{"id":"https://openalex.org/W2159113005","doi":"https://doi.org/10.1109/icassp.2005.1415635","title":"Detecting pitch of singing voice in polyphonic audio","display_name":"Detecting pitch of singing voice in polyphonic audio","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2159113005","doi":"https://doi.org/10.1109/icassp.2005.1415635","mag":"2159113005"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","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/A5101799190","display_name":"Yipeng Li","orcid":"https://orcid.org/0000-0001-9099-4077"},"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":true,"raw_author_name":"Yipeng Li","raw_affiliation_strings":["Department of Computer Science & Engineering and Center for Cognitive Science, Ohio State Uinversity, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering and Center for Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","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 & Center for Cognitive Science, Ohio State Uinversity, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering & Center for Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101799190"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":4.1345,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.94562701,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"3","issue":null,"first_page":"17","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9951000213623047,"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/polyphony","display_name":"Polyphony","score":0.8884913325309753},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7445648908615112},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7378056645393372},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7091501355171204},{"id":"https://openalex.org/keywords/salience","display_name":"Salience (neuroscience)","score":0.6955289244651794},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.5794159770011902},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4349293112754822},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.41860291361808777},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2929529547691345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2671056389808655},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2261664867401123},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13911712169647217}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8884913325309753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7445648908615112},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7378056645393372},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7091501355171204},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.6955289244651794},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.5794159770011902},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4349293112754822},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.41860291361808777},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2929529547691345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2671056389808655},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2261664867401123},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13911712169647217},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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":2,"locations":[{"id":"doi:10.1109/icassp.2005.1415635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.113.6493","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.113.6493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~dwang/papers/Li-Wang.icassp05.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W25953162","https://openalex.org/W2002125932","https://openalex.org/W2043694038","https://openalex.org/W2094792781","https://openalex.org/W2119599673","https://openalex.org/W2137509658","https://openalex.org/W2149425615","https://openalex.org/W2155208345","https://openalex.org/W2981666567","https://openalex.org/W3216401400","https://openalex.org/W4298257861"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W17155033","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2371528275","https://openalex.org/W2375454309","https://openalex.org/W2374135200"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,10],"robust":[3],"algorithm":[4],"to":[5,23,43],"detect":[6],"the":[7,25,28,32,45,58],"pitch":[8,69],"of":[9,27],"singing":[11,29],"voice":[12,30],"in":[13,35,71],"polyphonic":[14,72],"audio.":[15,73],"A":[16],"new":[17,59],"channel/peak":[18],"selection":[19],"scheme":[20],"is":[21,41],"introduced":[22],"exploit":[24],"salience":[26],"and":[31,51],"beating":[33],"phenomenon":[34],"high":[36],"frequency":[37,49],"channels.":[38],"An":[39],"HMM":[40],"employed":[42],"integrate":[44],"periodicity":[46],"information":[47],"across":[48],"channels":[50],"time":[52],"frames.":[53],"Quantitative":[54],"evaluation":[55],"shows":[56],"that":[57],"system":[60],"performs":[61],"significantly":[62],"better":[63],"than":[64],"existing":[65],"algorithms":[66],"for":[67],"predominant":[68],"detection":[70]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}