{"id":"https://openalex.org/W2922358226","doi":"https://doi.org/10.23919/apsipa.2018.8659607","title":"A Novel Training Strategy Using Dynamic Data Generation for Deep Neural Network Based Speech Enhancement","display_name":"A Novel Training Strategy Using Dynamic Data Generation for Deep Neural Network Based Speech Enhancement","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2922358226","doi":"https://doi.org/10.23919/apsipa.2018.8659607","mag":"2922358226"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659607","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5018657729","display_name":"Maokui He","orcid":null},"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":"Mao-Kui He","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, 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":["University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100607794","display_name":"Zi-Rui Wang","orcid":"https://orcid.org/0000-0002-6600-8801"},"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":"Zi-Rui Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101926390","display_name":"Lei Sun","orcid":"https://orcid.org/0000-0001-7680-6455"},"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":"Lei Sun","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5018657729"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.3303,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59809057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1228","last_page":"1232"},"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":0.9987999796867371,"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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":0.832196056842804},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.595159649848938},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5837079286575317},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.5757543444633484},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5738913416862488},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5663633346557617},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.552593469619751},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5337202548980713},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.52470862865448},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5201409459114075},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5175837278366089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5154317617416382},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4986295700073242},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.48143643140792847},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4464768171310425},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4292202591896057},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3609572649002075},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1583678424358368}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.832196056842804},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.595159649848938},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5837079286575317},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.5757543444633484},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5738913416862488},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5663633346557617},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.552593469619751},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5337202548980713},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.52470862865448},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5201409459114075},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5175837278366089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5154317617416382},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4986295700073242},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.48143643140792847},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4464768171310425},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4292202591896057},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3609572649002075},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1583678424358368},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659607","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1479329615","https://openalex.org/W1495679096","https://openalex.org/W1635564296","https://openalex.org/W1790748249","https://openalex.org/W1963950237","https://openalex.org/W1968939597","https://openalex.org/W1995536493","https://openalex.org/W2044893557","https://openalex.org/W2078528584","https://openalex.org/W2094461119","https://openalex.org/W2097491464","https://openalex.org/W2128653836","https://openalex.org/W2141998673","https://openalex.org/W2405774341","https://openalex.org/W2516547830","https://openalex.org/W2964121744","https://openalex.org/W3124794156","https://openalex.org/W4245919820","https://openalex.org/W6713658392"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W3135613579","https://openalex.org/W1973895194","https://openalex.org/W2166831097","https://openalex.org/W4386746628","https://openalex.org/W4388016426","https://openalex.org/W2546593254","https://openalex.org/W1980687383","https://openalex.org/W3209446892"],"abstract_inverted_index":{"In":[0,111],"this":[1,112,152],"paper,":[2],"a":[3,30,46,52,116],"new":[4,153],"training":[5,38,48,80,93,98,103,118,154,161,174,180,186,230],"strategy":[6],"is":[7,127,135,165],"proposed":[8,229],"to":[9,23,36,74,86,96,143,168],"address":[10],"the":[11,26,34,41,79,101,128,138,144,172,178,184,190,218,223,228],"key":[12,125],"issue":[13],"in":[14,40,68,78,177,189],"deep":[15,42],"neural":[16],"network":[17],"(DNN)":[18],"based":[19],"speech":[20,60,77,133],"enhancement:":[21],"how":[22],"effectively":[24],"utilize":[25],"limited":[27],"data":[28,39,94,122,134,162,196],"with":[29,183],"growing":[31],"awareness":[32],"of":[33,51,55,131,160,227],"necessity":[35],"increase":[37],"learning":[43],"era.":[44],"Traditionally,":[45],"fixed":[47,102,173],"set":[49,104,175],"consisting":[50],"large":[53],"amount":[54],"paired":[56],"utterances,":[57],"i.e.,":[58],"clean":[59],"and":[61,170,211],"corresponding":[62],"noisy":[63,76,132,195],"speech,":[64],"must":[65],"be":[66,106,214],"prepared":[67],"advance.":[69],"However,":[70],"it":[71,164],"seems":[72],"inevitable":[73],"enlarge":[75],"stage":[81],"for":[82,108,217],"making":[83],"model":[84],"adaptive":[85],"various":[87],"noise":[88,220],"environments.":[89],"Besides,":[90],"involving":[91],"more":[92,193],"leads":[95],"longer":[97],"time":[99,187],"as":[100,176,188],"should":[105],"repeated":[107],"multiple":[109],"epochs.":[110],"study,":[113],"we":[114],"propose":[115],"novel":[117],"method":[119],"via":[120],"dynamic":[121,158],"generation.":[123],"The":[124],"idea":[126],"synthetic":[129],"phase":[130],"conducted":[136],"on":[137],"fly":[139],"from":[140,151],"utterance":[141],"level":[142],"batch":[145],"level.":[146],"Three":[147],"advantages":[148],"are":[149,197],"gained":[150],"method.":[155,181],"First,":[156],"by":[157],"generation":[159],"batch,":[163],"not":[166],"necessary":[167],"prepare":[169],"store":[171],"conventional":[179,191],"Second,":[182],"same":[185],"method,":[192],"abundant":[194],"actually":[198],"fed":[199],"into":[200],"DNN":[201],"model.":[202],"Finally,":[203],"different":[204],"evaluation":[205],"measures,":[206],"including":[207],"PESQ,":[208],"STOI,":[209],"LSD,":[210],"SegSNR,":[212],"can":[213],"consistently":[215],"improved":[216],"unseen":[219],"types,":[221],"demonstrating":[222],"better":[224],"generalization":[225],"capability":[226],"strategy.":[231]},"counts_by_year":[{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}