{"id":"https://openalex.org/W2804228164","doi":"https://doi.org/10.1109/icassp.2018.8461930","title":"Efficient Integration of Fixed Beamformers and Speech Separation Networks for Multi-Channel Far-Field Speech Separation","display_name":"Efficient Integration of Fixed Beamformers and Speech Separation Networks for Multi-Channel Far-Field Speech Separation","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2804228164","doi":"https://doi.org/10.1109/icassp.2018.8461930","mag":"2804228164"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5100345094","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-9943-2262"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Microsoft AI & Research, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft AI & Research, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft AI & Research, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft AI & Research, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101602536","display_name":"Xiong Xiao","orcid":"https://orcid.org/0009-0001-5128-6518"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiong Xiao","raw_affiliation_strings":["Microsoft AI & Research, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft AI & Research, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101937752","display_name":"Linyu Li","orcid":"https://orcid.org/0000-0002-2341-1318"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linyu Li","raw_affiliation_strings":["Microsoft AI & Research, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft AI & Research, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041313589","display_name":"Michael L. Seltzer","orcid":"https://orcid.org/0000-0003-3474-2451"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Seltzer","raw_affiliation_strings":["Microsoft AI & Research, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft AI & Research, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107639889","display_name":"Yifan Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["Microsoft AI & Research, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft AI & Research, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100345094"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":2.6516,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.91007873,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5384","last_page":"5388"},"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7413771748542786},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7022355794906616},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6448663473129272},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5204896330833435},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4913310110569},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.48464614152908325},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.46853914856910706},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.46297687292099},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4335668683052063},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.42563462257385254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2941710352897644},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.17897379398345947},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13888341188430786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7413771748542786},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7022355794906616},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6448663473129272},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5204896330833435},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4913310110569},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.48464614152908325},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.46853914856910706},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.46297687292099},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4335668683052063},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.42563462257385254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2941710352897644},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.17897379398345947},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13888341188430786},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W37722415","https://openalex.org/W189850294","https://openalex.org/W1991139021","https://openalex.org/W2069681747","https://openalex.org/W2129934596","https://openalex.org/W2150678643","https://openalex.org/W2168379380","https://openalex.org/W2221409856","https://openalex.org/W2293634267","https://openalex.org/W2398042854","https://openalex.org/W2400339399","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2586584460","https://openalex.org/W2734774145","https://openalex.org/W2738829388","https://openalex.org/W2749588430","https://openalex.org/W2750380122","https://openalex.org/W2962715207","https://openalex.org/W2963301902","https://openalex.org/W3099832538","https://openalex.org/W6696934422"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W2161396743","https://openalex.org/W2386453889","https://openalex.org/W3134790285","https://openalex.org/W2345063900"],"abstract_inverted_index":{"Speech":[0],"separation":[1,28,53,68,95,130],"research":[2],"has":[3],"significantly":[4,168],"progressed":[5],"in":[6,14,34,69,108],"recent":[7],"years":[8],"thanks":[9],"to":[10],"the":[11,19,39,109,115,122,165,170,176],"rapid":[12],"advances":[13],"deep":[15],"learning":[16],"technology.":[17],"However":[18],"performance":[20,40,178],"of":[21,47,85,127],"recently":[22,43],"proposed":[23,80,166],"single-channel":[24,51,172,181],"neural":[25],"network-based":[26],"speech":[27,52,67,94,129,140],"methods":[29],"is":[30,136,157],"still":[31],"limited":[32],"especially":[33],"reverberant":[35,139],"environments.":[36],"To":[37],"push":[38],"limit,":[41],"we":[42],"developed":[44],"a":[45,58,70,83,88,93,180],"method":[46],"integrating":[48],"beamforming":[49,65],"and":[50,66,92,113],"approaches.":[54],"This":[55],"paper":[56],"proposes":[57],"novel":[59],"architecture":[60,81],"that":[61,164],"integrates":[62],"multi":[63],"-channel":[64],"much":[71],"more":[72],"efficient":[73],"way":[74],"than":[75],"our":[76],"previous":[77],"method.":[78],"The":[79,103,160],"comprises":[82],"set":[84],"fixed":[86],"beamformers,":[87],"beam":[89,104,117],"prediction":[90,105],"network,":[91],"network":[96,106],"based":[97],"on":[98,138],"permutation":[99],"invariant":[100],"training":[101],"(PIT).":[102],"takes":[107],"beamformed":[110],"audio":[111],"signals":[112],"estimates":[114],"best":[116],"for":[118],"each":[119],"speaker":[120],"constituting":[121],"input":[123],"mixture.":[124],"Two":[125],"variants":[126],"PIT-based":[128],"networks":[131],"are":[132],"proposed.":[133],"Our":[134],"approach":[135],"evaluated":[137],"mixtures":[141],"under":[142],"three":[143],"different":[144],"mixing":[145],"conditions,":[146],"covering":[147],"cases":[148],"where":[149],"speakers":[150],"partially":[151],"overlap":[152],"or":[153],"one":[154],"speaker's":[155],"utterance":[156],"very":[158],"short.":[159],"experimental":[161],"results":[162],"show":[163],"system":[167,182],"outperforms":[169],"conventional":[171],"PIT":[173],"system,":[174],"producing":[175],"same":[177],"as":[179],"using":[183],"oracle":[184],"masks.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}