{"id":"https://openalex.org/W2039739794","doi":"https://doi.org/10.1109/taslp.2014.2337842","title":"Codebook-Based Audio Feature Representation for Music Information Retrieval","display_name":"Codebook-Based Audio Feature Representation for Music Information Retrieval","publication_year":2014,"publication_date":"2014-07-10","ids":{"openalex":"https://openalex.org/W2039739794","doi":"https://doi.org/10.1109/taslp.2014.2337842","mag":"2039739794"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2014.2337842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2337842","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1312.5457","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yonatan Vaizman","orcid":"https://orcid.org/0000-0003-0965-2366"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yonatan Vaizman","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, San Diego"],"raw_orcid":"https://orcid.org/0000-0003-0965-2366","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Brian McFee","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian McFee","raw_affiliation_strings":["Center for Jazz Studies and LabROSA, Columbia University, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Jazz Studies and LabROSA, Columbia University, New York","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":null,"display_name":"Gert Lanckriet","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gert Lanckriet","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2137,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.96161699,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"22","issue":"10","first_page":"1483","last_page":"1493"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9930999875068665,"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":0.9930999875068665,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/music-information-retrieval","display_name":"Music information retrieval","score":0.7397000193595886},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.5622000098228455},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5202000141143799},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.5054000020027161},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.4713999927043915},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.43459999561309814},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43149998784065247},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.41499999165534973},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3837999999523163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8064000010490417},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.7397000193595886},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.5622000098228455},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5202000141143799},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5054000020027161},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.4713999927043915},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4675999879837036},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4489000141620636},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.43459999561309814},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43149998784065247},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.41499999165534973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40230000019073486},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.382099986076355},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.35440000891685486},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.33329999446868896},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.31610000133514404},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2962999939918518},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.26190000772476196}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2014.2337842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2337842","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1312.5457","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1312.5457","pdf_url":"https://arxiv.org/pdf/1312.5457","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1312.5457","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1312.5457","pdf_url":"https://arxiv.org/pdf/1312.5457","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1486009449","https://openalex.org/W1915070853","https://openalex.org/W1966273763","https://openalex.org/W1980599288","https://openalex.org/W2056507581","https://openalex.org/W2056680352","https://openalex.org/W2084983485","https://openalex.org/W2090879738","https://openalex.org/W2106326596","https://openalex.org/W2111331420","https://openalex.org/W2116373735","https://openalex.org/W2119862467","https://openalex.org/W2126410803","https://openalex.org/W2133285226","https://openalex.org/W2133824856","https://openalex.org/W2161937612","https://openalex.org/W2164877274","https://openalex.org/W2165320163","https://openalex.org/W2492959872","https://openalex.org/W4292363360","https://openalex.org/W6600593648","https://openalex.org/W6602025118","https://openalex.org/W6603081845","https://openalex.org/W6605236737","https://openalex.org/W6606613475","https://openalex.org/W6607690849","https://openalex.org/W6607765636","https://openalex.org/W6631829595","https://openalex.org/W6632423696","https://openalex.org/W6638712229","https://openalex.org/W6671530934","https://openalex.org/W6675093649","https://openalex.org/W6675881135","https://openalex.org/W6676727762","https://openalex.org/W6677512721","https://openalex.org/W6677919164","https://openalex.org/W6678117678","https://openalex.org/W6680873201","https://openalex.org/W6682443497","https://openalex.org/W6683338658","https://openalex.org/W6683737379","https://openalex.org/W6686418764","https://openalex.org/W6686925444","https://openalex.org/W6696901769","https://openalex.org/W6696978591","https://openalex.org/W6697597305","https://openalex.org/W6711949533","https://openalex.org/W6713465158","https://openalex.org/W6766005275"],"related_works":[],"abstract_inverted_index":{"Digital":[0],"music":[1,20,101,181],"has":[2],"become":[3],"prolific":[4],"in":[5,8,78,179,200,214],"the":[6,67,79,123,132,165,176,224],"web":[7],"recent":[9],"decades.":[10],"Automated":[11],"recommendation":[12,65],"systems":[13,44],"are":[14],"essential":[15],"for":[16,24,40,56,63,197],"users":[17],"to":[18,26,89,110,112,122,153],"discover":[19],"they":[21],"love":[22],"and":[23,33,58,103,108,148,170,186,217],"artists":[25],"reach":[27],"appropriate":[28],"audience.":[29],"When":[30],"manual":[31],"annotations":[32],"user":[34,118],"preference":[35],"data":[36],"is":[37,66],"lacking":[38],"(e.g.":[39],"new":[41,120,127],"artists)":[42],"these":[43],"must":[45],"rely":[46],"on":[47],"content":[48,69],"based":[49],"methods.":[50],"Besides":[51],"powerful":[52],"machine":[53],"learning":[54],"tools":[55],"classification":[57],"retrieval,":[59],"a":[60,117,140,145,149],"key":[61],"component":[62],"successful":[64,198],"audio":[68,80,128],"representation.":[70],"Good":[71],"representations":[72,85,193],"should":[73,86,104],"capture":[74],"informative":[75],"musical":[76],"patterns":[77],"signal":[81],"of":[82,99,134,142,151],"songs.":[83],"These":[84],"be":[87,106,195],"concise,":[88],"enable":[90,113],"efficient":[91],"(low":[92],"storage,":[93],"easy":[94,107],"indexing,":[95],"fast":[96,109],"search)":[97],"management":[98],"huge":[100],"repositories,":[102],"also":[105],"compute,":[111],"real-time":[114],"interaction":[115],"with":[116,144,160],"supplying":[119],"songs":[121],"system.":[124],"Before":[125],"designing":[126],"features,":[129,137],"we":[130],"explore":[131],"usage":[133],"traditional":[135],"local":[136],"while":[138],"adding":[139],"stage":[141,150],"encoding":[143,162],"pre-computed":[146],"codebook":[147],"pooling":[152],"get":[154],"compact":[155],"vectorial":[156],"representations.":[157],"We":[158,174,203],"experiment":[159],"different":[161],"methods,":[163],"namely":[164],"LASSO,":[166],"vector":[167],"quantization":[168],"(VQ)":[169],"cosine":[171],"similarity":[172],"(CS).":[173],"evaluate":[175],"representations'":[177],"quality":[178],"two":[180],"information":[182],"retrieval":[183],"applications:":[184],"query-by-tag":[185],"query-by-example.":[187],"Our":[188],"results":[189],"show":[190],"that":[191],"concise":[192],"can":[194],"used":[196],"performance":[199],"both":[201,215],"applications.":[202],"recommend":[204],"using":[205],"top-":[206],"\u03c4":[207],"VQ":[208],"encoding,":[209],"which":[210],"consistently":[211],"performs":[212],"well":[213],"applications,":[216],"requires":[218],"much":[219],"less":[220],"computation":[221],"time":[222],"than":[223],"LASSO.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}