{"id":"https://openalex.org/W3207841327","doi":"https://doi.org/10.1109/icassp43922.2022.9747261","title":"All-Neural Beamformer for Continuous Speech Separation","display_name":"All-Neural Beamformer for Continuous Speech Separation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3207841327","doi":"https://doi.org/10.1109/icassp43922.2022.9747261","mag":"3207841327"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747261","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5045388319","display_name":"Zhuohuang Zhang","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"]},{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhuohuang Zhang","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA","Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"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,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016279564","display_name":"Naoyuki Kanda","orcid":"https://orcid.org/0000-0002-8628-3288"},"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":"Naoyuki Kanda","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345092","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-9011-7928"},"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":"Zhuo Chen","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363470","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0000-0002-7223-1030"},"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":"Xiaofei Wang","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100408281","display_name":"Dongmei Wang","orcid":"https://orcid.org/0000-0002-6930-0066"},"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":"Dongmei Wang","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026088950","display_name":"\u015eefik Emre Eskimez","orcid":"https://orcid.org/0000-0001-6259-5925"},"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":"Sefik Emre Eskimez","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5045388319"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":1.5955,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85276461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6032","last_page":"6036"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.8187034130096436},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7541211843490601},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5886954069137573},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5705474615097046},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.540256917476654},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4915550649166107},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.47147229313850403},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47122088074684143},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.42315492033958435},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42095428705215454},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36610737442970276},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.19093653559684753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8187034130096436},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7541211843490601},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5886954069137573},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5705474615097046},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.540256917476654},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4915550649166107},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.47147229313850403},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47122088074684143},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.42315492033958435},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42095428705215454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36610737442970276},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.19093653559684753},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747261","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W262275730","https://openalex.org/W1494198834","https://openalex.org/W2117678320","https://openalex.org/W2125336414","https://openalex.org/W2219249508","https://openalex.org/W2460742184","https://openalex.org/W2539508298","https://openalex.org/W2586584460","https://openalex.org/W2718052359","https://openalex.org/W2803322398","https://openalex.org/W2803583024","https://openalex.org/W2805288670","https://openalex.org/W2889503488","https://openalex.org/W2890489755","https://openalex.org/W2891378882","https://openalex.org/W2891984996","https://openalex.org/W2908510526","https://openalex.org/W2939246703","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2963452667","https://openalex.org/W2964199361","https://openalex.org/W2996322586","https://openalex.org/W3008283340","https://openalex.org/W3015372568","https://openalex.org/W3016232124","https://openalex.org/W3095134095","https://openalex.org/W3096008106","https://openalex.org/W3097777922","https://openalex.org/W3099330747","https://openalex.org/W3114363279","https://openalex.org/W3162315798","https://openalex.org/W3162341667","https://openalex.org/W3163842642","https://openalex.org/W3196360884","https://openalex.org/W3207360934","https://openalex.org/W3216920799","https://openalex.org/W6629717138","https://openalex.org/W6678809451","https://openalex.org/W6688816777","https://openalex.org/W6751512325","https://openalex.org/W6757817989","https://openalex.org/W6787577498","https://openalex.org/W6802337413"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2380771148","https://openalex.org/W2396048001","https://openalex.org/W4240587264","https://openalex.org/W2348931051","https://openalex.org/W2109356272","https://openalex.org/W2900122540","https://openalex.org/W2905188205"],"abstract_inverted_index":{"Continuous":[0],"speech":[1,67,103],"separation":[2],"(CSS)":[3],"aims":[4],"to":[5,63,116,123,154,157,172],"separate":[6],"overlapping":[7],"voices":[8],"from":[9],"a":[10,35,40,56,101,138,158],"continuous":[11],"influx":[12],"of":[13,20,27,73],"conversational":[14],"audio":[15],"containing":[16],"an":[17,24],"unknown":[18,25],"number":[19,26],"utterances":[21],"spoken":[22],"by":[23,39,55,79],"speakers.":[28],"A":[29],"common":[30],"application":[31],"scenario":[32],"is":[33,76,152],"transcribing":[34],"meeting":[36,164],"conversation":[37],"recorded":[38],"microphone":[41],"array.":[42],"Prior":[43],"studies":[44],"explored":[45],"various":[46],"deep":[47,86],"learning":[48,87],"models":[49],"for":[50,93],"time-frequency":[51],"mask":[52],"estimation,":[53],"followed":[54],"minimum":[57],"variance":[58],"distortionless":[59],"response":[60],"(MVDR)":[61],"filter":[62],"improve":[64],"the":[65,84,117,144,148,175,180],"automatic":[66],"recognition":[68],"(ASR)":[69],"accuracy.":[70],"The":[71,128],"performance":[72,99],"these":[74],"methods":[75],"fundamentally":[77],"upper-bounded":[78],"MVDR\u2019s":[80],"spatial":[81],"selectivity.":[82],"Recently,":[83],"all":[85],"MVDR":[88],"(ADL-MVDR)":[89],"model":[90],"was":[91],"proposed":[92,129,149],"neural":[94,126,150],"beamforming":[95],"and":[96,178],"demonstrated":[97],"superior":[98],"in":[100,162],"target":[102],"extraction":[104],"task":[105,119],"using":[106],"pre-segmented":[107],"input.":[108],"In":[109],"this":[110],"paper,":[111],"we":[112],"further":[113,173],"adapt":[114],"ADL-MVDR":[115],"CSS":[118],"with":[120,183],"several":[121],"enhancements":[122],"enable":[124],"end-to-end":[125],"beamforming.":[127],"system":[130,142,161,181],"achieves":[131],"significant":[132],"word":[133],"error":[134],"rate":[135],"reduction":[136],"over":[137],"baseline":[139],"spectral":[140],"masking":[141],"on":[143],"LibriCSS":[145],"dataset.":[146],"Moreover,":[147],"beamformer":[151],"shown":[153],"be":[155],"comparable":[156],"state-of-the-art":[159],"MVDR-based":[160],"real":[163],"transcription":[165],"tasks,":[166],"including":[167],"AMI,":[168],"while":[169],"showing":[170],"potentials":[171],"simplify":[174],"run-time":[176],"implementation":[177],"reduce":[179],"latency":[182],"frame-wise":[184],"processing.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}