{"id":"https://openalex.org/W2105978559","doi":"https://doi.org/10.1109/icme.2003.1221722","title":"Conventional and periodic N-grams in the transcription of drum sequences","display_name":"Conventional and periodic N-grams in the transcription of drum sequences","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2105978559","doi":"https://doi.org/10.1109/icme.2003.1221722","mag":"2105978559"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2003.1221722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","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.K. Paulus","raw_affiliation_strings":["Tampere University of Technology, Tampere, Finland","Tampere University of Technology, , Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Tampere University of Technology, , Finland","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":"A.P. Klapuri","raw_affiliation_strings":["Tampere University of Technology, Tampere, Finland","Tampere University of Technology, , Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Tampere University of Technology, , Finland","institution_ids":["https://openalex.org/I4210133110"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5054389422"],"corresponding_institution_ids":["https://openalex.org/I4210133110"],"apc_list":null,"apc_paid":null,"fwci":4.7407,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.95760317,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"II","last_page":"737"},"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":0.9991999864578247,"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":0.998199999332428,"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/drum","display_name":"Drum","score":0.7351242303848267},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6662009954452515},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.6376186609268188},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.602379560470581},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5505974292755127},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5127931237220764},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4622023105621338},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4236932098865509},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3913348317146301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36805805563926697},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3670176863670349},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2614268660545349},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11124417185783386},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10147762298583984}],"concepts":[{"id":"https://openalex.org/C175845324","wikidata":"https://www.wikidata.org/wiki/Q2738285","display_name":"Drum","level":2,"score":0.7351242303848267},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6662009954452515},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.6376186609268188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.602379560470581},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5505974292755127},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5127931237220764},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4622023105621338},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4236932098865509},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3913348317146301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36805805563926697},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3670176863670349},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2614268660545349},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11124417185783386},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10147762298583984},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme.2003.1221722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.12.3961","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.12.3961","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/music/icme03_paulus.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W11703657","https://openalex.org/W182831726","https://openalex.org/W1555402191","https://openalex.org/W1560013842","https://openalex.org/W1576520375","https://openalex.org/W1604938182","https://openalex.org/W1994920552","https://openalex.org/W2112109770","https://openalex.org/W2113641473","https://openalex.org/W2119821739","https://openalex.org/W4239510810","https://openalex.org/W6600475410"],"related_works":["https://openalex.org/W2356237291","https://openalex.org/W2411659965","https://openalex.org/W2960896737","https://openalex.org/W2387677326","https://openalex.org/W2390208690","https://openalex.org/W4200063482","https://openalex.org/W2371365383","https://openalex.org/W2132597408","https://openalex.org/W2340483794","https://openalex.org/W2118730790"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"describe":[4],"a":[5,17,31,36,49,63,82,93,101],"system":[6],"for":[7,52,65],"transcribing":[8],"polyphonic":[9],"drum":[10,86],"sequences":[11,87],"from":[12,88],"an":[13,26],"acoustic":[14,27,111],"signal":[15,21],"to":[16,47,100],"symbolic":[18],"representation.":[19],"Low-level":[20],"analysis":[22],"is":[23,70],"done":[24],"with":[25,109],"model":[28,34],"consisting":[29],"of":[30,59,74,84,96,104],"Gaussian":[32],"mixture":[33],"and":[35,91],"support":[37],"vector":[38],"machine.":[39],"For":[40],"higher-level":[41],"modelling,":[42],"periodic":[43],"N-grams":[44,69,75],"are":[45],"proposed":[46],"construct":[48],"\"language":[50],"model\"":[51],"music,":[53],"based":[54],"on":[55],"the":[56,77,102,110],"repetitive":[57],"nature":[58],"musical":[60],"structure.":[61],"Also,":[62],"technique":[64],"estimating":[66],"relatively":[67],"long":[68],"introduced.":[71],"The":[72],"performance":[73,94],"in":[76],"transcription":[78],"was":[79],"evaluated":[80],"using":[81],"database":[83],"realistic":[85],"different":[89],"genres":[90],"yielded":[92],"increase":[95],"7.6":[97],"%":[98],"compared":[99],"use":[103],"only":[105],"prior":[106],"(unigram)":[107],"probabilities":[108],"model.":[112]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
