{"id":"https://openalex.org/W4412888735","doi":"https://doi.org/10.18653/v1/2025.findings-acl.142","title":"BrainECHO: Semantic Brain Signal Decoding through Vector-Quantized Spectrogram Reconstruction for Whisper-Enhanced Text Generation","display_name":"BrainECHO: Semantic Brain Signal Decoding through Vector-Quantized Spectrogram Reconstruction for Whisper-Enhanced Text Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888735","doi":"https://doi.org/10.18653/v1/2025.findings-acl.142"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.142","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.142","pdf_url":"https://aclanthology.org/2025.findings-acl.142.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.142.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100624845","display_name":"Jilong Li","orcid":"https://orcid.org/0000-0002-0004-8464"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jilong Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045795037","display_name":"Zhenxi Song","orcid":"https://orcid.org/0000-0001-8574-0857"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenxi Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365399","display_name":"Jiaqi Wang","orcid":"https://orcid.org/0009-0009-1913-5195"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaqi Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004953265","display_name":"Meishan Zhang","orcid":"https://orcid.org/0000-0001-6335-1340"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meishan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085867312","display_name":"Honghai Liu","orcid":"https://orcid.org/0000-0002-2880-4698"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Honghai Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402986","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0003-2219-8030"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100363345","display_name":"Zhiguo Zhang","orcid":"https://orcid.org/0000-0001-7992-7965"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiguo Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"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":"2762","last_page":"2778"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.8960000276565552,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.8960000276565552,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8083899021148682},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7987205386161804},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6642953157424927},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.546189546585083},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5202952027320862},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4818533658981323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43872132897377014},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3226214647293091},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06371334195137024}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8083899021148682},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7987205386161804},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6642953157424927},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.546189546585083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5202952027320862},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4818533658981323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43872132897377014},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3226214647293091},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06371334195137024}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.142","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.142","pdf_url":"https://aclanthology.org/2025.findings-acl.142.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.142","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.142","pdf_url":"https://aclanthology.org/2025.findings-acl.142.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3134777354","display_name":null,"funder_award_id":"2023SHIBS0003","funder_id":"https://openalex.org/F4320330381","funder_display_name":"Shenzhen-Hong Kong Institute of Brain Science"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320330381","display_name":"Shenzhen-Hong Kong Institute of Brain Science","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888735.pdf","grobid_xml":"https://content.openalex.org/works/W4412888735.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2368824897","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W1508050556","https://openalex.org/W1910862367","https://openalex.org/W2379365082","https://openalex.org/W2370747590","https://openalex.org/W2030109976","https://openalex.org/W2369260257","https://openalex.org/W2389120450"],"abstract_inverted_index":{"Current":[0],"EEG/MEG-to-text":[1],"decoding":[2,51,135,155],"systems":[3],"suffer":[4],"from":[5],"three":[6,81],"key":[7],"limitations:":[8],"(1)":[9,83],"reliance":[10,160],"on":[11,72,161],"teacher-forcing":[12],"methods,":[13],"which":[14,86,137],"compromises":[15],"robustness":[16,165],"during":[17],"inference,":[18],"(2)":[19],"sensitivity":[20],"to":[21,38,68,110],"session-specific":[22,122],"noise,":[23],"hindering":[24],"generalization":[25],"across":[26,166],"subjects,":[27],"and":[28,34,75,152,169,176],"(3)":[29],"misalignment":[30],"between":[31],"brain":[32,105],"signals":[33],"linguistic":[35],"representations":[36,98],"due":[37],"pre-trained":[39],"language":[40],"model":[41,142],"overdominance.To":[42],"overcome":[43],"these":[44],"challenges,":[45],"we":[46],"propose":[47],"BrainECHO":[48,78],"(Brain":[49],"signal":[50,106,147],"via":[52],"vEctor-quantized":[53],"speCtrogram":[54],"reconstruction":[55],"for":[56,99,143,180],"WHisper-enhanced":[57],"text":[58],"generatiOn),":[59],"a":[60,92,116,128],"multi-stage":[61],"framework":[62],"that":[63],"employs":[64],"decoupled":[65],"representation":[66],"learning":[67],"achieve":[69],"state-ofthe-art":[70],"performance":[71],"both":[73],"EEG":[74],"MEG":[76],"datasets.Specifically,":[77],"consists":[79],"of":[80,95],"stages:":[82],"Discrete":[84],"autoencoding,":[85],"transforms":[87],"continuous":[88],"Mel":[89,112],"spectrograms":[90],"into":[91],"finite":[93],"set":[94],"high-quality":[96],"discrete":[97],"subsequent":[100],"stages.(2)":[101],"Frozen":[102],"alignment,":[103],"where":[104],"embeddings":[107,114],"are":[108],"mapped":[109],"corresponding":[111],"spectrogram":[113],"in":[115,131],"frozen":[117],"latent":[118],"space,":[119],"effectively":[120],"filtering":[121],"noise":[123,174],"through":[124],"vectorquantized":[125],"reconstruction,":[126],"yielding":[127],"3.65%":[129],"improvement":[130],"BLEU-4":[132],"score.(3)":[133],"Constrained":[134],"fine-tuning,":[136],"leverages":[138],"the":[139],"pretrained":[140],"Whisper":[141],"audio-to-text":[144],"translation,":[145],"balancing":[146],"adaptation":[148],"with":[149],"knowledge":[150],"preservation,":[151],"achieving":[153],"74%-89%":[154],"BLEU":[156],"scores":[157],"without":[158],"excessive":[159],"teacher":[162],"forcing.BrainECHO":[163],"demonstrates":[164],"sentence,":[167],"session,":[168],"subject-independent":[170],"conditions,":[171],"passing":[172],"Gaussian":[173],"tests":[175],"showcasing":[177],"its":[178],"potential":[179],"enhancing":[181],"language-based":[182],"brain-computer":[183],"interfaces.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}