{"id":"https://openalex.org/W7107861268","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249072","title":"End-To-End Multi-Channel Speaker Extraction and Binaural Speech Synthesis","display_name":"End-To-End Multi-Channel Speaker Extraction and Binaural Speech Synthesis","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W7107861268","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249072"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249072","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":null,"display_name":"Cheng Chi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Chi","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences,Laboratory of Noise and Audio Research,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences,Laboratory of Noise and Audio Research,Beijing,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoyu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Li","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences,Laboratory of Noise and Audio Research,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences,Laboratory of Noise and Audio Research,Beijing,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuxuan Ke","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Ke","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences,Laboratory of Noise and Audio Research,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences,Laboratory of Noise and Audio Research,Beijing,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qunping Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111085","display_name":"Academy of Broadcasting Science","ror":"https://ror.org/01z4nez64","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210111085"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qunping Ni","raw_affiliation_strings":["Tianjin 712 Communication & Broadcasting Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin 712 Communication & Broadcasting Co., Ltd","institution_ids":["https://openalex.org/I4210111085"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ge Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133666","display_name":"Tiandi Science & Technology (China)","ror":"https://ror.org/03ssr6t63","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210133666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Yao","raw_affiliation_strings":["Tianjin Tianan Borui Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin Tianan Borui Technology Co., Ltd","institution_ids":["https://openalex.org/I4210133666"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaodong Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Li","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences,Laboratory of Noise and Audio Research,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences,Laboratory of Noise and Audio Research,Beijing,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chengshi Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengshi Zheng","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences,Laboratory of Noise and Audio Research,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences,Laboratory of Noise and Audio Research,Beijing,China","institution_ids":["https://openalex.org/I4210099069"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.54150457,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"950","last_page":"955"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9789999723434448,"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":0.9789999723434448,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.014299999922513962,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.0012000000569969416,"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/binaural-recording","display_name":"Binaural recording","score":0.857200026512146},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6600000262260437},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5794000029563904},{"id":"https://openalex.org/keywords/teleconference","display_name":"Teleconference","score":0.42410001158714294},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.415800005197525},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.40709999203681946},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.38519999384880066},{"id":"https://openalex.org/keywords/headphones","display_name":"Headphones","score":0.3824000060558319},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.38199999928474426}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.857200026512146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7648000121116638},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6922000050544739},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6600000262260437},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5794000029563904},{"id":"https://openalex.org/C126669455","wikidata":"https://www.wikidata.org/wiki/Q1630941","display_name":"Teleconference","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.415800005197525},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.40709999203681946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38530001044273376},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C2781258422","wikidata":"https://www.wikidata.org/wiki/Q186819","display_name":"Headphones","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.38199999928474426},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.38100001215934753},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C2777146004","wikidata":"https://www.wikidata.org/wiki/Q14949826","display_name":"CLARITY","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C103364767","wikidata":"https://www.wikidata.org/wiki/Q1807562","display_name":"Interaural time difference","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C2777185736","wikidata":"https://www.wikidata.org/wiki/Q7265603","display_name":"QUIET","level":2,"score":0.259799987077713}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249072","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":[{"id":"https://metadata.un.org/sdg/4","score":0.43633145093917847,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W2045043668","https://openalex.org/W2048909388","https://openalex.org/W2060422862","https://openalex.org/W2067584370","https://openalex.org/W2079158793","https://openalex.org/W2098882755","https://openalex.org/W2117678320","https://openalex.org/W2129188305","https://openalex.org/W2139929615","https://openalex.org/W2143270321","https://openalex.org/W2516001803","https://openalex.org/W2749196801","https://openalex.org/W2899845898","https://openalex.org/W2982624843","https://openalex.org/W3025800305","https://openalex.org/W3097906045","https://openalex.org/W3128268416","https://openalex.org/W3176000171","https://openalex.org/W3196940724","https://openalex.org/W3210189536","https://openalex.org/W3213191779","https://openalex.org/W4221164004","https://openalex.org/W4224934174","https://openalex.org/W4280592948","https://openalex.org/W4309619172","https://openalex.org/W4312891280","https://openalex.org/W4313485005","https://openalex.org/W4372259804","https://openalex.org/W4388620484","https://openalex.org/W4392903092"],"related_works":[],"abstract_inverted_index":{"Speech":[0],"clarity":[1],"and":[2,71,76,88,131],"spatial":[3,28,114,132],"audio":[4],"immersion":[5],"are":[6,19],"the":[7,25,43,65,111],"two":[8],"most":[9],"critical":[10],"factors":[11],"in":[12,125],"enhancing":[13],"remote":[14],"conferencing":[15],"experiences.":[16],"Existing":[17],"methods":[18],"often":[20],"limited:":[21],"either":[22],"due":[23],"to":[24,74,109],"lack":[26],"of":[27,45,67,113,127],"information":[29],"when":[30,48],"using":[31,49],"only":[32],"one":[33,92],"microphone,":[34],"or":[35],"because":[36],"their":[37],"performance":[38],"is":[39,105],"highly":[40],"dependent":[41],"on":[42],"accuracy":[44,112],"direction-of-arrival":[46],"estimation":[47],"microphone":[50],"array.":[51],"To":[52],"overcome":[53],"this":[54,95],"issue,":[55],"we":[56],"introduce":[57],"an":[58],"end-to-end":[59],"deep":[60],"learning":[61],"framework":[62,82],"that":[63,107,119],"has":[64],"capacity":[66],"mapping":[68],"multi-channel":[69],"noisy":[70],"reverberant":[72],"signals":[73],"clean":[75],"spatialized":[77],"binaural":[78,89],"speech":[79,129],"directly.":[80],"This":[81],"unifies":[83],"source":[84],"extraction,":[85],"noise":[86],"suppression,":[87],"rendering":[90],"into":[91],"network.":[93],"In":[94],"framework,":[96],"a":[97],"novel":[98],"magnitude-weighted":[99],"interaural":[100],"level":[101],"difference":[102],"loss":[103],"function":[104],"proposed":[106],"aims":[108],"improve":[110],"rendering.":[115],"Extensive":[116],"evaluations":[117],"show":[118],"our":[120],"method":[121],"outperforms":[122],"established":[123],"baselines":[124],"terms":[126],"both":[128],"quality":[130],"fidelity.":[133]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}