{"id":"https://openalex.org/W85184699","doi":null,"title":"Separation of Sound Sources by Convolutive Sparse Coding","display_name":"Separation of Sound Sources by Convolutive Sparse Coding","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W85184699","mag":"85184699"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.384.8415","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.384.8415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://isca-speech.org/archive_open/archive_papers/sapa_04/sap4_55.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5049691461","display_name":"Tuomas I. Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729","observed_orcids":["https://orcid.org/0000-0002-4604-9729"]},"institutions":[{"id":"https://openalex.org/I4387152565","display_name":"Tampere University of Technology","ror":"https://ror.org/02ba3pt07","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849","https://openalex.org/I4387152565"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["[Tampere Univ. of Tech.]"],"raw_orcid":"https://orcid.org/0000-0002-4604-9729","affiliations":[{"raw_affiliation_string":"[Tampere Univ. of Tech.]","institution_ids":["https://openalex.org/I4387152565"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5049691461"],"corresponding_institution_ids":["https://openalex.org/I4387152565"],"apc_list":null,"apc_paid":null,"fwci":12.2638,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":{"value":0.98751903,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"55","last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.4912000000476837,"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":0.4912000000476837,"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":0.29980000853538513,"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":0.17090000212192535,"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/sound-source-separation","display_name":"sound source separation","score":0.9760000109672546},{"id":"https://openalex.org/keywords/iterative-parameter-estimation","display_name":"iterative parameter estimation","score":0.5910000205039978},{"id":"https://openalex.org/keywords/sparse-coding","display_name":"sparse coding","score":0.5590000152587891},{"id":"https://openalex.org/keywords/drum-sounds","display_name":"drum sounds","score":0.6759999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6622234582901001},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6530011892318726},{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.576545000076294},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5714611411094666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5619354248046875},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5217805504798889},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.45544078946113586},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4531250298023224},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.45202186703681946},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.42592793703079224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36097925901412964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35103121399879456},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2970561683177948},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2367086410522461},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14023008942604065},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13010504841804504},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.384.8415","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.384.8415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://isca-speech.org/archive_open/archive_papers/sapa_04/sap4_55.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.74.3281","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.74.3281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.tut.fi/sgn/arg/music/tuomasv/sapa2004.pdf","raw_type":"text"},{"id":"mag:85184699","doi":null,"is_oa":false,"landing_page_url":"https://www.sapaworkshops.org/2004/papers/55.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Conference of the International Speech Communication Association","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W29021047","https://openalex.org/W186036538","https://openalex.org/W197919343","https://openalex.org/W1531715242","https://openalex.org/W1537504396","https://openalex.org/W1565658805","https://openalex.org/W1958993123","https://openalex.org/W2027884847","https://openalex.org/W2043843997","https://openalex.org/W2048854038","https://openalex.org/W2075665712","https://openalex.org/W2097191389","https://openalex.org/W2104298926","https://openalex.org/W2105464873","https://openalex.org/W2115857766","https://openalex.org/W2116216716","https://openalex.org/W2120847449","https://openalex.org/W2135029798"],"related_works":["https://openalex.org/W2961034873","https://openalex.org/W186036538","https://openalex.org/W3023781931","https://openalex.org/W7095372513","https://openalex.org/W5835172","https://openalex.org/W7097474771","https://openalex.org/W2147011586","https://openalex.org/W7100572072","https://openalex.org/W2110233288","https://openalex.org/W1997854217"],"abstract_inverted_index":{"An":[0,47],"algorithm":[1,49,58,117],"for":[2,37,52,83],"the":[3,53,55,63,67,79,90,94,107],"separation":[4,108],"of":[5,35,69,73,88,93,109,134],"sound":[6],"sources":[7,111,123],"is":[8,12,29,50,59,75,98,118],"presented.":[9],"Each":[10],"source":[11,27],"parametrized":[13],"as":[14],"a":[15,18],"convolution":[16],"between":[17],"time-frequency":[19],"magnitude":[20],"spectrogam":[21],"and":[22,42,66,105],"an":[23],"onset":[24,84],"vector.":[25],"The":[26,57,71,100,116],"model":[28],"able":[30,119],"to":[31,120],"represent":[32],"several":[33],"types":[34],"sounds,":[36],"example":[38],"repetitive":[39],"drum":[40],"sounds":[41,44],"harmonic":[43,135],"with":[45],"modulations.":[46],"iterative":[48],"proposed":[51],"estimation":[54],"parameters.":[56],"based":[60],"on":[61],"minimizing":[62],"reconstruction":[64],"error":[65],"number":[68,72],"onsets.":[70],"onsets":[74],"minimized":[76],"by":[77],"applying":[78],"sparse":[80],"coding":[81],"scheme":[82],"vectors.":[85],"A":[86],"way":[87],"modeling":[89],"loudness":[91],"perception":[92],"human":[95],"auditory":[96],"system":[97],"proposed.":[99],"method":[101],"compresses":[102],"high-energy":[103],"sources,":[104],"enables":[106],"lowenergy":[110],"which":[112],"are":[113,139],"perceptually":[114],"significant.":[115],"separate":[121],"meaningful":[122],"from":[124],"real-world":[125],"signals.":[126],"Simulation":[127],"experiments":[128],"were":[129],"carried":[130],"out":[131],"using":[132],"mixtures":[133],"instruments.":[136],"Demonstration":[137],"signals":[138],"available":[140],"at":[141]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}