{"id":"https://openalex.org/W3090632540","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207053","title":"Using a Neural Network Codec Approximation Loss to Improve Source Separation Performance in Limited Capacity Networks","display_name":"Using a Neural Network Codec Approximation Loss to Improve Source Separation Performance in Limited Capacity Networks","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3090632540","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207053","mag":"3090632540"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/1721.1/137109","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037474835","display_name":"Ishwarya Ananthabhotla","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142372","display_name":"Human Media","ror":"https://ror.org/04072nk43","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210142372"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ishwarya Ananthabhotla","raw_affiliation_strings":["Responsive Environments, MIT Media Lab, Cambridge, USA"],"affiliations":[{"raw_affiliation_string":"Responsive Environments, MIT Media Lab, Cambridge, USA","institution_ids":["https://openalex.org/I4210142372"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001413512","display_name":"Sebastian Ewert","orcid":"https://orcid.org/0000-0002-0718-0476"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sebastian Ewert","raw_affiliation_strings":["Spotify, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Spotify, Berlin, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086159548","display_name":"Joseph A. Paradiso","orcid":"https://orcid.org/0000-0002-0719-7104"},"institutions":[{"id":"https://openalex.org/I4210142372","display_name":"Human Media","ror":"https://ror.org/04072nk43","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210142372"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph A. Paradiso","raw_affiliation_strings":["Responsive Environments, MIT Media Lab, Cambridge, USA"],"affiliations":[{"raw_affiliation_string":"Responsive Environments, MIT Media Lab, Cambridge, USA","institution_ids":["https://openalex.org/I4210142372"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037474835"],"corresponding_institution_ids":["https://openalex.org/I4210142372"],"apc_list":null,"apc_paid":null,"fwci":0.1521,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.44731183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/computer-science","display_name":"Computer science","score":0.8094626665115356},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6165363788604736},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5908128619194031},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46592068672180176},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4592118263244629},{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.44491708278656006},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4273628890514374},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4224981367588043},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.23491773009300232},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13346418738365173}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8094626665115356},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6165363788604736},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5908128619194031},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46592068672180176},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4592118263244629},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.44491708278656006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4273628890514374},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4224981367588043},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.23491773009300232},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13346418738365173},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/137109","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/137109","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MIT web domain","raw_type":"Article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/137109.2","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/137109.2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MIT web domain","raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/137109","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/137109","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MIT web domain","raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1901129140","https://openalex.org/W2046869671","https://openalex.org/W2119144962","https://openalex.org/W2134797427","https://openalex.org/W2141998673","https://openalex.org/W2331128040","https://openalex.org/W2514828952","https://openalex.org/W2531409750","https://openalex.org/W2774707525","https://openalex.org/W2783538964","https://openalex.org/W2786008273","https://openalex.org/W2805233667","https://openalex.org/W2891607145","https://openalex.org/W2892129657","https://openalex.org/W2917340025","https://openalex.org/W2963125010","https://openalex.org/W2963141945","https://openalex.org/W2963452667","https://openalex.org/W2964299589","https://openalex.org/W2972443522","https://openalex.org/W2982030720","https://openalex.org/W4298310324","https://openalex.org/W6639824700","https://openalex.org/W6677580257","https://openalex.org/W6679909955","https://openalex.org/W6702130928","https://openalex.org/W6746914816","https://openalex.org/W6748015549","https://openalex.org/W6751512325","https://openalex.org/W6753100508","https://openalex.org/W6766320909"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"A":[0],"growing":[1],"need":[2],"for":[3,119,149,156],"on-device":[4],"machine":[5],"learning":[6],"has":[7],"led":[8],"to":[9,40,59,71,89,108],"an":[10,64,115],"increased":[11],"interest":[12],"in":[13,31,117,132],"light-weight":[14,86],"neural":[15,87,157],"networks":[16,88,121],"that":[17],"lower":[18],"model":[19,79,142],"complexity":[20],"while":[21],"retaining":[22],"performance.":[23],"While":[24],"a":[25,57,73],"variety":[26],"of":[27,63,128],"general-purpose":[28],"techniques":[29],"exist":[30],"this":[32,48,69],"context,":[33],"very":[34],"few":[35],"approaches":[36],"exploit":[37],"domain-specific":[38],"properties":[39,94],"further":[41],"improve":[42],"upon":[43],"the":[44,61,77,81,126,129,136,147],"capacity-performance":[45],"trade-off.":[46],"In":[47],"paper,":[49],"extending":[50],"our":[51,83,106],"prior":[52],"work":[53,145],"[1],":[54],"we":[55],"train":[56],"network":[58,70,131],"emulate":[60],"behaviour":[62,127],"audio":[65,110],"codec":[66],"and":[67,134,141],"use":[68],"construct":[72],"loss.":[74],"By":[75],"approximating":[76],"psychoacoustic":[78],"underlying":[80],"codec,":[82],"approach":[84],"enables":[85],"focus":[90],"on":[91,100],"perceptually":[92],"relevant":[93],"without":[95],"wasting":[96],"their":[97],"limited":[98],"capacity":[99],"imperceptible":[101],"signal":[102],"components.":[103],"We":[104],"adapt":[105],"method":[107],"two":[109],"source":[111],"separation":[112],"tasks,":[113],"demonstrate":[114],"improvement":[116],"performance":[118,139],"small-scale":[120],"via":[122],"listening":[123],"tests,":[124],"characterize":[125],"loss":[130],"detail,":[133],"quantify":[135],"relationship":[137],"between":[138],"gain":[140],"capacity.":[143],"Our":[144],"illustrates":[146],"potential":[148],"incorporating":[150],"perceptual":[151],"principles":[152],"into":[153],"objective":[154],"functions":[155],"networks.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}