{"id":"https://openalex.org/W2765586514","doi":"https://doi.org/10.1145/3123266.3123386","title":"Discriminative Training of Complex-valued Deep Recurrent Neural Network for Singing Voice Separation","display_name":"Discriminative Training of Complex-valued Deep Recurrent Neural Network for Singing Voice Separation","publication_year":2017,"publication_date":"2017-10-19","ids":{"openalex":"https://openalex.org/W2765586514","doi":"https://doi.org/10.1145/3123266.3123386","mag":"2765586514"},"language":"en","primary_location":{"id":"doi:10.1145/3123266.3123386","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","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/A5026413645","display_name":"Yuan-Shan Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yuan-Shan Lee","raw_affiliation_strings":["National Central University, Taoyuan City, Taiwan Roc"],"affiliations":[{"raw_affiliation_string":"National Central University, Taoyuan City, Taiwan Roc","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004506161","display_name":"Kuo Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuo Yu","raw_affiliation_strings":["National Central University, Taoyuan City, Taiwan Roc"],"affiliations":[{"raw_affiliation_string":"National Central University, Taoyuan City, Taiwan Roc","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035647047","display_name":"Sih-Huei Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Sih-Huei Chen","raw_affiliation_strings":["National Central University, Taoyuan City, Taiwan Roc"],"affiliations":[{"raw_affiliation_string":"National Central University, Taoyuan City, Taiwan Roc","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029325015","display_name":"Jia\u2010Ching Wang","orcid":"https://orcid.org/0000-0003-0024-6732"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jia-Ching Wang","raw_affiliation_strings":["National Central University, Taoyuan City, Taiwan Roc"],"affiliations":[{"raw_affiliation_string":"National Central University, Taoyuan City, Taiwan Roc","institution_ids":["https://openalex.org/I22265921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5026413645"],"corresponding_institution_ids":["https://openalex.org/I22265921"],"apc_list":null,"apc_paid":null,"fwci":0.1849,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.46829504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1327","last_page":"1335"},"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":0.9997000098228455,"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":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.7646529674530029},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7304562330245972},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6419551968574524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.612650990486145},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5865358114242554},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5844833254814148},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.5564370155334473},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5531566739082336},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4757620692253113},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4669547975063324},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.43767234683036804},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3445240259170532},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.3152637183666229},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12953105568885803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646529674530029},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7304562330245972},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6419551968574524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.612650990486145},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5865358114242554},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5844833254814148},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.5564370155334473},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5531566739082336},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4757620692253113},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4669547975063324},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.43767234683036804},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3445240259170532},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.3152637183666229},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12953105568885803},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3123266.3123386","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2044893557","https://openalex.org/W2048142341","https://openalex.org/W2065234731","https://openalex.org/W2069681747","https://openalex.org/W2127851351","https://openalex.org/W2291877678","https://openalex.org/W2404724332","https://openalex.org/W2406737436","https://openalex.org/W3140025309","https://openalex.org/W6662305780"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2366077683","https://openalex.org/W4205619918","https://openalex.org/W2059119686"],"abstract_inverted_index":{"Deep":[0],"neural":[1,49],"networks":[2],"(DNN)":[3],"have":[4,24],"performed":[5],"impressively":[6],"in":[7],"the":[8,60,72,76,88,92,107,111,123,127,138,144,155,163,169,182,186],"processing":[9,35],"of":[10,38,71,110,126,140],"multimedia":[11,39],"signals.":[12],"Most":[13],"DNN-based":[14,188],"approaches":[15],"were":[16],"developed":[17],"to":[18,86,105],"handle":[19],"real-valued":[20],"data;":[21],"very":[22],"few":[23],"been":[25],"designed":[26],"for":[27,34,52],"complex-valued":[28,46,61,108],"data,":[29],"despite":[30],"their":[31],"being":[32],"essential":[33],"various":[36],"types":[37],"signal.":[40,98],"Accordingly,":[41],"this":[42],"work":[43],"presents":[44],"a":[45,96,150,173],"deep":[47],"recurrent":[48],"network":[50],"(C-DRNN)":[51],"singing":[53,89,174],"voice":[54,90,175],"separation.":[55],"The":[56,82,129,147],"C-DRNN":[57,73],"operates":[58],"on":[59],"short-time":[62],"discrete":[63],"Fourier":[64],"transform":[65],"(STFT)":[66],"domain.":[67],"A":[68],"key":[69],"aspect":[70],"is":[74,85,103,131,149,166],"that":[75,136,153,181],"activations":[77],"and":[78,91,172],"weights":[79],"are":[80,120],"complex-valued.":[81],"goal":[83],"herein":[84],"reconstruct":[87],"background":[93],"music":[94],"from":[95],"mixed":[97],"For":[99],"error":[100],"back-propagation,":[101],"CR-calculus":[102],"utilized":[104],"calculate":[106],"gradients":[109],"objective":[112,124],"function.":[113],"To":[114],"reinforce":[115],"model":[116],"regularity,":[117],"two":[118,159],"constraints":[119],"incorporated":[121],"into":[122],"function":[125],"C-DRNN.":[128],"first":[130],"an":[132],"additional":[133],"masking":[134],"layer":[135],"ensures":[137],"sum":[139],"separated":[141,160],"sources":[142],"equals":[143],"input":[145],"mixture.":[146],"second":[148],"discriminative":[151],"term":[152],"preserves":[154],"mutual":[156],"difference":[157],"between":[158],"sources.":[161],"Finally,":[162],"proposed":[164,183],"method":[165,184],"evaluated":[167],"using":[168],"MIR-1K":[170],"dataset":[171],"separation":[176],"task.":[177],"Experimental":[178],"results":[179],"demonstrate":[180],"outperforms":[185],"state-of-the-art":[187],"methods.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}