{"id":"https://openalex.org/W2078101860","doi":"https://doi.org/10.1145/2072529.2072537","title":"Music identification via vocabulary tree with MFCC peaks","display_name":"Music identification via vocabulary tree with MFCC peaks","publication_year":2011,"publication_date":"2011-11-30","ids":{"openalex":"https://openalex.org/W2078101860","doi":"https://doi.org/10.1145/2072529.2072537","mag":"2078101860"},"language":"en","primary_location":{"id":"doi:10.1145/2072529.2072537","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2072529.2072537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st international ACM workshop on Music information retrieval with user-centered and multimodal strategies","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/A5088109976","display_name":"Tianjing Xu","orcid":"https://orcid.org/0000-0002-7293-430X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianjing Xu","raw_affiliation_strings":["State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045729519","display_name":"Adams Wei Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Adams Wei Yu","raw_affiliation_strings":["State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024067284","display_name":"Xianglong Liu","orcid":"https://orcid.org/0000-0002-7618-3275"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianglong Liu","raw_affiliation_strings":["State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100310123","display_name":"Bo Lang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Lang","raw_affiliation_strings":["State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088109976"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.3062,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54933795,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"26"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9919000267982483,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9746000170707703,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.819533109664917},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7598127722740173},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5962315797805786},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5885496735572815},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5543703436851501},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5512937307357788},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5477577447891235},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5451871156692505},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49048754572868347},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.46828314661979675},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4376547336578369},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4336474537849426},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14537912607192993},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13550499081611633}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.819533109664917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7598127722740173},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5962315797805786},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5885496735572815},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5543703436851501},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5512937307357788},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5477577447891235},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5451871156692505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49048754572868347},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.46828314661979675},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4376547336578369},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4336474537849426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14537912607192993},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13550499081611633},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2072529.2072537","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2072529.2072537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st international ACM workshop on Music information retrieval with user-centered and multimodal strategies","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W84505213","https://openalex.org/W95202560","https://openalex.org/W1515839227","https://openalex.org/W1548835820","https://openalex.org/W1553843758","https://openalex.org/W1898201904","https://openalex.org/W1966699657","https://openalex.org/W1978394996","https://openalex.org/W2023854218","https://openalex.org/W2027518030","https://openalex.org/W2047411082","https://openalex.org/W2095955955","https://openalex.org/W2104160358","https://openalex.org/W2124386111","https://openalex.org/W2128017662","https://openalex.org/W2137973178","https://openalex.org/W2221009957","https://openalex.org/W2692613512","https://openalex.org/W3021908862","https://openalex.org/W3157702951","https://openalex.org/W4210951666","https://openalex.org/W4285719527","https://openalex.org/W4301953474"],"related_works":["https://openalex.org/W2349769824","https://openalex.org/W2914532148","https://openalex.org/W2372625757","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2144773493"],"abstract_inverted_index":{"In":[0],"this":[1,32,105],"paper,":[2],"a":[3,18,21,27,35,43,91,95],"Vocabulary":[4,61],"Tree":[5,62],"based":[6],"framework":[7,33],"is":[8,15,34,42,80],"proposed":[9,126],"for":[10],"music":[11],"identification":[12],"whose":[13],"target":[14],"to":[16,26,90,104,111],"recognize":[17],"fragment":[19],"from":[20,70,87],"song":[22,76],"database.":[23,146],"The":[24,120],"key":[25],"high":[28],"recognition":[29],"precision":[30,160],"within":[31],"novel":[36],"feature,":[37],"namely":[38],"MFCC":[39,46,66],"Peaks,":[40],"which":[41],"combination":[44],"of":[45,54,72,145],"and":[47,115,131,169],"Spectral":[48],"Peaks":[49,67],"features.":[50],"Our":[51],"approach":[52,139],"consists":[53],"three":[55],"stages.":[56],"We":[57],"first":[58],"build":[59],"the":[60,78,100,108,112,117,143,157],"with":[63,142],"2":[64],"million":[65],"features":[68],"extracted":[69],"hundreds":[71],"music.":[73],"Then":[74],"each":[75],"in":[77],"database":[79],"quantified":[81],"into":[82],"some":[83],"words":[84],"by":[85],"traveling":[86],"root":[88],"down":[89],"certain":[92],"leaf.":[93],"Given":[94],"query":[96],"input,":[97],"we":[98],"apply":[99],"same":[101,158],"quantization":[102],"procedure":[103],"fragment,":[106],"score":[107],"archive":[109],"according":[110],"TF-IDF":[113],"scheme":[114],"return":[116],"best":[118],"matches.":[119],"experimental":[121],"results":[122],"demonstrate":[123],"that":[124,137,151],"our":[125,138,153],"feature":[127],"has":[128],"strong":[129],"identifying":[130],"generalization":[132],"ability.":[133],"Other":[134],"trials":[135],"show":[136],"scales":[140],"well":[141],"size":[144],"Further":[147],"comparison":[148],"also":[149],"demonstrates":[150],"while":[152],"algorithm":[154],"achieves":[155],"approximately":[156],"retrieval":[159],"as":[161],"other":[162],"state-of-the-art":[163],"methods,":[164],"it":[165],"cost":[166],"less":[167],"time":[168],"memory.":[170]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}