{"id":"https://openalex.org/W1577472237","doi":"https://doi.org/10.1109/icme.2015.7177492","title":"Music identification based on music word model","display_name":"Music identification based on music word model","publication_year":2015,"publication_date":"2015-06-01","ids":{"openalex":"https://openalex.org/W1577472237","doi":"https://doi.org/10.1109/icme.2015.7177492","mag":"1577472237"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2015.7177492","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2015.7177492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Multimedia and Expo (ICME)","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/A5113201411","display_name":"Wanyi Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wanyi Yang","raw_affiliation_strings":["Institute of Computer Science and Technology, Peking University, Beijing, China","Institute of Computer Science & Technology, Peking University, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Institute of Computer Science & Technology, Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100885747","display_name":"Deshun Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deshun Yang","raw_affiliation_strings":["Institute of Computer Science and Technology, Peking University, Beijing, China","Institute of Computer Science & Technology, Peking University, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Institute of Computer Science & Technology, Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017207620","display_name":"Xiaoou Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoou Chen","raw_affiliation_strings":["Institute of Computer Science and Technology, Peking University, Beijing, China","Institute of Computer Science & Technology, Peking University, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Institute of Computer Science & Technology, Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052901092","display_name":"Haiqian He","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiqian He","raw_affiliation_strings":["Institute of Computer Science and Technology, Peking University, Beijing, China","Institute of Computer Science & Technology, Peking University, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Institute of Computer Science & Technology, Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113201411"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.2872,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52751866,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2002","issue":null,"first_page":"1","last_page":"6"},"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":0.9898999929428101,"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":0.9886999726295471,"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/spectrogram","display_name":"Spectrogram","score":0.8982335329055786},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.6792005300521851},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6599260568618774},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6433889865875244},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6278549432754517},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5510403513908386},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.513575553894043},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5071468353271484},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.49277427792549133},{"id":"https://openalex.org/keywords/word-identification","display_name":"Word identification","score":0.47943586111068726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4533616006374359},{"id":"https://openalex.org/keywords/pop-music-automation","display_name":"Pop music automation","score":0.4459354877471924},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4384789764881134},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40730026364326477},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35322076082229614},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25789719820022583},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1606738269329071},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.14803868532180786},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10563492774963379},{"id":"https://openalex.org/keywords/musical-composition","display_name":"Musical composition","score":0.100309818983078},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.09836503863334656},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08851400017738342}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8982335329055786},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.6792005300521851},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6599260568618774},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6433889865875244},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6278549432754517},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5510403513908386},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.513575553894043},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5071468353271484},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.49277427792549133},{"id":"https://openalex.org/C2994428975","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word identification","level":4,"score":0.47943586111068726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4533616006374359},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.4459354877471924},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4384789764881134},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40730026364326477},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35322076082229614},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25789719820022583},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1606738269329071},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.14803868532180786},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10563492774963379},{"id":"https://openalex.org/C109568592","wikidata":"https://www.wikidata.org/wiki/Q207628","display_name":"Musical composition","level":3,"score":0.100309818983078},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.09836503863334656},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08851400017738342},{"id":"https://openalex.org/C13553968","wikidata":"https://www.wikidata.org/wiki/Q27908","display_name":"Music education","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2015.7177492","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2015.7177492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W83334756","https://openalex.org/W166844666","https://openalex.org/W197225201","https://openalex.org/W1515031775","https://openalex.org/W1555511196","https://openalex.org/W1790954942","https://openalex.org/W1966699657","https://openalex.org/W1967801899","https://openalex.org/W1977556410","https://openalex.org/W2009112943","https://openalex.org/W2018083238","https://openalex.org/W2048174296","https://openalex.org/W2076608692","https://openalex.org/W2077161640","https://openalex.org/W2161564256","https://openalex.org/W2163747209","https://openalex.org/W6603388714","https://openalex.org/W6606773126","https://openalex.org/W6630677618","https://openalex.org/W6633310046","https://openalex.org/W6642294712"],"related_works":["https://openalex.org/W1992616322","https://openalex.org/W2036873286","https://openalex.org/W2408487574","https://openalex.org/W4283746496","https://openalex.org/W2364032347","https://openalex.org/W438210688","https://openalex.org/W94805306","https://openalex.org/W3032649931","https://openalex.org/W2413876267","https://openalex.org/W2016905599"],"abstract_inverted_index":{"For":[0],"music":[1,25,46,70,73,76,92,97,138],"identification,":[2],"conventional":[3],"bag":[4],"of":[5,17,24,69,96,112,137,172],"audio":[6],"words":[7,71,77],"model":[8],"methods":[9],"generally":[10],"compute":[11],"a":[12,15,28,61,67,94,141,162],"histogram":[13,119],"for":[14,72,157],"piece":[16,95],"music,":[18],"which":[19,43,154],"ignores":[20],"the":[21,32,56,81,90,110,118,123,129,135,151,168],"temporal":[22],"characteristic":[23],"and":[26,104,122,170],"has":[27],"negative":[29],"influence":[30],"on":[31,40,66,89,134],"accuracy.":[33],"In":[34],"addition,":[35],"they":[36],"are":[37,78],"usually":[38],"based":[39,65,88],"DFT":[41],"spectrogram,":[42],"cannot":[44],"represent":[45],"as":[47,49,84,101,161],"well":[48],"Constant":[50],"Q":[51],"(CQ)":[52],"spectrogram.":[53],"To":[54],"address":[55],"above":[57],"problems,":[58],"we":[59],"propose":[60],"two-layer":[62],"representation":[63],"method":[64],"set":[68],"identification.":[74],"Firstly,":[75],"learned":[79],"from":[80],"CQ":[82],"spectrogram":[83],"typical":[85],"patterns.":[86],"Then,":[87],"obtained":[91],"words,":[93],"can":[98,108],"be":[99],"represented":[100],"word":[102,105,139,144],"sequence":[103,130],"histogram.":[106],"We":[107],"reduce":[109],"number":[111],"possible":[113],"similar":[114],"candidates":[115],"effectively":[116],"with":[117],"similarity":[120,131],"measure,":[121],"final":[124],"result":[125],"is":[126,147,155],"determined":[127],"by":[128],"measure.":[132],"Based":[133],"distribution":[136],"frequency,":[140],"low":[142],"frequency":[143],"filter":[145],"strategy":[146],"devised":[148],"to":[149],"increase":[150],"identification":[152],"speed,":[153],"essential":[156],"large":[158],"systems":[159],"such":[160],"million":[163],"song":[164],"library.":[165],"Experiments":[166],"demonstrate":[167],"effectiveness":[169],"efficiency":[171],"our":[173],"proposed":[174],"method.":[175]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}