{"id":"https://openalex.org/W3003755257","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207605","title":"The Impact of Audio Input Representations on Neural Network based Music Transcription","display_name":"The Impact of Audio Input Representations on Neural Network based Music Transcription","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3003755257","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207605","mag":"3003755257"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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/2001.09989","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069612434","display_name":"Kin Wai Cheuk","orcid":"https://orcid.org/0000-0003-3213-8242"},"institutions":[{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Kin Wai Cheuk","raw_affiliation_strings":["Information Systems, Technology, and Design Singapore University of Technology and Design Institute of High Performance Computing Agency for Science, Singapore","Singapore University of Technology and Design"],"affiliations":[{"raw_affiliation_string":"Information Systems, Technology, and Design Singapore University of Technology and Design Institute of High Performance Computing Agency for Science, Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I152815399"]},{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078786239","display_name":"Kat Agres","orcid":"https://orcid.org/0000-0001-7260-2447"},"institutions":[{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kat Agres","raw_affiliation_strings":["Technology and Research, Yong Siew Toh Conservatory of Music National University of Singapore Institute of High Performance Computing Agency for Science, Singapore","National University of Singapore,"],"affiliations":[{"raw_affiliation_string":"Technology and Research, Yong Siew Toh Conservatory of Music National University of Singapore Institute of High Performance Computing Agency for Science, Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore,","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069548004","display_name":"Dorien Herremans","orcid":"https://orcid.org/0000-0001-8607-1640"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dorien Herremans","raw_affiliation_strings":["Information Systems, Technology, and Design Singapore University of Technology and Design Institute of High Performance Computing Agency for Science, Singapore","Singapore University of Technology and Design"],"affiliations":[{"raw_affiliation_string":"Information Systems, Technology, and Design Singapore University of Technology and Design Institute of High Performance Computing Agency for Science, Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I152815399"]},{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069612434"],"corresponding_institution_ids":["https://openalex.org/I152815399","https://openalex.org/I3004594783"],"apc_list":null,"apc_paid":null,"fwci":0.6095,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.64882549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"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/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":0.9991000294685364,"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":0.9979000091552734,"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/spectrogram","display_name":"Spectrogram","score":0.9827700853347778},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.6625301837921143},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6592131853103638},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6578211784362793},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6351262927055359},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.4507076144218445},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4218025207519531},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3926481604576111},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39086177945137024},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2663291096687317},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.23633769154548645},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.13208124041557312},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.12480342388153076},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.07446843385696411}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9827700853347778},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.6625301837921143},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6592131853103638},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6578211784362793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6351262927055359},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.4507076144218445},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4218025207519531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3926481604576111},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39086177945137024},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2663291096687317},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.23633769154548645},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13208124041557312},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.12480342388153076},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.07446843385696411},{"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/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":4,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.09989","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.09989","pdf_url":"https://arxiv.org/pdf/2001.09989","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:3003755257","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2001.09989.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.2001.09989","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.09989","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:2001.09989","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.09989","pdf_url":"https://arxiv.org/pdf/2001.09989","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":[],"funders":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"},{"id":"https://openalex.org/F4320324110","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3003755257.pdf","grobid_xml":"https://content.openalex.org/works/W3003755257.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W88081813","https://openalex.org/W1004627091","https://openalex.org/W1819710477","https://openalex.org/W1838323663","https://openalex.org/W2042105302","https://openalex.org/W2076608692","https://openalex.org/W2103869314","https://openalex.org/W2105143211","https://openalex.org/W2106710516","https://openalex.org/W2144414181","https://openalex.org/W2147761286","https://openalex.org/W2149183817","https://openalex.org/W2152937398","https://openalex.org/W2559688696","https://openalex.org/W2566755135","https://openalex.org/W2593836007","https://openalex.org/W2618946976","https://openalex.org/W2753779507","https://openalex.org/W2891575704","https://openalex.org/W2906214917","https://openalex.org/W2950733131","https://openalex.org/W2962968839","https://openalex.org/W2963045359","https://openalex.org/W2963551352","https://openalex.org/W6600593648","https://openalex.org/W6603616073","https://openalex.org/W6714030504","https://openalex.org/W6730401039","https://openalex.org/W6731203071","https://openalex.org/W6733936739","https://openalex.org/W6738884980","https://openalex.org/W6745851314","https://openalex.org/W6745987316","https://openalex.org/W6772982332"],"related_works":["https://openalex.org/W3133318272","https://openalex.org/W3198163754","https://openalex.org/W3034641760","https://openalex.org/W3182750816","https://openalex.org/W2106634207","https://openalex.org/W2004453603","https://openalex.org/W2775058083","https://openalex.org/W2398396891","https://openalex.org/W2988796883","https://openalex.org/W2039258207","https://openalex.org/W2735085206","https://openalex.org/W1508756421","https://openalex.org/W2066772813","https://openalex.org/W3166832787","https://openalex.org/W3007302343","https://openalex.org/W2533136988","https://openalex.org/W2891814570","https://openalex.org/W2104497281","https://openalex.org/W2136856374","https://openalex.org/W2647772669"],"abstract_inverted_index":{"This":[0],"paper":[1],"thoroughly":[2],"analyses":[3],"the":[4,27,63,79,83,107],"effect":[5],"of":[6,29,109],"different":[7],"input":[8,65],"representations":[9],"on":[10],"polyphonic":[11],"multi-instrument":[12],"music":[13,121],"transcription.":[14],"We":[15],"use":[16],"our":[17],"own":[18],"GPU":[19],"based":[20],"spectrogram":[21,68,97],"extraction":[22],"tool,":[23],"nnAudio,":[24],"to":[25,112],"investigate":[26],"influence":[28],"using":[30],"a":[31,46,53,99,118],"linear-frequency":[32],"spectrogram,":[33,35,37],"log-frequency":[34],"Mel":[36,96],"and":[38,52,74],"constant-Q":[39],"transform":[40],"(CQT).":[41],"Our":[42,91],"results":[43],"show":[44,94],"that":[45,95],"8.33%":[47],"increase":[48],"in":[49,56,78],"transcription":[50,122],"accuracy":[51],"9.39%":[54],"reduction":[55],"error":[57],"can":[58,105],"be":[59],"obtained":[60],"by":[61],"choosing":[62],"appropriate":[64],"representation":[66,101],"(log-frequency":[67],"with":[69],"STFT":[70],"window":[71],"length":[72],"4,096":[73],"2,048":[75],"frequency":[76,110],"bins":[77,111],"spectrogram)":[80],"without":[81],"changing":[82],"neural":[84],"network":[85],"design":[86],"(single":[87],"layer":[88],"fully":[89],"connected).":[90],"experiments":[92],"also":[93],"is":[98],"compact":[100],"for":[102],"which":[103],"we":[104],"reduce":[106],"number":[108],"only":[113],"512":[114],"while":[115],"still":[116],"keeping":[117],"relatively":[119],"high":[120],"accuracy.":[123]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}