{"id":"https://openalex.org/W2150159182","doi":"https://doi.org/10.1109/icip.2008.4711699","title":"A multimodal approach to music transcription","display_name":"A multimodal approach to music transcription","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W2150159182","doi":"https://doi.org/10.1109/icip.2008.4711699","mag":"2150159182"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2008.4711699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2008.4711699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 15th IEEE International Conference on Image 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/A5030865569","display_name":"Marco Paleari","orcid":"https://orcid.org/0000-0002-8387-6678"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Marco Paleari","raw_affiliation_strings":["Multimedia Department, Eurecom Institute, France"],"affiliations":[{"raw_affiliation_string":"Multimedia Department, Eurecom Institute, France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038148603","display_name":"Beno\u00eet Huet","orcid":"https://orcid.org/0000-0002-0608-6939"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Benoit Huet","raw_affiliation_strings":["Multimedia Department, Eurecom Institute, France"],"affiliations":[{"raw_affiliation_string":"Multimedia Department, Eurecom Institute, France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051842352","display_name":"Antony Schutz","orcid":null},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antony Schutz","raw_affiliation_strings":["Mobile Communication Department, Eurecom Institute, France"],"affiliations":[{"raw_affiliation_string":"Mobile Communication Department, Eurecom Institute, France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014663629","display_name":"Dirk Slock","orcid":"https://orcid.org/0000-0003-4116-563X"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dirk Slock","raw_affiliation_strings":["Mobile Communication Department, Eurecom Institute, France"],"affiliations":[{"raw_affiliation_string":"Mobile Communication Department, Eurecom Institute, France","institution_ids":["https://openalex.org/I1902872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030865569"],"corresponding_institution_ids":["https://openalex.org/I1902872"],"apc_list":null,"apc_paid":null,"fwci":2.2395,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.88786911,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"8","issue":null,"first_page":"93","last_page":"96"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/guitar","display_name":"Guitar","score":0.944731593132019},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7572168111801147},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6851859092712402},{"id":"https://openalex.org/keywords/violin","display_name":"Violin","score":0.6401996612548828},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.6113114953041077},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5797975063323975},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5616679787635803},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5003111362457275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4183664321899414},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.13195282220840454},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09244075417518616}],"concepts":[{"id":"https://openalex.org/C95543465","wikidata":"https://www.wikidata.org/wiki/Q6607","display_name":"Guitar","level":2,"score":0.944731593132019},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7572168111801147},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6851859092712402},{"id":"https://openalex.org/C129554576","wikidata":"https://www.wikidata.org/wiki/Q8355","display_name":"Violin","level":2,"score":0.6401996612548828},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.6113114953041077},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5797975063323975},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5616679787635803},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5003111362457275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4183664321899414},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.13195282220840454},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09244075417518616},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip.2008.4711699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2008.4711699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 15th IEEE International Conference on Image Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.49000000953674316,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W52610099","https://openalex.org/W1571477232","https://openalex.org/W1969199662","https://openalex.org/W2786641303","https://openalex.org/W2984895252","https://openalex.org/W6602120865","https://openalex.org/W6634367950","https://openalex.org/W6747805115"],"related_works":["https://openalex.org/W4220911637","https://openalex.org/W4385984930","https://openalex.org/W1990291079","https://openalex.org/W3118230952","https://openalex.org/W2898671791","https://openalex.org/W3113369605","https://openalex.org/W2791247564","https://openalex.org/W3085943053","https://openalex.org/W126167045","https://openalex.org/W4298140471"],"abstract_inverted_index":{"Music":[0],"transcription":[1,21,99],"refers":[2],"to":[3,46,68,95,141,169],"extraction":[4],"of":[5,15,105,120,134,152,178,185],"a":[6,13,16,24,78,88,114,124,127,146,160,171,188],"human":[7],"readable":[8],"and":[9,42,112,158,166],"interpretable":[10],"description":[11],"from":[12],"recording":[14],"music":[17,20,63,71],"performance.":[18],"Automatic":[19],"remains,":[22],"nowadays,":[23],"challenging":[25],"research":[26],"problem":[27,48],"when":[28,34],"dealing":[29,60],"with":[30,61,87],"polyphonic":[31],"sounds":[32],"or":[33],"removing":[35],"certain":[36],"constraints.":[37],"Some":[38],"instruments":[39],"like":[40],"guitars":[41],"violins":[43],"add":[44],"ambiguity":[45],"the":[47,50,69,92,118,121,132,135,138,143,150,153,156,164],"as":[49,73],"same":[51],"note":[52],"can":[53,181],"be":[54],"played":[55],"at":[56],"different":[57],"positions.":[58],"When":[59],"guitar":[62,136],"tablature":[64],"are,":[65],"often,":[66],"preferred":[67],"usual":[70],"score,":[72],"they":[74],"present":[75],"information":[76,168],"in":[77,187],"more":[79],"accessible":[80],"way.":[81,190],"Here,":[82],"we":[83],"address":[84],"this":[85,176],"issue":[86],"system":[89,102,115,128,147,161],"which":[90,108,116,129,148,162],"uses":[91],"visual":[93,165],"modality":[94],"support":[96],"traditional":[97],"audio":[98,167],"techniques.":[100],"The":[101],"is":[103],"composed":[104],"four":[106],"modules":[107],"have":[109],"been":[110],"implemented":[111],"evaluated:":[113],"tracks":[117],"position":[119,133,151],"fretboard":[122],"on":[123,137,155],"video":[125],"stream,":[126],"automatically":[130],"detects":[131,149],"first":[139,144],"fret":[140],"initialize":[142],"system,":[145],"hand":[154],"guitar,":[157],"finally":[159],"fuses":[163],"extract":[170],"tablature.":[172],"Results":[173],"show":[174],"that":[175],"kind":[177],"multimodal":[179],"approach":[180],"easily":[182],"disambiguate":[183],"89%":[184],"notes":[186],"deterministic":[189]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
