{"id":"https://openalex.org/W1984517456","doi":"https://doi.org/10.1109/mmsp.2013.6659326","title":"Factors in factorization: Does better audio source separation imply better polyphonic music transcription?","display_name":"Factors in factorization: Does better audio source separation imply better polyphonic music transcription?","publication_year":2013,"publication_date":"2013-09-01","ids":{"openalex":"https://openalex.org/W1984517456","doi":"https://doi.org/10.1109/mmsp.2013.6659326","mag":"1984517456"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2013.6659326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2013.6659326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 15th International Workshop on Multimedia Signal Processing (MMSP)","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/A5057729011","display_name":"Tiago Fernandes Tavares","orcid":"https://orcid.org/0000-0002-9104-613X"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tiago Fernandes Tavares","raw_affiliation_strings":["Department of Computer Science, University of Victoria, BC, Canada","[Department of Computer Science, University of Victoria, Victoria, BC, Canada.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Victoria, BC, Canada","institution_ids":["https://openalex.org/I212119943"]},{"raw_affiliation_string":"[Department of Computer Science, University of Victoria, Victoria, BC, Canada.]","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010445045","display_name":"George Tzanetakis","orcid":"https://orcid.org/0000-0002-6844-7912"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"George Tzanetakis","raw_affiliation_strings":["Department of Computer Science, University of Victoria, BC, Canada","[Department of Computer Science, University of Victoria, Victoria, BC, Canada.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Victoria, BC, Canada","institution_ids":["https://openalex.org/I212119943"]},{"raw_affiliation_string":"[Department of Computer Science, University of Victoria, Victoria, BC, Canada.]","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052843273","display_name":"Peter F. Driessen","orcid":"https://orcid.org/0000-0003-1112-3738"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Peter Driessen","raw_affiliation_strings":["Department of Computer Science, University of Victoria, BC, Canada","[Department of Computer Science, University of Victoria, Victoria, BC, Canada.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Victoria, BC, Canada","institution_ids":["https://openalex.org/I212119943"]},{"raw_affiliation_string":"[Department of Computer Science, University of Victoria, Victoria, BC, Canada.]","institution_ids":["https://openalex.org/I212119943"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I212119943"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06390704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"424","last_page":"428"},"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":0.9998000264167786,"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":0.9991000294685364,"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/spectrogram","display_name":"Spectrogram","score":0.8519489765167236},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.8491523265838623},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.7935247421264648},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7619485259056091},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.7026685476303101},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7008172273635864},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6576238870620728},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6123424768447876},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.5716302394866943},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5116837024688721},{"id":"https://openalex.org/keywords/computer-music","display_name":"Computer music","score":0.43551886081695557},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34293419122695923},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32626622915267944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28384846448898315},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.20108544826507568},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.14588916301727295},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1062646210193634}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8519489765167236},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.8491523265838623},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.7935247421264648},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7619485259056091},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.7026685476303101},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7008172273635864},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6576238870620728},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6123424768447876},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.5716302394866943},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5116837024688721},{"id":"https://openalex.org/C34259666","wikidata":"https://www.wikidata.org/wiki/Q1122550","display_name":"Computer music","level":3,"score":0.43551886081695557},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34293419122695923},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32626622915267944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28384846448898315},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.20108544826507568},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.14588916301727295},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1062646210193634},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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":1,"locations":[{"id":"doi:10.1109/mmsp.2013.6659326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2013.6659326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 15th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W108002356","https://openalex.org/W144105221","https://openalex.org/W189345193","https://openalex.org/W1975506911","https://openalex.org/W2042659457","https://openalex.org/W2071207952","https://openalex.org/W2104298926","https://openalex.org/W2114508388","https://openalex.org/W2118992863","https://openalex.org/W2127851351","https://openalex.org/W2129638017","https://openalex.org/W2150415460","https://openalex.org/W2151909846","https://openalex.org/W2168103573","https://openalex.org/W2243331423","https://openalex.org/W2293149521","https://openalex.org/W2295824433","https://openalex.org/W2556247670","https://openalex.org/W2735921974","https://openalex.org/W2952929324","https://openalex.org/W4244253603","https://openalex.org/W6604365636","https://openalex.org/W6605910177","https://openalex.org/W6607768639","https://openalex.org/W6676113301","https://openalex.org/W6677781179","https://openalex.org/W6690485627","https://openalex.org/W6696820795","https://openalex.org/W6697408287"],"related_works":["https://openalex.org/W2547262076","https://openalex.org/W2150113039","https://openalex.org/W2563421448","https://openalex.org/W2774154397","https://openalex.org/W1565566036","https://openalex.org/W2534043196","https://openalex.org/W2098101267","https://openalex.org/W2615370628","https://openalex.org/W2156181515","https://openalex.org/W2806198829"],"abstract_inverted_index":{"Spectrogram":[0],"factorization":[1,101],"methods":[2,102],"such":[3],"as":[4,12,31],"Non-Negative":[5],"Matrix":[6],"Factorization":[7],"(NMF)":[8],"are":[9,91,96,110,114,120],"frequently":[10],"used":[11,30,121,128],"a":[13,32,81,137],"way":[14,112],"to":[15,52,70,122],"separate":[16],"individual":[17],"sound":[18,22,45,72],"sources":[19],"from":[20],"complex":[21],"mixtures.":[23],"More":[24],"recently,":[25],"they":[26,95],"have":[27,103],"also":[28],"been":[29,104,135],"first":[33,63],"stage":[34],"for":[35,129],"the":[36,53,62,65,75,78,87,111,126],"automatic":[37,56,148],"transcription":[38],"of":[39,44,55,61,77,100],"polyphonic":[40],"music.":[41],"The":[42,59],"problem":[43,54],"source":[46],"separation":[47,143],"is":[48,64,80,163],"different":[49],"(but":[50],"related)":[51],"music":[57],"transcription.":[58,149],"output":[60,76],"separated":[66],"audio":[67],"signals":[68],"corresponding":[69],"each":[71],"source,":[73],"whereas":[74],"second":[79],"symbolic":[82],"representation/music":[83],"score":[84],"that":[85,90,136,139,160],"encodes":[86],"discrete":[88],"pitches/notes":[89],"played":[92],"and":[93,116,158],"when":[94],"played.":[97],"Many":[98],"variations":[99],"proposed.":[105],"Two":[106],"important":[107],"design":[108],"choices":[109],"spectra":[113],"represented":[115],"what":[117],"distance":[118],"measures":[119],"compare":[123],"them":[124],"in":[125,146],"optimization":[127],"factorization.":[130],"A":[131],"common":[132],"assumption":[133],"has":[134],"variant":[138],"yields":[140],"better":[141,147],"signal":[142],"will":[144],"result":[145],"In":[150],"this":[151,156,161],"work,":[152],"we":[153],"investigate":[154],"experimentally":[155],"question":[157],"show":[159],"relationship":[162],"not":[164],"necessarily":[165],"true.":[166]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}