{"id":"https://openalex.org/W2255404133","doi":"https://doi.org/10.1186/s13636-015-0079-0","title":"Detecting fingering of overblown flute sound using sparse feature learning","display_name":"Detecting fingering of overblown flute sound using sparse feature learning","publication_year":2016,"publication_date":"2016-01-21","ids":{"openalex":"https://openalex.org/W2255404133","doi":"https://doi.org/10.1186/s13636-015-0079-0","mag":"2255404133"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-015-0079-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-015-0079-0","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-015-0079-0","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-015-0079-0","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065179879","display_name":"Yoonchang Han","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yoonchang Han","raw_affiliation_strings":["Music and Audio Research Group (MARG), Graduate School of Convergence Science and Technology, Seoul National University, 599 Gwanak-ro, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Music and Audio Research Group (MARG), Graduate School of Convergence Science and Technology, Seoul National University, 599 Gwanak-ro, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088852010","display_name":"Kyogu Lee","orcid":"https://orcid.org/0000-0002-4210-0312"},"institutions":[{"id":"https://openalex.org/I4210120602","display_name":"Advanced Institute of Convergence Technology","ror":"https://ror.org/01w62yz22","country_code":"KR","type":"facility","lineage":["https://openalex.org/I139264467","https://openalex.org/I4210120602"]},{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyogu Lee","raw_affiliation_strings":["Advanced Institutes of Convergence Technology (AICT), Suwon, Republic of Korea","Music and Audio Research Group (MARG), Graduate School of Convergence Science and Technology, Seoul National University, 599 Gwanak-ro, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Advanced Institutes of Convergence Technology (AICT), Suwon, Republic of Korea","institution_ids":["https://openalex.org/I4210120602"]},{"raw_affiliation_string":"Music and Audio Research Group (MARG), Graduate School of Convergence Science and Technology, Seoul National University, 599 Gwanak-ro, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065179879"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":0.2551,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.49468616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2016","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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":0.9976999759674072,"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/spectrogram","display_name":"Spectrogram","score":0.788277268409729},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.773646354675293},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6318458914756775},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5994166731834412},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5980084538459778},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5944627523422241},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5690786838531494},{"id":"https://openalex.org/keywords/flute","display_name":"Flute","score":0.5503944754600525},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5481293201446533},{"id":"https://openalex.org/keywords/octave","display_name":"Octave (electronics)","score":0.5359469652175903},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5041252374649048},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4675143361091614},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.4539579451084137},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.44180378317832947},{"id":"https://openalex.org/keywords/bioacoustics","display_name":"Bioacoustics","score":0.4160369634628296},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3616788983345032},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19336935877799988}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.788277268409729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.773646354675293},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6318458914756775},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5994166731834412},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5980084538459778},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5944627523422241},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5690786838531494},{"id":"https://openalex.org/C4060165","wikidata":"https://www.wikidata.org/wiki/Q11405","display_name":"Flute","level":2,"score":0.5503944754600525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5481293201446533},{"id":"https://openalex.org/C85841341","wikidata":"https://www.wikidata.org/wiki/Q1135984","display_name":"Octave (electronics)","level":2,"score":0.5359469652175903},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5041252374649048},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4675143361091614},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.4539579451084137},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.44180378317832947},{"id":"https://openalex.org/C34951282","wikidata":"https://www.wikidata.org/wiki/Q864191","display_name":"Bioacoustics","level":2,"score":0.4160369634628296},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3616788983345032},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19336935877799988},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1186/s13636-015-0079-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-015-0079-0","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-015-0079-0","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/s13636-015-0079-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-015-0079-0","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-015-0079-0","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1274167916","display_name":null,"funder_award_id":"NRF-2014","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G1798249494","display_name":null,"funder_award_id":"2014R1A2A2A","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G3034753964","display_name":null,"funder_award_id":"grant","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G342704958","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G3942910960","display_name":null,"funder_award_id":"(NRF) grant","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G626505518","display_name":null,"funder_award_id":"No. 201","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G6686156393","display_name":null,"funder_award_id":"Korean government (MSIP)","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G982292920","display_name":null,"funder_award_id":"NRF-20","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322030","display_name":"Ministry of Science, ICT and Future Planning","ror":"https://ror.org/032e49973"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2255404133.pdf","grobid_xml":"https://content.openalex.org/works/W2255404133.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W395933519","https://openalex.org/W571437208","https://openalex.org/W1970423186","https://openalex.org/W1981883484","https://openalex.org/W2022815646","https://openalex.org/W2025768430","https://openalex.org/W2076014259","https://openalex.org/W2078483607","https://openalex.org/W2086576426","https://openalex.org/W2105464873","https://openalex.org/W2107789863","https://openalex.org/W2129018774","https://openalex.org/W2131822674","https://openalex.org/W2136922672","https://openalex.org/W2187089797","https://openalex.org/W2188492526","https://openalex.org/W2295125894","https://openalex.org/W2295460171","https://openalex.org/W2295991281","https://openalex.org/W2395945925","https://openalex.org/W2400416460","https://openalex.org/W2403606565","https://openalex.org/W2406196141","https://openalex.org/W2542729039","https://openalex.org/W2911964244","https://openalex.org/W6600783858","https://openalex.org/W6601190526"],"related_works":["https://openalex.org/W409076290","https://openalex.org/W2332573710","https://openalex.org/W2362989621","https://openalex.org/W435349687","https://openalex.org/W4295242234","https://openalex.org/W2408862895","https://openalex.org/W274676238","https://openalex.org/W2359595350","https://openalex.org/W653986334","https://openalex.org/W2798116456"],"abstract_inverted_index":{"In":[0],"woodwind":[1],"instruments":[2],"such":[3,51],"as":[4,52,102],"a":[5,8,12,36,62,75,84,103,119,139,165,183],"flute,":[6],"producing":[7],"higher-pitched":[9],"tone":[10,14],"than":[11,48],"standard":[13,158],"by":[15,157],"increasing":[16],"the":[17,30,59,78,107,124,132,135,147,150,154,194,198,203,207,216],"blowing":[18],"pressure":[19],"is":[20,114],"called":[21],"overblowing,":[22],"and":[23,80,99,145,159,187,206],"this":[24],"allows":[25],"several":[26],"distinct":[27],"fingerings":[28,180],"for":[29,106,123,215],"same":[31],"notes.":[32],"This":[33],"article":[34],"presents":[35],"method":[37,137,200],"that":[38,44,126,181,193],"attempts":[39],"to":[40,83,94,177],"learn":[41],"acoustic":[42],"features":[43,50,152,196],"are":[45],"more":[46],"appropriate":[47],"conventional":[49,204],"mel-frequency":[53],"cepstral":[54],"coefficients":[55],"(MFCCs)":[56],"in":[57,118,138,149,211],"detecting":[58],"fingering":[60],"from":[61,77],"flute":[63],"sound":[64],"using":[65,197],"unsupervised":[66],"feature":[67,113,121],"learning.":[68],"To":[69],"do":[70],"so,":[71],"we":[72,88,142],"first":[73,143],"extract":[74],"spectrogram":[76],"audio":[79],"convert":[81],"it":[82,101],"mel":[85],"scale.":[86],"Then,":[87],"concatenate":[89],"four":[90],"consecutive":[91],"mel-spectrogram":[92],"frames":[93],"include":[95,182],"short":[96],"temporal":[97],"information":[98],"use":[100],"front":[104],"end":[105],"sparse":[108],"filtering":[109],"algorithm.":[110],"The":[111,190],"learned":[112,151,195],"then":[115,163],"max-pooled,":[116],"resulting":[117],"final":[120],"vector":[122],"classifier":[125],"has":[127],"extra":[128],"robustness.":[129],"We":[130,162],"demonstrate":[131],"advantages":[133],"of":[134,185],"proposed":[136,199],"twofold":[140],"manner:":[141],"visualize":[144],"analyze":[146],"differences":[148],"between":[153],"tones":[155],"generated":[156],"overblown":[160],"fingerings.":[161,189],"perform":[164],"quantitative":[166],"evaluation":[167],"through":[168],"classification":[169,217],"tasks":[170],"on":[171],"six":[172],"selected":[173],"pitches":[174],"with":[175],"up":[176],"five":[178],"different":[179],"variety":[184],"octave-related":[186],"non-octave-related":[188],"results":[191],"confirm":[192],"significantly":[201],"outperform":[202],"MFCCs":[205],"residual":[208],"noise":[209],"spectrum":[210],"every":[212],"experimental":[213],"condition":[214],"tasks.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-03-26T15:22:09.906841","created_date":"2025-10-10T00:00:00"}