{"id":"https://openalex.org/W3096571892","doi":"https://doi.org/10.21437/interspeech.2020-1981","title":"An End-to-End Architecture of Online Multi-Channel Speech Separation","display_name":"An End-to-End Architecture of Online Multi-Channel Speech Separation","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096571892","doi":"https://doi.org/10.21437/interspeech.2020-1981","mag":"3096571892"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1981","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101674460","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3101-7011"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345092","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-9011-7928"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036359785","display_name":"Zhili Tan","orcid":"https://orcid.org/0000-0002-2445-5240"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhili Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002012113","display_name":"Edward Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edward Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048439332","display_name":"Yi Luo","orcid":"https://orcid.org/0000-0002-7447-3885"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8118621110916138},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6510130167007446},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6230440735816956},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.573161244392395},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.5534650087356567},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5248691439628601},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4749196469783783},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.4238140881061554},{"id":"https://openalex.org/keywords/adaptive-beamformer","display_name":"Adaptive beamformer","score":0.41926732659339905},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.41747742891311646},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4159954786300659},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2936042547225952},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.22521787881851196},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11259597539901733},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08602520823478699}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8118621110916138},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6510130167007446},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6230440735816956},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.573161244392395},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.5534650087356567},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5248691439628601},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4749196469783783},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.4238140881061554},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.41926732659339905},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.41747742891311646},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4159954786300659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2936042547225952},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.22521787881851196},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11259597539901733},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08602520823478699},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1981","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2545798066","https://openalex.org/W2385145472","https://openalex.org/W2351541234","https://openalex.org/W2504308083","https://openalex.org/W1969439651","https://openalex.org/W2013108665","https://openalex.org/W2106386991","https://openalex.org/W2767070583","https://openalex.org/W2784052451","https://openalex.org/W2348931051"],"abstract_inverted_index":{"Although":[0],"mask":[1,150],"based":[2,151],"adaptive":[3],"beamforming":[4],"technique":[5],"benefits":[6],"speech":[7,71,78,154],"recognition":[8,79],"in":[9,31,57,145,161],"far-field,":[10],"noisy":[11],"and":[12,25,101,130,153],"multi-talker":[13],"scenarios,":[14],"it":[15],"depends":[16],"on":[17],"the":[18,44,115,122,139,149,162],"long":[19],"time":[20,50],"context":[21],"to":[22],"estimate":[23],"target":[24],"interference":[26],"statistics,":[27],"thus":[28],"when":[29],"applied":[30],"applications":[32],"with":[33,80,148],"low":[34,81,108],"latency":[35,82,109],"requirement,":[36],"its":[37],"performance":[38,144],"usually":[39,53],"drops":[40],"drastically.":[41],"In":[42,63,133],"contrast,":[43],"fixed":[45,95],"beamformers":[46],"do":[47],"not":[48],"import":[49],"delay":[51],"but":[52],"have":[54],"limited":[55],"capability":[56],"acoustic":[58],"cancellation":[59],"of":[60,94],"interfering":[61],"source.":[62],"this":[64],"work,":[65],"we":[66,136],"propose":[67],"a":[68,90,92],"novel":[69],"multi-channel":[70],"separation":[72,125],"system":[73,141],"that":[74,138],"targets":[75],"at":[76],"overlapped":[77],"processing,":[83],"which":[84],"includes":[85],"four":[86],"jointly":[87],"optimized":[88],"components:":[89],"pre-separator,":[91],"set":[93],"beamformer,":[96],"an":[97],"attentional":[98],"selection":[99],"module":[100],"neural":[102,127],"post":[103,128],"filtering.":[104],"With":[105],"proposed":[106,140],"model,":[107],"processing":[110],"is":[111],"achieved":[112],"by":[113],"utilizing":[114],"known":[116],"microphone":[117],"geometry":[118],"information,":[119],"while":[120,157],"keeps":[121],"high":[123],"quality":[124],"through":[126],"filtering":[129],"end-to-end":[131],"optimization.":[132],"our":[134],"experiments,":[135],"show":[137],"achieves":[142],"comparable":[143],"offline":[146],"evaluation":[147],"MVDR":[152],"extraction":[155],"system,":[156],"yield":[158],"remarkable":[159],"improvements":[160],"online":[163],"evaluation.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}