{"id":"https://openalex.org/W4413343957","doi":"https://doi.org/10.1109/lsp.2025.3600168","title":"DOA or Speaker Embedding: Which is Better for Multi-Microphone Target Speaker Extraction","display_name":"DOA or Speaker Embedding: Which is Better for Multi-Microphone Target Speaker Extraction","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413343957","doi":"https://doi.org/10.1109/lsp.2025.3600168"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3600168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3600168","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5101924462","display_name":"Shuang Zhang","orcid":"https://orcid.org/0000-0002-8427-1291"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuang Zhang","raw_affiliation_strings":["National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP), University of Science and Technology of China (USTC), Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP), University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436848","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0003-1124-0854"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP), University of Science and Technology of China (USTC), Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP), University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115595327","display_name":"Yichi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichi Wang","raw_affiliation_strings":["National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP), University of Science and Technology of China (USTC), Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP), University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036925221","display_name":"Haoyin Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyin Yan","raw_affiliation_strings":["National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP), University of Science and Technology of China (USTC), Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP), University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101924462"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":3.1913,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92548365,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"3350","last_page":"3354"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9969000220298767,"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/T11309","display_name":"Music and Audio Processing","score":0.9810000061988831,"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/speech-recognition","display_name":"Speech recognition","score":0.7648183703422546},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7356705665588379},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7257792353630066},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7036001682281494},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6059989929199219},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5780095458030701},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.4324505031108856},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4254457950592041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3304986357688904},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11556720733642578}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7648183703422546},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7356705665588379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7257792353630066},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7036001682281494},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6059989929199219},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5780095458030701},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.4324505031108856},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4254457950592041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3304986357688904},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11556720733642578},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3600168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3600168","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1991139021","https://openalex.org/W2141998673","https://openalex.org/W2898268964","https://openalex.org/W2909607850","https://openalex.org/W2951130829","https://openalex.org/W2973062255","https://openalex.org/W3015372568","https://openalex.org/W3016361963","https://openalex.org/W3024869864","https://openalex.org/W3097653961","https://openalex.org/W3157899172","https://openalex.org/W3160464260","https://openalex.org/W3162534564","https://openalex.org/W3198234746","https://openalex.org/W3206706278","https://openalex.org/W3207728800","https://openalex.org/W4210774825","https://openalex.org/W4221164375","https://openalex.org/W4223583411","https://openalex.org/W4226021932","https://openalex.org/W4312806213","https://openalex.org/W4367597591","https://openalex.org/W4372260086","https://openalex.org/W4372271325","https://openalex.org/W4372341573","https://openalex.org/W4372348071","https://openalex.org/W4375868926","https://openalex.org/W4392903292","https://openalex.org/W4395471087","https://openalex.org/W4401416441","https://openalex.org/W4402112351","https://openalex.org/W4408352717","https://openalex.org/W4410639153"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W36105149","https://openalex.org/W2545131480","https://openalex.org/W4401661962","https://openalex.org/W4247736853","https://openalex.org/W1521049138","https://openalex.org/W2997340161","https://openalex.org/W2911612049","https://openalex.org/W1589374915","https://openalex.org/W2136038945"],"abstract_inverted_index":{"Target":[0],"speaker":[1,22,36,90,108,115,147,163,180],"extraction":[2],"(TSE)":[3],"is":[4,98,110,120],"a":[5,77,81,107],"useful":[6],"front-end":[7],"to":[8,32,49,65,100,112],"improve":[9,44],"the":[10,27,34,45,93,114,124,156,162,172,187,192,198],"speech":[11,16,104,126],"quality":[12],"and":[13,21,69,89,106,191],"intelligibility":[14],"for":[15,80,86,128],"applications,":[17],"whereas":[18],"direction-of-arrival":[19],"(DOA)":[20],"embedding":[23,91,164],"are":[24],"two":[25],"of":[26,118,168,175,179],"most":[28],"often-used":[29],"assistive":[30,94],"clues":[31],"identify":[33],"target":[35],"in":[37,61,71,137,177,197],"audio-only":[38],"multi-microphone":[39],"systems.":[40],"Both":[41],"can":[42,131,194],"significantly":[43],"TSE":[46,51,158],"performance":[47],"compared":[48,60],"blind":[50],"models,":[52],"which":[53,119],"however":[54],"have":[55],"not":[56],"yet":[57],"been":[58],"comprehensively":[59],"literature.":[62],"In":[63],"order":[64],"show":[66,150],"their":[67,134],"pros":[68],"cons,":[70],"this":[72],"work":[73],"we":[74],"therefore":[75],"build":[76],"unified":[78],"framework":[79],"fair":[82],"comparison":[83],"that":[84,151],"allows":[85],"both":[87],"DOA":[88,97,154,176,188,200],"as":[92],"clue.":[95],"The":[96],"used":[99],"calculate":[101],"multichannel":[102],"spatiotemporal":[103],"features":[105,127],"encoder":[109],"designed":[111],"extract":[113],"embedding,":[116],"either":[117],"then":[121,132],"fused":[122],"with":[123],"noisy":[125],"TSE.":[129],"We":[130],"evaluate":[133],"respective":[135],"strengths":[136],"diverse":[138],"acoustic":[139],"conditions,":[140,170],"e.g.,":[141],"varying":[142],"noise":[143],"level,":[144],"microphone":[145],"number,":[146],"location.":[148],"Results":[149],"given":[152],"true":[153],"angles,":[155],"DOA-based":[157],"model":[159],"always":[160],"outperforms":[161],"based":[165],"counterpart":[166],"regardless":[167],"noise/microphone/location":[169],"meaning":[171],"stronger":[173],"discriminativity":[174],"terms":[178],"identity.":[181],"This":[182],"superiority":[183],"becomes":[184],"smaller":[185],"if":[186],"mis-match":[189],"increases,":[190],"latter":[193],"do":[195],"better":[196],"large":[199],"mismatch":[201],"case.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}