{"id":"https://openalex.org/W2939777271","doi":"https://doi.org/10.1109/icassp.2019.8683294","title":"Joint Optimization of Neural Network-based WPE Dereverberation and Acoustic Model for Robust Online ASR","display_name":"Joint Optimization of Neural Network-based WPE Dereverberation and Acoustic Model for Robust Online ASR","publication_year":2019,"publication_date":"2019-04-16","ids":{"openalex":"https://openalex.org/W2939777271","doi":"https://doi.org/10.1109/icassp.2019.8683294","mag":"2939777271"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006131416","display_name":"Jahn Heymann","orcid":null},"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":"Jahn Heymann","raw_affiliation_strings":["Department of Communications Engineering, Paderborn University, Paderborn, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Communications Engineering, Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011191228","display_name":"Lukas Drude","orcid":"https://orcid.org/0000-0003-3683-5432"},"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":"Lukas Drude","raw_affiliation_strings":["Department of Communications Engineering, Paderborn University, Paderborn, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Communications Engineering, Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","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":["Department of Communications Engineering, Paderborn University, Paderborn, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Communications Engineering, Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"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 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/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"]}]}],"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":32,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6655","last_page":"6659"},"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":0.9991999864578247,"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":0.9973999857902527,"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":0.8241051435470581},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6325530409812927},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6282775402069092},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5559096932411194},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.46914783120155334},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3660821318626404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3109945058822632},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.13533034920692444},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09314030408859253}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8241051435470581},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6325530409812927},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6282775402069092},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5559096932411194},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.46914783120155334},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3660821318626404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3109945058822632},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.13533034920692444},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09314030408859253},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1983812858","https://openalex.org/W1989314204","https://openalex.org/W2117090122","https://openalex.org/W2130722890","https://openalex.org/W2147166770","https://openalex.org/W2289912446","https://openalex.org/W2510942155","https://openalex.org/W2591355762","https://openalex.org/W2622203030","https://openalex.org/W2640112133","https://openalex.org/W2747732471","https://openalex.org/W2748661748","https://openalex.org/W2899625056","https://openalex.org/W2963197115","https://openalex.org/W2966212213","https://openalex.org/W4302156456","https://openalex.org/W6766380642","https://openalex.org/W6766475400"],"related_works":["https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W4287880334","https://openalex.org/W4366700029","https://openalex.org/W4285230481","https://openalex.org/W4385769873","https://openalex.org/W4281634296","https://openalex.org/W4319161863","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Signal":[0],"dereverberation":[1,162],"using":[2,78],"the":[3,19,53,56,62,101,125,129,133,139,143,147,152,160,166,188,195],"Weighted":[4],"Prediction":[5],"Error":[6],"(WPE)":[7],"method":[8],"has":[9],"been":[10],"proven":[11],"to":[12,17,85,119,165],"be":[13,137],"an":[14,28,66],"effective":[15],"means":[16],"raise":[18],"accuracy":[20],"of":[21,55,61,132,197],"far-field":[22],"speech":[23,91,134],"recognition.":[24,92],"First":[25],"proposed":[26],"as":[27,36],"iterative":[29],"algorithm,":[30,52],"follow-up":[31],"works":[32],"have":[33],"reformulated":[34],"it":[35],"a":[37,79,97],"recursive":[38],"least":[39],"squares":[40],"algorithm":[41],"and":[42,69,113,151,192],"therefore":[43],"enabled":[44],"its":[45,72],"use":[46],"in":[47,111],"online":[48,89],"applications.":[49,198],"For":[50],"this":[51,121],"estimation":[54,164],"power":[57],"spectral":[58],"density":[59],"(PSD)":[60],"anechoic":[63],"signal":[64],"plays":[65],"important":[67],"role":[68],"strongly":[70],"influences":[71],"performance.":[73],"Recently,":[74],"we":[75,103,117],"showed":[76],"that":[77],"neural":[80,167],"network":[81,126,155,168],"PSD":[82,170],"estimator":[83],"leads":[84],"improved":[86,177],"performance":[87,178],"for":[88,169,179],"automatic":[90],"This,":[93],"however,":[94],"comes":[95],"at":[96],"price.":[98],"To":[99,136],"train":[100],"network,":[102],"require":[104],"parallel":[105],"data,":[106],"i.e.,":[107],"utterances":[108],"simultaneously":[109],"available":[110,189],"clean":[112],"reverberated":[114],"form.":[115],"Here":[116],"propose":[118],"overcome":[120],"limitation":[122],"by":[123],"training":[124,190],"jointly":[127],"with":[128],"acoustic":[130,153],"model":[131,154],"recognizer.":[135],"specific,":[138],"gradients":[140],"computed":[141],"from":[142],"cross-entropy":[144],"loss":[145],"between":[146],"target":[148],"senone":[149],"sequence":[150],"output":[156],"is":[157],"backpropagated":[158],"through":[159],"complex-valued":[161],"filter":[163],"estimation.":[171],"Evaluation":[172],"on":[173,187],"two":[174],"databases":[175],"demonstrates":[176],"on-line":[180],"processing":[181],"scenarios":[182],"while":[183],"imposing":[184],"fewer":[185],"requirements":[186],"data":[191],"thus":[193],"widening":[194],"range":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}