{"id":"https://openalex.org/W2044893557","doi":"https://doi.org/10.1109/taslp.2014.2364452","title":"A Regression Approach to Speech Enhancement Based on Deep Neural Networks","display_name":"A Regression Approach to Speech Enhancement Based on Deep Neural Networks","publication_year":2014,"publication_date":"2014-10-21","ids":{"openalex":"https://openalex.org/W2044893557","doi":"https://doi.org/10.1109/taslp.2014.2364452","mag":"2044893557"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2014.2364452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2364452","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5101467338","display_name":"Yong Xu","orcid":"https://orcid.org/0000-0003-4944-6890"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yong Xu","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, HeFei, AnHui, China","The National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, HeFei, AnHui, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"The National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, HeFei, AnHui, China","The National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, HeFei, AnHui, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"The National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, HeFei, AnHui, China","The National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, HeFei, AnHui, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"The National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia, United States","School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, United States#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia, United States","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, United States#TAB#","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101467338"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":52.9938,"has_fulltext":false,"cited_by_count":1401,"citation_normalized_percentile":{"value":0.99942978,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"23","issue":"1","first_page":"7","last_page":"19"},"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":0.9987000226974487,"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/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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":0.7568700313568115},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7399588227272034},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.6237159967422485},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5739498734474182},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.5645207762718201},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5455600023269653},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5410811305046082},{"id":"https://openalex.org/keywords/minimum-mean-square-error","display_name":"Minimum mean square error","score":0.520596981048584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4829834997653961},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.46340322494506836},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.46016284823417664},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3719933032989502},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3514788746833801},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12861350178718567},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.10177037119865417},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08450835943222046},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07872834801673889}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7568700313568115},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7399588227272034},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6237159967422485},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5739498734474182},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.5645207762718201},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5455600023269653},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5410811305046082},{"id":"https://openalex.org/C90652560","wikidata":"https://www.wikidata.org/wiki/Q11091747","display_name":"Minimum mean square error","level":3,"score":0.520596981048584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4829834997653961},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.46340322494506836},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.46016284823417664},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3719933032989502},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3514788746833801},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12861350178718567},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.10177037119865417},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08450835943222046},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07872834801673889},{"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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2014.2364452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2364452","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2319099505","display_name":null,"funder_award_id":"61305002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3537084453","display_name":null,"funder_award_id":"61273264","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W258661521","https://openalex.org/W1495679096","https://openalex.org/W1538759723","https://openalex.org/W1603327663","https://openalex.org/W1904365287","https://openalex.org/W1968939597","https://openalex.org/W1972205360","https://openalex.org/W1974387177","https://openalex.org/W1993409002","https://openalex.org/W2006901874","https://openalex.org/W2020024436","https://openalex.org/W2035576074","https://openalex.org/W2042141988","https://openalex.org/W2057200980","https://openalex.org/W2062164080","https://openalex.org/W2069681747","https://openalex.org/W2072128103","https://openalex.org/W2078528584","https://openalex.org/W2086796102","https://openalex.org/W2100495367","https://openalex.org/W2104729299","https://openalex.org/W2112538788","https://openalex.org/W2114659828","https://openalex.org/W2115055618","https://openalex.org/W2119000949","https://openalex.org/W2121973264","https://openalex.org/W2125630648","https://openalex.org/W2126942983","https://openalex.org/W2128653836","https://openalex.org/W2136922672","https://openalex.org/W2138456300","https://openalex.org/W2138857742","https://openalex.org/W2140833774","https://openalex.org/W2141411743","https://openalex.org/W2141998673","https://openalex.org/W2146324387","https://openalex.org/W2148577181","https://openalex.org/W2153384885","https://openalex.org/W2153894152","https://openalex.org/W2155998647","https://openalex.org/W2162819960","https://openalex.org/W2168013545","https://openalex.org/W2168379380","https://openalex.org/W2171000037","https://openalex.org/W2290318471","https://openalex.org/W2294745040","https://openalex.org/W2396130155","https://openalex.org/W2405774341","https://openalex.org/W2561557072","https://openalex.org/W2606321545","https://openalex.org/W2914048585","https://openalex.org/W3147539069","https://openalex.org/W4231109964","https://openalex.org/W4252741098","https://openalex.org/W4253928870","https://openalex.org/W6640036494","https://openalex.org/W6676933636","https://openalex.org/W6679009796","https://openalex.org/W6680300913","https://openalex.org/W6680887930","https://openalex.org/W6697247452","https://openalex.org/W6712634873","https://openalex.org/W6713658392"],"related_works":["https://openalex.org/W3082178636","https://openalex.org/W1978572805","https://openalex.org/W2782041652","https://openalex.org/W2361247493","https://openalex.org/W2157330024","https://openalex.org/W2952979007","https://openalex.org/W1998374630","https://openalex.org/W2528250906","https://openalex.org/W1493471768","https://openalex.org/W2027761136"],"abstract_inverted_index":{"In":[0,40],"contrast":[1],"to":[2,18,42,45,84,96,107,123,131,162,178],"the":[3,98,109,113,117,126,139,153,165,183,206,209],"conventional":[4,154,216],"minimum":[5],"mean":[6],"square":[7],"error":[8],"(MMSE)-based":[9],"noise":[10,68,133],"reduction":[11],"techniques,":[12],"we":[13],"propose":[14],"a":[15,25,47,56,80,86],"supervised":[16],"method":[17],"enhance":[19],"speech":[20,32,66,100,199],"by":[21],"means":[22],"of":[23,50,65,112,129,208],"finding":[24],"mapping":[26],"function":[27,83],"between":[28],"noisy":[29,198],"and":[30,67,116,119,149],"clean":[31],"signals":[33],"based":[34,156],"on":[35],"deep":[36],"neural":[37],"networks":[38],"(DNNs).":[39],"order":[41],"be":[43],"able":[44],"handle":[46,179],"wide":[48],"range":[49],"additive":[51],"noises":[52],"in":[53,146,180,195,202,215],"real-world":[54,203],"situations,":[55],"large":[57],"training":[58,121],"set":[59],"that":[60,138,164],"encompasses":[61],"many":[62],"possible":[63],"combinations":[64],"types,":[69],"is":[70,76,159,176,192],"first":[71],"designed.":[72],"A":[73],"DNN":[74,167,185],"architecture":[75],"then":[77],"employed":[78],"as":[79],"nonlinear":[81],"regression":[82,114],"ensure":[85],"powerful":[87],"modeling":[88],"capability.":[89],"Several":[90],"techniques":[91],"have":[92],"also":[93,160,193],"been":[94],"proposed":[95,140,166],"improve":[97,125],"DNN-based":[99],"enhancement":[101,217],"system,":[102],"including":[103],"global":[104],"variance":[105],"equalization":[106],"alleviate":[108],"over-smoothing":[110],"problem":[111],"model,":[115,186],"dropout":[118],"noise-aware":[120],"strategies":[122],"further":[124],"generalization":[127],"capability":[128],"DNNs":[130],"unseen":[132],"conditions.":[134],"Experimental":[135],"results":[136],"demonstrate":[137],"framework":[141],"can":[142,169],"achieve":[143],"significant":[144],"improvements":[145],"both":[147],"objective":[148],"subjective":[150],"measures":[151],"over":[152],"MMSE":[155],"technique.":[157],"It":[158],"interesting":[161],"observe":[163],"approach":[168],"well":[170],"suppress":[171],"highly":[172],"nonstationary":[173],"noise,":[174],"which":[175],"tough":[177],"general.":[181],"Furthermore,":[182],"resulting":[184],"trained":[187],"with":[188,197],"artificial":[189],"synthesized":[190],"data,":[191],"effective":[194],"dealing":[196],"data":[200],"recorded":[201],"scenarios":[204],"without":[205],"generation":[207],"annoying":[210],"musical":[211],"artifact":[212],"commonly":[213],"observed":[214],"methods.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":91},{"year":2024,"cited_by_count":101},{"year":2023,"cited_by_count":136},{"year":2022,"cited_by_count":131},{"year":2021,"cited_by_count":193},{"year":2020,"cited_by_count":224},{"year":2019,"cited_by_count":174},{"year":2018,"cited_by_count":155},{"year":2017,"cited_by_count":89},{"year":2016,"cited_by_count":69},{"year":2015,"cited_by_count":22}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}