{"id":"https://openalex.org/W3095739951","doi":"https://doi.org/10.1109/slt48900.2021.9383604","title":"DESNet: A Multi-Channel Network for Simultaneous Speech Dereverberation, Enhancement and Separation","display_name":"DESNet: A Multi-Channel Network for Simultaneous Speech Dereverberation, Enhancement and Separation","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3095739951","doi":"https://doi.org/10.1109/slt48900.2021.9383604","mag":"3095739951"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.02131","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010250251","display_name":"Yihui Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihui Fu","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP), School of Computer Science,Xi\u2019an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP), School of Computer Science,Xi\u2019an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101674460","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3101-7011"},"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/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Speech and Language Group, Microsoft","Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP), School of Computer Science,Xi\u2019an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Speech and Language Group, Microsoft","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP), School of Computer Science,Xi\u2019an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101330960","display_name":"Yanxin Hu","orcid":"https://orcid.org/0009-0009-4388-8883"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanxin Hu","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP), School of Computer Science,Xi\u2019an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP), School of Computer Science,Xi\u2019an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049054911","display_name":"Mengtao Xing","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengtao Xing","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP), School of Computer Science,Xi\u2019an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP), School of Computer Science,Xi\u2019an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP), School of Computer Science,Xi\u2019an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP), School of Computer Science,Xi\u2019an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1813,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.28602982,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.998199999332428,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7850130200386047},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6810064315795898},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5336132049560547},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5263587236404419},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.5246667861938477},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5146682858467102},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.46040356159210205},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.42790094017982483},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4274669885635376},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.42408332228660583},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3863699734210968},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3632175624370575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3421734571456909},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15394273400306702},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12609624862670898},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.0896739661693573},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07394927740097046}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7850130200386047},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6810064315795898},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5336132049560547},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5263587236404419},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.5246667861938477},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5146682858467102},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.46040356159210205},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.42790094017982483},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4274669885635376},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.42408332228660583},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3863699734210968},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3632175624370575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3421734571456909},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15394273400306702},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12609624862670898},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0896739661693573},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07394927740097046},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/slt48900.2021.9383604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.02131","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02131","pdf_url":"https://arxiv.org/pdf/2011.02131","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},{"id":"mag:3095739951","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.02131.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.02131","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.02131","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/tkpm-9e58","is_oa":true,"landing_page_url":"https://doi.org/10.17023/tkpm-9e58","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.02131","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02131","pdf_url":"https://arxiv.org/pdf/2011.02131","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3095739951.pdf","grobid_xml":"https://content.openalex.org/works/W3095739951.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2221409856","https://openalex.org/W2242685705","https://openalex.org/W2563666542","https://openalex.org/W2603567530","https://openalex.org/W2747732471","https://openalex.org/W2888954542","https://openalex.org/W2891054259","https://openalex.org/W2897371647","https://openalex.org/W2939246703","https://openalex.org/W2952218014","https://openalex.org/W2952752702","https://openalex.org/W2964058413","https://openalex.org/W2972460025","https://openalex.org/W2972541922","https://openalex.org/W2972767900","https://openalex.org/W2998161426","https://openalex.org/W3002439978","https://openalex.org/W3008880747","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3015372568","https://openalex.org/W3015661721","https://openalex.org/W3016244460","https://openalex.org/W3016624877","https://openalex.org/W3028588916","https://openalex.org/W3046669506","https://openalex.org/W3083651055","https://openalex.org/W3096408984","https://openalex.org/W3096571892","https://openalex.org/W6772622344","https://openalex.org/W6774687970","https://openalex.org/W6775885218","https://openalex.org/W6778123894"],"related_works":["https://openalex.org/W3145364388","https://openalex.org/W2950073696","https://openalex.org/W3096073522","https://openalex.org/W2939777271","https://openalex.org/W3007256793","https://openalex.org/W3015756037","https://openalex.org/W3127555659","https://openalex.org/W3138190329","https://openalex.org/W2889224938","https://openalex.org/W3016094953","https://openalex.org/W3012980069","https://openalex.org/W3191985369","https://openalex.org/W3015661721","https://openalex.org/W3174609245","https://openalex.org/W3213305849","https://openalex.org/W2898826207","https://openalex.org/W3203119473","https://openalex.org/W2778508816","https://openalex.org/W2890720316","https://openalex.org/W2973934059"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,23],"propose":[4],"a":[5],"multi-channel":[6,31],"network":[7,52,66,93],"for":[8,75,88],"simultaneous":[9],"speech":[10,61,76,116],"dereverberation,":[11],"enhancement":[12,117],"and":[13,20,41,63,85,111,118],"separation":[14],"(DESNet).":[15],"To":[16],"enable":[17],"gradient":[18],"propagation":[19],"joint":[21],"optimization,":[22],"adopt":[24],"the":[25,30,46,57,60,64,81,89,92,97,106,129],"attentional":[26],"selection":[27],"mechanism":[28],"of":[29,59,91],"features,":[32],"which":[33],"is":[34,54,72],"originally":[35],"proposed":[36,107],"in":[37,103,115,121],"end-to-end":[38],"unmixing,":[39],"fixed-beamforming":[40],"extraction":[42],"(E2E-UFE)":[43],"structure.":[44],"Furthermore,":[45],"novel":[47],"deep":[48],"complex":[49],"convolutional":[50],"recurrent":[51],"(DCCRN)":[53],"used":[55],"as":[56],"structure":[58],"unmixing":[62],"neural":[65],"based":[67],"weighted":[68],"prediction":[69],"error":[70],"(WPE)":[71],"cascaded":[73,130],"before-hand":[74],"dereverberation.":[77],"We":[78],"also":[79,125],"introduce":[80],"staged":[82],"SNR":[83],"strategy":[84],"symphonic":[86],"loss":[87],"training":[90],"to":[94],"further":[95],"improve":[96],"final":[98],"performance.":[99],"Experiments":[100],"show":[101],"that":[102],"non-dereverberated":[104],"case,":[105],"DESNet":[108,124],"outperforms":[109],"DCCRN":[110],"most":[112],"state-of-the-art":[113],"structures":[114],"separation,":[119],"while":[120],"dereverberated":[122],"scenario,":[123],"shows":[126],"improvements":[127],"over":[128],"WPE-DCCRN":[131],"networks.":[132]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}