{"id":"https://openalex.org/W2803322398","doi":"https://doi.org/10.1109/icassp.2018.8462081","title":"Multi-Microphone Neural Speech Separation for Far-Field Multi-Talker Speech Recognition","display_name":"Multi-Microphone Neural Speech Separation for Far-Field Multi-Talker Speech Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2803322398","doi":"https://doi.org/10.1109/icassp.2018.8462081","mag":"2803322398"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462081","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/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 and Research, One Microsoft Way, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, One Microsoft Way, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065994318","display_name":"Hakan Erdo\u011fan","orcid":"https://orcid.org/0000-0003-3140-8642"},"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":"Hakan Erdogan","raw_affiliation_strings":["Microsoft AI and Research, One Microsoft Way, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, One Microsoft Way, Redmond, WA","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 AI and Research, One Microsoft Way, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, One Microsoft Way, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109977451","display_name":"Fil Alleva","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":"Fil Alleva","raw_affiliation_strings":["Microsoft AI and Research, One Microsoft Way, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, One Microsoft Way, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.3064,"has_fulltext":false,"cited_by_count":109,"citation_normalized_percentile":{"value":0.98931109,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5739","last_page":"5743"},"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":0.9977999925613403,"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/microphone","display_name":"Microphone","score":0.8053511381149292},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7458059191703796},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7235788702964783},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5907520055770874},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5637753009796143},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.5575794577598572},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5263396501541138},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5076156854629517},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45926228165626526},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4207102358341217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4056828022003174},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35994574427604675},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07641667127609253}],"concepts":[{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.8053511381149292},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7458059191703796},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7235788702964783},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5907520055770874},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5637753009796143},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.5575794577598572},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5263396501541138},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5076156854629517},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45926228165626526},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4207102358341217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4056828022003174},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35994574427604675},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07641667127609253},{"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/icassp.2018.8462081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462081","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W285277413","https://openalex.org/W1974343358","https://openalex.org/W2014768838","https://openalex.org/W2031583051","https://openalex.org/W2042860487","https://openalex.org/W2043216213","https://openalex.org/W2113679114","https://openalex.org/W2167689159","https://openalex.org/W2168729028","https://openalex.org/W2221409856","https://openalex.org/W2288645994","https://openalex.org/W2407022425","https://openalex.org/W2517616541","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2745634895","https://openalex.org/W2747357425","https://openalex.org/W2750380122","https://openalex.org/W2750446090","https://openalex.org/W2962894366","https://openalex.org/W6677000115"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2380771148","https://openalex.org/W2900122540","https://openalex.org/W2396048001","https://openalex.org/W4408354526","https://openalex.org/W4240587264","https://openalex.org/W2348931051"],"abstract_inverted_index":{"This":[0,35],"paper":[1],"describes":[2],"a":[3,90,98],"neural":[4],"network":[5],"approach":[6,16,80,118],"to":[7,22,60],"far-field":[8],"speech":[9,33,52,85,105],"separation":[10,106],"using":[11],"multiple":[12],"microphones.":[13],"Our":[14,103],"proposed":[15,49,79,117],"is":[17,36,58,66,81],"speaker-independent":[18],"and":[19,96],"can":[20],"learn":[21],"implicitly":[23],"figure":[24],"out":[25],"the":[26,40,78,110,116],"number":[27],"of":[28,77,93,100,115],"speakers":[29],"constituting":[30],"an":[31],"input":[32],"mixture.":[34],"realized":[37],"by":[38,83],"utilizing":[39],"permutation":[41],"invariant":[42],"training":[43,94],"(PIT)":[44],"framework,":[45],"which":[46],"was":[47],"recently":[48],"for":[50,71],"single-microphone":[51,111],"separation.":[53],"In":[54],"this":[55],"paper,":[56],"PIT":[57],"extended":[59],"effectively":[61],"leverage":[62],"multi-microphone":[63,104],"input.":[64],"It":[65],"also":[67],"combined":[68],"with":[69],"beamforming":[70],"better":[72],"recognition":[73,86],"accuracy.":[74],"The":[75],"effectiveness":[76],"investigated":[82],"multi-talker":[84],"experiments":[87],"that":[88],"use":[89],"large":[91],"quantity":[92],"data":[95],"encompass":[97],"range":[99],"mixing":[101],"conditions.":[102],"system":[107],"significantly":[108],"outperforms":[109],"PIT.":[112],"Several":[113],"aspects":[114],"are":[119],"experimentally":[120],"investigated.":[121]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":32},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}