{"id":"https://openalex.org/W1981861329","doi":"https://doi.org/10.1109/icassp.2013.6638242","title":"Towards a universal representation for audio information retrieval and analysis","display_name":"Towards a universal representation for audio information retrieval and analysis","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W1981861329","doi":"https://doi.org/10.1109/icassp.2013.6638242","mag":"1981861329"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 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/A5048873240","display_name":"Bj\u00f8rn Sand Jensen","orcid":"https://orcid.org/0000-0001-8074-228X"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Bjorn Sand Jensen","raw_affiliation_strings":["DTU Computer, Technical University of Denmark, Kongens Lyngby, Denmark","DTU Compute, Tech. Univ. of Denmark, Lyngby, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DTU Computer, Technical University of Denmark, Kongens Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]},{"raw_affiliation_string":"DTU Compute, Tech. Univ. of Denmark, Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073169308","display_name":"Rasmus Troelsgaard","orcid":"https://orcid.org/0000-0002-4115-4140"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Rasmus Troelsgaard","raw_affiliation_strings":["DTU Computer, Technical University of Denmark, Kongens Lyngby, Denmark","DTU Compute, Tech. Univ. of Denmark, Lyngby, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DTU Computer, Technical University of Denmark, Kongens Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]},{"raw_affiliation_string":"DTU Compute, Tech. Univ. of Denmark, Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070673552","display_name":"Jan Larsen","orcid":"https://orcid.org/0000-0003-1880-1810"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jan Larsen","raw_affiliation_strings":["DTU Computer, Technical University of Denmark, Kongens Lyngby, Denmark","DTU Compute, Tech. Univ. of Denmark, Lyngby, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DTU Computer, Technical University of Denmark, Kongens Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]},{"raw_affiliation_string":"DTU Compute, Tech. Univ. of Denmark, Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018292103","display_name":"Lars Kai Hansen","orcid":"https://orcid.org/0000-0003-0442-5877"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Lars Kai Hansen","raw_affiliation_strings":["DTU Computer, Technical University of Denmark, Kongens Lyngby, Denmark","DTU Compute, Tech. Univ. of Denmark, Lyngby, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DTU Computer, Technical University of Denmark, Kongens Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]},{"raw_affiliation_string":"DTU Compute, Tech. Univ. of Denmark, Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I96673099"],"apc_list":null,"apc_paid":null,"fwci":0.4696,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53202614,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"101","issue":null,"first_page":"3168","last_page":"3172"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9850999712944031,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9836000204086304,"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/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.7929470539093018},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7883307337760925},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6889725923538208},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6808033585548401},{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.59376060962677},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4950648844242096},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.4896145462989807},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.487105131149292},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4663141667842865},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.46217578649520874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4516165256500244},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.439716100692749},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3768351972103119},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3707970380783081},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.138162761926651}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.7929470539093018},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7883307337760925},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6889725923538208},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6808033585548401},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.59376060962677},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4950648844242096},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.4896145462989807},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.487105131149292},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4663141667842865},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.46217578649520874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4516165256500244},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.439716100692749},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3768351972103119},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3707970380783081},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.138162761926651},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6638242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:119566","is_oa":false,"landing_page_url":"http://eprints.gla.ac.uk/119566/","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":false,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceedings"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6499999761581421,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W38176230","https://openalex.org/W127011120","https://openalex.org/W128719644","https://openalex.org/W1045314183","https://openalex.org/W1508679722","https://openalex.org/W1556219185","https://openalex.org/W1576667197","https://openalex.org/W1612003148","https://openalex.org/W1880262756","https://openalex.org/W1989445502","https://openalex.org/W1998937440","https://openalex.org/W2001082470","https://openalex.org/W2017160234","https://openalex.org/W2020842694","https://openalex.org/W2097807493","https://openalex.org/W2103028434","https://openalex.org/W2111940465","https://openalex.org/W2112008792","https://openalex.org/W2113229563","https://openalex.org/W2128637751","https://openalex.org/W2141714363","https://openalex.org/W2144100511","https://openalex.org/W2146078527","https://openalex.org/W2158266063","https://openalex.org/W2186456736","https://openalex.org/W2296248436","https://openalex.org/W2398055577","https://openalex.org/W2740190835","https://openalex.org/W2764559134","https://openalex.org/W4237791300","https://openalex.org/W4248892431","https://openalex.org/W6605085756","https://openalex.org/W6627142433","https://openalex.org/W6636440780","https://openalex.org/W6674678309","https://openalex.org/W6676823600","https://openalex.org/W6680837174","https://openalex.org/W6683603713","https://openalex.org/W6686722886","https://openalex.org/W6697014533","https://openalex.org/W6712240000","https://openalex.org/W6742061585"],"related_works":["https://openalex.org/W2888805565","https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W4293863151","https://openalex.org/W3159709618","https://openalex.org/W2611137333","https://openalex.org/W3005513013"],"abstract_inverted_index":{"A":[0],"fundamental":[1],"and":[2,7,19,65,83,116],"general":[3],"representation":[4,50,73],"of":[5,35,101,114],"audio":[6,66],"music":[8],"which":[9,41],"integrates":[10],"multi-modal":[11,33],"data":[12],"sources":[13],"is":[14,74],"important":[15],"for":[16,87,121],"both":[17],"application":[18],"basic":[20],"research":[21],"purposes.":[22],"In":[23],"this":[24,28,49],"paper":[25],"we":[26],"address":[27],"challenge":[29],"by":[30,56,108],"proposing":[31],"a":[32,43],"version":[34],"the":[36,52,71,88,106,122],"Latent":[37],"Dirichlet":[38],"Allocation":[39],"model":[40,107],"provides":[42],"joint":[44],"latent":[45,99],"representation.":[46],"We":[47,68,103],"evaluate":[48],"on":[51],"Million":[53,123],"Song":[54,124],"Dataset":[55],"integrating":[57],"three":[58],"fundamentally":[59],"different":[60],"modalities,":[61],"namely":[62],"tags,":[63,82],"lyrics,":[64],"features.":[67],"show":[69],"how":[70],"resulting":[72],"aligned":[75],"with":[76],"common":[77,89],"'cognitive'":[78],"variables":[79],"such":[80],"as":[81],"provide":[84],"some":[85],"evidence":[86],"assumption":[90],"that":[91],"genres":[92],"form":[93],"an":[94],"acceptable":[95],"categorization":[96],"when":[97],"evaluating":[98],"representations":[100],"music.":[102],"furthermore":[104],"quantify":[105],"its":[109],"predictive":[110],"performance":[111],"in":[112],"terms":[113],"genre":[115],"style,":[117],"providing":[118],"benchmark":[119],"results":[120],"Dataset.":[125]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
