{"id":"https://openalex.org/W1496920063","doi":"https://doi.org/10.1109/icassp.2015.7178063","title":"Vocal activity informed singing voice separation with the iKala dataset","display_name":"Vocal activity informed singing voice separation with the iKala dataset","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1496920063","doi":"https://doi.org/10.1109/icassp.2015.7178063","mag":"1496920063"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178063","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":"conference-paper","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/A5068325856","display_name":"Tak-Shing Chan","orcid":"https://orcid.org/0000-0002-8302-3974"},"institutions":[{"id":"https://openalex.org/I29955533","display_name":"Center for Information Technology","ror":"https://ror.org/03jh5a977","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I29955533"]},{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Tak-Shing Chan","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan","(Research Center for Information Technology Innovation, Academia Sinica, Taiwan)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"(Research Center for Information Technology Innovation, Academia Sinica, Taiwan)","institution_ids":["https://openalex.org/I29955533"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074676744","display_name":"Tzu\u2010Chun Yeh","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tzu-Chun Yeh","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University, Taiwan","Department of Computer Science and Information Engineering, National Taiwan Univ., Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan Univ., Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050120270","display_name":"Zhe-Cheng Fan","orcid":"https://orcid.org/0000-0003-0495-0436"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Zhe-Cheng Fan","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University, Taiwan","Department of Computer Science and Information Engineering, National Taiwan Univ., Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan Univ., Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101539571","display_name":"Hung-Wei Chen","orcid":"https://orcid.org/0000-0002-8185-3544"},"institutions":[{"id":"https://openalex.org/I4210148979","display_name":"MediaTek (Taiwan)","ror":"https://ror.org/05g9jck81","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210148979"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Wei Chen","raw_affiliation_strings":["iKala Interactive Media Inc., Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iKala Interactive Media Inc., Taiwan","institution_ids":["https://openalex.org/I4210148979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038264558","display_name":"Li Su","orcid":"https://orcid.org/0000-0003-4275-8832"},"institutions":[{"id":"https://openalex.org/I29955533","display_name":"Center for Information Technology","ror":"https://ror.org/03jh5a977","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I29955533"]},{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Li Su","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan","(Research Center for Information Technology Innovation, Academia Sinica, Taiwan)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"(Research Center for Information Technology Innovation, Academia Sinica, Taiwan)","institution_ids":["https://openalex.org/I29955533"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061291906","display_name":"Yi\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0002-2724-6161"},"institutions":[{"id":"https://openalex.org/I29955533","display_name":"Center for Information Technology","ror":"https://ror.org/03jh5a977","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I29955533"]},{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan","(Research Center for Information Technology Innovation, Academia Sinica, Taiwan)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"(Research Center for Information Technology Innovation, Academia Sinica, Taiwan)","institution_ids":["https://openalex.org/I29955533"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073451247","display_name":"Jyh\u2010Shing Roger Jang","orcid":"https://orcid.org/0000-0002-7319-9095"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Roger Jang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University, Taiwan","Department of Computer Science and Information Engineering, National Taiwan Univ., Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan Univ., Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.149,"has_fulltext":false,"cited_by_count":133,"citation_normalized_percentile":{"value":0.99111692,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"718","last_page":"722"},"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":0.9995999932289124,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/singing","display_name":"Singing","score":0.9321544766426086},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.739274799823761},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.7213156819343567},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6626337766647339},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6465499997138977},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.6145408153533936},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5955355167388916},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5756217837333679},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4919314384460449},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4780612289905548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4518243670463562},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37652015686035156},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24385622143745422},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08534437417984009},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06059315800666809}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9321544766426086},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.739274799823761},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.7213156819343567},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6626337766647339},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6465499997138977},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.6145408153533936},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5955355167388916},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5756217837333679},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4919314384460449},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4780612289905548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4518243670463562},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37652015686035156},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24385622143745422},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08534437417984009},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06059315800666809},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178063","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":38,"referenced_works":["https://openalex.org/W87112183","https://openalex.org/W160800111","https://openalex.org/W1669104078","https://openalex.org/W1736339626","https://openalex.org/W1974186229","https://openalex.org/W1974493579","https://openalex.org/W1979654135","https://openalex.org/W2007664495","https://openalex.org/W2017548439","https://openalex.org/W2029878753","https://openalex.org/W2036339641","https://openalex.org/W2048310341","https://openalex.org/W2067200573","https://openalex.org/W2069681747","https://openalex.org/W2086357144","https://openalex.org/W2089204011","https://openalex.org/W2113217465","https://openalex.org/W2124539664","https://openalex.org/W2127851351","https://openalex.org/W2144774941","https://openalex.org/W2145905122","https://openalex.org/W2145962650","https://openalex.org/W2147437692","https://openalex.org/W2158216966","https://openalex.org/W2164098335","https://openalex.org/W2295824433","https://openalex.org/W2296573765","https://openalex.org/W2399539226","https://openalex.org/W2400577536","https://openalex.org/W2403380333","https://openalex.org/W2403623315","https://openalex.org/W6678799340","https://openalex.org/W6697668227","https://openalex.org/W6712695463","https://openalex.org/W6712801791","https://openalex.org/W6713339159","https://openalex.org/W6713353306","https://openalex.org/W6929385289"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2024908463","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W1969227305","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W3093803487","https://openalex.org/W2077498359"],"abstract_inverted_index":{"A":[0],"new":[1,39,82],"algorithm":[2,15,91],"is":[3,16],"proposed":[4],"for":[5,56],"robust":[6],"principal":[7],"component":[8],"analysis":[9],"with":[10],"predefined":[11],"sparsity":[12],"patterns.":[13],"The":[14],"then":[17],"applied":[18],"to":[19],"separate":[20],"the":[21,25,52,67,77,81,87,90,93,95],"singing":[22,57],"voice":[23,58],"from":[24],"instrumental":[26],"accompaniment":[27],"using":[28],"vocal":[29],"activity":[30],"information.":[31],"To":[32],"evaluate":[33],"its":[34],"performance,":[35],"we":[36],"construct":[37],"a":[38],"publicly":[40],"available":[41],"iKala":[42,83],"dataset":[43,55,79,84],"that":[44,86],"features":[45],"longer":[46],"durations":[47],"and":[48,80],"higher":[49],"quality":[50],"than":[51],"existing":[53],"MIR-1K":[54,78],"separation.":[59],"Part":[60],"of":[61],"it":[62],"will":[63],"be":[64],"used":[65],"in":[66],"MIREX":[68],"Singing":[69],"Voice":[70],"Separation":[71],"task.":[72],"Experimental":[73],"results":[74,97],"on":[75],"both":[76],"confirmed":[85],"more":[88],"informed":[89],"is,":[92],"better":[94],"separation":[96],"are.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":29},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":22},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":3}],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2025-10-10T00:00:00"}
