{"id":"https://openalex.org/W2788560150","doi":"https://doi.org/10.1109/icassp.2018.8461329","title":"Crepe: A Convolutional Representation for Pitch Estimation","display_name":"Crepe: A Convolutional Representation for Pitch Estimation","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2788560150","doi":"https://doi.org/10.1109/icassp.2018.8461329","mag":"2788560150"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461329","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1802.06182","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100726106","display_name":"Jong Wook Kim","orcid":"https://orcid.org/0000-0001-8373-1893"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jong Wook Kim","raw_affiliation_strings":["Music and Audio Research Laboratory, New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music and Audio Research Laboratory, New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037548450","display_name":"Justin Salamon","orcid":"https://orcid.org/0000-0001-6345-4593"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Salamon","raw_affiliation_strings":["Center for Urban Science and Progress, New York University","Music and Audio Research Laboratory, New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Urban Science and Progress, New York University","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Music and Audio Research Laboratory, New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064435741","display_name":"Peter Li","orcid":"https://orcid.org/0000-0001-9602-9550"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Li","raw_affiliation_strings":["Music and Audio Research Laboratory, New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music and Audio Research Laboratory, New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031398497","display_name":"Juan Pablo Bello","orcid":"https://orcid.org/0000-0001-8561-5204"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan Pablo Bello","raw_affiliation_strings":["Music and Audio Research Laboratory, New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music and Audio Research Laboratory, New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9905,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.94642508,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"161","last_page":"165"},"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":0.9997000098228455,"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":0.9976000189781189,"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":0.7767336368560791},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.7375351190567017},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6232104897499084},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6184247136116028},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5597577691078186},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.48711442947387695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.472037672996521},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4305630326271057},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.4259456694126129},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.42154136300086975},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.41754212975502014},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3873734474182129},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38452115654945374},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09577128291130066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7767336368560791},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.7375351190567017},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6232104897499084},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6184247136116028},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5597577691078186},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.48711442947387695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.472037672996521},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4305630326271057},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.4259456694126129},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.42154136300086975},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.41754212975502014},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3873734474182129},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38452115654945374},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09577128291130066},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2018.8461329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461329","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:1802.06182","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.06182","pdf_url":"https://arxiv.org/pdf/1802.06182","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":"doi:10.48550/arxiv.1802.06182","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1802.06182","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"},{"id":"mag:2788560150","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1802.06182","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.06182","pdf_url":"https://arxiv.org/pdf/1802.06182","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2788560150.pdf","grobid_xml":"https://content.openalex.org/works/W2788560150.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1878565453","https://openalex.org/W1975079546","https://openalex.org/W1982446897","https://openalex.org/W2034995162","https://openalex.org/W2084044763","https://openalex.org/W2091425152","https://openalex.org/W2107831318","https://openalex.org/W2108771579","https://openalex.org/W2118774185","https://openalex.org/W2161632835","https://openalex.org/W2171321863","https://openalex.org/W2296724634","https://openalex.org/W2350911425","https://openalex.org/W2398243923","https://openalex.org/W2398618787","https://openalex.org/W2586947700","https://openalex.org/W2949117887","https://openalex.org/W2951535099","https://openalex.org/W2964121744","https://openalex.org/W6605982055","https://openalex.org/W6631117800","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6676245417","https://openalex.org/W6697040288","https://openalex.org/W6705744009","https://openalex.org/W6712594816","https://openalex.org/W6712738854","https://openalex.org/W6714030504","https://openalex.org/W6733426572","https://openalex.org/W6746960179"],"related_works":["https://openalex.org/W2118774185","https://openalex.org/W1976069042","https://openalex.org/W2162977283","https://openalex.org/W2186901608","https://openalex.org/W2315083471","https://openalex.org/W2897446521","https://openalex.org/W3014036488","https://openalex.org/W2980624499","https://openalex.org/W1519491777","https://openalex.org/W2990594533","https://openalex.org/W2890043615","https://openalex.org/W3015721817","https://openalex.org/W2774097455","https://openalex.org/W3038026903","https://openalex.org/W2791716806","https://openalex.org/W3179030250","https://openalex.org/W3161037993","https://openalex.org/W3187219273","https://openalex.org/W3177975252","https://openalex.org/W2097492920"],"abstract_inverted_index":{"The":[0],"task":[1],"of":[2,7,48,124,130],"estimating":[3],"the":[4,34,40,72,98,104,119],"fundamental":[5,18],"frequency":[6],"a":[8,46,79,89],"monophonic":[9],"sound":[10],"recording,":[11],"also":[12],"known":[13],"as":[14,39,136],"pitch":[15,81],"tracking,":[16],"is":[17,86,132],"to":[19,69],"audio":[20],"processing":[21,27],"with":[22],"multiple":[23],"applications":[24],"in":[25,65,122],"speech":[26],"and":[28,51],"music":[29],"information":[30],"retrieval.":[31],"To":[32],"date,":[33],"best":[35],"performing":[36,110],"techniques,":[37],"such":[38,54],"pYIN":[41],"algorithm,":[42,83],"are":[43],"based":[44,87],"on":[45,59,88,97],"combination":[47],"DSP":[49],"pipelines":[50],"heuristics.":[52],"While":[53],"techniques":[55],"perform":[56],"very":[57],"well":[58],"average,":[60],"there":[61],"remain":[62],"many":[63],"cases":[64],"which":[66,85],"they":[67],"fail":[68],"correctly":[70],"estimate":[71],"pitch.":[73],"In":[74],"this":[75],"paper,":[76],"we":[77,117],"propose":[78],"data-driven":[80],"tracking":[82],"CREPE,":[84],"deep":[90],"convolutional":[91],"neural":[92],"network":[93],"that":[94,103],"operates":[95],"directly":[96],"time-domain":[99],"waveform.":[100],"We":[101],"show":[102],"proposed":[105],"model":[106],"produces":[107],"state-of-the-art":[108],"results,":[109],"equally":[111],"or":[112],"better":[113],"than":[114],"pYIN.":[115],"Furthermore,":[116],"evaluate":[118],"model's":[120],"generalizability":[121],"terms":[123],"noise":[125],"robustness.":[126],"A":[127],"pre-trained":[128],"version":[129],"CREPE":[131],"made":[133],"freely":[134],"available":[135],"an":[137],"open-source":[138],"Python":[139],"module":[140],"for":[141],"easy":[142],"application.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}