{"id":"https://openalex.org/W2024339477","doi":"https://doi.org/10.1155/2009/497292","title":"Drum Sound Detection in Polyphonic Music with Hidden Markov Models","display_name":"Drum Sound Detection in Polyphonic Music with Hidden Markov Models","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2024339477","doi":"https://doi.org/10.1155/2009/497292","mag":"2024339477"},"language":"en","primary_location":{"id":"doi:10.1155/2009/497292","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2009/497292","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1155/2009/497292","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054389422","display_name":"Jouni Paulus","orcid":"https://orcid.org/0000-0003-2283-2062"},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jouni Paulus","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology, Tampere, Finland 33720#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology, Tampere, Finland 33720#TAB#","institution_ids":["https://openalex.org/I4210133110"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035987859","display_name":"Anssi Klapuri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Anssi Klapuri","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology, Tampere, Finland 33720#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology, Tampere, Finland 33720#TAB#","institution_ids":["https://openalex.org/I4210133110"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":1.7859,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.83751739,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"2009","issue":null,"first_page":"1","last_page":"9"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9954000115394592,"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/polyphony","display_name":"Polyphony","score":0.8551692962646484},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.6644203662872314},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6089708805084229},{"id":"https://openalex.org/keywords/drum","display_name":"Drum","score":0.5956200361251831},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5771828293800354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48812350630760193},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4103814959526062},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.20901602506637573},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07264366745948792}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8551692962646484},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.6644203662872314},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6089708805084229},{"id":"https://openalex.org/C175845324","wikidata":"https://www.wikidata.org/wiki/Q2738285","display_name":"Drum","level":2,"score":0.5956200361251831},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5771828293800354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48812350630760193},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4103814959526062},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.20901602506637573},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07264366745948792},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1155/2009/497292","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2009/497292","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.156.1875","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.156.1875","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.tut.fi/sgn/arg/paulus/paulus_jasmp09.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.618.1639","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.618.1639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.tut.fi/sgn/arg/paulus/paulus_jasmp_preprint.pdf","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:99118af33b354b8db6a459095ea81b56","is_oa":true,"landing_page_url":"https://doaj.org/article/99118af33b354b8db6a459095ea81b56","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2009 (2009)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1155/2009/497292","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2009/497292","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W16748735","https://openalex.org/W27187656","https://openalex.org/W84529036","https://openalex.org/W102395857","https://openalex.org/W148257418","https://openalex.org/W186036538","https://openalex.org/W192383697","https://openalex.org/W579432544","https://openalex.org/W1497176473","https://openalex.org/W1551226391","https://openalex.org/W1571477232","https://openalex.org/W1603632465","https://openalex.org/W1985014571","https://openalex.org/W2062989416","https://openalex.org/W2097954800","https://openalex.org/W2105978559","https://openalex.org/W2113641473","https://openalex.org/W2114640443","https://openalex.org/W2118367648","https://openalex.org/W2125838338","https://openalex.org/W2129258718","https://openalex.org/W2137617114","https://openalex.org/W2139998076","https://openalex.org/W2146871184","https://openalex.org/W2148154194","https://openalex.org/W2152131289","https://openalex.org/W2155084615","https://openalex.org/W2155413697","https://openalex.org/W2157342986","https://openalex.org/W2164764235","https://openalex.org/W2165387890","https://openalex.org/W2330519819","https://openalex.org/W2533278577","https://openalex.org/W2792718482"],"related_works":["https://openalex.org/W2356237291","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,12,48,82,151,189],"method":[4,147],"for":[5,132,184],"transcribing":[6],"drums":[7,80],"from":[8],"polyphonic":[9],"music":[10],"using":[11,71,176,181],"network":[13],"of":[14,28,70,77,85,105,144],"connected":[15,57,177],"hidden":[16],"Markov":[17],"models":[18,183],"(HMMs).":[19],"The":[20,103,142,168],"task":[21],"is":[22,53,92,118,130,148,174],"to":[23,44,61],"detect":[24],"the":[25,40,63,78,107,134,137,145,172],"temporal":[26,101],"locations":[27],"unpitched":[29],"percussive":[30],"sounds":[31],"(such":[32],"as":[33],"bass":[34],"drum":[35,187,194],"or":[36],"hi-hat)":[37],"and":[38,65,81,98,114,139,159,162,179],"recognise":[39],"instruments":[41],"played.":[42],"Contrary":[43],"many":[45],"earlier":[46],"methods,":[47],"separate":[49],"sound":[50],"event":[51],"segmentation":[52,64],"not":[54],"done,":[55],"but":[56],"HMMs":[58,72],"are":[59,73],"used":[60],"perform":[62],"recognition":[66],"jointly.":[67],"Two":[68],"ways":[69],"studied:":[74],"modelling":[75,84,193],"combinations":[76],"target":[79,87,140,186],"detector-like":[83,182],"each":[86,185],"drum.":[88],"Acoustic":[89],"feature":[90,108],"parametrisation":[91],"done":[93],"with":[94,110,125,158,164],"mel-frequency":[95],"cepstral":[96],"coefficients":[97],"their":[99],"first-order":[100],"derivatives.":[102],"effect":[104],"lowering":[106],"dimensionality":[109],"principal":[111],"component":[112],"analysis":[113,117],"linear":[115,128],"discriminant":[116],"evaluated.":[119],"Unsupervised":[120],"acoustic":[121],"model":[122],"parameter":[123],"adaptation":[124],"maximum":[126],"likelihood":[127],"regression":[129],"evaluated":[131,149],"compensating":[133],"differences":[135],"between":[136],"training":[138],"signals.":[141],"performance":[143,191],"proposed":[146],"on":[150],"publicly":[152],"available":[153],"data":[154],"set":[155],"containing":[156],"signals":[157],"without":[160],"accompaniment,":[161],"compared":[163],"two":[165],"reference":[166],"methods.":[167],"results":[169],"suggest":[170],"that":[171,180],"transcription":[173],"possible":[175],"HMMs,":[178],"provides":[188],"better":[190],"than":[192],"combinations.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}