{"id":"https://openalex.org/W2512342189","doi":"https://doi.org/10.1109/icme.2016.7552957","title":"Joint optimization of audible noise suppression and deep neural networks for single-channel speech enhancement","display_name":"Joint optimization of audible noise suppression and deep neural networks for single-channel speech enhancement","publication_year":2016,"publication_date":"2016-07-01","ids":{"openalex":"https://openalex.org/W2512342189","doi":"https://doi.org/10.1109/icme.2016.7552957","mag":"2512342189"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2016.7552957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2016.7552957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Multimedia and Expo (ICME)","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/A5101655190","display_name":"Wei Han","orcid":"https://orcid.org/0000-0003-0154-5574"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Han","raw_affiliation_strings":["Lab of Intelligent Information Processing, PLAUST, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Lab of Intelligent Information Processing, PLAUST, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011581435","display_name":"Xiongwei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiongwei Zhang","raw_affiliation_strings":["Lab of Intelligent Information Processing, PLAUST, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Lab of Intelligent Information Processing, PLAUST, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063753668","display_name":"Gang Min","orcid":"https://orcid.org/0000-0003-4413-146X"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Min","raw_affiliation_strings":["Lab of Intelligent Information Processing, PLAUST, Nanjing, China","Xi'an Communications Institute, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Lab of Intelligent Information Processing, PLAUST, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]},{"raw_affiliation_string":"Xi'an Communications Institute, Xi'an, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085248515","display_name":"Meng Sun","orcid":"https://orcid.org/0000-0002-7435-3752"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Sun","raw_affiliation_strings":["Lab of Intelligent Information Processing, PLAUST, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Lab of Intelligent Information Processing, PLAUST, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024997158","display_name":"Jibin Yang","orcid":"https://orcid.org/0000-0002-1072-5422"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]},{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jibin Yang","raw_affiliation_strings":["Lab of Intelligent Information Processing, PLAUST, Nanjing, China","Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Lab of Intelligent Information Processing, PLAUST, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]},{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101655190"],"corresponding_institution_ids":["https://openalex.org/I4210163363"],"apc_list":null,"apc_paid":null,"fwci":0.2522,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52846255,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"23","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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9988999962806702,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7595117092132568},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7230585813522339},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7013082504272461},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6940580606460571},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5784600377082825},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5078383088111877},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4995083808898926},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4953576326370239},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.48664626479148865},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.47253870964050293},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.431209921836853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41664043068885803},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3220008909702301},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.17414003610610962},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.16380971670150757},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.10861265659332275},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10694941878318787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7595117092132568},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7230585813522339},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7013082504272461},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6940580606460571},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5784600377082825},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5078383088111877},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4995083808898926},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4953576326370239},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.48664626479148865},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.47253870964050293},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.431209921836853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41664043068885803},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3220008909702301},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.17414003610610962},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.16380971670150757},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.10861265659332275},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10694941878318787},{"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/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2016.7552957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2016.7552957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1790748249","https://openalex.org/W1963950237","https://openalex.org/W1968939597","https://openalex.org/W2013608223","https://openalex.org/W2044893557","https://openalex.org/W2051428568","https://openalex.org/W2096698681","https://openalex.org/W2127851351","https://openalex.org/W2130178255","https://openalex.org/W2140419980","https://openalex.org/W2146324387","https://openalex.org/W2156387975","https://openalex.org/W2167873188","https://openalex.org/W3124794156","https://openalex.org/W6682889407"],"related_works":["https://openalex.org/W2597829360","https://openalex.org/W4375869169","https://openalex.org/W2921661700","https://openalex.org/W2138406058","https://openalex.org/W2153897396","https://openalex.org/W2157102033","https://openalex.org/W2131486661","https://openalex.org/W2005805562","https://openalex.org/W4375869276","https://openalex.org/W1585241115"],"abstract_inverted_index":{"Improving":[0],"the":[1,21,70,74,79,82,86,102,105,109,114,120],"perceptual":[2],"quality":[3],"of":[4,24,73,81,104],"speech":[5,33,76],"signals":[6],"is":[7,36,66],"a":[8,30,49],"key":[9],"yet":[10],"challenging":[11],"problem":[12],"for":[13],"many":[14],"real":[15],"world":[16],"applications.":[17],"Taking":[18],"into":[19],"account":[20],"good":[22],"performance":[23],"deep":[25,55],"learning":[26],"in":[27,119],"signal":[28],"representation,":[29],"novel":[31],"single-channel":[32],"enhancement":[34],"technique":[35],"presented":[37],"based":[38],"on":[39,91],"joint":[40],"Deep":[41],"Neural":[42],"Networks":[43],"and":[44,77],"audible":[45,61,83],"noise":[46,62,84,95,99,115],"suppression":[47,63],"as":[48],"whole":[50],"network":[51,57],"architecture.":[52],"This":[53],"new":[54],"neural":[56],"jointly":[58],"trains":[59],"an":[60],"function":[64],"which":[65],"used":[67],"to":[68],"estimate":[69],"magnitude":[71],"spectrum":[72,80],"clean":[75],"shape":[78],"at":[85,97],"same":[87],"time.":[88],"Experimental":[89],"results":[90],"TIMIT":[92],"with":[93],"20":[94],"types":[96],"various":[98],"levels":[100],"demonstrate":[101],"superiority":[103],"proposed":[106],"method":[107],"over":[108],"baselines,":[110],"no":[111],"matter":[112],"whether":[113],"conditions":[116],"are":[117],"included":[118],"training":[121],"set":[122],"or":[123],"not.":[124]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}