{"id":"https://openalex.org/W3108100693","doi":"https://doi.org/10.1109/icassp39728.2021.9414661","title":"Convolutive Transfer Function Invariant SDR Training Criteria for Multi-Channel Reverberant Speech Separation","display_name":"Convolutive Transfer Function Invariant SDR Training Criteria for Multi-Channel Reverberant Speech Separation","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3108100693","doi":"https://doi.org/10.1109/icassp39728.2021.9414661","mag":"3108100693"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/2011.15003","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064522438","display_name":"Christoph Boeddeker","orcid":"https://orcid.org/0000-0002-8701-1567"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Boeddeker","raw_affiliation_strings":["Paderborn University, Paderborn, Germany","Paderborn University,Department of Communications Engineering,Paderborn,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]},{"raw_affiliation_string":"Paderborn University,Department of Communications Engineering,Paderborn,Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071937621","display_name":"Wangyou Zhang","orcid":"https://orcid.org/0000-0003-4500-3515"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangyou Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, China","Shanghai Jiao Tong University,SpeechLab,Department of Computer Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University,SpeechLab,Department of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I183067930"]}]},{"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 Corporation, Japan","NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"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":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Corporation, Japan","NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070624983","display_name":"Tsubasa Ochiai","orcid":"https://orcid.org/0000-0002-2519-2032"},"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":"Tsubasa Ochiai","raw_affiliation_strings":["NTT Corporation, Japan","NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"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 Corporation, Japan","NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034382743","display_name":"Naoyuki Kamo","orcid":null},"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":"Naoyuki Kamo","raw_affiliation_strings":["NTT Corporation, Japan","NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University, China","Shanghai Jiao Tong University,SpeechLab,Department of Computer Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University,SpeechLab,Department of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":["Paderborn University, Paderborn, Germany","Paderborn University,Department of Communications Engineering,Paderborn,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]},{"raw_affiliation_string":"Paderborn University,Department of Communications Engineering,Paderborn,Germany","institution_ids":["https://openalex.org/I206945453"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8428","last_page":"8432"},"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":0.9987999796867371,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9980999827384949,"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/beamforming","display_name":"Beamforming","score":0.6162872314453125},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5676814913749695},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.539786696434021},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5355422496795654},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5066981911659241},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4948350787162781},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.44249486923217773},{"id":"https://openalex.org/keywords/transfer-function","display_name":"Transfer function","score":0.4422457218170166},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34971684217453003},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3261029124259949},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.16775363683700562},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12406334280967712},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11669397354125977},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.090119868516922}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6162872314453125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5676814913749695},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.539786696434021},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5355422496795654},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5066981911659241},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4948350787162781},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.44249486923217773},{"id":"https://openalex.org/C81299745","wikidata":"https://www.wikidata.org/wiki/Q334269","display_name":"Transfer function","level":2,"score":0.4422457218170166},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34971684217453003},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3261029124259949},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.16775363683700562},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12406334280967712},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11669397354125977},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.090119868516922},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.15003","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.15003","pdf_url":"https://arxiv.org/pdf/2011.15003","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2011.15003","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.15003","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:10.17023/4r4j-sh68","is_oa":true,"landing_page_url":"https://doi.org/10.17023/4r4j-sh68","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"},{"id":"mag:3108100693","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.15003","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.15003","pdf_url":"https://arxiv.org/pdf/2011.15003","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3108100693.pdf","grobid_xml":"https://content.openalex.org/works/W3108100693.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1902027874","https://openalex.org/W1982172017","https://openalex.org/W1987906574","https://openalex.org/W2060108923","https://openalex.org/W2099741732","https://openalex.org/W2117678320","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2155515171","https://openalex.org/W2170768669","https://openalex.org/W2221409856","https://openalex.org/W2591810467","https://openalex.org/W2640112133","https://openalex.org/W2699350432","https://openalex.org/W2714509385","https://openalex.org/W2734774145","https://openalex.org/W2891997645","https://openalex.org/W2892163332","https://openalex.org/W2942172990","https://openalex.org/W2962780374","https://openalex.org/W2962935966","https://openalex.org/W2964058413","https://openalex.org/W2971417062","https://openalex.org/W2972818416","https://openalex.org/W2982456909","https://openalex.org/W3008762051","https://openalex.org/W3015843733","https://openalex.org/W3098606562","https://openalex.org/W4205370808","https://openalex.org/W6682646797","https://openalex.org/W6769802879"],"related_works":["https://openalex.org/W3163217847","https://openalex.org/W3095507987","https://openalex.org/W2945926039","https://openalex.org/W3151596526","https://openalex.org/W2606569801","https://openalex.org/W3195155284","https://openalex.org/W2166772024","https://openalex.org/W2777466939","https://openalex.org/W3080704265","https://openalex.org/W2734288477","https://openalex.org/W2778508816","https://openalex.org/W2899990587","https://openalex.org/W2053371020","https://openalex.org/W1983554408","https://openalex.org/W1494622171","https://openalex.org/W1893646033","https://openalex.org/W2151876174","https://openalex.org/W2714359112","https://openalex.org/W2243943790","https://openalex.org/W1592139864"],"abstract_inverted_index":{"Time-domain":[0],"training":[1,46,82,131],"criteria":[2],"have":[3],"proven":[4],"to":[5,35,54],"be":[6],"very":[7],"effective":[8],"for":[9],"the":[10,50,87,91,101,105],"separation":[11,42],"of":[12,120],"single-channel":[13],"non-reverberant":[14,111],"speech":[15,27],"mixtures.":[16,97],"Likewise,":[17],"mask-based":[18],"beamforming":[19],"has":[20,76],"shown":[21],"impressive":[22],"performance":[23,92],"in":[24],"multi-channel":[25,40],"reverberant":[26,96],"enhancement":[28],"and":[29,134],"source":[30,41],"separation.":[31],"Here,":[32],"we":[33,52,89],"propose":[34,53],"combine":[36],"neural":[37],"network":[38],"supported":[39],"with":[43,117],"a":[44,56,69,81,118,127,143],"time-domain":[45],"objective":[47,51,83],"function.":[48],"For":[49],"use":[55],"convolutive":[57],"transfer":[58],"function":[59],"invariant":[60,130],"Signal-to-Distortion":[61,140],"Ratio":[62,141],"(CI-SDR)":[63],"based":[64,95,132],"loss.":[65],"While":[66],"this":[67,99],"is":[68],"well-known":[70],"evaluation":[71],"metric":[72],"(BSS":[73],"Eval),":[74],"it":[75],"not":[77],"been":[78],"used":[79],"as":[80],"before.":[84],"To":[85],"show":[86],"effectiveness,":[88],"demonstrate":[90],"on":[93,109],"LibriSpeech":[94,114],"On":[98],"task,":[100],"proposed":[102],"system":[103,133],"approaches":[104],"error":[106],"rate":[107],"obtained":[108],"single-source":[110],"input,":[112],"i.e.,":[113],"test":[115],"clean,":[116],"difference":[119],"only":[121],"1.2":[122],"percentage":[123],"points,":[124],"thus":[125],"outperforming":[126],"conventional":[128],"permutation":[129],"alternative":[135],"objectives":[136],"like":[137],"Scale":[138],"Invariant":[139],"by":[142],"large":[144],"margin.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-07-25T00:00:00"}