{"id":"https://openalex.org/W4392904673","doi":"https://doi.org/10.1109/icassp48485.2024.10447755","title":"Hierarchical Speaker Representation for Target Speaker Extraction","display_name":"Hierarchical Speaker Representation for Target Speaker Extraction","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904673","doi":"https://doi.org/10.1109/icassp48485.2024.10447755"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447755","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/A5103195569","display_name":"Shulin He","orcid":"https://orcid.org/0009-0002-0382-3515"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shulin He","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,China","Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000417495","display_name":"Huaiwen Zhang","orcid":"https://orcid.org/0000-0002-3183-9218"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaiwen Zhang","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,China","College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072851763","display_name":"Wei Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Rao","raw_affiliation_strings":["Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022778367","display_name":"Kanghao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kanghao Zhang","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,China","College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015448985","display_name":"Yukai Ju","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yukai Ju","raw_affiliation_strings":["Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397772","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0003-2690-7180"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,China","College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100693230","display_name":"Xueliang Zhang","orcid":"https://orcid.org/0000-0002-0406-1105"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueliang Zhang","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,China","College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1383,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.88454085,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10361","last_page":"10365"},"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.7910169363021851},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6948487162590027},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6396712064743042},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5951632857322693},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5932098031044006},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5409935116767883},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.516539990901947},{"id":"https://openalex.org/keywords/isolation","display_name":"Isolation (microbiology)","score":0.44772839546203613},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4294242262840271},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4203197956085205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38828590512275696}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7910169363021851},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6948487162590027},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6396712064743042},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5951632857322693},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5932098031044006},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5409935116767883},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.516539990901947},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.44772839546203613},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4294242262840271},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4203197956085205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38828590512275696},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C89423630","wikidata":"https://www.wikidata.org/wiki/Q7193","display_name":"Microbiology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447755","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":[],"funders":[{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2144082342","https://openalex.org/W2563356726","https://openalex.org/W2752782242","https://openalex.org/W2928165649","https://openalex.org/W2939771864","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2973062255","https://openalex.org/W2974407961","https://openalex.org/W2991361823","https://openalex.org/W3008003372","https://openalex.org/W3015623828","https://openalex.org/W3015636705","https://openalex.org/W3016361963","https://openalex.org/W3024869864","https://openalex.org/W3097653961","https://openalex.org/W3099330747","https://openalex.org/W3101330598","https://openalex.org/W3103434036","https://openalex.org/W3105928222","https://openalex.org/W3165776651","https://openalex.org/W3190394743","https://openalex.org/W3206706278","https://openalex.org/W4224919629","https://openalex.org/W4225905067","https://openalex.org/W4319780101","https://openalex.org/W4372346771","https://openalex.org/W4385822829","https://openalex.org/W4390480998"],"related_works":["https://openalex.org/W112947718","https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W1998549096","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Target":[0],"speaker":[1,29,54,121,161],"extraction":[2,162],"aims":[3],"to":[4,41,75,118],"isolate":[5],"a":[6,11,62,84],"specific":[7],"speaker\u2019s":[8],"voice":[9,44],"from":[10,31],"composite":[12],"of":[13,45,52,102,109,116],"multiple":[14],"sound":[15],"sources,":[16],"guided":[17],"by":[18],"an":[19],"enrollment":[20],"utterance":[21],"or":[22],"called":[23,87],"anchor.":[24],"Current":[25],"methods":[26],"predominantly":[27],"derive":[28],"embeddings":[30],"the":[32,38,43,46,50,53,72,103,107,114,124,143],"anchor":[33,94,165],"and":[34,98],"integrate":[35],"them":[36],"into":[37],"separation":[39,73,104],"network":[40,74],"separate":[42],"target":[47,110,120,160],"speaker.":[48],"However,":[49],"representation":[51],"embedding":[55],"is":[56],"too":[57],"simplistic,":[58],"often":[59],"being":[60],"merely":[61],"1\u00d71024":[63],"vector.":[64],"This":[65],"dense":[66],"information":[67],"makes":[68],"it":[69],"difficult":[70],"for":[71,158],"harness":[76],"effectively.":[77],"To":[78],"address":[79],"this":[80],"limitation,":[81],"we":[82,138],"introduce":[83],"pioneering":[85],"methodology":[86,154],"Hierarchical":[88],"Representation":[89],"(HR)":[90],"that":[91],"seamlessly":[92],"fuses":[93],"data":[95],"across":[96],"granular":[97],"overarching":[99],"5":[100],"layers":[101],"network,":[105],"enhancing":[106],"precision":[108],"extraction.":[111],"HR":[112,127,153],"amplifies":[113],"efficacy":[115],"anchors":[117],"improve":[119],"isolation.":[122],"On":[123],"Libri-2talker":[125],"dataset,":[126],"substantially":[128],"outperforms":[129],"state-of-the-art":[130],"time-frequency":[131],"domain":[132],"techniques.":[133],"Further":[134],"demonstrating":[135],"HR\u2019s":[136],"capabilities,":[137],"achieved":[139],"first":[140],"place":[141],"in":[142],"prestigious":[144],"ICASSP":[145],"2023":[146],"Deep":[147],"Noise":[148],"Suppression":[149],"Challenge.":[150],"The":[151],"proposed":[152],"shows":[155],"great":[156],"promise":[157],"advancing":[159],"through":[163],"enhanced":[164],"utilization.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}