{"id":"https://openalex.org/W141691577","doi":"https://doi.org/10.21437/interspeech.2011-498","title":"Single channel speech music separation using nonnegative matrix factorization with sliding windows and spectral masks","display_name":"Single channel speech music separation using nonnegative matrix factorization with sliding windows and spectral masks","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W141691577","doi":"https://doi.org/10.21437/interspeech.2011-498","mag":"141691577"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-498","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5013467271","display_name":"Emad M. Grais","orcid":"https://orcid.org/0000-0002-6387-0981"},"institutions":[{"id":"https://openalex.org/I134235054","display_name":"Sabanc\u0131 \u00dcniversitesi","ror":"https://ror.org/049asqa32","country_code":"TR","type":"education","lineage":["https://openalex.org/I134235054"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Emad M. Grais","raw_affiliation_strings":["Sabanci Univ.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sabanci Univ.#TAB#","institution_ids":["https://openalex.org/I134235054"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065994318","display_name":"Hakan Erdo\u011fan","orcid":"https://orcid.org/0000-0003-3140-8642"},"institutions":[{"id":"https://openalex.org/I134235054","display_name":"Sabanc\u0131 \u00dcniversitesi","ror":"https://ror.org/049asqa32","country_code":"TR","type":"education","lineage":["https://openalex.org/I134235054"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Hakan Erdogan","raw_affiliation_strings":["Sabanci Univ.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sabanci Univ.#TAB#","institution_ids":["https://openalex.org/I134235054"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I134235054"],"apc_list":null,"apc_paid":null,"fwci":2.7803,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.91968658,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1773","last_page":"1776"},"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":0.9995999932289124,"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":0.9994000196456909,"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/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.9250720739364624},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.9211124181747437},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.7032633423805237},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6354163885116577},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5722629427909851},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.527155339717865},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.523469090461731},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.4796333909034729},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47645998001098633},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46639105677604675},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.46458959579467773},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.45755282044410706},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40554967522621155},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37957802414894104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34273263812065125},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10796380043029785},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09329333901405334}],"concepts":[{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.9250720739364624},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9211124181747437},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.7032633423805237},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6354163885116577},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5722629427909851},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.527155339717865},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.523469090461731},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.4796333909034729},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47645998001098633},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46639105677604675},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.46458959579467773},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.45755282044410706},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40554967522621155},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37957802414894104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34273263812065125},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10796380043029785},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09329333901405334},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2011-498","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},{"id":"pmh:oai:research.sabanciuniv.edu:17516","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402254","display_name":"Sabanci University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I134235054","host_organization_name":"Sabanc\u0131 \u00dcniversitesi","host_organization_lineage":["https://openalex.org/I134235054"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:alma.44SUR_INST:11139052640002346","is_oa":false,"landing_page_url":"https://openresearch.surrey.ac.uk/esploro/outputs/conferencePresentation/Single-channel-speech-music-separation-using/99513033602346","pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:epubs.surrey.ac.uk:840744","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/840744/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400680","display_name":"Surrey Research Insight Open Access (The University of Surrey)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28290843","host_organization_name":"University of Surrey","host_organization_lineage":["https://openalex.org/I28290843"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W146976060","https://openalex.org/W185399533","https://openalex.org/W2045402776","https://openalex.org/W2127851351","https://openalex.org/W2135029798","https://openalex.org/W2146544734","https://openalex.org/W2150415460","https://openalex.org/W2158291955","https://openalex.org/W3143596294"],"related_works":["https://openalex.org/W2123043102","https://openalex.org/W2577807713","https://openalex.org/W2098101267","https://openalex.org/W2037504162","https://openalex.org/W2774154397","https://openalex.org/W2921513691","https://openalex.org/W1979654135","https://openalex.org/W2156699640","https://openalex.org/W2081322759","https://openalex.org/W2156181515"],"abstract_inverted_index":{"A":[0],"single":[1,56],"channel":[2],"speech-music":[3],"separation":[4],"algorithm":[5],"based":[6],"on":[7],"nonnegative":[8],"matrix":[9],"factorization":[10],"(NMF)":[11],"with":[12,62],"sliding":[13],"windows":[14],"and":[15,105],"spectral":[16,39,57,64,107],"masks":[17],"is":[18,76,103,109,117,139],"proposed":[19],"in":[20,36,67,133],"this":[21],"work.":[22],"We":[23],"train":[24],"a":[25,55,84,106],"set":[26],"of":[27,46,54,88,129],"basis":[28,91],"vectors":[29,92],"for":[30,93,100],"each":[31,101,130],"source":[32,102,131],"signal":[33,123,132],"using":[34,111],"NMF":[35,53,75,147],"the":[37,44,47,72,89,121,127,134,145],"magnitude":[38,81],"domain.":[40],"Rather":[41],"than":[42,144],"forming":[43],"columns":[45],"matrices":[48],"to":[49,78,119,125,141],"be":[50],"decomposed":[51],"by":[52],"frame,":[58],"we":[59],"build":[60],"them":[61],"multiple":[63],"frames":[65],"stacked":[66],"one":[68],"column.":[69],"After":[70],"observing":[71],"mixed":[73,122,135],"signal,":[74],"used":[77,118],"decompose":[79],"its":[80],"spectra":[82],"into":[83],"weighted":[85],"linear":[86],"combination":[87],"trained":[90],"both":[94],"sources.":[95],"An":[96],"initial":[97,113],"spectrogram":[98,124],"estimate":[99],"found,":[104],"mask":[108,116],"built":[110],"these":[112],"estimates.":[114],"This":[115],"weight":[120],"find":[126],"contributions":[128],"signal.":[136],"The":[137],"method":[138],"shown":[140],"perform":[142],"better":[143],"conventional":[146],"approach.":[148],"Copyright":[149],"\u00a9":[150],"2011":[151],"ISCA.":[152]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}