{"id":"https://openalex.org/W2151486992","doi":"https://doi.org/10.1109/icassp.2012.6288292","title":"Cluster aware normalization for enhancing audio similarity","display_name":"Cluster aware normalization for enhancing audio similarity","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2151486992","doi":"https://doi.org/10.1109/icassp.2012.6288292","mag":"2151486992"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5029522748","display_name":"Mathieu Lagrange","orcid":"https://orcid.org/0000-0002-1253-4427"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mathieu Lagrange","raw_affiliation_strings":["IRCAM CNRS, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IRCAM CNRS, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I35345632"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084890477","display_name":"Lu\u00eds Gustavo Martins","orcid":"https://orcid.org/0000-0001-7758-5471"},"institutions":[{"id":"https://openalex.org/I25169866","display_name":"Universidade Cat\u00f3lica Portuguesa","ror":"https://ror.org/03b9snr86","country_code":"PT","type":"education","lineage":["https://openalex.org/I25169866"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Luis Gustavo Martins","raw_affiliation_strings":["School of Arts / CITAR, Portuguese Catholic University, Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Arts / CITAR, Portuguese Catholic University, Porto, Portugal","institution_ids":["https://openalex.org/I25169866"]}]},{"author_position":"last","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Victoria, BC, Canada","institution_ids":["https://openalex.org/I212119943"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1969","last_page":"1972"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9937000274658203,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/normalization","display_name":"Normalization (sociology)","score":0.73696368932724},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7366561889648438},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.696806788444519},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.598511815071106},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.593650221824646},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5543458461761475},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5013186931610107},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.49326032400131226},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4643924832344055},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37523841857910156},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.27039968967437744},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.24080249667167664},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.07945758104324341},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06912431120872498}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.73696368932724},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7366561889648438},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.696806788444519},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.598511815071106},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.593650221824646},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5543458461761475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5013186931610107},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.49326032400131226},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4643924832344055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37523841857910156},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.27039968967437744},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.24080249667167664},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.07945758104324341},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06912431120872498},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W137835716","https://openalex.org/W158861595","https://openalex.org/W1510073064","https://openalex.org/W1532325895","https://openalex.org/W1537603892","https://openalex.org/W2098006457","https://openalex.org/W2131681506","https://openalex.org/W2136846911","https://openalex.org/W2138917100","https://openalex.org/W2152322845","https://openalex.org/W2165874743","https://openalex.org/W3099768174","https://openalex.org/W4213009331","https://openalex.org/W6606450208","https://openalex.org/W6632423696","https://openalex.org/W6684578312"],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W2904022177","https://openalex.org/W2359348847","https://openalex.org/W3011538607","https://openalex.org/W4294432981","https://openalex.org/W4387830220","https://openalex.org/W4381714195","https://openalex.org/W2296317756","https://openalex.org/W4210523093"],"abstract_inverted_index":{"An":[0],"important":[1],"task":[2],"in":[3,11,25],"Music":[4],"Information":[5],"Retrieval":[6],"is":[7,63,131,142],"content-based":[8],"similarity":[9,74,147],"retrieval":[10],"which":[12,80,92],"given":[13],"a":[14,18,126],"query":[15],"music":[16,45,61,73],"track,":[17],"set":[19],"of":[20,27,34,43,108,137,167],"tracks":[21,82,94],"that":[22,37,70,83,95,130,149],"are":[23,30,81,84,93,96,105],"similar":[24,85,98],"terms":[26],"musical":[28,119],"content":[29],"retrieved.":[31],"A":[32],"variety":[33],"audio":[35,54],"features":[36],"attempt":[38],"to":[39,58,86,99,133,158,163],"model":[40],"different":[41],"aspects":[42],"the":[44,52,109,118,135,146,151,160,164,168],"have":[46],"been":[47,68],"proposed.":[48],"In":[49,121],"most":[50,100],"cases":[51],"resulting":[53],"feature":[55,169],"vector":[56],"used":[57],"represent":[59],"each":[60],"track":[62,153],"high":[64,71,110],"dimensional.":[65],"It":[66,141],"has":[67],"observed":[69],"dimensional":[72,111],"spaces":[75],"exhibit":[76],"some":[77],"anomalies:":[78],"hubs":[79,138],"many":[87],"other":[88,101],"tracks,":[89],"and":[90,139,155],"orphans":[91],"not":[97],"tracks.":[102],"These":[103],"anomalies":[104],"an":[106],"artifact":[107],"representation":[112],"rather":[113],"than":[114],"actually":[115],"based":[116,143],"on":[117,144],"content.":[120],"this":[122],"work":[123],"we":[124],"describe":[125],"distance":[127,161],"normalization":[128,162],"method":[129],"shown":[132],"reduce":[134],"number":[136],"orphans.":[140],"post-processing":[145],"matrix":[148],"encodes":[150],"pair-wise":[152],"similarities":[154],"utilizes":[156],"clustering":[157],"adapt":[159],"local":[165],"structure":[166],"space.":[170]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}