{"id":"https://openalex.org/W2749588430","doi":"https://doi.org/10.21437/interspeech.2017-515","title":"Improving Mask Learning Based Speech Enhancement System with Restoration Layers and Residual Connection","display_name":"Improving Mask Learning Based Speech Enhancement System with Restoration Layers and Residual Connection","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2749588430","doi":"https://doi.org/10.21437/interspeech.2017-515","mag":"2749588430"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-515","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/A5100345097","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0003-0563-1760"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100764456","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0002-0575-0156"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Huang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5077401426","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0001-8786-3391"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100345097"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3286,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.93410612,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3632","last_page":"3636"},"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":0.9994000196456909,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9950000047683716,"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/residual","display_name":"Residual","score":0.794228196144104},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7597278356552124},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6224433779716492},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5748509764671326},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5002374649047852},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4591045379638672},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45034971833229065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4467775523662567},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4284172058105469},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4231877326965332},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3515690863132477},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.11619719862937927},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10195580124855042}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.794228196144104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7597278356552124},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6224433779716492},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5748509764671326},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5002374649047852},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4591045379638672},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45034971833229065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4467775523662567},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4284172058105469},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4231877326965332},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3515690863132477},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.11619719862937927},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10195580124855042},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2017-515","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1973681148","https://openalex.org/W1979651826","https://openalex.org/W1981617403","https://openalex.org/W1992475611","https://openalex.org/W2036635146","https://openalex.org/W2046869671","https://openalex.org/W2080921589","https://openalex.org/W2094461119","https://openalex.org/W2118497033","https://openalex.org/W2147768505","https://openalex.org/W2148613904","https://openalex.org/W2194775991","https://openalex.org/W2289394825","https://openalex.org/W2290318471","https://openalex.org/W2405774341","https://openalex.org/W2407080277","https://openalex.org/W2559260703","https://openalex.org/W2755891984","https://openalex.org/W2963410064","https://openalex.org/W2966212213"],"related_works":["https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1847088711","https://openalex.org/W4225394202","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W2964335273","https://openalex.org/W2982145560","https://openalex.org/W2790400419","https://openalex.org/W2972212393"],"abstract_inverted_index":{"For":[0],"single-channel":[1],"speech":[2,29,74,97,130],"enhancement,":[3],"mask":[4,71,120],"learning":[5,72,95,121],"based":[6,73,96],"approach":[7],"through":[8],"neural":[9],"network":[10],"has":[11],"been":[12],"shown":[13],"to":[14,21,56,83,105],"outperform":[15],"the":[16,35,42,70,85,119,123,128,139,142],"feature":[17,107,124],"mapping":[18,108],"approach,":[19],"and":[20,37,53,122,157],"be":[22],"effective":[23],"as":[24],"a":[25,92,106,113],"pre-processor":[26],"for":[27],"automatic":[28],"recognition.":[30],"However,":[31],"its":[32],"assumption":[33],"that":[34],"mixture":[36],"clean":[38],"reference":[39],"must":[40],"have":[41],"correspondent":[43],"scale":[44,86],"doesn\u2019t":[45],"hold":[46],"in":[47],"data":[48,156],"collected":[49],"from":[50,117],"real":[51,155],"world,":[52],"thus":[54],"leads":[55],"significant":[57],"performance":[58],"degradation":[59],"on":[60,133,154,160],"parallel":[61],"recorded":[62],"data.":[63,136,162],"In":[64],"this":[65],"paper,":[66],"we":[67],"first":[68],"extend":[69],"enhancement":[75,98,131],"by":[76],"integrating":[77],"two":[78],"types":[79],"of":[80],"restoration":[81],"layer":[82],"address":[84],"mismatch":[87],"problem.":[88],"We":[89,110,126],"further":[90],"propose":[91],"novel":[93],"residual":[94],"model":[99],"via":[100],"adding":[101],"different":[102],"shortcut":[103],"connections":[104,148],"network.":[109],"show":[111],"such":[112],"structure":[114],"can":[115],"benefit":[116],"both":[118],"mapping.":[125],"evaluate":[127],"proposed":[129],"models":[132],"CHiME":[134],"3":[135],"Without":[137],"retraining":[138],"acoustic":[140],"model,":[141],"best":[143],"bidirection":[144],"LSTM":[145],"with":[146],"residue":[147],"yields":[149],"24.90%":[150],"relative":[151],"WER":[152,159],"reduction":[153],"34.57%":[158],"simulated":[161]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}