{"id":"https://openalex.org/W2163468724","doi":"https://doi.org/10.1109/icassp.2011.5946423","title":"A trend estimation algorithm for singing pitch detection in musical recordings","display_name":"A trend estimation algorithm for singing pitch detection in musical recordings","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2163468724","doi":"https://doi.org/10.1109/icassp.2011.5946423","mag":"2163468724"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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/A5000838826","display_name":"Chao-Ling Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chao-Ling Hsu","raw_affiliation_strings":["Computer Science Department, National Tsing Hua University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering & Centre of Cognitive Science, Ohio State Uinversity, Columbus, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering & Centre of Cognitive Science, Ohio State Uinversity, Columbus, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073451247","display_name":"Jyh\u2010Shing Roger Jang","orcid":"https://orcid.org/0000-0002-7319-9095"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jyh-Shing Roger Jang","raw_affiliation_strings":["Computer Science Department, National Tsing Hua University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":null,"first_page":"393","last_page":"396"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9966999888420105,"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":0.9965999722480774,"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/singing","display_name":"Singing","score":0.935041606426239},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.8753713369369507},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7005207538604736},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6834772825241089},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6288043856620789},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4401388168334961},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.366835355758667},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.26532837748527527},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.18952122330665588},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09074890613555908},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07980379462242126}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.935041606426239},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.8753713369369507},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7005207538604736},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6834772825241089},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6288043856620789},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4401388168334961},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.366835355758667},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.26532837748527527},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.18952122330665588},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09074890613555908},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07980379462242126},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5946423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W27427732","https://openalex.org/W126277046","https://openalex.org/W2035852710","https://openalex.org/W2123169318","https://openalex.org/W2124232593","https://openalex.org/W2124539664","https://openalex.org/W2150113039","https://openalex.org/W2152728141","https://openalex.org/W2168103573","https://openalex.org/W4285719527","https://openalex.org/W6601134270","https://openalex.org/W6605095414","https://openalex.org/W6678415575","https://openalex.org/W6678626330","https://openalex.org/W6682433475"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2024908463","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W1969227305","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W1714737510","https://openalex.org/W2400828047"],"abstract_inverted_index":{"Detecting":[0],"pitch":[1,28,47,56,82],"values":[2],"for":[3,16,113],"singing":[4,32,46,68,81],"voice":[5,33],"in":[6,34],"the":[7,27,43,64,67,78,99,108],"presence":[8],"of":[9,30,45,54,66,80],"music":[10],"accompaniment":[11],"is":[12],"challenging":[13],"but":[14],"useful":[15],"many":[17],"applications.":[18],"We":[19],"propose":[20],"a":[21,31,51],"trend":[22,40,89],"estimation":[23,90],"algorithm":[24,72,94],"to":[25,76],"detect":[26],"ranges":[29],"each":[35],"time":[36],"frame.":[37],"The":[38,70,96],"detected":[39],"substantially":[41],"reduces":[42],"difficulty":[44],"detection":[48],"by":[49,60],"reducing":[50],"large":[52],"number":[53],"wrong":[55],"candidates":[57],"either":[58],"produced":[59],"musical":[61],"instruments":[62],"or":[63],"overtones":[65],"voice.":[69],"proposed":[71,88],"can":[73],"be":[74],"applied":[75],"improve":[77],"performance":[79],"detection.":[83],"Quantitative":[84],"evaluations":[85],"show":[86,103],"that":[87,104],"improves":[91],"an":[92],"existing":[93],"significantly.":[95],"results":[97],"from":[98],"MIREX":[100],"2010":[101],"competition":[102],"our":[105],"system":[106],"achieves":[107],"best":[109],"overall":[110],"raw-pitch":[111],"accuracy":[112],"vocal":[114],"songs.":[115]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}