{"id":"https://openalex.org/W2964607787","doi":"https://doi.org/10.24963/ijcai.2019/655","title":"Dilated Convolution with Dilated GRU for Music Source Separation","display_name":"Dilated Convolution with Dilated GRU for Music Source Separation","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2964607787","doi":"https://doi.org/10.24963/ijcai.2019/655","mag":"2964607787"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/655","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/655","pdf_url":"https://www.ijcai.org/proceedings/2019/0655.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0655.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101719938","display_name":"Jen-Yu Liu","orcid":"https://orcid.org/0000-0003-1299-6688"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Yu Liu","raw_affiliation_strings":["Research Center for IT Innovation, Academia Sinica"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for IT Innovation, Academia Sinica","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061291906","display_name":"Yi\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0002-2724-6161"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["Research Center for IT Innovation, Academia Sinica"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for IT Innovation, Academia Sinica","institution_ids":["https://openalex.org/I4210086894"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5061291906"],"corresponding_institution_ids":["https://openalex.org/I4210086894"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4718","last_page":"4724"},"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":0.9994000196456909,"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":0.9952999949455261,"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/computer-science","display_name":"Computer science","score":0.7159081697463989},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6769647002220154},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6461741924285889},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5268318057060242},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5127642750740051},{"id":"https://openalex.org/keywords/dilation","display_name":"Dilation (metric space)","score":0.5013482570648193},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4507763087749481},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.43764981627464294},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40841591358184814},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3875977396965027},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16043871641159058}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7159081697463989},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6769647002220154},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6461741924285889},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5268318057060242},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5127642750740051},{"id":"https://openalex.org/C2780757906","wikidata":"https://www.wikidata.org/wiki/Q5276676","display_name":"Dilation (metric space)","level":2,"score":0.5013482570648193},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4507763087749481},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43764981627464294},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40841591358184814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3875977396965027},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16043871641159058},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/655","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/655","pdf_url":"https://www.ijcai.org/proceedings/2019/0655.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/655","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/655","pdf_url":"https://www.ijcai.org/proceedings/2019/0655.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964607787.pdf","grobid_xml":"https://content.openalex.org/works/W2964607787.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1603632465","https://openalex.org/W1924770834","https://openalex.org/W2284050935","https://openalex.org/W2519091744","https://openalex.org/W2559302184","https://openalex.org/W2563534197","https://openalex.org/W2669032454","https://openalex.org/W2750814024","https://openalex.org/W2774707525","https://openalex.org/W2796571515","https://openalex.org/W2807116244","https://openalex.org/W2894398294","https://openalex.org/W2916985722","https://openalex.org/W2949267040","https://openalex.org/W2963125010","https://openalex.org/W2963452667","https://openalex.org/W2963697785","https://openalex.org/W2963750251","https://openalex.org/W2963751183","https://openalex.org/W2963840672","https://openalex.org/W2964005873","https://openalex.org/W2964199361","https://openalex.org/W4297775537"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W2051113792","https://openalex.org/W4287548622"],"abstract_inverted_index":{"Stacked":[0],"dilated":[1,65,76,117],"convolutions":[2,66,77,84],"used":[3],"in":[4,19,38,59,168],"Wavenet":[5],"have":[6],"been":[7],"shown":[8],"effective":[9,87],"for":[10,70,99,143,191],"generating":[11],"high-quality":[12],"audios.":[13],"By":[14],"replacing":[15],"pooling/striding":[16],"with":[17,119,157,177],"dilation":[18],"convolution":[20,118],"layers,":[21],"they":[22],"can":[23,78,166],"preserve":[24],"high-resolution":[25,33],"information":[26,108,134],"and":[27,93,161,195],"still":[28,91],"reach":[29,79,105,154],"distant":[30],"locations.":[31],"Producing":[32],"predictions":[34],"is":[35,44],"also":[36],"crucial":[37],"music":[39,71,101],"source":[40,72],"separation,":[41],"whose":[42],"goal":[43],"to":[45,114,126,153],"separate":[46],"different":[47],"sound":[48],"sources":[49],"while":[50],"maintain":[51],"the":[52,55,68,140,174,189],"quality":[53],"of":[54,139,180],"separated":[56],"sounds.":[57],"Therefore,":[58],"this":[60],"paper,":[61],"we":[62,112],"use":[63],"stacked":[64,75],"as":[67],"backbone":[69],"separation.":[73],"Although":[74],"wider":[80],"context":[81],"than":[82,188],"standard":[83],"do,":[85],"their":[86],"receptive":[88],"fields":[89],"are":[90],"fixed":[92,145],"might":[94],"not":[95],"be":[96],"wide":[97],"enough":[98],"complex":[100],"audio":[102],"signals.":[103],"To":[104],"even":[106],"further":[107],"at":[109],"remote":[110],"locations,":[111],"propose":[113],"combine":[115],"a":[116,120,128,144,150,155,178],"modified":[121],"GRU":[122,125,132,151],"called":[123],"Dilated":[124,131],"form":[127],"block.":[129],"A":[130],"receives":[133],"from":[135],"k-step":[136],"before":[137],"instead":[138],"previous":[141],"step":[142],"k.":[146],"This":[147],"modification":[148],"allows":[149],"unit":[152],"location":[156],"fewer":[158],"recurrent":[159],"steps":[160],"run":[162],"faster":[163],"because":[164],"it":[165],"execute":[167],"parallel":[169],"partially.":[170],"We":[171],"show":[172],"that":[173],"proposed":[175],"model":[176],"stack":[179],"such":[181],"blocks":[182],"performs":[183],"equally":[184],"well":[185],"or":[186],"better":[187],"state-of-the-art":[190],"separating":[192],"both":[193],"vocals":[194],"accompaniment.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}