{"id":"https://openalex.org/W2669032454","doi":"https://doi.org/10.1109/icassp.2017.7952158","title":"Improving music source separation based on deep neural networks through data augmentation and network blending","display_name":"Improving music source separation based on deep neural networks through data augmentation and network blending","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2669032454","doi":"https://doi.org/10.1109/icassp.2017.7952158","mag":"2669032454"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5010554448","display_name":"Stefan Uhlich","orcid":"https://orcid.org/0000-0003-3158-4945"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Stefan Uhlich","raw_affiliation_strings":["Sony European Technology Center (EuTEC), Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Sony European Technology Center (EuTEC), Stuttgart, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071761336","display_name":"Marcello Porcu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcello Porcu","raw_affiliation_strings":["Sony European Technology Center (EuTEC), Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Sony European Technology Center (EuTEC), Stuttgart, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058439547","display_name":"Franck Giron","orcid":"https://orcid.org/0000-0002-6960-1037"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Franck Giron","raw_affiliation_strings":["Sony European Technology Center (EuTEC), Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Sony European Technology Center (EuTEC), Stuttgart, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041481636","display_name":"Michael Enenkl","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Enenkl","raw_affiliation_strings":["Sony European Technology Center (EuTEC), Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Sony European Technology Center (EuTEC), Stuttgart, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007616499","display_name":"Thomas Kemp","orcid":"https://orcid.org/0000-0002-7570-5916"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Kemp","raw_affiliation_strings":["Sony European Technology Center (EuTEC), Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Sony European Technology Center (EuTEC), Stuttgart, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101589290","display_name":"Naoya Takahashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naoya Takahashi","raw_affiliation_strings":["Sony Kabushiki Kaisha, Minato-ku, Tokyo, JP"],"affiliations":[{"raw_affiliation_string":"Sony Kabushiki Kaisha, Minato-ku, Tokyo, JP","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuki Mitsufuji","raw_affiliation_strings":["Audio Technology Development Department, Sony Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Audio Technology Development Department, Sony Corporation, Tokyo, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5010554448"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.5271,"has_fulltext":false,"cited_by_count":193,"citation_normalized_percentile":{"value":0.99563884,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"261","last_page":"265"},"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":0.9998999834060669,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/overfitting","display_name":"Overfitting","score":0.8740310668945312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7825803756713867},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6332849264144897},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6329481601715088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5816950798034668},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5787100195884705},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5378716588020325},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.515568733215332},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5074064135551453},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.4780559837818146},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4658907651901245},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4605739116668701},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4357840418815613},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4135405421257019},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4067632555961609},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09388837218284607},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0921725332736969},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07074838876724243}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8740310668945312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7825803756713867},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6332849264144897},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6329481601715088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5816950798034668},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5787100195884705},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5378716588020325},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.515568733215332},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5074064135551453},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.4780559837818146},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4658907651901245},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4605739116668701},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4357840418815613},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4135405421257019},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4067632555961609},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09388837218284607},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0921725332736969},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07074838876724243},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7952158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1545453738","https://openalex.org/W1555814299","https://openalex.org/W1584895311","https://openalex.org/W1594771616","https://openalex.org/W1790748249","https://openalex.org/W1981755271","https://openalex.org/W2010575420","https://openalex.org/W2022668263","https://openalex.org/W2039844283","https://openalex.org/W2053165762","https://openalex.org/W2054804336","https://openalex.org/W2061212083","https://openalex.org/W2079735306","https://openalex.org/W2090681206","https://openalex.org/W2097361095","https://openalex.org/W2098950531","https://openalex.org/W2116244429","https://openalex.org/W2117438264","https://openalex.org/W2127851351","https://openalex.org/W2130789253","https://openalex.org/W2143027228","https://openalex.org/W2286859569","https://openalex.org/W2292743699","https://openalex.org/W2296724634","https://openalex.org/W2304609584","https://openalex.org/W2341535507","https://openalex.org/W2395156013","https://openalex.org/W2398243923","https://openalex.org/W2398306137","https://openalex.org/W2405258286","https://openalex.org/W2405589348","https://openalex.org/W2406222150","https://openalex.org/W2408744528","https://openalex.org/W2508884455","https://openalex.org/W2563534197","https://openalex.org/W2917831833","https://openalex.org/W2919115771","https://openalex.org/W3124794156","https://openalex.org/W4206180546","https://openalex.org/W6632656686","https://openalex.org/W6635089314","https://openalex.org/W6697040288","https://openalex.org/W6703949738","https://openalex.org/W6711778157","https://openalex.org/W6712594816","https://openalex.org/W6712656540","https://openalex.org/W6713519970","https://openalex.org/W6713676406","https://openalex.org/W6713966589"],"related_works":["https://openalex.org/W2989932438","https://openalex.org/W3099765033","https://openalex.org/W4285802257","https://openalex.org/W4380075502","https://openalex.org/W4223943233","https://openalex.org/W4312200629","https://openalex.org/W4360585206","https://openalex.org/W4361732492","https://openalex.org/W4360619137","https://openalex.org/W4246751904"],"abstract_inverted_index":{"This":[0,105],"paper":[1],"deals":[2],"with":[3],"the":[4,49,54,109,118],"separation":[5,68],"of":[6,41,85],"music":[7],"into":[8],"individual":[9],"instrument":[10],"tracks":[11],"which":[12],"is":[13,78],"known":[14],"to":[15,72],"be":[16],"a":[17,31,34,83,100],"challenging":[18],"problem.":[19],"We":[20],"describe":[21],"two":[22],"different":[23],"deep":[24],"neural":[25,87],"network":[26,88],"architectures":[27],"for":[28],"this":[29],"task,":[30],"feed-forward":[32],"and":[33,37,63,97],"recurrent":[35,55],"one,":[36],"show":[38,64],"that":[39,65,112],"each":[40],"them":[42],"yields":[43,108],"themselves":[44],"state-of-the":[45],"art":[46],"results":[47,111],"on":[48,117],"SiSEC":[50,119],"DSD100":[51,120],"dataset.":[52,121],"For":[53],"network,":[56],"we":[57,81,91],"use":[58],"data":[59,76],"augmentation":[60,77],"during":[61],"training":[62],"even":[66],"simple":[67],"networks":[69],"are":[70],"prone":[71],"overfitting":[73],"if":[74],"no":[75],"used.":[79],"Furthermore,":[80],"propose":[82],"blending":[84,106],"both":[86],"systems":[89],"where":[90],"linearly":[92],"combine":[93],"their":[94],"raw":[95],"outputs":[96],"then":[98],"perform":[99],"multi-channel":[101],"Wiener":[102],"filter":[103],"post-processing.":[104],"scheme":[107],"best":[110],"have":[113],"been":[114],"reported":[115],"to-date":[116]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":41},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":8}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}