{"id":"https://openalex.org/W3026939869","doi":"https://doi.org/10.21437/interspeech.2020-2432","title":"End-to-End Far-Field Speech Recognition with Unified Dereverberation and Beamforming","display_name":"End-to-End Far-Field Speech Recognition with Unified Dereverberation and Beamforming","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3026939869","doi":"https://doi.org/10.21437/interspeech.2020-2432","mag":"3026939869"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2432","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/2005.10479","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048730867","display_name":"Aswin Shanmugam Subramanian","orcid":"https://orcid.org/0000-0003-4446-001X"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aswin Shanmugam Subramanian","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"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":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"324","last_page":"328"},"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":0.9990000128746033,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9966999888420105,"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":0.751217246055603},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7089905738830566},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6855639219284058},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6047356724739075},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5255050659179688},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.4737618565559387},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4444253742694855},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.41502296924591064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23409754037857056},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1635074019432068},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15996837615966797},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13362690806388855},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.09957310557365417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.751217246055603},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7089905738830566},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6855639219284058},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6047356724739075},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5255050659179688},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.4737618565559387},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4444253742694855},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.41502296924591064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23409754037857056},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1635074019432068},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15996837615966797},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13362690806388855},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.09957310557365417},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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":4,"locations":[{"id":"doi:10.21437/interspeech.2020-2432","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.10479","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.10479","pdf_url":"https://arxiv.org/pdf/2005.10479","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":"doi:10.48550/arxiv.2005.10479","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2005.10479","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":"article-journal"},{"id":"mag:3026939869","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:2005.10479","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.10479","pdf_url":"https://arxiv.org/pdf/2005.10479","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":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W102482883","https://openalex.org/W1989314204","https://openalex.org/W2039553327","https://openalex.org/W2042141988","https://openalex.org/W2173850849","https://openalex.org/W2184045248","https://openalex.org/W2288645994","https://openalex.org/W2398042854","https://openalex.org/W2460742184","https://openalex.org/W2517616541","https://openalex.org/W2526425061","https://openalex.org/W2600628583","https://openalex.org/W2609317876","https://openalex.org/W2734774145","https://openalex.org/W2747732471","https://openalex.org/W2771275309","https://openalex.org/W2797187289","https://openalex.org/W2886180730","https://openalex.org/W2916979304","https://openalex.org/W2939777271","https://openalex.org/W2940526039","https://openalex.org/W2962715207","https://openalex.org/W2962780374","https://openalex.org/W2963477857","https://openalex.org/W2972818416","https://openalex.org/W2982471419","https://openalex.org/W2998438979","https://openalex.org/W2998616931","https://openalex.org/W3008762051","https://openalex.org/W3015834770","https://openalex.org/W3016400019","https://openalex.org/W3017474798","https://openalex.org/W3098052090","https://openalex.org/W3151596526"],"related_works":["https://openalex.org/W3096073522","https://openalex.org/W3007256793","https://openalex.org/W3167822394","https://openalex.org/W3016094953","https://openalex.org/W2166772024","https://openalex.org/W3095739951","https://openalex.org/W2950073696","https://openalex.org/W1605657850","https://openalex.org/W2939777271","https://openalex.org/W3015661721","https://openalex.org/W3138190329","https://openalex.org/W3191985369","https://openalex.org/W2133908567","https://openalex.org/W3127555659","https://openalex.org/W2889224938","https://openalex.org/W3102070904","https://openalex.org/W2778508816","https://openalex.org/W2152158092","https://openalex.org/W2734353505","https://openalex.org/W3012980069"],"abstract_inverted_index":{"Despite":[0],"successful":[1],"applications":[2],"of":[3],"end-to-end":[4,32,122],"approaches":[5],"in":[6,54,119,147],"multi-channel":[7,33],"speech":[8,17,34,127],"recognition,":[9],"the":[10,16,27,31,55,68,89,102,108,126,144],"performance":[11],"still":[12],"degrades":[13],"severely":[14],"when":[15],"is":[18,52,64],"corrupted":[19],"by":[20],"reverberation.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25],"integrate":[26],"dereverberation":[28],"module":[29,51],"into":[30],"recognition":[35,128],"system":[36],"and":[37,81,97,136],"explore":[38],"two":[39,115],"different":[40],"frontend":[41,56,62],"architectures.":[42],"First,":[43],"a":[44,85,120],"multi-source":[45,95],"mask-based":[46],"weighted":[47,69],"prediction":[48],"error":[49],"(WPE)":[50],"incorporated":[53],"for":[57],"dereverberation.":[58,82],"Second,":[59],"another":[60],"novel":[61],"architecture":[63],"proposed,":[65],"which":[66,92],"extends":[67],"power":[70],"minimization":[71],"distortionless":[72],"response":[73],"(WPD)":[74],"convolutional":[75],"beamformer":[76],"to":[77,106],"perform":[78],"simultaneous":[79],"separation":[80],"We":[83],"derive":[84],"new":[86],"formulation":[87],"from":[88],"original":[90],"WPD,":[91],"can":[93],"handle":[94],"input,":[96],"replace":[98],"eigenvalue":[99],"decomposition":[100],"with":[101],"matrix":[103],"inverse":[104],"operation":[105],"make":[107],"back-propagation":[109],"algorithm":[110],"more":[111],"stable.":[112],"The":[113],"above":[114],"architectures":[116],"are":[117],"optimized":[118],"fully":[121],"manner,":[123],"only":[124],"using":[125],"criterion.":[129],"Experiments":[130],"on":[131],"both":[132],"spatialized":[133],"wsj1-2mix":[134],"corpus":[135],"REVERB":[137],"show":[138],"that":[139],"our":[140],"proposed":[141],"model":[142],"outperformed":[143],"conventional":[145],"methods":[146],"reverberant":[148],"scenarios.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}