{"id":"https://openalex.org/W2150709457","doi":"https://doi.org/10.1109/icassp.2004.1326816","title":"Comparing features for forming music streams in automatic music transcription","display_name":"Comparing features for forming music streams in automatic music transcription","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2150709457","doi":"https://doi.org/10.1109/icassp.2004.1326816","mag":"2150709457"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326816","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/A5039827334","display_name":"Yohei Sakuraba","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Y. Sakuraba","raw_affiliation_strings":["Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Sakyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Sakyo, Tokyo, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076173920","display_name":"T Kitahara","orcid":"https://orcid.org/0000-0002-5347-7924"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Kitahara","raw_affiliation_strings":["Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Sakyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Sakyo, Tokyo, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005141184","display_name":"Hiroshi G. Okuno","orcid":"https://orcid.org/0000-0002-8704-4318"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"J.G. Okuno","raw_affiliation_strings":["Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Sakyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Sakyo, Tokyo, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5039827334"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":4.2864,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.94584989,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"4","issue":null,"first_page":"iv","last_page":"273"},"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":0.9994000196456909,"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":0.9958999752998352,"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/timbre","display_name":"Timbre","score":0.9583069086074829},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.770847737789154},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6527841091156006},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6464959383010864},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6120551824569702},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5062769651412964},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4335230588912964},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4106051027774811},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37647202610969543},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.36571237444877625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33382296562194824},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.25733381509780884},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.08347928524017334},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07128101587295532}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.9583069086074829},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.770847737789154},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6527841091156006},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6464959383010864},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6120551824569702},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5062769651412964},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4335230588912964},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4106051027774811},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37647202610969543},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.36571237444877625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33382296562194824},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.25733381509780884},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.08347928524017334},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07128101587295532},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2004.1326816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326816","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.142.456","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.142.456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://winnie.kuis.kyoto-u.ac.jp/~kitahara/papers/FinalPDFs/FY2004/icassp-2004-sakuraba.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.74.5537","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.74.5537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://winnie.kuis.kyoto-u.ac.jp/~okuno/paper/ICASSP04-Sakuraba.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":11,"referenced_works":["https://openalex.org/W1496493329","https://openalex.org/W1519655822","https://openalex.org/W1623821838","https://openalex.org/W1958993123","https://openalex.org/W2042731730","https://openalex.org/W2088832111","https://openalex.org/W2113539812","https://openalex.org/W4231393202","https://openalex.org/W6631117800","https://openalex.org/W6636725911","https://openalex.org/W6677251940"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2371528275","https://openalex.org/W2797744129","https://openalex.org/W2727800297","https://openalex.org/W2591743215"],"abstract_inverted_index":{"In":[0,25,77,124],"formating":[1],"temporal":[2],"sequences":[3],"of":[4,17,30,128],"notes":[5],"played":[6],"by":[7,136,142],"the":[8,28,52,96,114,122,126],"same":[9,53],"instrument":[10],"(referred":[11],"to":[12,94,140],"as":[13,74],"music":[14,101,108,129],"streams),":[15],"timbre":[16,31,62,84,138],"musical":[18],"instruments":[19],"may":[20],"be":[21],"a":[22],"predominant":[23],"feature.":[24],"polyphonic":[26],"music,":[27],"performance":[29,127],"extraction":[32],"based":[33],"on":[34],"power-related":[35],"features":[36,40,73],"deteriorates,":[37],"because":[38],"such":[39],"are":[41,49],"blurred":[42],"when":[43],"two":[44],"or":[45],"more":[46],"frequency":[47],"components":[48],"superimposed":[50],"in":[51,100],"frequency.":[54],"To":[55],"cope":[56],"with":[57,67,106],"this":[58,78],"problem,":[59],"we":[60,80],"integrated":[61],"similarity":[63,139],"and":[64,90,118],"direction":[65,86,111],"proximity":[66,112],"success,":[68],"but":[69],"left":[70],"using":[71],"other":[72],"future":[75],"work.":[76],"paper,":[79],"investigate":[81],"four":[82,144],"features.":[83,145],"similarity,":[85],"proximity,":[87],"pitch":[88,91,119],"transition":[89,120],"relation":[92],"consistency":[93],"clarify":[95],"precedence":[97],"among":[98],"them":[99],"stream":[102,130],"formation.":[103],"Experimental":[104],"results":[105],"quartet":[107],"show":[109],"that":[110],"is":[113,121],"most":[115],"dominant":[116],"feature,":[117],"secondary.":[123],"addition,":[125],"formation":[131],"was":[132],"improved":[133],"from":[134],"63.3%":[135],"only":[137],"84.9%":[141],"integrating":[143]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}