{"id":"https://openalex.org/W2921462073","doi":"https://doi.org/10.23919/apsipa.2018.8659640","title":"Unsupervised Singing Voice Separation Using Gammatone Auditory Filterbank and Constraint Robust Principal Component Analysis","display_name":"Unsupervised Singing Voice Separation Using Gammatone Auditory Filterbank and Constraint Robust Principal Component Analysis","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2921462073","doi":"https://doi.org/10.23919/apsipa.2018.8659640","mag":"2921462073"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659640","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dspace.jaist.ac.jp/dspace/bitstream/10119/15777/1/2909.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100448828","display_name":"Feng Li","orcid":"https://orcid.org/0000-0001-7633-7863"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Feng Li","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055059119","display_name":"Masato Akagi","orcid":"https://orcid.org/0000-0003-2450-6754"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Akagi","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100448828"],"corresponding_institution_ids":["https://openalex.org/I177738480"],"apc_list":null,"apc_paid":null,"fwci":0.1658,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50546306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1924","last_page":"1928"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9994999766349792,"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/filter-bank","display_name":"Filter bank","score":0.8340481519699097},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7579145431518555},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7294544577598572},{"id":"https://openalex.org/keywords/robust-principal-component-analysis","display_name":"Robust principal component analysis","score":0.7290419340133667},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.6986879110336304},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6480072736740112},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6248997449874878},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46815967559814453},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4441496431827545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4172244071960449},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.4155391454696655},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.4150264263153076},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.22542759776115417},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13504469394683838},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09955668449401855},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.06812801957130432}],"concepts":[{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.8340481519699097},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7579145431518555},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7294544577598572},{"id":"https://openalex.org/C2777749129","wikidata":"https://www.wikidata.org/wiki/Q17148469","display_name":"Robust principal component analysis","level":3,"score":0.7290419340133667},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.6986879110336304},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6480072736740112},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6248997449874878},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46815967559814453},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4441496431827545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4172244071960449},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.4155391454696655},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.4150264263153076},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.22542759776115417},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13504469394683838},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09955668449401855},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.06812801957130432},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/apsipa.2018.8659640","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01333:0004032847","is_oa":true,"landing_page_url":"http://hdl.handle.net/10119/15777","pdf_url":"https://dspace.jaist.ac.jp/dspace/bitstream/10119/15777/1/2909.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01333:0004032847","is_oa":true,"landing_page_url":"http://hdl.handle.net/10119/15777","pdf_url":"https://dspace.jaist.ac.jp/dspace/bitstream/10119/15777/1/2909.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2921462073.pdf","grobid_xml":"https://content.openalex.org/works/W2921462073.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1482071412","https://openalex.org/W1594771616","https://openalex.org/W1736339626","https://openalex.org/W1967834974","https://openalex.org/W2002016907","https://openalex.org/W2009702064","https://openalex.org/W2022668263","https://openalex.org/W2038678505","https://openalex.org/W2098950531","https://openalex.org/W2111007352","https://openalex.org/W2116244429","https://openalex.org/W2124539664","https://openalex.org/W2127851351","https://openalex.org/W2145962650","https://openalex.org/W2147455188","https://openalex.org/W2149425615","https://openalex.org/W2150415460","https://openalex.org/W2164098335","https://openalex.org/W2221409856","https://openalex.org/W2403623315","https://openalex.org/W2405258286","https://openalex.org/W2552071709","https://openalex.org/W2561557072","https://openalex.org/W2765849780","https://openalex.org/W2902298796","https://openalex.org/W2916985722","https://openalex.org/W6676368125","https://openalex.org/W6678626330","https://openalex.org/W6688843265","https://openalex.org/W6713353306","https://openalex.org/W6713676406","https://openalex.org/W6759212570"],"related_works":["https://openalex.org/W1889291648","https://openalex.org/W3094316140","https://openalex.org/W3133205200","https://openalex.org/W2898145319","https://openalex.org/W4289363934","https://openalex.org/W2098101267","https://openalex.org/W2059119686","https://openalex.org/W2533590149","https://openalex.org/W2898606530","https://openalex.org/W4289362680"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,11,44,51],"unsupervised":[4],"singing":[5],"voice":[6],"separation":[7,89],"algorithm":[8,85],"which":[9],"using":[10,50,76],"extension":[12,45],"of":[13,46,69],"robust":[14],"principal":[15],"component":[16],"analysis":[17,38],"(RPCA)":[18],"with":[19],"rank-1":[20],"constraint":[21],"(CRPCA)":[22],"based":[23,55],"on":[24,28,36,48,56,91],"gammatone":[25,57],"auditory":[26,58],"filterbank":[27],"cochleagram.":[29],"Unlike":[30],"the":[31,67,83],"conventional":[32],"algorithms":[33],"that":[34,82],"focus":[35],"spectrogram":[37],"or":[39],"its":[40],"variants,":[41],"we":[42],"develop":[43],"RPCA":[47],"cochleagram":[49],"alternative":[52],"time-frequency":[53,63],"representation":[54],"filterbank.":[59],"We":[60],"also":[61],"apply":[62],"masking":[64],"to":[65],"improve":[66],"results":[68,80],"separated":[70],"low-rank":[71],"and":[72],"sparse":[73],"matrices":[74],"by":[75],"CRPCA":[77],"method.":[78],"Evaluation":[79],"demonstrate":[81],"proposed":[84],"can":[86],"achieve":[87],"better":[88],"performance":[90],"MIR-IK":[92],"dataset.":[93]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}