{"id":"https://openalex.org/W4406858409","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848628","title":"Target Speaker Extraction Method by Emphasizing the Active Speech with an Additional Enhancer","display_name":"Target Speaker Extraction Method by Emphasizing the Active Speech with an Additional Enhancer","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858409","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848628"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5064549045","display_name":"Xue Yang","orcid":"https://orcid.org/0000-0001-5846-5319"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xue Yang","raw_affiliation_strings":["Beijing University of Technology,Institute of Speech and Audio Information Processing, School of Information Science and Technology,Beijing,China,100124"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Institute of Speech and Audio Information Processing, School of Information Science and Technology,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070475244","display_name":"Changchun Bao","orcid":"https://orcid.org/0000-0002-5606-5343"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changchun Bao","raw_affiliation_strings":["Beijing University of Technology,Institute of Speech and Audio Information Processing, School of Information Science and Technology,Beijing,China,100124"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Institute of Speech and Audio Information Processing, School of Information Science and Technology,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437166","display_name":"Xu Zhang","orcid":"https://orcid.org/0000-0001-7320-4360"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Zhang","raw_affiliation_strings":["Beijing University of Technology,Institute of Speech and Audio Information Processing, School of Information Science and Technology,Beijing,China,100124"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Institute of Speech and Audio Information Processing, School of Information Science and Technology,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059065171","display_name":"Xianhong Chen","orcid":"https://orcid.org/0000-0002-5001-0587"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianhong Chen","raw_affiliation_strings":["Beijing University of Technology,Institute of Speech and Audio Information Processing, School of Information Science and Technology,Beijing,China,100124"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Institute of Speech and Audio Information Processing, School of Information Science and Technology,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064549045"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71022527,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9366999864578247,"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":0.9366999864578247,"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/computer-science","display_name":"Computer science","score":0.6747350692749023},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6222699284553528},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5151092410087585},{"id":"https://openalex.org/keywords/enhancer","display_name":"Enhancer","score":0.47677093744277954},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33657461404800415},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06646773219108582}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6747350692749023},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6222699284553528},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5151092410087585},{"id":"https://openalex.org/C111936080","wikidata":"https://www.wikidata.org/wiki/Q913367","display_name":"Enhancer","level":4,"score":0.47677093744277954},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33657461404800415},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06646773219108582},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10848628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321793","display_name":"Beijing Municipal Education Commission","ror":"https://ror.org/04bpn6s66"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2891833136","https://openalex.org/W2938646939","https://openalex.org/W2939771864","https://openalex.org/W2962866211","https://openalex.org/W2964058413","https://openalex.org/W2972541922","https://openalex.org/W2973062255","https://openalex.org/W3008003372","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3015636705","https://openalex.org/W3015915076","https://openalex.org/W3016361963","https://openalex.org/W3096893582","https://openalex.org/W3097653961","https://openalex.org/W3120336970","https://openalex.org/W3160464260","https://openalex.org/W3162534564","https://openalex.org/W3196570692","https://openalex.org/W3198234746","https://openalex.org/W4232747912","https://openalex.org/W4367597591","https://openalex.org/W4372260086","https://openalex.org/W4372271325","https://openalex.org/W4385756463","https://openalex.org/W4385807442","https://openalex.org/W4385822827","https://openalex.org/W4388342027","https://openalex.org/W4391021760","https://openalex.org/W4392902910","https://openalex.org/W4392902992","https://openalex.org/W4393157278","https://openalex.org/W4400105722","https://openalex.org/W6631190155"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2113330652","https://openalex.org/W2061914098","https://openalex.org/W4393004084","https://openalex.org/W2118646732","https://openalex.org/W4387565139","https://openalex.org/W4389440207","https://openalex.org/W4378781551"],"abstract_inverted_index":{"Target":[0],"speaker":[1],"extraction":[2],"(TSE)":[3],"is":[4,75,118,217],"a":[5,14,138],"practical":[6],"solution":[7],"to":[8,33,57,98,123,153,200],"the":[9,24,27,35,39,42,46,50,58,63,73,84,87,96,101,108,130,150,155,159,167,178,181,189,193,206,213,224,229],"cocktail":[10],"party":[11],"problem.":[12],"Recently,":[13],"novel":[15],"embedding-free":[16],"TSE":[17],"method":[18,234],"was":[19],"proposed.":[20],"In":[21,41,164],"this":[22,113,121,134,165],"method,":[23],"enrollment":[25,74,97,160,182,194],"and":[26,53,80,141,161,169,177,183,195,216],"mixed":[28,59,162,196],"signal":[29,197],"are":[30,172,198],"directly":[31],"interacted":[32,76],"exploit":[34],"contextual":[36],"information":[37],"within":[38],"enrollment.":[40],"absence":[43],"of":[44,65,137,158,192,231],"noise,":[45,66],"derived":[47],"guidance":[48,103,127,222],"exhibits":[49],"onset,":[51],"offset":[52],"voice":[54],"activity":[55],"similar":[56],"signal.":[60,163],"However,":[61],"in":[62,83,120,174,205,235],"presence":[64],"such":[67],"similarity":[68,179],"may":[69,104],"be":[70,105,186],"destroyed":[71],"since":[72],"with":[77],"both":[78],"speech":[79,168,215],"noise":[81,88,170,184],"signals":[82,171],"mixture.":[85],"If":[86],"(e.g.,":[89],"babble":[90],"noise)":[91],"contains":[92],"components":[93],"that":[94,128],"resemble":[95],"some":[99],"extent,":[100],"misleading":[102],"generated":[106],"after":[107],"direct":[109],"interaction.":[110],"To":[111],"tackle":[112],"issue,":[114],"an":[115,125,142,202,220],"additional":[116],"enhancer":[117,135],"designed":[119],"paper":[122],"derive":[124,201],"auxiliary":[126,221],"emphasizes":[129,212],"active":[131,214],"speech.":[132],"Specifically,":[133],"consists":[136],"processing":[139,146],"block":[140,147],"interaction":[143,207],"block.":[144,208],"The":[145],"mainly":[148],"utilizes":[149],"recurrent":[151],"layers":[152],"model":[154],"temporal":[156],"dynamics":[157],"block,":[166],"modeled":[173],"different":[175],"manners":[176],"between":[180],"can":[185],"reduced.":[187],"Afterwards,":[188],"processed":[190],"representations":[191],"utilized":[199],"enhanced":[203,210],"representation":[204,211],"This":[209],"employed":[218],"as":[219],"for":[223],"extraction.":[225],"Experimental":[226],"results":[227],"demonstrate":[228],"effectiveness":[230],"our":[232],"proposed":[233],"complex":[236],"acoustic":[237],"environments.":[238]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}