{"id":"https://openalex.org/W4388821343","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317106","title":"Target Speaker Extraction with Attention Enhancement and Gated Fusion Mechanism","display_name":"Target Speaker Extraction with Attention Enhancement and Gated Fusion Mechanism","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388821343","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317106"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5100712619","display_name":"Sijie Wang","orcid":"https://orcid.org/0000-0002-2912-0773"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wang Sijie","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,Urumqi,China","School of Information Science and Engineering, Xinjiang University, Urumqi, China","Key Laboratory of Signal Detection and Processing, Urumqi, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Key Laboratory of Signal Detection and Processing, Urumqi, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075133420","display_name":"Askar Hamdulla","orcid":"https://orcid.org/0000-0002-2321-308X"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Askar Hamdulla","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,Urumqi,China","Key Laboratory of Signal Detection and Processing, Urumqi, China","School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Key Laboratory of Signal Detection and Processing, Urumqi, China","institution_ids":[]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023562009","display_name":"Mijit Ablimit","orcid":"https://orcid.org/0009-0008-0781-4150"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mijit Ablimit","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,Urumqi,China","Key Laboratory of Signal Detection and Processing, Urumqi, China","School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Key Laboratory of Signal Detection and Processing, Urumqi, China","institution_ids":[]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100712619"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":0.3491,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66680617,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1995","last_page":"2001"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech 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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.7332191467285156},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6082379817962646},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5530727505683899},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.541360080242157},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.5183102488517761},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5177758932113647},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.506548285484314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4384308457374573},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3264574408531189},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10477638244628906},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07645052671432495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7332191467285156},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6082379817962646},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5530727505683899},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.541360080242157},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.5183102488517761},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5177758932113647},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.506548285484314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4384308457374573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3264574408531189},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10477638244628906},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07645052671432495},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":30,"referenced_works":["https://openalex.org/W2046056978","https://openalex.org/W2116261113","https://openalex.org/W2150769028","https://openalex.org/W2170864449","https://openalex.org/W2890964092","https://openalex.org/W2924115626","https://openalex.org/W2939771864","https://openalex.org/W2950635152","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2973062255","https://openalex.org/W3012065388","https://openalex.org/W3015636705","https://openalex.org/W3016361963","https://openalex.org/W3097353642","https://openalex.org/W3097653961","https://openalex.org/W3099330747","https://openalex.org/W3103434036","https://openalex.org/W3148386121","https://openalex.org/W4205462621","https://openalex.org/W4224918929","https://openalex.org/W4283320926","https://openalex.org/W4297798711","https://openalex.org/W4297798768","https://openalex.org/W4301581299","https://openalex.org/W4310745277","https://openalex.org/W4312878242","https://openalex.org/W4372259900","https://openalex.org/W4381327724","https://openalex.org/W6731370813"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W4221148444","https://openalex.org/W4387678054","https://openalex.org/W2389596151","https://openalex.org/W3095575180","https://openalex.org/W4306784355","https://openalex.org/W2169308097","https://openalex.org/W4246226292","https://openalex.org/W3091984855","https://openalex.org/W2150768546"],"abstract_inverted_index":{"The":[0,67],"objective":[1],"of":[2,13,20,29,32,43,82,156,173,186],"a":[3,18,26],"target":[4,15,34,55],"speaker":[5,16,94,117],"extraction":[6],"system":[7,46],"is":[8,102,182],"to":[9,72,109,184],"extract":[10],"the":[11,14,33,41,44,49,54,58,64,80,87,107,112,131,135,141,145,154,166,171,174,178,188],"speech":[12],"from":[17,124],"mixture":[19,98],"multiple":[21],"speakers":[22],"and":[23,57,84,86,96,126,134,144],"noises":[24],"using":[25,187],"certain":[27],"amount":[28],"additional":[30],"information":[31,114],"speaker.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39],"investigate":[40],"improvements":[42],"baseline":[45,73],"by":[47,104,116],"incorporating":[48],"light-weight":[50,136],"CBAM":[51,68,132],"module":[52,61,133,138,147,176,190],"in":[53,63,79],"extractor,":[56],"gated":[59],"fusion":[60,65,90],"(GFM)":[62],"layer.":[66],"introduces":[69],"attention":[70],"enhancement":[71],"model":[74,108,142],"with":[75],"no":[76],"significant":[77],"increase":[78],"number":[81],"parameters":[83],"complexity,":[85],"previous":[88],"concatenation-based":[89],"method":[91],"used":[92],"for":[93],"embedding":[95],"input":[97],"(or":[99],"intermediate":[100],"output)":[101],"replaced":[103],"GFM,":[105],"enabling":[106],"better":[110,149],"leverage":[111],"supplementary":[113],"provided":[115],"embedding.":[118],"Experimental":[119],"results":[120],"on":[121,151,165,177],"datasets":[122],"built":[123],"WSJ0-2mix":[125],"WHAM!":[127,181],"demonstrate":[128],"that":[129,185],"both":[130],"GFM":[137,146,189],"individually":[139],"improve":[140],"performance,":[143],"shows":[148],"improvement":[150],"WHAM!.":[152],"However,":[153],"combination":[155],"these":[157],"two":[158],"modules":[159],"only":[160],"exhibits":[161],"mutually":[162],"beneficial":[163],"effects":[164],"clean":[167],"dataset":[168,180],"WSJ0-2mix,":[169],"while":[170],"performance":[172],"combined":[175],"noisy":[179],"inferior":[183],"alone.":[191]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}