{"id":"https://openalex.org/W1970115974","doi":"https://doi.org/10.1109/icassp.2010.5495773","title":"Harmonic variable-size dictionary learning for music source separation","display_name":"Harmonic variable-size dictionary learning for music source separation","publication_year":2010,"publication_date":"2010-03-01","ids":{"openalex":"https://openalex.org/W1970115974","doi":"https://doi.org/10.1109/icassp.2010.5495773","mag":"1970115974"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5110251567","display_name":"Steven K. Tjoa","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven K. Tjoa","raw_affiliation_strings":["Signals and Information Group, Department of Electrical and Computer Engineering, University of Maryland, College Park, MD, USA","Dept of Electr. & Comput. Eng., Univ. of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signals and Information Group, Department of Electrical and Computer Engineering, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Dept of Electr. & Comput. Eng., Univ. of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023433042","display_name":"Matthew C. Stamm","orcid":"https://orcid.org/0000-0002-3986-4039"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew C. Stamm","raw_affiliation_strings":["Signals and Information Group, Department of Electrical and Computer Engineering, University of Maryland, College Park, MD, USA","Dept of Electr. & Comput. Eng., Univ. of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signals and Information Group, Department of Electrical and Computer Engineering, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Dept of Electr. & Comput. Eng., Univ. of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":null,"display_name":"W. Sabrina Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W. Sabrina Lin","raw_affiliation_strings":["Signals and Information Group, Department of Electrical and Computer Engineering, University of Maryland, College Park, MD, USA","Dept of Electr. & Comput. Eng., Univ. of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signals and Information Group, Department of Electrical and Computer Engineering, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Dept of Electr. & Comput. Eng., Univ. of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061391764","display_name":"K. J. Ray Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K. J. Ray Liu","raw_affiliation_strings":["Signals and Information Group, Department of Electrical and Computer Engineering, University of Maryland, College Park, MD, USA","Dept of Electr. & Comput. Eng., Univ. of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signals and Information Group, Department of Electrical and Computer Engineering, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Dept of Electr. & Comput. Eng., Univ. of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":1.9211,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85995595,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"54","issue":null,"first_page":"413","last_page":"416"},"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.7921910285949707},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.7379453182220459},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6951383948326111},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.676843523979187},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.6433446407318115},{"id":"https://openalex.org/keywords/dictionary-learning","display_name":"Dictionary learning","score":0.5833904147148132},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5691401958465576},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5383440256118774},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5343320369720459},{"id":"https://openalex.org/keywords/k-svd","display_name":"K-SVD","score":0.4698064923286438},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.436377614736557},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.42043623328208923},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.41141337156295776},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.1855936348438263},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10428157448768616}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7921910285949707},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.7379453182220459},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6951383948326111},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.676843523979187},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.6433446407318115},{"id":"https://openalex.org/C2988886741","wikidata":"https://www.wikidata.org/wiki/Q25304494","display_name":"Dictionary learning","level":3,"score":0.5833904147148132},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5691401958465576},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5383440256118774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5343320369720459},{"id":"https://openalex.org/C154771677","wikidata":"https://www.wikidata.org/wiki/Q17098361","display_name":"K-SVD","level":3,"score":0.4698064923286438},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.436377614736557},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.42043623328208923},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.41141337156295776},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.1855936348438263},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10428157448768616},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2010.5495773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.301.974","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.301.974","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.umd.edu/~mcstamm/Tjoa_Stamm_Lin_Liu_ICASSP_2010_c.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.419.7171","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.419.7171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sig.umd.edu/publications/Tjoa_ICASSP_201003.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2004163116","https://openalex.org/W2010161441","https://openalex.org/W2101212989","https://openalex.org/W2104298926","https://openalex.org/W2115429828","https://openalex.org/W2135029798","https://openalex.org/W2160547390","https://openalex.org/W3143596294","https://openalex.org/W6652907427","https://openalex.org/W6680012447"],"related_works":["https://openalex.org/W2551137307","https://openalex.org/W2113526703","https://openalex.org/W2123043102","https://openalex.org/W2577807713","https://openalex.org/W3094316140","https://openalex.org/W3133205200","https://openalex.org/W2547262076","https://openalex.org/W2098101267","https://openalex.org/W2563421448","https://openalex.org/W2898145319"],"abstract_inverted_index":{"Dictionary":[0],"learning":[1,65,89],"through":[2],"matrix":[3,106],"factorization":[4,107],"has":[5],"become":[6],"widely":[7],"popular":[8,104],"for":[9],"performing":[10],"music":[11],"transcription":[12],"and":[13,50,114],"source":[14],"separation.":[15],"These":[16],"methods":[17,108],"learn":[18],"a":[19,62],"concise":[20],"set":[21],"of":[22,28,75,116],"dictionary":[23,64,78,82,118],"atoms":[24,38,74],"which":[25],"represent":[26],"spectrograms":[27],"musical":[29,55,99],"objects.":[30],"However,":[31],"there":[32,46,92],"is":[33,93],"no":[34],"guarantee":[35],"that":[36,67],"the":[37,54,73,76,81,88,98,112],"learned":[39,77,117],"will":[40],"be":[41],"perceptually":[42],"meaningful,":[43],"particularly":[44],"when":[45],"exists":[47],"significant":[48,94],"spectral":[49],"temporal":[51],"overlap":[52,96],"among":[53,97],"sources.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60],"propose":[61],"novel":[63],"method":[66,102],"imposes":[68],"additional":[69],"harmonic":[70],"constraints":[71],"upon":[72],"while":[79],"allowing":[80],"size":[83],"to":[84],"grow":[85],"appropriately":[86],"during":[87],"procedure.":[90],"When":[91],"spectral-temporal":[95],"sources,":[100],"our":[101],"outperforms":[103],"existing":[105],"as":[109],"measured":[110],"by":[111],"recall":[113],"precision":[115],"atoms.":[119]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}