{"id":"https://openalex.org/W3131201176","doi":"https://doi.org/10.1109/icassp39728.2021.9414464","title":"End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend","display_name":"End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3131201176","doi":"https://doi.org/10.1109/icassp39728.2021.9414464","mag":"3131201176"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414464","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":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2102.11525","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,MoE Key Lab of Artificial Intelligence,AI Institute, SpeechLab,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,AI Institute, SpeechLab,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064522438","display_name":"Christoph Boeddeker","orcid":"https://orcid.org/0000-0002-8701-1567"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christoph Boeddeker","raw_affiliation_strings":["Paderbom University,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Paderbom University,Germany","institution_ids":[]}]},{"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,USA","[Johns Hopkins University,USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"[Johns Hopkins University,USA]","institution_ids":["https://openalex.org/I145311948"]}]},{"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"],"raw_orcid":null,"affiliations":[{"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"],"raw_orcid":null,"affiliations":[{"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"],"raw_orcid":null,"affiliations":[{"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"],"raw_orcid":null,"affiliations":[{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":["Paderbom University,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Paderbom University,Germany","institution_ids":[]}]},{"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,MoE Key Lab of Artificial Intelligence,AI Institute, SpeechLab,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,AI Institute, SpeechLab,China","institution_ids":["https://openalex.org/I183067930"]}]}],"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":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6898","last_page":"6902"},"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":0.9988999962806702,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9965000152587891,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.738813042640686},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7298485636711121},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7241572141647339},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6417519450187683},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6038193702697754},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4897732734680176},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.48902830481529236},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4279959499835968},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4252833127975464},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4159051179885864},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2600742280483246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2223168909549713},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15166354179382324},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0942898690700531},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08006125688552856}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.738813042640686},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7298485636711121},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7241572141647339},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6417519450187683},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6038193702697754},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4897732734680176},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.48902830481529236},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4279959499835968},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4252833127975464},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4159051179885864},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2600742280483246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2223168909549713},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15166354179382324},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0942898690700531},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08006125688552856},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414464","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":"doi:10.48550/arxiv.2102.11525","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.11525","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":"article-journal"},{"id":"doi:10.17023/2vcq-k348","is_oa":true,"landing_page_url":"https://doi.org/10.17023/2vcq-k348","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:3131201176","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":"doi:10.48550/arxiv.2102.11525","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.11525","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":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8399999737739563,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307764","display_name":"Microsoft","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1991139021","https://openalex.org/W2041256929","https://openalex.org/W2060108923","https://openalex.org/W2062572859","https://openalex.org/W2152536723","https://openalex.org/W2164502538","https://openalex.org/W2283145987","https://openalex.org/W2289480995","https://openalex.org/W2398042854","https://openalex.org/W2398972335","https://openalex.org/W2460742184","https://openalex.org/W2516001803","https://openalex.org/W2517616541","https://openalex.org/W2526425061","https://openalex.org/W2595142274","https://openalex.org/W2600628583","https://openalex.org/W2622589392","https://openalex.org/W2640112133","https://openalex.org/W2714509385","https://openalex.org/W2747732471","https://openalex.org/W2767071179","https://openalex.org/W2794289187","https://openalex.org/W2890244912","https://openalex.org/W2891405874","https://openalex.org/W2902894493","https://openalex.org/W2905402910","https://openalex.org/W2939777271","https://openalex.org/W2940526039","https://openalex.org/W2962715207","https://openalex.org/W2963197115","https://openalex.org/W2972460025","https://openalex.org/W2972818416","https://openalex.org/W3002595344","https://openalex.org/W3008762051","https://openalex.org/W3008880747","https://openalex.org/W3015199127","https://openalex.org/W3015306655","https://openalex.org/W3015834770","https://openalex.org/W3026041220","https://openalex.org/W3096073522","https://openalex.org/W3098052090","https://openalex.org/W6666139384","https://openalex.org/W6734797129","https://openalex.org/W6735168207","https://openalex.org/W6761806390","https://openalex.org/W6766380642","https://openalex.org/W6774687970"],"related_works":["https://openalex.org/W3162315798","https://openalex.org/W34570267","https://openalex.org/W25872593","https://openalex.org/W1982846521","https://openalex.org/W3010738343","https://openalex.org/W2951228927","https://openalex.org/W2112748425","https://openalex.org/W2711335087","https://openalex.org/W149263754","https://openalex.org/W1820182450","https://openalex.org/W2972033414","https://openalex.org/W1600171372","https://openalex.org/W3205415598","https://openalex.org/W2175027794","https://openalex.org/W2737400496","https://openalex.org/W2902298602","https://openalex.org/W2116590962","https://openalex.org/W2789949544","https://openalex.org/W2076893062","https://openalex.org/W2033793417"],"abstract_inverted_index":{"Recently,":[0],"the":[1,28,52,89,96,102,133,141],"end-to-end":[2,65,90],"approach":[3],"has":[4],"been":[5],"successfully":[6],"applied":[7],"to":[8,59,112],"multi-speaker":[9,54,135],"speech":[10,69,123],"separation":[11,126],"and":[12,17,30,33,43,57,68,75,119,125],"recognition":[13,70],"in":[14,27,132],"both":[15],"singlechannel":[16],"multichannel":[18,53],"conditions.":[19,45],"However,":[20],"severe":[21],"performance":[22,39,127],"degradation":[23],"is":[24,35],"still":[25,36],"observed":[26],"reverberant":[29,44,55,134],"noisy":[31],"scenarios,":[32],"there":[34],"a":[37],"large":[38],"gap":[40],"between":[41],"anechoic":[42],"In":[46],"this":[47],"work,":[48],"we":[49],"focus":[50],"on":[51,95],"condition,":[56],"propose":[58],"extend":[60],"our":[61,113],"previous":[62],"framework":[63],"for":[64],"dereverberation,":[66],"beamforming,":[67],"with":[71,140],"improved":[72],"numerical":[73],"stability":[74],"advanced":[76],"frontend":[77],"subnetworks":[78],"including":[79],"voice":[80],"activity":[81],"detection":[82],"like":[83],"masks.":[84],"The":[85,93],"techniques":[86],"significantly":[87],"stabilize":[88],"training":[91],"process.":[92],"experiments":[94],"spatialized":[97],"wsj1-2mix":[98],"corpus":[99],"show":[100],"that":[101],"proposed":[103],"system":[104],"achieves":[105],"about":[106],"35%":[107],"WER":[108],"relative":[109],"reduction":[110],"compared":[111],"conventional":[114],"multi-channel":[115],"E2E":[116],"ASR":[117,142],"system,":[118],"also":[120],"obtains":[121],"decent":[122],"dereverberation":[124],"(SDR":[128],"=":[129],"12.5":[130],"dB)":[131],"condition":[136],"while":[137],"trained":[138],"only":[139],"criterion.":[143]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}