{"id":"https://openalex.org/W1974548373","doi":"https://doi.org/10.1109/mlsp.2015.7324332","title":"Piano music transcription with fast convolutional sparse coding","display_name":"Piano music transcription with fast convolutional sparse coding","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W1974548373","doi":"https://doi.org/10.1109/mlsp.2015.7324332","mag":"1974548373"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp.2015.7324332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2015.7324332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5055474305","display_name":"Andrea Cogliati","orcid":"https://orcid.org/0000-0001-5877-7654"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrea Cogliati","raw_affiliation_strings":["University of Rochester, Rochester, NY, USA","Univ of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Univ of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102749436","display_name":"Zhiyao Duan","orcid":"https://orcid.org/0000-0002-8334-9974"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyao Duan","raw_affiliation_strings":["University of Rochester, Rochester, NY, USA","Univ of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Univ of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015244709","display_name":"Brendt Wohlberg","orcid":"https://orcid.org/0000-0002-4767-1843"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brendt Wohlberg","raw_affiliation_strings":["Los Alamos National Laboratory, Los Alamos, NM, USA","Los Alamos National Laboratory,Los Alamos, NM, USA"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"Los Alamos National Laboratory,Los Alamos, NM, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055474305"],"corresponding_institution_ids":["https://openalex.org/I5388228"],"apc_list":null,"apc_paid":null,"fwci":3.4463,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.93120336,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/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/T11447","display_name":"Blind Source Separation Techniques","score":0.9983000159263611,"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/piano","display_name":"Piano","score":0.8690173029899597},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7297054529190063},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6699365377426147},{"id":"https://openalex.org/keywords/midi","display_name":"MIDI","score":0.6538835763931274},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6408265829086304},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.49408820271492004},{"id":"https://openalex.org/keywords/convolutional-code","display_name":"Convolutional code","score":0.4670027494430542},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4463382363319397},{"id":"https://openalex.org/keywords/musical-notation","display_name":"Musical notation","score":0.44192230701446533},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.42905133962631226},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.4226149320602417},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.29797282814979553},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.2261357605457306},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.15356677770614624},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14576515555381775},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1428534984588623}],"concepts":[{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.8690173029899597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7297054529190063},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6699365377426147},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.6538835763931274},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6408265829086304},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49408820271492004},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.4670027494430542},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4463382363319397},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.44192230701446533},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.42905133962631226},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.4226149320602417},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.29797282814979553},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2261357605457306},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.15356677770614624},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14576515555381775},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1428534984588623},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp.2015.7324332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2015.7324332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311061","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1538937743","https://openalex.org/W1551494903","https://openalex.org/W1574263887","https://openalex.org/W1591581110","https://openalex.org/W1596640533","https://openalex.org/W1902027874","https://openalex.org/W1916044666","https://openalex.org/W1935284635","https://openalex.org/W1983476815","https://openalex.org/W1986931325","https://openalex.org/W2029507661","https://openalex.org/W2055356414","https://openalex.org/W2081611951","https://openalex.org/W2086127342","https://openalex.org/W2091425152","https://openalex.org/W2104298926","https://openalex.org/W2105143211","https://openalex.org/W2105343238","https://openalex.org/W2106582496","https://openalex.org/W2110007838","https://openalex.org/W2120809168","https://openalex.org/W2123804611","https://openalex.org/W2135029798","https://openalex.org/W2135151673","https://openalex.org/W2150415460","https://openalex.org/W2293078015","https://openalex.org/W2402404264","https://openalex.org/W2569560225","https://openalex.org/W2963909185","https://openalex.org/W4250297470","https://openalex.org/W4388353869","https://openalex.org/W6640379892","https://openalex.org/W6679714990","https://openalex.org/W6680012447","https://openalex.org/W6713065916"],"related_works":["https://openalex.org/W2096042855","https://openalex.org/W2064626218","https://openalex.org/W4301398814","https://openalex.org/W3093121331","https://openalex.org/W2002473771","https://openalex.org/W2203718630","https://openalex.org/W1907897748","https://openalex.org/W2245965895","https://openalex.org/W2951185014","https://openalex.org/W2418422832"],"abstract_inverted_index":{"Automatic":[0],"music":[1],"transcription":[2,76],"(AMT)":[3],"is":[4,93],"the":[5,25,27,32,49,54,61,91,98,131,135],"process":[6],"of":[7,31,60,119,134],"converting":[8],"an":[9,80,87],"acoustic":[10],"musical":[11,16],"signal":[12],"into":[13],"a":[14,20,74,105,116],"symbolic":[15],"representation,":[17],"such":[18],"as":[19],"MIDI":[21],"file,":[22],"which":[23,52],"contains":[24],"pitches,":[26],"onsets":[28],"and":[29,38,66,95,121,126],"offsets":[30],"notes":[33],"and,":[34],"possibly,":[35],"their":[36],"dynamics":[37],"sources":[39],"(i.e.,":[40],"instruments).":[41],"Most":[42],"existing":[43],"algorithms":[44],"for":[45,130],"AMT":[46,108],"operate":[47],"in":[48,86,113],"frequency":[50,127],"domain,":[51],"introduces":[53],"well":[55],"known":[56],"time/frequency":[57],"resolution":[58],"trade-off":[59],"Short":[62],"Time":[63],"Fourier":[64],"Transform":[65],"its":[67],"variants.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72],"propose":[73],"time-domain":[75],"algorithm":[77,85],"based":[78],"on":[79,97],"efficient":[81],"convolutional":[82],"sparse":[83],"coding":[84],"instrument-specific":[88],"scenario,":[89],"i.e.,":[90],"dictionary":[92],"trained":[94],"tested":[96],"same":[99],"piano.":[100],"The":[101],"proposed":[102],"method":[103,109],"outperforms":[104],"current":[106],"state-of-the-art":[107],"by":[110],"over":[111],"26%":[112],"F-measure,":[114],"achieving":[115],"median":[117],"F-measure":[118],"93.6%,":[120],"drastically":[122],"increases":[123],"both":[124],"time":[125],"resolutions,":[128],"especially":[129],"lowest":[132],"octaves":[133],"piano":[136],"keyboard.":[137]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}