{"id":"https://openalex.org/W4416798694","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249056","title":"Exploring Dual-Mode Training for Real-Time Target Speaker Extraction","display_name":"Exploring Dual-Mode Training for Real-Time Target Speaker Extraction","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798694","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249056"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5111401131","display_name":"Li Li","orcid":"https://orcid.org/0009-0008-3033-0891"},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["CyberAgent,AI Lab,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CyberAgent,AI Lab,Japan","institution_ids":["https://openalex.org/I4210089607"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101792863","display_name":"Shogo Seki","orcid":"https://orcid.org/0000-0001-8284-188X"},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shogo Seki","raw_affiliation_strings":["CyberAgent,AI Lab,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CyberAgent,AI Lab,Japan","institution_ids":["https://openalex.org/I4210089607"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210089607"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17277939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9193999767303467,"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":0.9193999767303467,"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":0.039799999445676804,"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":0.008899999782443047,"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/process","display_name":"Process (computing)","score":0.5055000185966492},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4740000069141388},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4440000057220459},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.40380001068115234},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.35910001397132874},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.35409998893737793},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.3517000079154968}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134999871253967},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5055000185966492},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4740000069141388},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4440000057220459},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4415999948978424},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.40380001068115234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39430001378059387},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2825999855995178},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28060001134872437},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2590000033378601},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C2777611316","wikidata":"https://www.wikidata.org/wiki/Q39045282","display_name":"Streaming data","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":26,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W2067295501","https://openalex.org/W2127851351","https://openalex.org/W2763188033","https://openalex.org/W2964058413","https://openalex.org/W2972541922","https://openalex.org/W2972568703","https://openalex.org/W2972802573","https://openalex.org/W3015199127","https://openalex.org/W3034368386","https://openalex.org/W3096090308","https://openalex.org/W3097653961","https://openalex.org/W3136499730","https://openalex.org/W3161590371","https://openalex.org/W3206706278","https://openalex.org/W3217643883","https://openalex.org/W4226185896","https://openalex.org/W4367597591","https://openalex.org/W4375869299","https://openalex.org/W4385756463","https://openalex.org/W4385823352","https://openalex.org/W4396833001","https://openalex.org/W4402112399","https://openalex.org/W4406208517","https://openalex.org/W4407780075"],"related_works":[],"abstract_inverted_index":{"Implementing":[0],"real-time":[1,20,23,46,57],"target":[2],"speaker":[3],"extraction":[4],"(TSE)":[5],"presents":[6],"significant":[7],"challenges,":[8],"primarily":[9],"due":[10],"to":[11,14,18,26,131],"the":[12,28,43,51,78,111,115,133],"need":[13],"minimize":[15],"computational":[16,112],"time":[17],"meet":[19],"constraints.":[21],"Additionally,":[22],"TSE":[24,98,137],"struggles":[25],"match":[27],"performance":[29,44,84,134],"of":[30,45,53,80,106,114,135,142],"offline":[31],"systems":[32],"because":[33],"future":[34],"information":[35],"is":[36,129],"inaccessible":[37],"in":[38,140],"streaming":[39,71,82,116,136],"process.":[40],"To":[41],"enhance":[42,132],"models,":[47],"this":[48],"paper":[49],"investigates":[50],"use":[52],"dual-mode":[54,104,120,127],"training":[55,62,128],"for":[56,69],"TSE.":[58],"This":[59,108],"approach":[60],"involves":[61],"a":[63,96,103],"single":[64],"model":[65],"with":[66,77],"shared":[67],"weights":[68],"both":[70],"and":[72,88],"batch":[73],"processing":[74,83],"modes":[75],"concurrently,":[76],"goal":[79],"optimizing":[81],"through":[85],"full-context":[86],"modeling":[87],"joint":[89],"training.":[90,121],"The":[91,122],"experiments":[92,123],"are":[93],"conducted":[94],"on":[95],"TFGridNet-based":[97],"system,":[99,138],"where":[100],"we":[101],"introduce":[102],"implementation":[105,109],"TFGridNet.":[107],"maintains":[110],"complexity":[113],"process":[117],"while":[118],"enabling":[119],"have":[124],"indicated":[125],"that":[126],"able":[130],"particularly":[139],"terms":[141],"intelligibility":[143],"metrics.":[144]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}