{"id":"https://openalex.org/W2885097646","doi":"https://doi.org/10.1109/iwssip.2018.8439708","title":"Polyphonic Note Transcription of Time-Domain Audio Signal with Deep WaveNet Architecture","display_name":"Polyphonic Note Transcription of Time-Domain Audio Signal with Deep WaveNet Architecture","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2885097646","doi":"https://doi.org/10.1109/iwssip.2018.8439708","mag":"2885097646"},"language":"en","primary_location":{"id":"doi:10.1109/iwssip.2018.8439708","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwssip.2018.8439708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 25th International Conference on Systems, Signals and Image Processing (IWSSIP)","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/A5030064907","display_name":"Luk\u00e1\u0161 Samuel Mart\u00e1k","orcid":"https://orcid.org/0000-0003-0723-3010"},"institutions":[{"id":"https://openalex.org/I110757952","display_name":"Slovak University of Technology in Bratislava","ror":"https://ror.org/0561ghm58","country_code":"SK","type":"education","lineage":["https://openalex.org/I110757952"]}],"countries":["SK"],"is_corresponding":true,"raw_author_name":"Lukas S. Martak","raw_affiliation_strings":["Faculty of Informatics and Information Technologies, Slovak University of Technology, Bratislava, Slovakia"],"affiliations":[{"raw_affiliation_string":"Faculty of Informatics and Information Technologies, Slovak University of Technology, Bratislava, Slovakia","institution_ids":["https://openalex.org/I110757952"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082945034","display_name":"M\u00e1rius \u0160ajgal\u00edk","orcid":null},"institutions":[{"id":"https://openalex.org/I110757952","display_name":"Slovak University of Technology in Bratislava","ror":"https://ror.org/0561ghm58","country_code":"SK","type":"education","lineage":["https://openalex.org/I110757952"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Marius Sajgalik","raw_affiliation_strings":["Faculty of Informatics and Information Technologies, Slovak University of Technology, Bratislava, Slovakia"],"affiliations":[{"raw_affiliation_string":"Faculty of Informatics and Information Technologies, Slovak University of Technology, Bratislava, Slovakia","institution_ids":["https://openalex.org/I110757952"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042086801","display_name":"Wanda Bene\u0161ov\u00e1","orcid":"https://orcid.org/0000-0001-6929-9694"},"institutions":[{"id":"https://openalex.org/I110757952","display_name":"Slovak University of Technology in Bratislava","ror":"https://ror.org/0561ghm58","country_code":"SK","type":"education","lineage":["https://openalex.org/I110757952"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Wanda Benesova","raw_affiliation_strings":["Faculty of Informatics and Information Technologies, Slovak University of Technology, Bratislava, Slovakia"],"affiliations":[{"raw_affiliation_string":"Faculty of Informatics and Information Technologies, Slovak University of Technology, Bratislava, Slovakia","institution_ids":["https://openalex.org/I110757952"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5030064907"],"corresponding_institution_ids":["https://openalex.org/I110757952"],"apc_list":null,"apc_paid":null,"fwci":0.3303,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.55366969,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"27","issue":null,"first_page":"1","last_page":"5"},"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":0.998199999332428,"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/computer-science","display_name":"Computer science","score":0.8017963171005249},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.668212890625},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6479326486587524},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6470378041267395},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5852629542350769},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5732925534248352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5016665458679199},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4986546039581299},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4281432628631592},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4127132296562195},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3576010465621948},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2176063060760498}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8017963171005249},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.668212890625},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6479326486587524},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6470378041267395},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5852629542350769},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5732925534248352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5016665458679199},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4986546039581299},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4281432628631592},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4127132296562195},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3576010465621948},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2176063060760498},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/iwssip.2018.8439708","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwssip.2018.8439708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 25th International Conference on Systems, Signals and Image Processing (IWSSIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323641","display_name":"Vedeck\u00e1 Grantov\u00e1 Agent\u00fara M\u0160VVa\u0160 SR a SAV","ror":"https://ror.org/044gwpv05"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W2096354165","https://openalex.org/W2105143211","https://openalex.org/W2107789863","https://openalex.org/W2144414181","https://openalex.org/W2152937398","https://openalex.org/W2158983491","https://openalex.org/W2198584637","https://openalex.org/W2295460171","https://openalex.org/W2295991281","https://openalex.org/W2407685581","https://openalex.org/W2519091744","https://openalex.org/W2559688696","https://openalex.org/W2963493667","https://openalex.org/W2964121744","https://openalex.org/W3210141620","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6676071220","https://openalex.org/W6681236507","https://openalex.org/W6696901769","https://openalex.org/W6697000175","https://openalex.org/W6714030504"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2340483794","https://openalex.org/W2132597408","https://openalex.org/W4316036082","https://openalex.org/W2103924733"],"abstract_inverted_index":{"Deep":[0],"neural":[1,42],"networks-especially":[2],"new,":[3],"sophisticated":[4],"architectures-are":[5],"gaining":[6],"increased":[7],"competence":[8],"at":[9],"various":[10],"tasks":[11],"of":[12,17,54,76,113,147],"growing":[13],"complexity.":[14],"Automatic":[15],"transcription":[16,65,130],"polyphonic":[18,63,90],"music":[19],"is":[20,38,141],"a":[21,39],"complex":[22],"problem":[23],"with":[24,45],"state-of-the-art":[25],"approaches":[26],"still":[27],"suffering":[28],"from":[29,71],"high":[30],"error":[31],"rates":[32],"relative":[33],"to":[34,62,86,95,132,143],"human-level":[35],"performance.":[36],"WaveNet":[37,67,82],"novel":[40],"deep":[41],"network":[43],"architecture":[44],"significant":[46],"audio":[47,56,73,91],"modelling":[48],"capacity,":[49],"operating":[50],"directly":[51],"on":[52,102,122],"samples":[53],"digital":[55],"signal.":[57],"We":[58,79,118],"propose":[59],"an":[60],"approach":[61],"note":[64,77],"using":[66,111],"for":[68],"feature":[69],"extraction":[70],"raw":[72],"and":[74,109,127],"recognition":[75],"presence.":[78],"show,":[80],"that":[81],"can":[83],"be":[84],"used":[85],"detect":[87],"pitch":[88],"in":[89],"texture,":[92],"as":[93],"opposed":[94],"most":[96],"other":[97],"approaches,":[98],"which":[99],"mostly":[100],"depend":[101],"time-frequency":[103],"representations.":[104],"Model":[105],"outputs":[106],"are":[107,136],"smoothed":[108],"truncated":[110],"one":[112],"two":[114],"alternative":[115],"thresholding":[116],"techniques.":[117],"evaluate":[119],"our":[120],"method":[121],"recently":[123],"released":[124],"dataset":[125],"MusicNet":[126],"compare":[128],"frame-level":[129],"performance":[131,145],"benchmark":[133],"models.":[134],"Results":[135],"promising,":[137],"although":[138],"further":[139],"evaluation":[140],"needed":[142],"explore":[144],"limits":[146],"this":[148],"method.":[149]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}