{"id":"https://openalex.org/W2727515876","doi":"https://doi.org/10.1109/waspaa.2017.8170012","title":"An augmented lagrangian method for piano transcription using equal loudness thresholding and lstm-based decoding","display_name":"An augmented lagrangian method for piano transcription using equal loudness thresholding and lstm-based decoding","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2727515876","doi":"https://doi.org/10.1109/waspaa.2017.8170012","mag":"2727515876"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2017.8170012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2017.8170012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1707.00160","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001413512","display_name":"Sebastian Ewert","orcid":"https://orcid.org/0000-0002-0718-0476"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Sebastian Ewert","raw_affiliation_strings":["Machine Listening Lab (MLLAB) and Centre for Digital Music (C4DM), Queen Mary University of London, United Kingdom","Machine Listening Lab (MLLAB) and Centre for Digital Music (C4DM), School of Electronic Engineering and Computer Science, Queen Mary University of London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Machine Listening Lab (MLLAB) and Centre for Digital Music (C4DM), Queen Mary University of London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Machine Listening Lab (MLLAB) and Centre for Digital Music (C4DM), School of Electronic Engineering and Computer Science, Queen Mary University of London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076173089","display_name":"M. Sandler","orcid":"https://orcid.org/0000-0002-5691-8107"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark B. Sandler","raw_affiliation_strings":["Machine Listening Lab (MLLAB) and Centre for Digital Music (C4DM), Queen Mary University of London, United Kingdom","Machine Listening Lab (MLLAB) and Centre for Digital Music (C4DM), School of Electronic Engineering and Computer Science, Queen Mary University of London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Machine Listening Lab (MLLAB) and Centre for Digital Music (C4DM), Queen Mary University of London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Machine Listening Lab (MLLAB) and Centre for Digital Music (C4DM), School of Electronic Engineering and Computer Science, Queen Mary University of London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5001413512"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07433265,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"50","issue":null,"first_page":"146","last_page":"150"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9994999766349792,"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":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.6187237501144409},{"id":"https://openalex.org/keywords/loudness","display_name":"Loudness","score":0.5913375020027161},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5757764577865601},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.550478994846344},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.46129950881004333},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45747753977775574},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.45135271549224854},{"id":"https://openalex.org/keywords/augmented-lagrangian-method","display_name":"Augmented Lagrangian method","score":0.4380439221858978},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4176065921783447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3696592450141907},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2438298463821411},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2064966857433319}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6187237501144409},{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.5913375020027161},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5757764577865601},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.550478994846344},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.46129950881004333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45747753977775574},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.45135271549224854},{"id":"https://openalex.org/C150452318","wikidata":"https://www.wikidata.org/wiki/Q4820432","display_name":"Augmented Lagrangian method","level":2,"score":0.4380439221858978},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4176065921783447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3696592450141907},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2438298463821411},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2064966857433319},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/waspaa.2017.8170012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2017.8170012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1707.00160","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.00160","pdf_url":"https://arxiv.org/pdf/1707.00160","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2727515876","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1707.00160.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1707.00160","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1707.00160","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1707.00160","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.00160","pdf_url":"https://arxiv.org/pdf/1707.00160","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8217561489","display_name":null,"funder_award_id":"EP/L019981/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2727515876.pdf","grobid_xml":"https://content.openalex.org/works/W2727515876.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W129413713","https://openalex.org/W173399573","https://openalex.org/W1485835175","https://openalex.org/W1591801644","https://openalex.org/W1752772649","https://openalex.org/W1806891645","https://openalex.org/W1819710477","https://openalex.org/W1882026191","https://openalex.org/W1916044666","https://openalex.org/W2079735306","https://openalex.org/W2106582496","https://openalex.org/W2110007838","https://openalex.org/W2123023890","https://openalex.org/W2137619888","https://openalex.org/W2139878068","https://openalex.org/W2147834639","https://openalex.org/W2164278908","https://openalex.org/W2198584637","https://openalex.org/W2288725033","https://openalex.org/W2416173453","https://openalex.org/W2587310949","https://openalex.org/W2950335938","https://openalex.org/W2964121744","https://openalex.org/W3100135054","https://openalex.org/W4205974199","https://openalex.org/W4292363360","https://openalex.org/W6607112371","https://openalex.org/W6629029132","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6635446068","https://openalex.org/W6637898492","https://openalex.org/W6639490307","https://openalex.org/W6640725723","https://openalex.org/W6681822791","https://openalex.org/W6732171656","https://openalex.org/W6733936739"],"related_works":["https://openalex.org/W2963652792","https://openalex.org/W2172386361","https://openalex.org/W2788101720","https://openalex.org/W2265943708","https://openalex.org/W2111940465","https://openalex.org/W2952979223","https://openalex.org/W2803256244","https://openalex.org/W2398043770","https://openalex.org/W2899918473","https://openalex.org/W2953340873","https://openalex.org/W3131784842","https://openalex.org/W852785498","https://openalex.org/W329869691","https://openalex.org/W606407343","https://openalex.org/W2985780925","https://openalex.org/W3112881292","https://openalex.org/W2760770458","https://openalex.org/W2472226770","https://openalex.org/W2989309436","https://openalex.org/W3206645560"],"abstract_inverted_index":{"A":[0,66],"central":[1],"goal":[2],"in":[3,13,32,147],"automatic":[4],"music":[5,14,21],"transcription":[6,22,51],"is":[7,19],"to":[8,56,99,109,126,141,152],"detect":[9],"individual":[10],"note":[11,115,132,148],"events":[12],"recordings.":[15],"An":[16],"important":[17],"variant":[18],"instrument-dependent":[20],"where":[23],"methods":[24],"can":[25,53],"use":[26],"calibration":[27],"data":[28],"for":[29],"the":[30,36,50,79,128,153],"instruments":[31],"use.":[33],"However,":[34],"despite":[35],"additional":[37],"information,":[38],"results":[39],"rarely":[40],"exceed":[41],"an":[42],"f-measure":[43],"of":[44,73,130,144],"80%.":[45],"As":[46],"a":[47,71,105,142],"potential":[48],"explanation,":[49],"problem":[52],"be":[54,57],"shown":[55],"badly":[58],"conditioned":[59],"and":[60,83],"thus":[61],"relies":[62],"on":[63],"appropriate":[64],"regularization.":[65],"recently":[67],"proposed":[68],"method":[69],"employs":[70],"mixture":[72],"simple,":[74],"convex":[75],"regularizers":[76],"(to":[77,87],"stabilize":[78],"parameter":[80],"estimation":[81],"process)":[82],"more":[84,89],"complex":[85],"terms":[86],"encourage":[88],"meaningful":[90],"structure).":[91],"In":[92],"this":[93,100],"paper,":[94],"we":[95,103,118],"present":[96],"two":[97,138],"extensions":[98,139],"method.":[101],"First,":[102],"integrate":[104],"computational":[106],"loudness":[107],"model":[108],"better":[110],"differentiate":[111],"real":[112],"from":[113],"spurious":[114],"detections.":[116],"Second,":[117],"employ":[119],"(Bidirectional)":[120],"Long":[121],"Short":[122],"Term":[123],"Memory":[124],"networks":[125],"re-weight":[127],"likelihood":[129],"detected":[131],"constellations.":[133],"Despite":[134],"their":[135],"simplicity,":[136],"our":[137],"lead":[140],"drop":[143],"about":[145],"35%":[146],"error":[149],"rate":[150],"compared":[151],"state-of-the-art.":[154]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}