{"id":"https://openalex.org/W4385768169","doi":"https://doi.org/10.24963/ijcai.2023/544","title":"JEPOO: Highly Accurate Joint Estimation of Pitch, Onset and Offset for Music Information Retrieval","display_name":"JEPOO: Highly Accurate Joint Estimation of Pitch, Onset and Offset for Music Information Retrieval","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385768169","doi":"https://doi.org/10.24963/ijcai.2023/544"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/544","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/544","pdf_url":"https://www.ijcai.org/proceedings/2023/0544.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0544.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101939672","display_name":"Haojie Wei","orcid":"https://orcid.org/0000-0003-2716-7866"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haojie Wei","raw_affiliation_strings":["School of Information, Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100347992","display_name":"Jun Yuan","orcid":"https://orcid.org/0000-0001-8302-4064"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yuan","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab, Shenzhen, China","Huawei Noah's Ark Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100421929","display_name":"Rui Zhang","orcid":"https://orcid.org/0000-0001-5230-5998"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057384573","display_name":"Yueguo Chen","orcid":"https://orcid.org/0000-0003-2720-7135"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueguo Chen","raw_affiliation_strings":["School of Information, Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100367310","display_name":"Gang Wang","orcid":"https://orcid.org/0000-0001-7018-9513"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Wang","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab, Shenzhen, China","Huawei Noah's Ark Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101939672"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":1.1233,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78299665,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4892","last_page":"4902"},"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":0.9961000084877014,"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":0.9955999851226807,"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":0.7844880819320679},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.7002114057540894},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.6711359620094299},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5019280910491943},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.4634746015071869},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4390369653701782},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4122791886329651},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3429511785507202},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.15180712938308716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7844880819320679},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.7002114057540894},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.6711359620094299},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5019280910491943},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.4634746015071869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4390369653701782},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4122791886329651},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3429511785507202},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.15180712938308716},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/544","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/544","pdf_url":"https://www.ijcai.org/proceedings/2023/0544.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/544","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/544","pdf_url":"https://www.ijcai.org/proceedings/2023/0544.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3527113235","display_name":null,"funder_award_id":"62272466","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322499","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385768169.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2084044763","https://openalex.org/W2091425152","https://openalex.org/W2108771579","https://openalex.org/W2110007838","https://openalex.org/W2118774185","https://openalex.org/W2191779130","https://openalex.org/W2407685581","https://openalex.org/W2604959036","https://openalex.org/W2767434619","https://openalex.org/W2774581901","https://openalex.org/W2788560150","https://openalex.org/W2795042520","https://openalex.org/W2884561390","https://openalex.org/W2895387432","https://openalex.org/W2906214917","https://openalex.org/W2938774173","https://openalex.org/W2950547518","https://openalex.org/W2952823162","https://openalex.org/W2962866891","https://openalex.org/W2963430933","https://openalex.org/W2997646596","https://openalex.org/W3091031764","https://openalex.org/W3114569718","https://openalex.org/W3118301015","https://openalex.org/W3124061379","https://openalex.org/W3160649916","https://openalex.org/W3174341621","https://openalex.org/W4226199190","https://openalex.org/W4286980120","https://openalex.org/W4287072584","https://openalex.org/W4289563769","https://openalex.org/W4293775315","https://openalex.org/W4322615164","https://openalex.org/W6790825729","https://openalex.org/W6795670242","https://openalex.org/W6863994431","https://openalex.org/W6864014924","https://openalex.org/W6864487941"],"related_works":["https://openalex.org/W2534386362","https://openalex.org/W2080996473","https://openalex.org/W2010034188","https://openalex.org/W4240250933","https://openalex.org/W2542236698","https://openalex.org/W2532016591","https://openalex.org/W2400828047","https://openalex.org/W2622566875","https://openalex.org/W2161086097","https://openalex.org/W1607425652"],"abstract_inverted_index":{"Melody":[0],"extraction":[1],"is":[2,93,148],"a":[3,46,80,109,118],"core":[4],"task":[5],"in":[6,21],"music":[7,105],"information":[8],"retrieval,":[9],"and":[10,16,29,56,68,72,79,103,107,135,143,146,155],"the":[11,62,94,138,161],"estimation":[12,52],"of":[13,35,53,64,111,121,140,153,163,166],"pitch,":[14,54],"onset":[15,55],"offset":[17],"are":[18],"key":[19],"sub-tasks":[20],"melody":[22],"extraction.":[23],"Existing":[24],"methods":[25,129],"have":[26],"limited":[27],"accuracy,":[28],"work":[30],"for":[31,50,137,150],"only":[32],"one":[33],"type":[34],"data,":[36,106],"either":[37],"single-pitch":[38,71,102],"or":[39],"multi-pitch.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44],"propose":[45],"highly":[47],"accurate":[48],"method":[49,96],"joint":[51,65],"offset,":[57],"named":[58,84],"JEPOO.":[59,167],"We":[60],"address":[61],"challenges":[63],"learning":[66],"optimization":[67,82],"handling":[69],"both":[70,101],"multi-pitch":[73,104],"data":[74,154],"through":[75],"novel":[76],"model":[77],"design":[78],"new":[81],"technique":[83],"Pareto":[85],"modulated":[86],"loss":[87,89],"with":[88],"weight":[90],"regularization.":[91],"This":[92],"first":[95],"that":[97,125],"can":[98],"accurately":[99],"handle":[100],"even":[108],"mix":[110],"them.":[112],"A":[113],"comprehensive":[114],"experimental":[115],"study":[116,159],"on":[117],"wide":[119],"range":[120],"real":[122],"datasets":[123],"shows":[124],"JEPOO":[126,147],"outperforms":[127],"state-of-the-art":[128],"by":[130],"up":[131],"to":[132],"10.6\\%,":[133],"8.3\\%":[134],"10.3\\%":[136],"prediction":[139],"Pitch,":[141],"Onset":[142],"Offset,":[144],"respectively,":[145],"robust":[149],"various":[151],"types":[152],"instruments.":[156],"The":[157],"ablation":[158],"validates":[160],"effectiveness":[162],"each":[164],"component":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}