{"id":"https://openalex.org/W4408352717","doi":"https://doi.org/10.1109/icassp49660.2025.10889409","title":"Multi-Level Speaker Representation for Target Speaker Extraction","display_name":"Multi-Level Speaker Representation for Target Speaker Extraction","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352717","doi":"https://doi.org/10.1109/icassp49660.2025.10889409"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889409","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100365672","display_name":"Ke Zhang","orcid":"https://orcid.org/0000-0001-5073-959X"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Zhang","raw_affiliation_strings":["Northeastern University,Key Laboratory of Intelligent Computing in Medical Image,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,Key Laboratory of Intelligent Computing in Medical Image,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367662","display_name":"Junjie Li","orcid":"https://orcid.org/0000-0002-9107-5563"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Junjie Li","raw_affiliation_strings":["The Hong Kong Polytechnic University,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Hong Kong,China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328340","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0003-1523-9631"},"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":"Shuai Wang","raw_affiliation_strings":["The Chinese University of Hong Kong,SDS, SRIBD,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,SDS, SRIBD,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025048527","display_name":"Yangjie Wei","orcid":"https://orcid.org/0000-0001-6615-5484"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangjie Wei","raw_affiliation_strings":["Northeastern University,Key Laboratory of Intelligent Computing in Medical Image,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,Key Laboratory of Intelligent Computing in Medical Image,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364982","display_name":"Yi Wang","orcid":"https://orcid.org/0000-0002-8448-8570"},"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/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Wang","raw_affiliation_strings":["Northeastern University,Key Laboratory of Intelligent Computing in Medical Image,China","Tencent,Tencent Ethereal Audio Lab,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,Key Laboratory of Intelligent Computing in Medical Image,China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"Tencent,Tencent Ethereal Audio Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084128157","display_name":"Yannan Wang","orcid":"https://orcid.org/0000-0001-7248-4954"},"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/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yannan Wang","raw_affiliation_strings":["Northeastern University,Key Laboratory of Intelligent Computing in Medical Image,China","Tencent,Tencent Ethereal Audio Lab,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,Key Laboratory of Intelligent Computing in Medical Image,China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"Tencent,Tencent Ethereal Audio Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"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"],"raw_orcid":null,"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":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9866999983787537,"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":0.9866999983787537,"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":0.9293000102043152,"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/speaker-recognition","display_name":"Speaker recognition","score":0.785699725151062},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7374795079231262},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6137125492095947},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5532910227775574},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5521449446678162},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4762461483478546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3957645893096924}],"concepts":[{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.785699725151062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7374795079231262},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6137125492095947},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5532910227775574},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5521449446678162},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4762461483478546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3957645893096924},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/icassp49660.2025.10889409","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2124149378","https://openalex.org/W2150415460","https://openalex.org/W2221409856","https://openalex.org/W2808631503","https://openalex.org/W2964058413","https://openalex.org/W2973062255","https://openalex.org/W3015636705","https://openalex.org/W3024869864","https://openalex.org/W3097653961","https://openalex.org/W3197381252","https://openalex.org/W3198575250","https://openalex.org/W4200634403","https://openalex.org/W4226021932","https://openalex.org/W4226338831","https://openalex.org/W4283074506","https://openalex.org/W4295308317","https://openalex.org/W4367597591","https://openalex.org/W4372265824","https://openalex.org/W4372271325","https://openalex.org/W4372340947","https://openalex.org/W4375928773","https://openalex.org/W4385822391","https://openalex.org/W4385822449","https://openalex.org/W4385822829","https://openalex.org/W4385822857","https://openalex.org/W4385823017","https://openalex.org/W4387609344","https://openalex.org/W4392902910","https://openalex.org/W4392902992","https://openalex.org/W4392903066","https://openalex.org/W4392909318","https://openalex.org/W4393863141","https://openalex.org/W4402111748","https://openalex.org/W4402112065","https://openalex.org/W4402112342","https://openalex.org/W4406461495","https://openalex.org/W6600345780","https://openalex.org/W6680012447","https://openalex.org/W6777776875","https://openalex.org/W6848964695","https://openalex.org/W6859669612"],"related_works":["https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939","https://openalex.org/W2144470400","https://openalex.org/W1516392727","https://openalex.org/W2140022733","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Target":[0],"speaker":[1,23,46,55,68,111,115],"extraction":[2,141],"(TSE)":[3],"relies":[4],"on":[5,101,143],"a":[6,18,22,36,53,73,82,96,109,132,137],"reference":[7,30,69],"cue":[8],"of":[9,39,45,125],"the":[10,14,29,67,77,89,123,126,148],"target":[11,15],"to":[12,61,64],"extract":[13],"speech":[16,19],"from":[17,43,58,76,108],"mixture.":[20],"While":[21],"embedding":[24,33,98],"is":[25],"commonly":[26],"used":[27],"as":[28,66,81],"cue,":[31],"such":[32],"pre-trained":[34,110],"with":[35],"large":[37],"number":[38],"speakers":[40],"may":[41],"suffer":[42],"confusion":[44],"identity.":[47],"In":[48],"this":[49],"work,":[50],"we":[51,94,120],"propose":[52,95],"multi-level":[54],"representation":[56,75],"approach,":[57],"raw":[59],"features":[60,116],"neural":[62],"embeddings,":[63],"serve":[65],"cue.":[70],"We":[71],"generate":[72],"spectral-level":[74],"enrollment":[78],"magnitude":[79],"spectrogram":[80],"raw,":[83],"low-level":[84],"feature,":[85],"which":[86],"significantly":[87,121],"improves":[88],"model\u2019s":[90],"generalization":[91],"capability.":[92],"Additionally,":[93],"contextual":[97],"feature":[99],"based":[100],"cross-attention":[102],"mechanisms":[103],"that":[104],"integrate":[105],"frame-level":[106],"embeddings":[107],"encoder.":[112],"By":[113],"incorporating":[114],"across":[117],"multiple":[118],"levels,":[119],"enhance":[122],"performance":[124],"TSE":[127],"model.":[128],"Our":[129],"approach":[130],"achieves":[131],"2.74":[133],"dB":[134],"improvement":[135],"and":[136],"4.94%":[138],"increase":[139],"in":[140],"accuracy":[142],"Libri2mix":[144],"test":[145],"set":[146],"over":[147],"baseline.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}