{"id":"https://openalex.org/W2096637354","doi":"https://doi.org/10.1109/icassp.2009.4959973","title":"On the importance of modeling temporal information in music tag annotation","display_name":"On the importance of modeling temporal information in music tag annotation","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2096637354","doi":"https://doi.org/10.1109/icassp.2009.4959973","mag":"2096637354"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4959973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959973","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"article","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/A5004463431","display_name":"Jeremy Reed","orcid":"https://orcid.org/0000-0002-7499-5747"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jeremy Reed","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","School of Electrical & Computer Engineering, Georgia Institute of Technology, Atlanta 30332, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Electrical & Computer Engineering, Georgia Institute of Technology, Atlanta 30332, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","School of Electrical & Computer Engineering, Georgia Institute of Technology, Atlanta 30332, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Electrical & Computer Engineering, Georgia Institute of Technology, Atlanta 30332, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5004463431"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":3.1722,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.91780544,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1873","last_page":"1876"},"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":0.9973000288009644,"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":0.9968000054359436,"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/computer-science","display_name":"Computer science","score":0.7715712785720825},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6302874088287354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5970442891120911},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.576797366142273},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.5710986256599426},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5531010627746582},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5294275879859924},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.49548637866973877},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4755534827709198},{"id":"https://openalex.org/keywords/viterbi-decoder","display_name":"Viterbi decoder","score":0.47445377707481384},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4619278311729431},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4547812044620514},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43873706459999084},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.4234470725059509},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3979724645614624},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3948887288570404},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10307687520980835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7715712785720825},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6302874088287354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5970442891120911},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.576797366142273},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.5710986256599426},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5531010627746582},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5294275879859924},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.49548637866973877},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4755534827709198},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.47445377707481384},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4619278311729431},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4547812044620514},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43873706459999084},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.4234470725059509},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3979724645614624},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3948887288570404},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10307687520980835},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4959973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959973","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W161183367","https://openalex.org/W1576520375","https://openalex.org/W1950396994","https://openalex.org/W2116373735","https://openalex.org/W2118714763","https://openalex.org/W2120803704","https://openalex.org/W2121310556","https://openalex.org/W2130976598","https://openalex.org/W2154016477","https://openalex.org/W2159561775","https://openalex.org/W2167277498","https://openalex.org/W2167314423","https://openalex.org/W2172287020","https://openalex.org/W3146463283","https://openalex.org/W6606613475","https://openalex.org/W6678117678","https://openalex.org/W6684436838"],"related_works":["https://openalex.org/W2162372932","https://openalex.org/W3007206597","https://openalex.org/W246155136","https://openalex.org/W3185351655","https://openalex.org/W2165931417","https://openalex.org/W2107432317","https://openalex.org/W2146661721","https://openalex.org/W2130658921","https://openalex.org/W2038107365","https://openalex.org/W3009003662"],"abstract_inverted_index":{"Music":[0],"is":[1],"an":[2,27,123],"art":[3],"form":[4],"in":[5,10,48,114],"which":[6,32],"sounds":[7],"are":[8],"organized":[9],"time;":[11],"however,":[12],"current":[13],"approaches":[14],"for":[15,94,102],"determining":[16],"similarity":[17],"and":[18,76],"classification":[19,96],"largely":[20],"ignore":[21],"temporal":[22,34],"information.":[23],"This":[24],"paper":[25],"presents":[26],"approach":[28,111],"to":[29,60,125],"automatic":[30],"tagging":[31],"incorporates":[33],"aspects":[35],"of":[36,63,81,116,135],"music":[37,50],"directly":[38],"into":[39,91],"the":[40,44,88,109,117],"statistical":[41],"models,":[42],"unlike":[43],"typical":[45],"bag-of-frames":[46],"paradigm":[47],"traditional":[49],"information":[51],"retrieval":[52],"techniques.":[53],"Vector":[54],"quantization":[55],"on":[56],"song":[57,89],"segments":[58],"leads":[59],"a":[61,92,98],"vocabulary":[62],"acoustic":[64,136],"segment":[65,137],"models.":[66,138],"An":[67],"unsupervised,":[68],"iterative":[69],"process":[70],"that":[71,108],"cycles":[72],"between":[73],"Viterbi":[74],"decoding":[75],"Baum-Welch":[77],"estimation":[78],"builds":[79],"transcripts":[80],"this":[82],"vocabulary.":[83],"Latent":[84],"semantic":[85],"analysis":[86,121],"converts":[87],"transcriptions":[90],"vector":[93,100],"subsequent":[95],"using":[97],"support":[99],"machine":[101],"each":[103],"tag.":[104],"Experimental":[105],"results":[106],"demonstrate":[107],"proposed":[110],"performs":[112],"better":[113],"15":[115],"18":[118],"tags.":[119],"Further":[120],"demonstrates":[122],"ability":[124],"capture":[126],"local":[127],"timbral":[128],"characteristics":[129],"as":[130,132],"well":[131],"sequential":[133],"arrangements":[134]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}