector.The":[67],"learns":[70,87],"better":[72],"represent":[73],"while":[76],"the":[77,90,93],"generates":[80],"model":[84,125],"representations.The":[85],"connector":[86],"bridge":[89],"distributions":[91],"latent":[94],"spaces":[95],"speech.The":[99],"both":[103],"simple":[104],"efficient,":[106],"by":[107],"allowing":[108],"single-step":[109],"inference,":[110],"outperforms":[112],"prior":[113],"works":[114],"on":[115],"objective":[116],"metrics.A":[117],"fine-grained":[118],"phoneme":[119],"analysis":[120],"conducted":[122],"unveil":[124],"decoding.The":[129],"source":[130],"code":[131],"available":[133],"here:":[134],"github.com/":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
