{"id":"https://openalex.org/W4406461329","doi":"https://doi.org/10.1109/slt61566.2024.10832172","title":"Neurospex: Neuro-Guided Speaker Extraction With Cross-Modal Fusion","display_name":"Neurospex: Neuro-Guided Speaker Extraction With Cross-Modal Fusion","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461329","doi":"https://doi.org/10.1109/slt61566.2024.10832172"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5071260574","display_name":"Dashanka De Silva","orcid":"https://orcid.org/0000-0003-2209-9390"},"institutions":[{"id":"https://openalex.org/I180437899","display_name":"University of Bremen","ror":"https://ror.org/04ers2y35","country_code":"DE","type":"education","lineage":["https://openalex.org/I180437899"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Dashanka De Silva","raw_affiliation_strings":["University of Bremen,Machine Listening Lab (MLL),Germany"],"affiliations":[{"raw_affiliation_string":"University of Bremen,Machine Listening Lab (MLL),Germany","institution_ids":["https://openalex.org/I180437899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088380372","display_name":"Siqi Cai","orcid":"https://orcid.org/0000-0003-3282-9246"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Siqi Cai","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082298285","display_name":"Saurav Pahuja","orcid":"https://orcid.org/0000-0003-1170-5199"},"institutions":[{"id":"https://openalex.org/I180437899","display_name":"University of Bremen","ror":"https://ror.org/04ers2y35","country_code":"DE","type":"education","lineage":["https://openalex.org/I180437899"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Saurav Pahuja","raw_affiliation_strings":["University of Bremen,Machine Listening Lab (MLL),Germany"],"affiliations":[{"raw_affiliation_string":"University of Bremen,Machine Listening Lab (MLL),Germany","institution_ids":["https://openalex.org/I180437899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058049725","display_name":"Tanja Schultz","orcid":"https://orcid.org/0000-0002-9809-7028"},"institutions":[{"id":"https://openalex.org/I180437899","display_name":"University of Bremen","ror":"https://ror.org/04ers2y35","country_code":"DE","type":"education","lineage":["https://openalex.org/I180437899"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tanja Schultz","raw_affiliation_strings":["University of Bremen,Cognitive Systems Lab (CSL),Germany"],"affiliations":[{"raw_affiliation_string":"University of Bremen,Cognitive Systems Lab (CSL),Germany","institution_ids":["https://openalex.org/I180437899"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["The Chinese University of Hong Kong,SDS SRIBD,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,SDS SRIBD,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5071260574"],"corresponding_institution_ids":["https://openalex.org/I180437899"],"apc_list":null,"apc_paid":null,"fwci":0.7501,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73214477,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"341","last_page":"348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.6971806287765503},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6412960290908813},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5259314179420471},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.507860004901886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4375803470611572},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.41052964329719543},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09269040822982788}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6971806287765503},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6412960290908813},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5259314179420471},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.507860004901886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4375803470611572},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.41052964329719543},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09269040822982788},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320331102","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1991139021","https://openalex.org/W2066652080","https://openalex.org/W2067295501","https://openalex.org/W2082183045","https://openalex.org/W2138164020","https://openalex.org/W2158904676","https://openalex.org/W2408166852","https://openalex.org/W2531409750","https://openalex.org/W2559463885","https://openalex.org/W2594607416","https://openalex.org/W2734774145","https://openalex.org/W2742722178","https://openalex.org/W2952218014","https://openalex.org/W2964058413","https://openalex.org/W2972568703","https://openalex.org/W3015199127","https://openalex.org/W3016361963","https://openalex.org/W3057611960","https://openalex.org/W3099330747","https://openalex.org/W3102455230","https://openalex.org/W3103434036","https://openalex.org/W3126966983","https://openalex.org/W3161550781","https://openalex.org/W3190915878","https://openalex.org/W4226208605","https://openalex.org/W4226338831","https://openalex.org/W4289665794","https://openalex.org/W4372347386","https://openalex.org/W4385245566","https://openalex.org/W4385822730","https://openalex.org/W4388963755","https://openalex.org/W4389382699","https://openalex.org/W4392903132","https://openalex.org/W4392903215","https://openalex.org/W4402592606","https://openalex.org/W6858667472"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2099421762","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2530546662","https://openalex.org/W2377297411","https://openalex.org/W2967030268"],"abstract_inverted_index":{"In":[0,53],"the":[1,33,42,45,66,70,73,95,107],"study":[2],"of":[3,44,69],"auditory":[4],"attention,":[5],"it":[6,28],"has":[7],"been":[8],"revealed":[9],"that":[10,93,124],"there":[11],"exists":[12],"a":[13,49,58,88,101,112,119],"robust":[14],"correlation":[15],"between":[16],"attended":[17,80],"speech":[18,81,84,108],"and":[19],"elicited":[20],"neural":[21],"responses,":[22],"measurable":[23],"through":[24],"electroencephalography":[25],"(EEG).":[26],"Therefore,":[27],"is":[29],"possible":[30],"to":[31,40,78,105],"use":[32],"attention":[34,96],"information":[35],"available":[36,121],"within":[37],"EEG":[38,67,90],"signals":[39],"guide":[41],"extraction":[43,61,114],"target":[46],"speaker":[47,60,113],"in":[48],"cocktail":[50],"party":[51],"computationally.":[52],"this":[54],"paper,":[55],"we":[56,99],"present":[57],"neuro-guided":[59],"model,":[62],"i.e.":[63],"NeuroSpex,":[64],"using":[65],"response":[68],"listener":[71],"as":[72],"sole":[74],"auxiliary":[75],"reference":[76],"cue":[77],"extract":[79],"from":[82],"monaural":[83],"mixtures.":[85],"We":[86],"propose":[87,100],"novel":[89],"signal":[91],"encoder":[92],"captures":[94],"information.":[97],"Additionally,":[98],"cross-attention":[102],"(CA)":[103],"mechanism":[104],"enhance":[106],"feature":[109],"representations,":[110],"generating":[111],"mask.":[115],"Experimental":[116],"results":[117],"on":[118],"publicly":[120],"dataset":[122],"demonstrate":[123],"our":[125],"proposed":[126],"model":[127],"outperforms":[128],"two":[129],"baseline":[130],"models":[131],"across":[132],"various":[133],"evaluation":[134],"metrics.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}