{"id":"https://openalex.org/W3016094953","doi":"https://doi.org/10.1109/icassp40776.2020.9053833","title":"On End-to-end Multi-channel Time Domain Speech Separation in Reverberant Environments","display_name":"On End-to-end Multi-channel Time Domain Speech Separation in Reverberant Environments","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016094953","doi":"https://doi.org/10.1109/icassp40776.2020.9053833","mag":"3016094953"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.05958","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008123626","display_name":"Jisi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jisi Zhang","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044462635","display_name":"C\u0103t\u0103lin Zoril\u0103","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Catalin Zorila","raw_affiliation_strings":["Toshiba Cambridge Research Laboratory, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Toshiba Cambridge Research Laboratory, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086312107","display_name":"Rama Doddipatla","orcid":"https://orcid.org/0000-0003-1061-9512"},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rama Doddipatla","raw_affiliation_strings":["Toshiba Cambridge Research Laboratory, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Toshiba Cambridge Research Laboratory, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074458312","display_name":"Jon Barker","orcid":"https://orcid.org/0000-0002-1684-5660"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jon Barker","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008123626"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":4.8687,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.96077665,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6389","last_page":"6393"},"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":0.998199999332428,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9970999956130981,"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":0.8167179822921753},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.7380435466766357},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6710243821144104},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6666790246963501},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5667661428451538},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5440298318862915},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.516869068145752},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5049858689308167},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.49501127004623413},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.45360928773880005},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4477074146270752},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4281246066093445},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3881692588329315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37930136919021606},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.16997912526130676},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09977895021438599},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09166479110717773},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08729833364486694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8167179822921753},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7380435466766357},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6710243821144104},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6666790246963501},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5667661428451538},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5440298318862915},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.516869068145752},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5049858689308167},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.49501127004623413},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.45360928773880005},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4477074146270752},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4281246066093445},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3881692588329315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37930136919021606},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.16997912526130676},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09977895021438599},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09166479110717773},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08729833364486694},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.05958","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.05958","pdf_url":"https://arxiv.org/pdf/2011.05958","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.05958","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.05958","pdf_url":"https://arxiv.org/pdf/2011.05958","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1983812858","https://openalex.org/W2101045344","https://openalex.org/W2117678320","https://openalex.org/W2164502538","https://openalex.org/W2221409856","https://openalex.org/W2510642588","https://openalex.org/W2531409750","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2804228164","https://openalex.org/W2884797218","https://openalex.org/W2888867175","https://openalex.org/W2891283181","https://openalex.org/W2892163332","https://openalex.org/W2900893004","https://openalex.org/W2939360348","https://openalex.org/W2943934118","https://openalex.org/W2944972166","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962866211","https://openalex.org/W2963301902","https://openalex.org/W2963477857","https://openalex.org/W2963574857","https://openalex.org/W2968723745","https://openalex.org/W2972693890","https://openalex.org/W2973054567","https://openalex.org/W2996969697","https://openalex.org/W3099330747","https://openalex.org/W6631362777","https://openalex.org/W6688843265","https://openalex.org/W6725336789","https://openalex.org/W6748559479","https://openalex.org/W6759323020","https://openalex.org/W6762182681"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2022849831","https://openalex.org/W2037265366","https://openalex.org/W2026603686","https://openalex.org/W2331622705","https://openalex.org/W2391832549","https://openalex.org/W1562475690","https://openalex.org/W1488529827","https://openalex.org/W2112728813"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,49,118],"new":[4],"method":[5,52],"for":[6],"multi-channel":[7],"time":[8],"domain":[9],"speech":[10,26,80],"separation":[11,60,78,101],"in":[12],"reverberant":[13],"environments.":[14],"A":[15,62],"fully-convolutional":[16,96],"neural":[17],"network":[18,97],"structure":[19],"has":[20,53,68],"been":[21,54,69,88],"used":[22],"to":[23,56,71,128],"directly":[24],"separate":[25],"from":[27],"multiple":[28],"microphone":[29],"recordings,":[30],"with":[31,121],"no":[32],"need":[33],"of":[34,43,65,83],"conventional":[35,122],"spatial":[36,46],"feature":[37,47],"extraction.":[38],"To":[39],"reduce":[40,134],"the":[41,59,73,84,94,99,104,129,135],"influence":[42],"reverberation":[44],"on":[45,145],"extraction,":[48],"dereverberation":[50,125],"pre-processing":[51,127],"applied":[55],"further":[57,133],"improve":[58],"performance.":[61],"spatialized":[63],"version":[64],"wsj0-2mix":[66],"dataset":[67],"simulated":[70],"evaluate":[72],"proposed":[74,95,130],"system.":[75],"Both":[76],"source":[77,100],"and":[79,103,113,147],"recognition":[81],"performance":[82],"separated":[85],"signals":[86],"have":[87],"evaluated":[89],"objectively.":[90],"Experiments":[91],"show":[92],"that":[93],"improves":[98],"metric":[102],"word":[105],"error":[106],"rate":[107],"(WER)":[108],"by":[109,137],"more":[110],"than":[111],"13%":[112],"50%":[114],"relative,":[115],"respectively,":[116],"over":[117],"reference":[119],"system":[120,131],"features.":[123],"Applying":[124],"as":[126],"can":[132],"WER":[136],"29%":[138],"relative":[139],"using":[140],"an":[141],"acoustic":[142],"model":[143],"trained":[144],"clean":[146],"reverberated":[148],"data.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}