{"id":"https://openalex.org/W2133119264","doi":"https://doi.org/10.1109/icassp.2004.1326815","title":"Automatic transcription of drum loops","display_name":"Automatic transcription of drum loops","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2133119264","doi":"https://doi.org/10.1109/icassp.2004.1326815","mag":"2133119264"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326815","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5031087667","display_name":"Olivier Gillet","orcid":null},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"O. Gillet","raw_affiliation_strings":["Signal and Image Processing Department, GET-ENST (TELECOM Paris), Paris, France","Signal & Image Process. Dept., Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal and Image Processing Department, GET-ENST (TELECOM Paris), Paris, France","institution_ids":["https://openalex.org/I12356871"]},{"raw_affiliation_string":"Signal & Image Process. Dept., Paris, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055423112","display_name":"Ga\u00ebl Richard","orcid":"https://orcid.org/0000-0002-4960-0010"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"G. Richard","raw_affiliation_strings":["Signal and Image Processing Department, GET-ENST (TELECOM Paris), Paris, France","Signal & Image Process. Dept., Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal and Image Processing Department, GET-ENST (TELECOM Paris), Paris, France","institution_ids":["https://openalex.org/I12356871"]},{"raw_affiliation_string":"Signal & Image Process. Dept., Paris, France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I12356871"],"apc_list":null,"apc_paid":null,"fwci":6.0146,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":{"value":0.9677959,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"4","issue":null,"first_page":"iv","last_page":"269"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.7537206411361694},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7017866969108582},{"id":"https://openalex.org/keywords/drum","display_name":"Drum","score":0.6969369649887085},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6891319751739502},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.6873099207878113},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6273257732391357},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.60425865650177},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5242172479629517},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.49030163884162903},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.46627548336982727},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4633885324001312},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.44934380054473877},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.43408313393592834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42201489210128784},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32705387473106384},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.22985175251960754},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1275048851966858},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1075102686882019},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.07907336950302124}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7537206411361694},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7017866969108582},{"id":"https://openalex.org/C175845324","wikidata":"https://www.wikidata.org/wiki/Q2738285","display_name":"Drum","level":2,"score":0.6969369649887085},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6891319751739502},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.6873099207878113},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6273257732391357},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.60425865650177},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5242172479629517},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.49030163884162903},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.46627548336982727},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4633885324001312},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.44934380054473877},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.43408313393592834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42201489210128784},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32705387473106384},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.22985175251960754},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1275048851966858},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1075102686882019},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.07907336950302124},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1326815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326815","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W102921845","https://openalex.org/W1537504396","https://openalex.org/W2067063915","https://openalex.org/W2105978559","https://openalex.org/W2120132744","https://openalex.org/W2139998076","https://openalex.org/W2153104898","https://openalex.org/W2153635508","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W126167045","https://openalex.org/W4298140471","https://openalex.org/W2289868279","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W2056234363","https://openalex.org/W2088690926","https://openalex.org/W1590604789","https://openalex.org/W2155527258"],"abstract_inverted_index":{"Recent":[0],"efforts":[1],"in":[2,7,52,74],"audio":[3,31,76,83],"indexing":[4],"and":[5,79,98],"retrieval":[6],"music":[8,20],"databases":[9],"mostly":[10],"focus":[11,48],"on":[12,49,93],"melody.":[13],"If":[14],"this":[15,55],"is":[16],"appropriate":[17],"for":[18,26,61,113],"polyphonic":[19],"signals,":[21],"specific":[22],"approaches":[23,89],"are":[24,91,105],"needed":[25],"systems":[27],"dealing":[28],"with":[29,107],"percussive":[30],"signals":[32,68],"such":[33],"as":[34],"those":[35],"produced":[36],"by":[37],"drums,":[38],"tabla":[39],"or":[40],"djembe.":[41],"Most":[42],"studies":[43],"of":[44],"drum":[45,62,81],"signal":[46],"transcription":[47,64],"sounds":[50],"taken":[51],"isolation.":[53],"In":[54],"paper,":[56],"we":[57],"propose":[58],"several":[59],"methods":[60],"loop":[63],"where":[65],"the":[66,71],"drums":[67],"dataset":[69],"reflects":[70],"variability":[72],"encountered":[73],"modern":[75],"recordings":[77],"(real":[78],"natural":[80],"kits,":[82],"effects,":[84],"simultaneous":[85],"instruments,":[86],"etc.).":[87],"The":[88],"described":[90],"based":[92],"hidden":[94],"Markov":[95],"models":[96],"(HMM)":[97],"support":[99],"vector":[100],"machines":[101],"(SVM).":[102],"Promising":[103],"results":[104],"obtained":[106],"a":[108,114],"83.9%":[109],"correct":[110],"recognition":[111],"rate":[112],"simplified":[115],"taxonomy.":[116]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}