{"id":"https://openalex.org/W3107565136","doi":"https://doi.org/10.1109/slt48900.2021.9383612","title":"Integration of Variational Autoencoder and Spatial Clustering for Adaptive Multi-Channel Neural Speech Separation","display_name":"Integration of Variational Autoencoder and Spatial Clustering for Adaptive Multi-Channel Neural Speech Separation","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3107565136","doi":"https://doi.org/10.1109/slt48900.2021.9383612","mag":"3107565136"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383612","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/2011.11984","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067790073","display_name":"Kate\u0159ina \u017dmol\u00edkov\u00e1","orcid":"https://orcid.org/0000-0003-4438-8580"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Katerina Zmolikova","raw_affiliation_strings":["Faculty of IT, IT4I Centre of Excellence, Brno University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of IT, IT4I Centre of Excellence, Brno University of Technology","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Faculty of IT, IT4I Centre of Excellence, Brno University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of IT, IT4I Centre of Excellence, Brno University of Technology","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Honza Cernocky","raw_affiliation_strings":["Faculty of IT, IT4I Centre of Excellence, Brno University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of IT, IT4I Centre of Excellence, Brno University of Technology","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/autoencoder","display_name":"Autoencoder","score":0.8903841972351074},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7301062941551208},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6504759192466736},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6088961362838745},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5291830897331238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5120032429695129},{"id":"https://openalex.org/keywords/factorial","display_name":"Factorial","score":0.4942004978656769},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.47813212871551514},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46345043182373047},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4495674967765808},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44603753089904785},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4138898253440857},{"id":"https://openalex.org/keywords/spectral-clustering","display_name":"Spectral clustering","score":0.4110450744628906},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32126384973526},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.23343899846076965},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22206321358680725},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09859669208526611}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8903841972351074},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7301062941551208},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6504759192466736},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6088961362838745},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5291830897331238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5120032429695129},{"id":"https://openalex.org/C183763347","wikidata":"https://www.wikidata.org/wiki/Q120976","display_name":"Factorial","level":2,"score":0.4942004978656769},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.47813212871551514},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46345043182373047},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4495674967765808},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44603753089904785},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4138898253440857},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.4110450744628906},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32126384973526},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.23343899846076965},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22206321358680725},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09859669208526611},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/slt48900.2021.9383612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383612","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:2011.11984","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.11984","pdf_url":"https://arxiv.org/pdf/2011.11984","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"},{"id":"mag:3107565136","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.11984.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.11984","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.11984","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/g2a1-v563","is_oa":true,"landing_page_url":"https://doi.org/10.17023/g2a1-v563","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:2011.11984","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.11984","pdf_url":"https://arxiv.org/pdf/2011.11984","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/10","display_name":"Reduced inequalities","score":0.7599999904632568}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3107565136.pdf","grobid_xml":"https://content.openalex.org/works/W3107565136.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1819207621","https://openalex.org/W1909320841","https://openalex.org/W1989954041","https://openalex.org/W2018205510","https://openalex.org/W2021553162","https://openalex.org/W2024490156","https://openalex.org/W2031583051","https://openalex.org/W2043216213","https://openalex.org/W2079362249","https://openalex.org/W2129171989","https://openalex.org/W2168729028","https://openalex.org/W2221409856","https://openalex.org/W2398042854","https://openalex.org/W2460742184","https://openalex.org/W2465697055","https://openalex.org/W2517616541","https://openalex.org/W2563666542","https://openalex.org/W2702006285","https://openalex.org/W2750446090","https://openalex.org/W2766672686","https://openalex.org/W2883322837","https://openalex.org/W2889503488","https://openalex.org/W2892163332","https://openalex.org/W2900212944","https://openalex.org/W2901552243","https://openalex.org/W2905196628","https://openalex.org/W2922004249","https://openalex.org/W2942172990","https://openalex.org/W2943237054","https://openalex.org/W2951004968","https://openalex.org/W2952218014","https://openalex.org/W2963618559","https://openalex.org/W2972530081","https://openalex.org/W2982840733","https://openalex.org/W3011982609","https://openalex.org/W3016400019","https://openalex.org/W3100968126","https://openalex.org/W6639732818","https://openalex.org/W6640963894","https://openalex.org/W6661582794","https://openalex.org/W6714030504","https://openalex.org/W6719417910","https://openalex.org/W6745117592","https://openalex.org/W6775537894"],"related_works":["https://openalex.org/W2912829682","https://openalex.org/W2943678367","https://openalex.org/W3129724288","https://openalex.org/W2970947734","https://openalex.org/W2912987408","https://openalex.org/W3011930947","https://openalex.org/W3186137048","https://openalex.org/W3158921892","https://openalex.org/W2091964862","https://openalex.org/W2295537791","https://openalex.org/W3037803052","https://openalex.org/W2512601085","https://openalex.org/W1174626372","https://openalex.org/W2963146253","https://openalex.org/W2802172308","https://openalex.org/W3162217009","https://openalex.org/W2540940674","https://openalex.org/W2974692022","https://openalex.org/W3117848197","https://openalex.org/W3092661407"],"abstract_inverted_index":{"In":[0,56],"this":[1],"paper,":[2],"we":[3,59,83],"propose":[4],"a":[5,14,29,68,73,77,98,102],"method":[6],"combining":[7],"variational":[8,78],"autoencoder":[9],"model":[10,31,70,103,120,130,135,140],"of":[11,24,48,63,89,118,146],"speech":[12,20,51],"with":[13,28,150],"spatial":[15,26,151],"clustering":[16,27],"approach":[17],"for":[18],"multi-channel":[19],"separation.":[21],"The":[22],"advantage":[23],"integrating":[25],"spectral":[30,39],"was":[32],"shown":[33],"in":[34],"several":[35],"works.":[36],"As":[37],"the":[38,49,61,86,94,115,119],"model,":[40],"previous":[41,133],"works":[42],"used":[43],"either":[44],"factorial":[45,69,134],"generative":[46,74],"models":[47],"mixed":[50],"or":[52],"discriminative":[53],"neural":[54,75,90],"networks.":[55],"our":[57,129],"work,":[58],"combine":[60],"strengths":[62],"both":[64],"approaches,":[65],"by":[66],"building":[67],"based":[71,136],"on":[72,137],"network,":[76],"autoencoder.":[79],"By":[80],"doing":[81],"so,":[82],"can":[84,104],"exploit":[85],"modeling":[87],"power":[88],"networks,":[91],"but":[92],"at":[93],"same":[95],"time,":[96],"keep":[97],"structured":[99],"model.":[100],"Such":[101],"be":[105,123],"advantageous":[106],"when":[107],"adapting":[108],"to":[109,122,144,156,159],"new":[110,160],"noise":[111,116,161],"conditions":[112],"as":[113],"only":[114],"part":[117],"needs":[121],"modified.":[124],"We":[125],"show":[126],"experimentally,":[127],"that":[128],"significantly":[131],"outperforms":[132],"Gaussian":[138],"mixture":[139],"(DOLPHIN),":[141],"performs":[142],"comparably":[143],"integration":[145],"permutation":[147],"invariant":[148],"training":[149],"clustering,":[152],"and":[153],"enables":[154],"us":[155],"easily":[157],"adapt":[158],"conditions.":[162]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}