{"id":"https://openalex.org/W3010327795","doi":"https://doi.org/10.1109/icspcs47537.2019.9008699","title":"Single-Channel Speech Enhancement with Sequentially Trained DNN System","display_name":"Single-Channel Speech Enhancement with Sequentially Trained DNN System","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3010327795","doi":"https://doi.org/10.1109/icspcs47537.2019.9008699","mag":"3010327795"},"language":"en","primary_location":{"id":"doi:10.1109/icspcs47537.2019.9008699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icspcs47537.2019.9008699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 13th International Conference on Signal Processing and Communication Systems (ICSPCS)","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/A5100714901","display_name":"Yang Sun","orcid":"https://orcid.org/0000-0002-5483-0953"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yang Sun","raw_affiliation_strings":["Intelligent Sensing and Communications Research Group, Newcastle University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Sensing and Communications Research Group, Newcastle University, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031139212","display_name":"Yang Xian","orcid":"https://orcid.org/0000-0002-3896-234X"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yang Xian","raw_affiliation_strings":["Intelligent Sensing and Communications Research Group, Newcastle University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Sensing and Communications Research Group, Newcastle University, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053121936","display_name":"Syed Mohsen Naqvi","orcid":"https://orcid.org/0000-0002-1547-0908"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Syed Mohsen Naqvi","raw_affiliation_strings":["Intelligent Sensing and Communications Research Group, Newcastle University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Sensing and Communications Research Group, Newcastle University, UK","institution_ids":["https://openalex.org/I84884186"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.19234281,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"16","issue":null,"first_page":"1","last_page":"6"},"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":0.9958999752998352,"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":0.9958999752998352,"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/pesq","display_name":"PESQ","score":0.8933653831481934},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.8422021865844727},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.797029972076416},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.7918380498886108},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7336475253105164},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6958224773406982},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6786226034164429},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4315636157989502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42890533804893494},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4113450050354004},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41028618812561035},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33483004570007324},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.29834842681884766},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2657131850719452},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.17447921633720398}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.8933653831481934},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.8422021865844727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.797029972076416},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.7918380498886108},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7336475253105164},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6958224773406982},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6786226034164429},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4315636157989502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42890533804893494},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4113450050354004},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41028618812561035},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33483004570007324},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.29834842681884766},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2657131850719452},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.17447921633720398},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icspcs47537.2019.9008699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icspcs47537.2019.9008699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 13th International Conference on Signal Processing and Communication Systems (ICSPCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2006129368","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2074290069","https://openalex.org/W2096301647","https://openalex.org/W2104887782","https://openalex.org/W2121973264","https://openalex.org/W2122982914","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2151554678","https://openalex.org/W2291877678","https://openalex.org/W2304609584","https://openalex.org/W2542605056","https://openalex.org/W2625041691","https://openalex.org/W2767832833","https://openalex.org/W2897917529","https://openalex.org/W2902298602","https://openalex.org/W3147539069"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W1823208675","https://openalex.org/W2342810974","https://openalex.org/W3016109656","https://openalex.org/W2513767140","https://openalex.org/W3135613579","https://openalex.org/W2037635165","https://openalex.org/W4200562864","https://openalex.org/W2153897396","https://openalex.org/W2157102033"],"abstract_inverted_index":{"One":[0],"of":[1,82,136,155],"the":[2,11,19,32,43,58,79,83,99,103,109,127,140,152,156,160],"recent":[3],"methods":[4],"for":[5],"speech":[6,16,21,137],"enhancement":[7,68],"is":[8,39],"to":[9,77,97,106,125,147],"find":[10],"mapping":[12],"function":[13],"between":[14],"noisy":[15],"mixture":[17],"and":[18,46,52,102,120,129,145],"clean":[20],"signals":[22],"with":[23,42,50,70,94,111],"a":[24,36],"trained":[25,73,88],"deep":[26],"neural":[27],"network(DNN)":[28],"model,":[29,37],"especially":[30],"in":[31,57,75],"monaural":[33],"case.":[34],"Such":[35],"however,":[38],"often":[40],"over-fit":[41],"training":[44,59,92,128],"data,":[45],"limited":[47],"when":[48],"dealing":[49],"noise":[51,100,119],"interferences":[53],"that":[54],"are":[55,87,123],"unseen":[56],"process.":[60],"To":[61],"address":[62],"this":[63],"issue,":[64],"we":[65],"propose":[66],"an":[67],"system":[69],"two":[71],"sequentially":[72,89],"DNNs,":[74],"order":[76],"improve":[78,108],"generalization":[80],"ability":[81],"model.":[84],"Two":[85],"DNNs":[86],"using":[90,133],"different":[91],"targets,":[93],"one":[95],"applied":[96],"remove":[98],"interference":[101],"other":[104],"used":[105,124],"further":[107],"quality":[110,138],"time-frequency":[112],"(T-F)":[113],"mask.":[114],"The":[115],"TIMIT":[116],"corpus,":[117],"non-speech":[118],"NOISEX":[121],"datasets":[122],"generate":[126],"testing":[130],"data.":[131],"Evaluations":[132],"perceptual":[134],"evaluation":[135],"(PESQ),":[139],"short-time":[141],"objective":[142],"intelligibility":[143],"(STOI)":[144],"signal":[146],"distortion":[148],"ratio":[149],"(SDR)":[150],"show":[151],"improved":[153],"performance":[154],"proposed":[157],"method":[158],"over":[159],"state-of-the-art":[161],"method.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}