{"id":"https://openalex.org/W2891355459","doi":"https://doi.org/10.1109/icassp.2018.8461819","title":"Gated Residual Networks with Dilated Convolutions for Supervised Speech Separation","display_name":"Gated Residual Networks with Dilated Convolutions for Supervised Speech Separation","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891355459","doi":"https://doi.org/10.1109/icassp.2018.8461819","mag":"2891355459"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461819","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461819","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5058209019","display_name":"Ke Tan","orcid":"https://orcid.org/0000-0001-5073-8060"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Tan","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046063537","display_name":"Jitong Chen","orcid":"https://orcid.org/0000-0001-6084-043X"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jitong Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Center for Cognitive and Brain Sciences, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"25"},"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7970651388168335},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.7800617814064026},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6702397465705872},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5600301027297974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5279837250709534},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5178654193878174},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.45092886686325073},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41954925656318665},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41283875703811646},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3818163573741913},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24701249599456787},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.13174891471862793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7970651388168335},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7800617814064026},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6702397465705872},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5600301027297974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5279837250709534},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5178654193878174},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.45092886686325073},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41954925656318665},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41283875703811646},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3818163573741913},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24701249599456787},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.13174891471862793},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461819","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461819","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"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":31,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1836465849","https://openalex.org/W2024490156","https://openalex.org/W2069681747","https://openalex.org/W2116988482","https://openalex.org/W2141998673","https://openalex.org/W2156387975","https://openalex.org/W2168379380","https://openalex.org/W2194775991","https://openalex.org/W2285420822","https://openalex.org/W2423557781","https://openalex.org/W2559302184","https://openalex.org/W2567070169","https://openalex.org/W2592939477","https://openalex.org/W2678916739","https://openalex.org/W2949117887","https://openalex.org/W2962850830","https://openalex.org/W2962866211","https://openalex.org/W2963453742","https://openalex.org/W2963636093","https://openalex.org/W2963828919","https://openalex.org/W2963840672","https://openalex.org/W2963970792","https://openalex.org/W6638667902","https://openalex.org/W6682889407","https://openalex.org/W6696085341","https://openalex.org/W6730350449","https://openalex.org/W6731370813","https://openalex.org/W6738846887"],"related_works":["https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3167935049","https://openalex.org/W3103566983","https://openalex.org/W1986772939","https://openalex.org/W3029198973","https://openalex.org/W2037635165"],"abstract_inverted_index":{"In":[0],"supervised":[1],"speech":[2,61,94],"separation,":[3],"deep":[4],"neural":[5,52],"networks":[6],"(DNNs)":[7],"are":[8],"typically":[9],"employed":[10],"to":[11,20,55],"predict":[12],"an":[13],"ideal":[14],"time-frequency":[15],"(T-F)":[16],"mask":[17],"in":[18,90],"order":[19],"remove":[21],"background":[22],"interference.":[23],"However,":[24],"the":[25,77,99,107],"performance":[26],"of":[27,92],"DNNs":[28],"is":[29,102],"frequently":[30],"degraded":[31],"for":[32,44],"untrained":[33],"noises":[34],"and":[35,59,71,96],"speakers.":[36],"Inspired":[37],"by":[38],"recent":[39],"research":[40],"on":[41],"dilated":[42,67],"convolutions":[43],"context":[45],"aggregation,":[46],"we":[47],"propose":[48],"a":[49,82],"novel":[50],"convolutional":[51],"network":[53],"(CNN)":[54],"deal":[56],"with":[57],"noise-":[58],"speaker-independent":[60],"separation.":[62],"The":[63],"proposed":[64,78,100],"model":[65,79,89],"incorporates":[66],"convolutions,":[68],"gating":[69],"mechanisms":[70],"residual":[72],"learning.":[73],"We":[74],"find":[75],"that":[76],"consistently":[80],"outperforms":[81],"state-of-the-art":[83],"long":[84],"short-term":[85],"memory":[86],"(LSTM)":[87],"based":[88],"terms":[91],"objective":[93],"intelligibility":[95],"quality.":[97],"Additionally,":[98],"CNN":[101],"more":[103],"computationally":[104],"efficient":[105],"than":[106],"LSTM":[108],"model.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}