{"id":"https://openalex.org/W4392902910","doi":"https://doi.org/10.1109/icassp48485.2024.10447529","title":"Target Speaker Extraction by Directly Exploiting Contextual Information in the Time-Frequency Domain","display_name":"Target Speaker Extraction by Directly Exploiting Contextual Information in the Time-Frequency Domain","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902910","doi":"https://doi.org/10.1109/icassp48485.2024.10447529"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100585683","display_name":"Xue Yang","orcid":"https://orcid.org/0000-0002-4146-9177"},"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, Faculty of Information Technology,Beijing,China,100124"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Institute of Speech and Audio Information Processing, Faculty of Information 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, Faculty of Information Technology,Beijing,China,100124"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Institute of Speech and Audio Information Processing, Faculty of Information Technology,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101955372","display_name":"Jing Zhou","orcid":"https://orcid.org/0000-0002-4193-637X"},"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":"Jing Zhou","raw_affiliation_strings":["Beijing University of Technology,Institute of Speech and Audio Information Processing, Faculty of Information Technology,Beijing,China,100124"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Institute of Speech and Audio Information Processing, Faculty of Information 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, Faculty of Information Technology,Beijing,China,100124"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Institute of Speech and Audio Information Processing, Faculty of Information 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/A5100585683"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":5.4449,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.96476448,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10476","last_page":"10480"},"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9997000098228455,"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/weighting","display_name":"Weighting","score":0.8322561979293823},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7603747844696045},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7388542294502258},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6927302479743958},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6387659311294556},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5310362577438354},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5249031782150269},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4796595871448517},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44553685188293457},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.44477224349975586},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.44236406683921814},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.418448805809021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4026111364364624},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33781319856643677},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13397088646888733}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.8322561979293823},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7603747844696045},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7388542294502258},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6927302479743958},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6387659311294556},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5310362577438354},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5249031782150269},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4796595871448517},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44553685188293457},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.44477224349975586},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.44236406683921814},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.418448805809021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4026111364364624},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33781319856643677},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13397088646888733},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1712271690","display_name":null,"funder_award_id":"6183101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3862795372","display_name":null,"funder_award_id":"62006010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3909335432","display_name":null,"funder_award_id":"61831019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7033253288","display_name":null,"funder_award_id":"Grants","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":32,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2891833136","https://openalex.org/W2924115626","https://openalex.org/W2938646939","https://openalex.org/W2939771864","https://openalex.org/W2951130829","https://openalex.org/W2962866211","https://openalex.org/W2964058413","https://openalex.org/W2972541922","https://openalex.org/W2973062255","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3015623828","https://openalex.org/W3015915076","https://openalex.org/W3016361963","https://openalex.org/W3096893582","https://openalex.org/W3097653961","https://openalex.org/W3103434036","https://openalex.org/W3120336970","https://openalex.org/W3160464260","https://openalex.org/W3162534564","https://openalex.org/W3196570692","https://openalex.org/W3198234746","https://openalex.org/W4224936432","https://openalex.org/W4232747912","https://openalex.org/W4372260086","https://openalex.org/W4372271325","https://openalex.org/W4385822827","https://openalex.org/W4385822829","https://openalex.org/W6631190155"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"In":[0,42],"target":[1,19],"speaker":[2,9,20,29],"extraction,":[3],"many":[4],"studies":[5],"rely":[6],"on":[7,128],"the":[8,18,24,35,40,52,57,61,64,71,82,88,97,102,110,117,121,125,129,137],"embedding":[10,30],"which":[11],"is":[12],"obtained":[13],"from":[14],"an":[15,75],"enrollment":[16,62],"of":[17,60,87,101,116],"and":[21,63,91,132],"employed":[22,94],"as":[23,109],"guidance.":[25],"However,":[26],"solely":[27],"using":[28],"may":[31],"not":[32],"fully":[33],"utilize":[34],"contextual":[36,49,118],"information":[37,50],"contained":[38],"in":[39,51,136],"enrollment.":[41,103],"this":[43,48],"paper,":[44],"we":[45],"directly":[46],"exploit":[47],"time-frequency":[53],"(T-F)":[54],"domain.":[55],"Specifically,":[56],"T-F":[58,89,99],"representations":[59,90,100,106],"mixed":[65],"signal":[66],"are":[67,92,107],"interacted":[68],"to":[69,95],"compute":[70],"weighting":[72,79],"matrices":[73,80],"through":[74],"attention":[76],"mechanism.":[77],"These":[78,104],"reflect":[81],"similarity":[83],"among":[84],"different":[85],"frames":[86],"further":[93],"obtain":[96],"consistent":[98,105],"served":[108],"guidance,":[111],"allowing":[112],"for":[113],"better":[114],"exploitation":[115],"information.":[119],"Furthermore,":[120],"proposed":[122],"method":[123],"achieves":[124],"state-of-the-art":[126],"performance":[127],"benchmark":[130],"dataset":[131],"shows":[133],"its":[134],"effectiveness":[135],"complex":[138],"scenarios.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}