{"id":"https://openalex.org/W3160983285","doi":"https://doi.org/10.1109/icassp39728.2021.9413499","title":"Neural Kalman Filtering for Speech Enhancement","display_name":"Neural Kalman Filtering for Speech Enhancement","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160983285","doi":"https://doi.org/10.1109/icassp39728.2021.9413499","mag":"3160983285"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413499","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":"article","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/A5100652844","display_name":"Wei Xue","orcid":"https://orcid.org/0000-0002-4942-7748"},"institutions":[{"id":"https://openalex.org/I72427458","display_name":"JDSU (United States)","ror":"https://ror.org/01a5v8x09","country_code":"US","type":"company","lineage":["https://openalex.org/I72427458"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wei Xue","raw_affiliation_strings":["JD AI Research"],"affiliations":[{"raw_affiliation_string":"JD AI Research","institution_ids":["https://openalex.org/I72427458"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090912445","display_name":"Gang Quan","orcid":null},"institutions":[{"id":"https://openalex.org/I72427458","display_name":"JDSU (United States)","ror":"https://ror.org/01a5v8x09","country_code":"US","type":"company","lineage":["https://openalex.org/I72427458"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gang Quan","raw_affiliation_strings":["JD AI Research"],"affiliations":[{"raw_affiliation_string":"JD AI Research","institution_ids":["https://openalex.org/I72427458"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460193","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-6519-3371"},"institutions":[{"id":"https://openalex.org/I72427458","display_name":"JDSU (United States)","ror":"https://ror.org/01a5v8x09","country_code":"US","type":"company","lineage":["https://openalex.org/I72427458"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["JD AI Research"],"affiliations":[{"raw_affiliation_string":"JD AI Research","institution_ids":["https://openalex.org/I72427458"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054954177","display_name":"Guohong Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I72427458","display_name":"JDSU (United States)","ror":"https://ror.org/01a5v8x09","country_code":"US","type":"company","lineage":["https://openalex.org/I72427458"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guohong Ding","raw_affiliation_strings":["JD AI Research"],"affiliations":[{"raw_affiliation_string":"JD AI Research","institution_ids":["https://openalex.org/I72427458"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727205","display_name":"Xiaodong He","orcid":"https://orcid.org/0000-0002-9463-9168"},"institutions":[{"id":"https://openalex.org/I72427458","display_name":"JDSU (United States)","ror":"https://ror.org/01a5v8x09","country_code":"US","type":"company","lineage":["https://openalex.org/I72427458"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodong He","raw_affiliation_strings":["JD AI Research"],"affiliations":[{"raw_affiliation_string":"JD AI Research","institution_ids":["https://openalex.org/I72427458"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107808331","display_name":"Bowen Zhou","orcid":"https://orcid.org/0009-0004-3414-6267"},"institutions":[{"id":"https://openalex.org/I72427458","display_name":"JDSU (United States)","ror":"https://ror.org/01a5v8x09","country_code":"US","type":"company","lineage":["https://openalex.org/I72427458"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bowen Zhou","raw_affiliation_strings":["JD AI Research"],"affiliations":[{"raw_affiliation_string":"JD AI Research","institution_ids":["https://openalex.org/I72427458"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100652844"],"corresponding_institution_ids":["https://openalex.org/I72427458"],"apc_list":null,"apc_paid":null,"fwci":0.3074,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52214828,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"7108","last_page":"7112"},"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":0.9986000061035156,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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":0.7686092257499695},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.7049686908721924},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6736790537834167},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5807110667228699},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5693179368972778},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5248061418533325},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.520401120185852},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5128552913665771},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.5014538764953613},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.49224868416786194},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.4893154799938202},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4857507348060608},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.43756625056266785},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4185611605644226},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3572138249874115},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34909749031066895},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2929195165634155},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2514609694480896},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.08702796697616577}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7686092257499695},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.7049686908721924},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6736790537834167},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5807110667228699},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5693179368972778},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5248061418533325},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.520401120185852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5128552913665771},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.5014538764953613},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.49224868416786194},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.4893154799938202},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4857507348060608},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.43756625056266785},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4185611605644226},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3572138249874115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34909749031066895},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2929195165634155},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2514609694480896},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.08702796697616577},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413499","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:repository.hkust.edu.hk:1783.1-125439","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-125439","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W189595333","https://openalex.org/W1494198834","https://openalex.org/W1495679096","https://openalex.org/W1510355813","https://openalex.org/W1897240248","https://openalex.org/W1968939597","https://openalex.org/W2022647283","https://openalex.org/W2048510784","https://openalex.org/W2078528584","https://openalex.org/W2113131123","https://openalex.org/W2131975357","https://openalex.org/W2147817981","https://openalex.org/W2159202424","https://openalex.org/W2219249508","https://openalex.org/W2605589342","https://openalex.org/W2687223163","https://openalex.org/W2736138094","https://openalex.org/W2807518508","https://openalex.org/W2889286744","https://openalex.org/W2889442120","https://openalex.org/W2891433113","https://openalex.org/W2902573132","https://openalex.org/W2936689732","https://openalex.org/W2943519238","https://openalex.org/W2949756029","https://openalex.org/W2963453742","https://openalex.org/W2972381775","https://openalex.org/W3014522660","https://openalex.org/W3015844538","https://openalex.org/W3108234410","https://openalex.org/W3124610495","https://openalex.org/W4253928870","https://openalex.org/W6607758087","https://openalex.org/W6683207941","https://openalex.org/W6688816777","https://openalex.org/W6757632829"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W2598586350","https://openalex.org/W2161396743","https://openalex.org/W111365173","https://openalex.org/W2386453889"],"abstract_inverted_index":{"Conventional":[0],"learning-based":[1],"speech":[2,66,80,102,119],"enhancement":[3],"methods":[4,188],"usually":[5],"utilize":[6],"existing":[7],"building":[8],"blocks":[9],"to":[10,19,69,116,125,128],"design":[11,41,149],"the":[12,22,35,39,51,71,79,86,94,101,107,118,142,152,156,163,178,182,186],"deep":[13],"neural":[14,61],"networks":[15],"(DNNs),":[16],"while":[17],"how":[18],"effectively":[20],"integrate":[21],"statistical":[23],"signal":[24,154,194],"processing":[25,195],"based":[26,60,140,191],"schemes,":[27],"which":[28,189],"are":[29,96,190],"expert-knowledge":[30],"driven":[31],"and":[32,56,83,93,106,127,177],"could":[33],"ameliorate":[34],"over-fitting":[36],"problem,":[37],"into":[38],"network":[40,113,148],"remains":[42],"an":[43],"open":[44],"issue.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49],"extend":[50],"conventional":[52,132,153],"Kalman":[53,62],"filtering":[54,134,165],"(KF)":[55],"propose":[57],"a":[58,76,146],"supervised-learning":[59],"filter":[63],"(NKF)":[64],"for":[65],"enhancement.":[67],"Similar":[68],"KF,":[70],"proposed":[72,143,183],"method":[73,144,184],"first":[74],"obtains":[75],"prediction":[77,103,121],"from":[78,151,168],"evolution":[81],"model":[82,122],"then":[84],"integrates":[85],"short-term":[87],"instantaneous":[88],"observation":[89],"by":[90,98],"linear":[91,120,133,164],"weighting,":[92],"weights":[95],"calculated":[97],"comparing":[99],"between":[100],"residual":[104],"error":[105],"environmental":[108],"noise":[109],"level.":[110],"An":[111],"end-to-end":[112],"is":[114],"designed":[115],"convert":[117],"in":[123,173],"KF":[124],"non-linear,":[126],"compact":[129],"all":[130],"other":[131,138],"operations.":[135],"Different":[136],"with":[137],"DNN":[139],"methods,":[141],"provides":[145],"specialized":[147],"inspired":[150],"processing,":[155],"backpropagation":[157],"can":[158],"be":[159],"directly":[160],"applied":[161],"on":[162,192],"operations":[166],"integrated":[167],"KF.":[169],"We":[170],"conduct":[171],"experiments":[172],"different":[174],"noisy":[175],"conditions,":[176],"results":[179],"demonstrate":[180],"that":[181],"outperforms":[185],"baseline":[187],"either":[193],"or":[196],"DNNs.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2025-10-10T00:00:00"}