{"id":"https://openalex.org/W1594771616","doi":"https://doi.org/10.1109/icassp.2015.7178348","title":"Deep neural network based instrument extraction from music","display_name":"Deep neural network based instrument extraction from music","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1594771616","doi":"https://doi.org/10.1109/icassp.2015.7178348","mag":"1594771616"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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/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":"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":["Sony Corporation, Audio Technology Development Department, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Corporation, Audio Technology Development Department, Tokyo, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010554448"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.3492,"has_fulltext":false,"cited_by_count":108,"citation_normalized_percentile":{"value":0.99072994,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2135","last_page":"2139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech 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":0.9993000030517578,"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/initialization","display_name":"Initialization","score":0.9307689666748047},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.7810842990875244},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7701472043991089},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.6233181953430176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5522666573524475},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4253774881362915},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3539566397666931}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.9307689666748047},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7810842990875244},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7701472043991089},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6233181953430176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5522666573524475},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4253774881362915},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3539566397666931},{"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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":39,"referenced_works":["https://openalex.org/W1584895311","https://openalex.org/W1607142029","https://openalex.org/W1755563775","https://openalex.org/W1932803568","https://openalex.org/W1992385219","https://openalex.org/W2022508996","https://openalex.org/W2022668263","https://openalex.org/W2025768430","https://openalex.org/W2031647436","https://openalex.org/W2035424729","https://openalex.org/W2037271374","https://openalex.org/W2052384514","https://openalex.org/W2053165762","https://openalex.org/W2096873754","https://openalex.org/W2097361095","https://openalex.org/W2101042021","https://openalex.org/W2116244429","https://openalex.org/W2127851351","https://openalex.org/W2146544734","https://openalex.org/W2149368536","https://openalex.org/W2156387975","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2167353662","https://openalex.org/W2242076280","https://openalex.org/W2405258286","https://openalex.org/W2949821452","https://openalex.org/W3150091332","https://openalex.org/W4285719527","https://openalex.org/W6635089314","https://openalex.org/W6636203886","https://openalex.org/W6648595712","https://openalex.org/W6657028776","https://openalex.org/W6658463413","https://openalex.org/W6674764686","https://openalex.org/W6684191040","https://openalex.org/W6690257645","https://openalex.org/W6713676406","https://openalex.org/W7071105756"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W3095877357","https://openalex.org/W2072565696","https://openalex.org/W10861731","https://openalex.org/W2050451745"],"abstract_inverted_index":{"This":[0,74],"paper":[1],"deals":[2],"with":[3,46],"the":[4,25,32,40,65,71,81,87,90,112],"extraction":[5,113],"of":[6,68,80,89,107,122],"an":[7],"instrument":[8,26,48],"from":[9,43,56],"music":[10],"by":[11],"using":[12,35,115],"a":[13,44,76,95,119],"deep":[14],"neural":[15,51],"network.":[16],"As":[17],"prior":[18],"information,":[19,37],"we":[20,38],"only":[21],"assume":[22],"to":[23,94],"know":[24],"types":[27],"that":[28],"are":[29],"present":[30],"in":[31],"mixture":[33],"and,":[34],"this":[36],"generate":[39],"training":[41,88],"data":[42],"database":[45],"solo":[47],"performances.":[49],"The":[50],"network":[52,91],"is":[53],"built":[54],"up":[55,86],"rectified":[57],"linear":[58],"units":[59],"where":[60],"each":[61,105],"hidden":[62,123],"layer":[63,82],"has":[64],"same":[66],"number":[67,121],"nodes":[69],"as":[70],"output":[72],"layer.":[73],"allows":[75],"least":[77],"squares":[78],"initialization":[79],"weights":[83],"and":[84,110],"speeds":[85],"considerably":[92],"compared":[93],"traditional":[96],"random":[97],"initialization.":[98],"We":[99],"give":[100],"results":[101],"for":[102,118],"two":[103],"mixtures,":[104],"consisting":[106],"three":[108],"instruments,":[109],"evaluate":[111],"performance":[114],"BSS":[116],"Eval":[117],"varying":[120],"layers.":[124]},"counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":22},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}