{"id":"https://openalex.org/W2768370276","doi":"https://doi.org/10.1109/icassp.2018.8461686","title":"Invariances and Data Augmentation for Supervised Music Transcription","display_name":"Invariances and Data Augmentation for Supervised Music Transcription","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2768370276","doi":"https://doi.org/10.1109/icassp.2018.8461686","mag":"2768370276"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1711.04845","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039056454","display_name":"John Thickstun","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Thickstun","raw_affiliation_strings":["University of Washington","University of Washington ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University of Washington ;","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010613767","display_name":"Za\u00efd Harchaoui","orcid":"https://orcid.org/0000-0003-1186-1343"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zaid Harchaoui","raw_affiliation_strings":["University of Washington","University of Washington ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University of Washington ;","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112767220","display_name":"Dean P. Foster","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dean P. Foster","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108381794","display_name":"Sham M. Kakade","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sham M. Kakade","raw_affiliation_strings":["University of Washington","University of Washington ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University of Washington ;","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2241","last_page":"2245"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9973999857902527,"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":0.9968000054359436,"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/overfitting","display_name":"Overfitting","score":0.8880506753921509},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7215596437454224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5189435482025146},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.5139238834381104},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.49947619438171387},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4972875416278839},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.4743693768978119},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.47427114844322205},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4655628204345703},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4638044834136963},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.43385568261146545},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4122796654701233},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41002869606018066},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37925559282302856},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3594464957714081},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.2116169035434723},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16048073768615723},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.146526038646698}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8880506753921509},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7215596437454224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5189435482025146},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.5139238834381104},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.49947619438171387},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4972875416278839},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.4743693768978119},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.47427114844322205},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4655628204345703},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4638044834136963},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.43385568261146545},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4122796654701233},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41002869606018066},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37925559282302856},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3594464957714081},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.2116169035434723},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16048073768615723},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.146526038646698},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2018.8461686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1711.04845","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1711.04845","pdf_url":"https://arxiv.org/pdf/1711.04845","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":"","raw_type":"text"},{"id":"mag:2768370276","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1711.04845.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.1711.04845","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1711.04845","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1711.04845","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1711.04845","pdf_url":"https://arxiv.org/pdf/1711.04845","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2099617666","display_name":"Graduate Research Fellowship Program (GRFP)","funder_award_id":"1256082","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3943856530","display_name":null,"funder_award_id":"DGE-1256082","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306854","display_name":"Washington Research Foundation","ror":"https://ror.org/00hasdx88"},{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2768370276.pdf","grobid_xml":"https://content.openalex.org/works/W2768370276.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1607142029","https://openalex.org/W1990517717","https://openalex.org/W2059652044","https://openalex.org/W2101234009","https://openalex.org/W2110007838","https://openalex.org/W2144414181","https://openalex.org/W2156163116","https://openalex.org/W2198584637","https://openalex.org/W2295460171","https://openalex.org/W2398243923","https://openalex.org/W2433636802","https://openalex.org/W2475687244","https://openalex.org/W2523056285","https://openalex.org/W2559688696","https://openalex.org/W2583165630","https://openalex.org/W2773294482","https://openalex.org/W4205267278","https://openalex.org/W6636203886","https://openalex.org/W6665302887","https://openalex.org/W6675354045","https://openalex.org/W6681236507","https://openalex.org/W6682739439","https://openalex.org/W6684191040","https://openalex.org/W6697000175","https://openalex.org/W6712594816","https://openalex.org/W6714030504","https://openalex.org/W6718206412","https://openalex.org/W6727368055","https://openalex.org/W6730401039","https://openalex.org/W6732480393","https://openalex.org/W6746836464"],"related_works":["https://openalex.org/W2963045359","https://openalex.org/W2953452843","https://openalex.org/W104395549","https://openalex.org/W3129403009","https://openalex.org/W2888364892","https://openalex.org/W3080285855","https://openalex.org/W3209592505","https://openalex.org/W3003445351","https://openalex.org/W2805760974","https://openalex.org/W2996335500","https://openalex.org/W111292237","https://openalex.org/W3182949211","https://openalex.org/W3159942986","https://openalex.org/W2944642884","https://openalex.org/W3035680157","https://openalex.org/W3100594686","https://openalex.org/W2949777502","https://openalex.org/W3162391602","https://openalex.org/W3154478085","https://openalex.org/W2607836359"],"abstract_inverted_index":{"This":[0,54],"paper":[1,89],"explores":[2],"a":[3,33,37],"variety":[4],"of":[5,56,69,75],"models":[6,57,86],"for":[7],"frame-based":[8],"music":[9,70],"transcription,":[10],"with":[11,36,92],"an":[12],"emphasis":[13],"on":[14,21],"the":[15,42,46,61,66,73,82,98],"methods":[16],"needed":[17],"to":[18,71,81],"reach":[19],"state-of-the-art":[20],"human":[22],"recordings.":[23],"The":[24],"translation-invariant":[25],"network":[26],"discussed":[27],"in":[28,45,60,87],"this":[29,88],"paper,":[30],"which":[31,64],"combines":[32],"traditional":[34],"filterbank":[35],"convolutional":[38],"neural":[39],"network,":[40],"was":[41],"top-performing":[43],"model":[44,76],"2017":[47],"MIREX":[48],"Multiple":[49],"Fundamental":[50],"Frequency":[51],"Estimation":[52],"evaluation.":[53],"class":[55],"shares":[58],"parameters":[59,77],"log-frequency":[62],"domain,":[63],"exploits":[65],"frequency":[67],"invariance":[68],"reduce":[72],"number":[74],"and":[78],"avoid":[79],"overfitting":[80],"training":[83],"data.":[84],"All":[85],"were":[90],"trained":[91],"supervision":[93],"by":[94,102],"labeled":[95],"data":[96],"from":[97],"MusicNet":[99],"dataset,":[100],"augmented":[101],"random":[103],"label-preserving":[104],"pitch-shift":[105],"transformations.":[106]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}