{"id":"https://openalex.org/W2891814570","doi":"https://doi.org/10.1109/icassp.2018.8462079","title":"Automatic Music Transcription Leveraging Generalized Cepstral Features and Deep Learning","display_name":"Automatic Music Transcription Leveraging Generalized Cepstral Features and Deep Learning","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891814570","doi":"https://doi.org/10.1109/icassp.2018.8462079","mag":"2891814570"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462079","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":["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/A5080942813","display_name":"Yu\u2010Te Wu","orcid":"https://orcid.org/0000-0002-6942-0340"},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Te Wu","raw_affiliation_strings":["Dept. CSIE, National Taiwan Normal University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. CSIE, National Taiwan Normal University, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115595070","display_name":"Berlin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Berlin Chen","raw_affiliation_strings":["Dept. CSIE, National Taiwan Normal University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. CSIE, National Taiwan Normal University, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038264558","display_name":"Li Su","orcid":"https://orcid.org/0000-0003-4275-8832"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li Su","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4432,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.83455175,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"401","last_page":"405"},"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":0.9987000226974487,"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":0.9977999925613403,"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":0.7208033800125122},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6219518184661865},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.5711143016815186},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5546782612800598},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5526319146156311},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5415440201759338},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5145255923271179},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5094776749610901},{"id":"https://openalex.org/keywords/harmonic-analysis","display_name":"Harmonic analysis","score":0.5033003687858582},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5025973320007324},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.4848533868789673},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.47342541813850403},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.4652266204357147},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4582977890968323},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.42848747968673706},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4223950505256653},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40050068497657776},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3201534152030945},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.2290390431880951},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18706625699996948},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.16685190796852112},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1207960844039917},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09595108032226562},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08480697870254517},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07546019554138184}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7208033800125122},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6219518184661865},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.5711143016815186},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5546782612800598},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5526319146156311},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5415440201759338},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5145255923271179},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5094776749610901},{"id":"https://openalex.org/C131770355","wikidata":"https://www.wikidata.org/wiki/Q876215","display_name":"Harmonic analysis","level":2,"score":0.5033003687858582},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5025973320007324},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.4848533868789673},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.47342541813850403},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.4652266204357147},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4582977890968323},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.42848747968673706},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4223950505256653},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40050068497657776},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3201534152030945},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.2290390431880951},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18706625699996948},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.16685190796852112},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1207960844039917},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09595108032226562},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08480697870254517},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07546019554138184},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462079","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2001426554","https://openalex.org/W2105143211","https://openalex.org/W2109770219","https://openalex.org/W2110007838","https://openalex.org/W2114377386","https://openalex.org/W2148899569","https://openalex.org/W2149095746","https://openalex.org/W2149180301","https://openalex.org/W2152937398","https://openalex.org/W2198584637","https://openalex.org/W2288725033","https://openalex.org/W2347179934","https://openalex.org/W2416173453","https://openalex.org/W2478884216","https://openalex.org/W2494437503","https://openalex.org/W2571951934","https://openalex.org/W2575864022","https://openalex.org/W2577202280","https://openalex.org/W2756184659","https://openalex.org/W2950335938","https://openalex.org/W2963158112","https://openalex.org/W2963454111","https://openalex.org/W2964177567","https://openalex.org/W3100135054","https://openalex.org/W6681947682","https://openalex.org/W6705075777","https://openalex.org/W6731524272","https://openalex.org/W6731597384","https://openalex.org/W6732421929","https://openalex.org/W6739575965","https://openalex.org/W6739879593","https://openalex.org/W6750611726"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2160511961","https://openalex.org/W2066371342"],"abstract_inverted_index":{"Spectral":[0],"features":[1,37,55,84],"are":[2,56],"limited":[3],"in":[4,39],"modeling":[5,49],"musical":[6],"signals":[7],"with":[8,46,82],"multiple":[9,36],"concurrent":[10],"pitches":[11],"due":[12],"to":[13,16,27,66],"the":[14,18,21,41,70],"challenge":[15],"suppress":[17],"interference":[19],"of":[20],"harmonic":[22],"peaks":[23],"from":[24,59],"one":[25,67],"pitch":[26,61],"another.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32],"show":[33],"that":[34,64],"using":[35,89],"represented":[38],"both":[40],"frequency":[42],"and":[43,74],"time":[44],"domains":[45],"deep":[47],"learning":[48],"can":[50],"reduce":[51],"such":[52],"interference.":[53],"These":[54],"derived":[57],"systematically":[58],"conventional":[60],"detection":[62],"functions":[63],"relate":[65],"another":[68],"through":[69],"discrete":[71],"Fourier":[72],"transform":[73],"a":[75],"nonlinear":[76],"scaling":[77],"function.":[78],"Neural":[79],"networks":[80],"modeled":[81],"these":[83],"outperform":[85],"state-of-the-art":[86],"methods":[87],"while":[88],"less":[90],"training":[91],"data.":[92]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}