{"id":"https://openalex.org/W4406861246","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849054","title":"What to Refer and How? - Exploring Handling of Auxiliary Information in Target Speaker Extraction","display_name":"What to Refer and How? - Exploring Handling of Auxiliary Information in Target Speaker Extraction","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406861246","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849054"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10849054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849054","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/A5017264900","display_name":"T. Hayashi","orcid":"https://orcid.org/0000-0002-4065-1807"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tomohiro Hayashi","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001987466","display_name":"Riku Ogino","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Riku Ogino","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013385059","display_name":"Kohei Saijo","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kohei Saijo","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102081667","display_name":"Tetsuji Ogawa","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuji Ogawa","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5017264900"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23714675,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.9623000025749207,"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":0.9623000025749207,"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":0.7123342156410217},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5064979791641235},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4765622913837433},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.46233460307121277},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4203249216079712},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.395449697971344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3535478711128235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7123342156410217},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5064979791641235},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4765622913837433},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.46233460307121277},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4203249216079712},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.395449697971344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3535478711128235},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10849054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849054","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1494198834","https://openalex.org/W2020997493","https://openalex.org/W2057826000","https://openalex.org/W2064675550","https://openalex.org/W2099741732","https://openalex.org/W2398776621","https://openalex.org/W2539141352","https://openalex.org/W2763188033","https://openalex.org/W2891833136","https://openalex.org/W2939771864","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2964058413","https://openalex.org/W2972474532","https://openalex.org/W2972492143","https://openalex.org/W2976460547","https://openalex.org/W3015636705","https://openalex.org/W3151596526","https://openalex.org/W4289665794","https://openalex.org/W4297841846","https://openalex.org/W4318903188","https://openalex.org/W4372348071","https://openalex.org/W6777776875"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4313854686","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366","https://openalex.org/W3197877226"],"abstract_inverted_index":{"This":[0,116],"study":[1,117],"explored":[2],"the":[3,14,42,68,78,87,90,94,104,107,121,149,158,165,170],"appropriate":[4],"auxiliary":[5,23,47,91,110,125,152],"information":[6,31],"for":[7],"target":[8,43,69],"speaker":[9],"extraction":[10,79],"(TSE).":[11],"In":[12],"TSE,":[13],"conventional":[15],"method":[16,80],"involves":[17],"using":[18],"pre-recorded":[19],"speech":[20,44,53,63],"as":[21,45],"an":[22,46],"signal.":[24],"However,":[25],"in":[26,86,127,143],"multi-channel":[27,145],"environments":[28],"where":[29],"spatial":[30],"is":[32,54],"available,":[33],"alternative":[34],"approaches":[35,84],"that":[36],"utilize":[37],"a":[38,133,144],"rough":[39],"pre-extraction":[40],"of":[41,74,89,109,124,136,151,167,172],"signal":[48],"are":[49],"being":[50],"explored.":[51],"Pre-recorded":[52],"typically":[55],"clean":[56],"but":[57,70],"contains":[58],"different":[59],"content,":[60],"whereas":[61],"pre-extracted":[62],"has":[64,100],"content":[65,161],"aligned":[66],"with":[67],"includes":[71],"various":[72],"types":[73],"distortion":[75],"depending":[76],"on":[77],"used.":[81],"These":[82],"two":[83],"differ":[85],"characteristics":[88],"signals":[92,111,126,153],"and":[93,112,130,163,169],"conditioning":[95],"methods":[96],"applied.":[97],"Previous":[98],"research":[99],"not":[101],"thoroughly":[102],"examined":[103],"relationship":[105],"between":[106,160],"nature":[108],"TSE":[113,128,140],"model":[114],"performance.":[115],"aims":[118],"to":[119,131],"explore":[120],"effective":[122],"use":[123],"models":[129],"provide":[132],"comprehensive":[134],"analysis":[135],"their":[137],"impact.":[138],"Through":[139],"experiments":[141],"conducted":[142],"environment,":[146],"we":[147],"investigated":[148],"effects":[150],"from":[154],"three":[155],"key":[156],"perspectives:":[157],"trade-off":[159],"consistency":[162],"distortion,":[164],"level":[166],"referencing,":[168],"type":[171],"distortion.":[173]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}