{"id":"https://openalex.org/W2132614156","doi":"https://doi.org/10.1109/icassp.2005.1415682","title":"Automatic Transcription of Drum Sequences using Audiovisual Features","display_name":"Automatic Transcription of Drum Sequences using Audiovisual Features","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2132614156","doi":"https://doi.org/10.1109/icassp.2005.1415682","mag":"2132614156"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415682","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","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., Telecom 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., Telecom Paris, France","institution_ids":["https://openalex.org/I12356871"]}]},{"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., Telecom 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., Telecom Paris, France","institution_ids":["https://openalex.org/I12356871"]}]}],"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":2.5866,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.89595165,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"3","issue":null,"first_page":"205","last_page":"208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987999796867371,"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":0.9965000152587891,"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/transcription","display_name":"Transcription (linguistics)","score":0.7620798349380493},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6881201863288879},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6254805326461792},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5523315072059631},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5412044525146484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4617362916469574},{"id":"https://openalex.org/keywords/drum","display_name":"Drum","score":0.4175513982772827},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4153425097465515},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.16297563910484314},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10748350620269775}],"concepts":[{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7620798349380493},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6881201863288879},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6254805326461792},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5523315072059631},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5412044525146484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4617362916469574},{"id":"https://openalex.org/C175845324","wikidata":"https://www.wikidata.org/wiki/Q2738285","display_name":"Drum","level":2,"score":0.4175513982772827},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4153425097465515},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.16297563910484314},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10748350620269775},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/icassp.2005.1415682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415682","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.422.2781","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.422.2781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ee.columbia.edu/~dpwe/papers/GilletR05-avdrums.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":18,"referenced_works":["https://openalex.org/W6854706","https://openalex.org/W194480839","https://openalex.org/W1517808374","https://openalex.org/W1618905105","https://openalex.org/W2003521087","https://openalex.org/W2019575783","https://openalex.org/W2056961398","https://openalex.org/W2120132744","https://openalex.org/W2133119264","https://openalex.org/W2153635508","https://openalex.org/W2168818958","https://openalex.org/W2548695521","https://openalex.org/W2998678080","https://openalex.org/W3120421331","https://openalex.org/W4285719527","https://openalex.org/W6607976278","https://openalex.org/W6630956611","https://openalex.org/W6684447540"],"related_works":["https://openalex.org/W2356237291","https://openalex.org/W2960896737","https://openalex.org/W2390208690","https://openalex.org/W2371365383","https://openalex.org/W2386180132","https://openalex.org/W2383392149","https://openalex.org/W2392428765","https://openalex.org/W2355941487","https://openalex.org/W3012488370","https://openalex.org/W2028097510"],"abstract_inverted_index":{"The":[0,53],"transcription":[1,46,54],"of":[2,19,47,75],"a":[3,40,81,85],"musical":[4],"performance":[5],"from":[6,34],"the":[7,17,35,45],"audio":[8,36],"signal":[9],"is":[10,55],"often":[11],"problematic,":[12],"either":[13],"because":[14,24],"it":[15],"requires":[16],"separation":[18],"complex":[20],"sources,":[21],"or":[22],"simply":[23],"some":[25],"important":[26],"high-level":[27],"music":[28],"information":[29,66],"cannot":[30],"be":[31,78],"directly":[32],"extracted":[33],"signal.":[37],"We":[38],"propose":[39],"novel":[41],"multimodal":[42],"approach":[43],"for":[44,80],"drum":[48],"sequences":[49],"using":[50],"audiovisual":[51],"features.":[52],"performed":[56],"by":[57],"support":[58],"vector":[59],"machine":[60],"(SVM)":[61],"classifiers,":[62],"and":[63,84],"three":[64],"different":[65],"fusion":[67],"strategies":[68],"are":[69],"evaluated.":[70],"A":[71],"correct":[72],"recognition":[73],"rate":[74],"85.8%":[76],"can":[77],"achieved":[79],"detailed":[82],"taxonomy":[83],"fully":[86],"automated":[87],"transcription.":[88]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}