{"id":"https://openalex.org/W2928988674","doi":"https://doi.org/10.48550/arxiv.1904.04161","title":"Audio Source Separation via Multi-Scale Learning with Dilated Dense U-Nets","display_name":"Audio Source Separation via Multi-Scale Learning with Dilated Dense U-Nets","publication_year":2019,"publication_date":"2019-04-08","ids":{"openalex":"https://openalex.org/W2928988674","doi":"https://doi.org/10.48550/arxiv.1904.04161","mag":"2928988674"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1904.04161","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.04161","pdf_url":"https://arxiv.org/pdf/1904.04161","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.04161","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090107273","display_name":"Vivek Narayanaswamy","orcid":"https://orcid.org/0000-0002-6570-2930","observed_orcids":["https://orcid.org/0000-0002-6570-2930"]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Narayanaswamy, Vivek Sivaraman","raw_affiliation_strings":["Arizona State University ,","Arizona State University**"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University ,","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Arizona State University**","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103081221","display_name":"Sameeksha Katoch","orcid":"https://orcid.org/0000-0002-4034-0988","observed_orcids":["https://orcid.org/0000-0002-4034-0988"]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katoch, Sameeksha","raw_affiliation_strings":["Arizona State University ,","Arizona State University**"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University ,","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Arizona State University**","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046632395","display_name":"Jayaraman J. Thiagarajan","orcid":"https://orcid.org/0000-0002-8517-5816","observed_orcids":["https://orcid.org/0000-0002-8517-5816"]},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thiagarajan, Jayaraman J.","raw_affiliation_strings":["Lawrence Livermore National Labs ,","Lawrence livermore National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Labs ,","institution_ids":["https://openalex.org/I1282311441"]},{"raw_affiliation_string":"Lawrence livermore National Laboratory","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101697214","display_name":"Huan Song","orcid":"https://orcid.org/0000-0002-9639-9962","observed_orcids":["https://orcid.org/0000-0002-9639-9962"]},"institutions":[{"id":"https://openalex.org/I4210120115","display_name":"Robert Bosch (United States)","ror":"https://ror.org/02venad53","country_code":"US","type":"company","lineage":["https://openalex.org/I4210120115","https://openalex.org/I889804353"]},{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Song, Huan","raw_affiliation_strings":["Bosch Research North America","Robert Bosch GmBH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bosch Research North America","institution_ids":["https://openalex.org/I4210120115"]},{"raw_affiliation_string":"Robert Bosch GmBH","institution_ids":["https://openalex.org/I889804353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074371899","display_name":"Andreas Spanias","orcid":"https://orcid.org/0000-0003-0306-9348","observed_orcids":["https://orcid.org/0000-0003-0306-9348"]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Spanias, Andreas","raw_affiliation_strings":["Arizona State University ,","Arizona State University**"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University ,","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Arizona State University**","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9258000254631042,"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/T11309","display_name":"Music and Audio Processing","score":0.9258000254631042,"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/T10860","display_name":"Speech and Audio Processing","score":0.07090000063180923,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.0012000000569969416,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/audio-source-separation","display_name":"audio source separation","score":1.0},{"id":"https://openalex.org/keywords/multiscale-feature-extraction","display_name":"multi-scale feature extraction","score":0.9079999923706055},{"id":"https://openalex.org/keywords/dilated-convolution","display_name":"dilated convolution","score":0.8529999852180481},{"id":"https://openalex.org/keywords/dense-u-net","display_name":"Dense U-Net","score":0.8159999847412109},{"id":"https://openalex.org/keywords/wave-u-net","display_name":"Wave-U-Net","score":0.8389999866485596},{"id":"https://openalex.org/keywords/temporal-receptive-field","display_name":"temporal receptive field","score":0.8360000252723694},{"id":"https://openalex.org/keywords/dense-connections","display_name":"dense connections","score":0.8949999809265137},{"id":"https://openalex.org/keywords/u-net-architecture","display_name":"U-Net architecture","score":0.6629999876022339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8113800287246704},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.796007513999939},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6757159233093262},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6239060163497925},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5505958199501038},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5420277118682861},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5271990895271301},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5205907821655273},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.48892655968666077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4839804172515869},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.46924543380737305},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4592127799987793},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4480550289154053},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3785136044025421},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33025452494621277},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17476344108581543},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1547558605670929},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1904.04161","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.04161","pdf_url":"https://arxiv.org/pdf/1904.04161","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2928988674","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1904.04161.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1904.04161","doi":"https://doi.org/10.48550/arxiv.1904.04161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.04161","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.04161","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.04161","pdf_url":"https://arxiv.org/pdf/1904.04161","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.46000000834465027,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1985834699","https://openalex.org/W2079985975","https://openalex.org/W2127851351","https://openalex.org/W2167752533","https://openalex.org/W2519091744","https://openalex.org/W2552071709","https://openalex.org/W2600556233","https://openalex.org/W2669032454","https://openalex.org/W2774707525","https://openalex.org/W2916985722","https://openalex.org/W2962935966","https://openalex.org/W2963446712","https://openalex.org/W2963452667","https://openalex.org/W2963519193","https://openalex.org/W2964013315"],"related_works":["https://openalex.org/W3008237812","https://openalex.org/W3047483306","https://openalex.org/W2899376030","https://openalex.org/W3197769325","https://openalex.org/W2973667836","https://openalex.org/W2959203930","https://openalex.org/W2962865320","https://openalex.org/W3086800256","https://openalex.org/W2963154919","https://openalex.org/W3091656561","https://openalex.org/W2986771821","https://openalex.org/W3103105386","https://openalex.org/W3010364879","https://openalex.org/W2969278887","https://openalex.org/W2980844349","https://openalex.org/W3084879081","https://openalex.org/W2990711949","https://openalex.org/W3013880286","https://openalex.org/W2968708806","https://openalex.org/W3195587117"],"abstract_inverted_index":{"Modern":[0],"audio":[1],"source":[2,179],"separation":[3],"techniques":[4],"rely":[5],"on":[6,14,27,110,148,167,174],"optimizing":[7],"sequence":[8],"model":[9],"architectures":[10,30,52],"such":[11,31],"as,":[12],"1D-CNNs,":[13],"mixture":[15],"recordings":[16],"to":[17,20,139,155],"generalize":[18],"well":[19,56],"unseen":[21],"mixtures.":[22],"Specifically,":[23],"recent":[24],"focus":[25],"is":[26],"time-domain":[28],"based":[29],"as":[32],"Wave-U-Net":[33],"which":[34],"exploit":[35],"temporal":[36,99,141],"context":[37,95],"by":[38,96],"extracting":[39],"multi-scale":[40,72],"features.":[41],"However,":[42],"the":[43,46,105,111,126,145,149,161,168],"optimality":[44],"of":[45,92,107,131,170],"feature":[47,73,116],"extraction":[48,74,112],"process":[49,113],"in":[50],"these":[51],"has":[53],"not":[54],"been":[55],"investigated.":[57],"In":[58,153],"this":[59,77],"paper,":[60],"we":[61,79,163],"examine":[62],"and":[63,118,128],"recommend":[64],"critical":[65],"architectural":[66,172],"changes":[67],"that":[68,88,114],"forge":[69],"an":[70,157],"optimal":[71],"process.":[75],"To":[76],"end,":[78],"replace":[80],"regular":[81],"$1-$D":[82],"convolutions":[83,87],"with":[84],"adaptive":[85],"dilated":[86],"have":[89],"innate":[90],"capability":[91],"capturing":[93],"increased":[94],"using":[97],"large":[98],"receptive":[100],"fields.":[101],"We":[102,143],"also":[103,164],"investigate":[104],"impact":[106,169],"dense":[108,123],"connections":[109,124],"encourage":[115],"reuse":[117],"better":[119],"gradient":[120],"flow.":[121],"The":[122],"between":[125],"downsampling":[127],"upsampling":[129],"paths":[130],"a":[132],"U-Net":[133],"architecture":[134],"capture":[135],"multi-resolution":[136],"information":[137],"leading":[138],"improved":[140,158],"modelling.":[142],"evaluate":[144],"proposed":[146],"approaches":[147],"MUSDB":[150],"test":[151],"dataset.":[152],"addition":[154],"providing":[156],"performance":[159],"over":[160],"state-of-the-art,":[162],"provide":[165],"insights":[166],"different":[171],"choices":[173],"complex":[175],"data-driven":[176],"solutions":[177],"for":[178],"separation.":[180]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2025-10-10T00:00:00"}