{"id":"https://openalex.org/W4408354485","doi":"https://doi.org/10.1109/icassp49660.2025.10888158","title":"Leveraging Boolean Directivity Embedding for Binaural Target Speaker Extraction","display_name":"Leveraging Boolean Directivity Embedding for Binaural Target Speaker Extraction","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354485","doi":"https://doi.org/10.1109/icassp49660.2025.10888158"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888158","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":"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/A5115595327","display_name":"Yichi Wang","orcid":"https://orcid.org/0009-0000-7986-2209"},"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":"Yichi Wang","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,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":["University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chengqian Jiang","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":"Chengqian Jiang","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042203856","display_name":"Weitai Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weitai Zhang","raw_affiliation_strings":["iFlytek Research,Hefei,China"],"affiliations":[{"raw_affiliation_string":"iFlytek Research,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087587703","display_name":"Zhongyi Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongyi Ye","raw_affiliation_strings":["iFlytek Research,Hefei,China"],"affiliations":[{"raw_affiliation_string":"iFlytek Research,Hefei,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"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":"Lirong Dai","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5115595327"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01817333,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9966999888420105,"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":0.9765999913215637,"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":0.7543498873710632},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.7443875074386597},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6207179427146912},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6065983772277832},{"id":"https://openalex.org/keywords/directivity","display_name":"Directivity","score":0.5237298607826233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29350316524505615},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07130098342895508}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7543498873710632},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.7443875074386597},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6207179427146912},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6065983772277832},{"id":"https://openalex.org/C189039984","wikidata":"https://www.wikidata.org/wiki/Q8225412","display_name":"Directivity","level":3,"score":0.5237298607826233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29350316524505615},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07130098342895508},{"id":"https://openalex.org/C21822782","wikidata":"https://www.wikidata.org/wiki/Q131214","display_name":"Antenna (radio)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888158","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"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1983108229","https://openalex.org/W1991139021","https://openalex.org/W2108668360","https://openalex.org/W2119131192","https://openalex.org/W2137026380","https://openalex.org/W2150625370","https://openalex.org/W2761234876","https://openalex.org/W2897924318","https://openalex.org/W2962960500","https://openalex.org/W2964058413","https://openalex.org/W2964171275","https://openalex.org/W2967913447","https://openalex.org/W2972474532","https://openalex.org/W2972802573","https://openalex.org/W3015256813","https://openalex.org/W3015279216","https://openalex.org/W3015372568","https://openalex.org/W3117396592","https://openalex.org/W3140783160","https://openalex.org/W3157899172","https://openalex.org/W4205955626","https://openalex.org/W4221164375","https://openalex.org/W4223583411","https://openalex.org/W4283074506","https://openalex.org/W4296069323","https://openalex.org/W4312319640","https://openalex.org/W4372265901","https://openalex.org/W4372269199","https://openalex.org/W4372341573","https://openalex.org/W4372347386","https://openalex.org/W4372348071","https://openalex.org/W4375869370","https://openalex.org/W4385822730","https://openalex.org/W4385823318","https://openalex.org/W4390331187","https://openalex.org/W4392903292","https://openalex.org/W4399939359","https://openalex.org/W4402112007","https://openalex.org/W6675117242"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2766995619","https://openalex.org/W4224270619","https://openalex.org/W2579722767","https://openalex.org/W2168148781","https://openalex.org/W1991848873","https://openalex.org/W2026165661","https://openalex.org/W2099651033"],"abstract_inverted_index":{"Direction-based":[0],"target":[1,70,148],"speaker":[2,71,149],"extraction":[3],"(TSE)":[4],"attracts":[5],"a":[6,59,121],"constant":[7],"attention":[8],"due":[9,41],"to":[10,42,65,144],"the":[11,27,36,43,69,88,91,100,112,116,136,140,145,156,162],"convenience":[12],"of":[13,38,147,164],"direction":[14,23,61],"acquisition":[15],"over":[16],"assistive":[17],"video":[18],"or":[19],"enrollment":[20],"audio.":[21],"The":[22,128,173],"clue":[24],"heavily":[25],"affects":[26],"TSE":[28,79],"performance,":[29],"which":[30,132],"might":[31],"be":[32],"more":[33],"seriously":[34],"in":[35,63,167,178],"case":[37],"binaural":[39,78],"setups":[40],"small-sized":[44],"and":[45,107,123,151,170],"irregular":[46],"microphone":[47,74],"array.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52,110],"propose":[53],"Boolean":[54,101],"Directivity":[55],"Embedding":[56],"(BDE)":[57],"as":[58,139],"new":[60],"feature":[62,96],"order":[64],"precisely":[66],"lock":[67],"onto":[68],"independent":[72],"on":[73,135],"array":[75],"configurations":[76],"for":[77,95,126],"(BiTSE).":[80],"We":[81],"design":[82],"an":[83],"encoder":[84],"that":[85,99],"accurately":[86],"aligns":[87],"BDE":[89,113],"with":[90],"mixed":[92],"audio":[93],"signals":[94],"fusion.":[97],"Considering":[98],"representation":[102],"may":[103],"contain":[104],"insufficient":[105],"spatial":[106],"temporal":[108],"information,":[109],"enhance":[111],"by":[114,153],"incorporating":[115],"previously-proposed":[117],"spatiotemporal":[118],"features,":[119],"showing":[120],"compatibility":[122],"stronger":[124],"capacity":[125],"BiTSE.":[127],"proposed":[129,174],"BiTSE":[130],"model,":[131],"is":[133,176],"based":[134],"narrow-band":[137],"Conformer":[138],"backbone,":[141],"can":[142],"adapt":[143],"cases":[146],"switching":[150],"moving":[152],"simply":[154],"modifying":[155],"frame-wise":[157],"BDE.":[158],"Experimental":[159],"results":[160],"demonstrate":[161],"efficacy":[163],"our":[165],"method":[166,175],"both":[168],"stationary":[169],"dynamic":[171],"scenarios.":[172],"open-sourced":[177],"https://github.com/ichi131/Direction-based-BiTSE.":[179]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}