{"id":"https://openalex.org/W4385822304","doi":"https://doi.org/10.21437/interspeech.2023-528","title":"RMVPE: A Robust Model for Vocal Pitch Estimation in Polyphonic Music","display_name":"RMVPE: A Robust Model for Vocal Pitch Estimation in Polyphonic Music","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822304","doi":"https://doi.org/10.21437/interspeech.2023-528"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-528","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/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/A5101319196","display_name":"Xueke Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueke Cao","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022310235","display_name":"Tangpeng Dan","orcid":"https://orcid.org/0000-0003-0824-5494"},"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":"Tangpeng Dan","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/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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101939672"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":4.2919,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.95538757,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5421","last_page":"5425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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":0.9980000257492065,"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":0.996399998664856,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9839000105857849,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.9326239824295044},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6994739770889282},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6612000465393066},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5262036919593811},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.23275181651115417},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08388972282409668}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.9326239824295044},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6994739770889282},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6612000465393066},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5262036919593811},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.23275181651115417},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08388972282409668},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-528","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1924770834","https://openalex.org/W1975079546","https://openalex.org/W2051880409","https://openalex.org/W2091425152","https://openalex.org/W2118774185","https://openalex.org/W2124539664","https://openalex.org/W2191779130","https://openalex.org/W2398618787","https://openalex.org/W2407685581","https://openalex.org/W2774581901","https://openalex.org/W2962866891","https://openalex.org/W2972353749","https://openalex.org/W2972411915","https://openalex.org/W2980121906","https://openalex.org/W2990594533","https://openalex.org/W3037149862","https://openalex.org/W3160649916","https://openalex.org/W3161758688","https://openalex.org/W4221159539","https://openalex.org/W4225401194","https://openalex.org/W4283388885"],"related_works":["https://openalex.org/W2122830402","https://openalex.org/W2101119896","https://openalex.org/W2368779261","https://openalex.org/W2778699561","https://openalex.org/W2963095134","https://openalex.org/W178932670","https://openalex.org/W2160136308","https://openalex.org/W2406972062","https://openalex.org/W2130581557","https://openalex.org/W1922092259"],"abstract_inverted_index":{"Vocal":[0],"pitch":[1,13,57,110],"is":[2,17,59,128,139],"an":[3],"important":[4],"high-level":[5],"feature":[6],"in":[7,14,106],"music":[8,16,36,46,63],"audio":[9],"processing.However,":[10],"extracting":[11],"vocal":[12,49,56,73,94],"polyphonic":[15,45,76,97],"more":[18],"challenging":[19],"due":[20],"to":[21,40],"the":[22,27,30,53,62,102],"presence":[23],"of":[24,29,55,104,108,123,137],"accompaniment.To":[25],"eliminate":[26],"influence":[28],"accompaniment,":[31],"most":[32],"previous":[33],"methods":[34],"adopt":[35],"source":[37,64],"separation":[38,65],"models":[39],"obtain":[41],"clean":[42],"vocals":[43],"from":[44,75,96],"before":[47],"predicting":[48],"pitches.As":[50],"a":[51,80],"result,":[52],"performance":[54],"estimation":[58],"affected":[60],"by":[61],"models.To":[66],"address":[67],"this":[68],"issue":[69],"and":[70,91,113],"directly":[71],"extract":[72,87],"pitches":[74,95],"music,":[77],"we":[78],"propose":[79],"robust":[81,129],"model":[82,85],"named":[83],"RMVPE.This":[84],"can":[86],"effective":[88],"hidden":[89],"features":[90],"accurately":[92],"predict":[93],"music.The":[98],"experimental":[99],"results":[100],"demonstrate":[101],"superiority":[103],"RMVPE":[105,127,138],"terms":[107],"raw":[109,114],"accuracy":[111,116],"(RPA)":[112],"chroma":[115],"(RCA).Additionally,":[117],"experiments":[118],"conducted":[119],"with":[120],"different":[121],"types":[122],"noise":[124],"show":[125],"that":[126],"across":[130],"all":[131],"signal-to-noise":[132],"ratio":[133],"(SNR)":[134],"levels.The":[135],"code":[136],"available":[140],"at":[141],"https:":[142],"//github.com/Dream-High/RMVPE.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":6}],"updated_date":"2026-05-28T09:10:13.091523","created_date":"2025-10-10T00:00:00"}