{"id":"https://openalex.org/W2170827177","doi":"https://doi.org/10.1109/icme.2005.1521428","title":"A HMM-Embedded Unsupervised Learning to Musical Event Detection","display_name":"A HMM-Embedded Unsupervised Learning to Musical Event Detection","publication_year":2005,"publication_date":"2005-10-24","ids":{"openalex":"https://openalex.org/W2170827177","doi":"https://doi.org/10.1109/icme.2005.1521428","mag":"2170827177"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2005.1521428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2005.1521428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Multimedia and Expo","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/A5109192907","display_name":"Sheng Gao","orcid":"https://orcid.org/0000-0001-8118-411X"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Sheng Gao","raw_affiliation_strings":["Institute for Infocomm Research, Terrace, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Terrace, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100974065","display_name":"Yongwei Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yong-wei Zhu","raw_affiliation_strings":["Institute for Infocomm Research, Terrace, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Terrace, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3005327000"],"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":"334","last_page":"337"},"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":0.9962999820709229,"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":0.9944000244140625,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7839385271072388},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7280303835868835},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7030766010284424},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6029409170150757},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6015540361404419},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5962499380111694},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5592277646064758},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5567914247512817},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5211072564125061},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.48199668526649475},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.47086846828460693},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.43189045786857605},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.42432790994644165},{"id":"https://openalex.org/keywords/bayesian-information-criterion","display_name":"Bayesian information criterion","score":0.41515377163887024},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14161410927772522}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7839385271072388},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7280303835868835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7030766010284424},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6029409170150757},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6015540361404419},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5962499380111694},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5592277646064758},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5567914247512817},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5211072564125061},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.48199668526649475},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.47086846828460693},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.43189045786857605},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.42432790994644165},{"id":"https://openalex.org/C168136583","wikidata":"https://www.wikidata.org/wiki/Q1988242","display_name":"Bayesian information criterion","level":2,"score":0.41515377163887024},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14161410927772522},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme.2005.1521428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2005.1521428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.612.8884","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.612.8884","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cecs.uci.edu/~papers/icme05/defevent/papers/cr1223.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8799999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W193881641","https://openalex.org/W1497564599","https://openalex.org/W1560013842","https://openalex.org/W2071913706","https://openalex.org/W2131016009","https://openalex.org/W2132875213","https://openalex.org/W2141119838","https://openalex.org/W2143235280","https://openalex.org/W2155405164","https://openalex.org/W2165578912","https://openalex.org/W2799061466","https://openalex.org/W3021051756","https://openalex.org/W4229691956","https://openalex.org/W4285719527","https://openalex.org/W6607965971","https://openalex.org/W6679486929","https://openalex.org/W6679651670","https://openalex.org/W6684292600"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2140773153","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"an":[3],"HMM-embedded":[4],"unsupervised":[5],"learning":[6],"approach":[7,25,63,83],"is":[8,44,84,129,142,152],"proposed":[9,62],"to":[10,70,144],"detect":[11],"the":[12,17,21,28,35,40,51,61,72,75,82,92,99,112,156,160],"music":[13,22,88,136],"events":[14,89,102,118],"by":[15,91],"grouping":[16],"similar":[18],"segments":[19,29],"of":[20,34,74,81,87,135],"signal.":[23],"This":[24,43],"can":[26,64],"cluster":[27],"based":[30,114],"on":[31,132],"their":[32],"similarity":[33,53],"spectral":[36],"as":[37,39],"well":[38],"temporal":[41],"structures.":[42],"not":[45],"easily":[46],"done":[47],"for":[48],"clustering":[49,162],"with":[50,56,121,155],"traditional":[52],"measures.":[54],"Together":[55],"a":[57,66,85,133],"Bayesian":[58],"information":[59],"criterion,":[60],"obtain":[65],"suitable":[67],"event":[68],"set":[69,86],"regularize":[71],"complexity":[73],"model":[76],"structure.":[77],"The":[78,116,138],"natural":[79],"product":[80],"modeled":[90],"HMMs.":[93],"Our":[94],"experimental":[95],"analyses":[96],"show":[97],"that":[98],"detected":[100],"musical":[101],"have":[103],"more":[104,109],"perceptual":[105],"meaning":[106],"and":[107,146],"are":[108],"consistent":[110],"than":[111],"KL-distance":[113,161],"clustering.":[115],"learned":[117],"match":[119],"better":[120],"our":[122],"experience":[123],"in":[124],"spectrogram":[125],"reading.":[126],"Its":[127],"capacity":[128],"further":[130],"evaluated":[131],"task":[134],"identification.":[137],"identification":[139],"error":[140,149],"rate":[141,150],"reduced":[143],"1.57%,":[145],"56.3%":[147],"relative":[148],"reduction":[151],"observed":[153],"comparing":[154],"system":[157],"trained":[158],"using":[159],"method.":[163]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}