{"id":"https://openalex.org/W2152131289","doi":"https://doi.org/10.1109/icassp.2006.1661257","title":"Acoustic Modelling of Drum Sounds with Hidden Markov Models for Music Transcription","display_name":"Acoustic Modelling of Drum Sounds with Hidden Markov Models for Music Transcription","publication_year":2006,"publication_date":"2006-08-03","ids":{"openalex":"https://openalex.org/W2152131289","doi":"https://doi.org/10.1109/icassp.2006.1661257","mag":"2152131289"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1661257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1661257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","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/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":true,"raw_author_name":"J. Paulus","raw_affiliation_strings":["Institute of Signal Processing, Tampere University of Technology, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Institute of Signal Processing, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5054389422"],"corresponding_institution_ids":["https://openalex.org/I4210133110"],"apc_list":null,"apc_paid":null,"fwci":0.9673,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.76370786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"5","issue":null,"first_page":"V","last_page":"241"},"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":0.9997000098228455,"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":0.9995999932289124,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8308581709861755},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7010139226913452},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6164926290512085},{"id":"https://openalex.org/keywords/drum","display_name":"Drum","score":0.597595751285553},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.5629544854164124},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.5389770269393921},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5135248303413391},{"id":"https://openalex.org/keywords/silence","display_name":"Silence","score":0.4803634583950043},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3421071171760559},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33832836151123047},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.323175847530365},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24150651693344116},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14995306730270386}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8308581709861755},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7010139226913452},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6164926290512085},{"id":"https://openalex.org/C175845324","wikidata":"https://www.wikidata.org/wiki/Q2738285","display_name":"Drum","level":2,"score":0.597595751285553},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.5629544854164124},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.5389770269393921},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5135248303413391},{"id":"https://openalex.org/C2781115785","wikidata":"https://www.wikidata.org/wiki/Q502261","display_name":"Silence","level":2,"score":0.4803634583950043},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3421071171760559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33832836151123047},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.323175847530365},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24150651693344116},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14995306730270386},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2006.1661257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1661257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.133.6031","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.133.6031","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/icassp06_paulus.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.163.6484","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.163.6484","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/icassp06_paulus_copy.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W27187656","https://openalex.org/W75089651","https://openalex.org/W579432544","https://openalex.org/W1497176473","https://openalex.org/W1519655822","https://openalex.org/W1541908801","https://openalex.org/W1560013842","https://openalex.org/W1603632465","https://openalex.org/W2041823554","https://openalex.org/W2105978559","https://openalex.org/W2132214932","https://openalex.org/W2133119264","https://openalex.org/W2137617114","https://openalex.org/W2155084615","https://openalex.org/W6601066586","https://openalex.org/W6603030901","https://openalex.org/W6629679819","https://openalex.org/W6631117800","https://openalex.org/W6632191535","https://openalex.org/W6636328019","https://openalex.org/W6680327777"],"related_works":["https://openalex.org/W1510894296","https://openalex.org/W2134386692","https://openalex.org/W2082284720","https://openalex.org/W2194396582","https://openalex.org/W2116722627","https://openalex.org/W2379938888","https://openalex.org/W2537260108","https://openalex.org/W4233405330","https://openalex.org/W2176285001","https://openalex.org/W2792905593"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"two":[3,91],"methods":[4,24,80],"for":[5,18],"applying":[6],"hidden":[7],"Markov":[8],"models":[9],"(HMMs)":[10],"to":[11],"acoustic":[12,86],"modelling":[13,28,30,98,103],"of":[14,31],"drum":[15],"sound":[16],"events":[17],"polyphonic":[19],"music":[20],"transcription.":[21],"The":[22,78],"proposed":[23,79],"are":[25,69,81],"instrument-wise":[26,102],"binary":[27],"and":[29,46,71,88],"instrument":[32,39,55,67],"combinations.":[33],"In":[34,62],"the":[35,60,63],"first,":[36],"each":[37],"target":[38,48],"is":[40,56,76],"modelled":[41],"with":[42,83,85,90],"a":[43,51],"\"sound\"":[44],"model":[45,75],"all":[47],"instruments":[49],"share":[50],"\"silence\"":[52,74],"model.":[53],"Each":[54],"transcribed":[57],"independently":[58],"from":[59],"others.":[61],"latter":[64],"method,":[65],"different":[66],"combinations":[68],"modelled,":[70],"an":[72],"additional":[73],"created.":[77],"evaluated":[82],"simulations":[84],"data,":[87],"compared":[89],"reference":[92],"methods.":[93],"Simulations":[94],"show":[95],"that":[96],"combination":[97],"performs":[99],"better":[100],"than":[101]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}