{"id":"https://openalex.org/W2098166503","doi":"https://doi.org/10.1109/icassp.2012.6287915","title":"A hybrid approach to singing pitch extraction based on trend estimation and hidden Markov models","display_name":"A hybrid approach to singing pitch extraction based on trend estimation and hidden Markov models","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2098166503","doi":"https://doi.org/10.1109/icassp.2012.6287915","mag":"2098166503"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6287915","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287915","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 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/A5074676744","display_name":"Tzu\u2010Chun Yeh","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":"Tzu-Chun Yeh","raw_affiliation_strings":["Computer Science Department, National Tsinghua University, Hsinchu, Taiwan","Computer Science Department, National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, National Tsinghua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Computer Science Department, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001137398","display_name":"Ming-Ju Wu","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":"Ming-Ju Wu","raw_affiliation_strings":["Computer Science Department, National Tsinghua University, Hsinchu, Taiwan","Computer Science Department, National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, National Tsinghua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Computer Science Department, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","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 Tsinghua University, Hsinchu, Taiwan","Computer Science Department, National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, National Tsinghua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Computer Science Department, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064774926","display_name":"Wei\u2010Lun Chang","orcid":"https://orcid.org/0000-0002-0238-527X"},"institutions":[{"id":"https://openalex.org/I92172085","display_name":"Chunghwa Telecom (Taiwan)","ror":"https://ror.org/04f786589","country_code":"TW","type":"company","lineage":["https://openalex.org/I92172085"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Lun Chang","raw_affiliation_strings":["Telecommunication Laboratories, Chunghwa Telecom Company Limited, Taoyuan, Taiwan","Telecommunication Laboratories, Chunghwa Telecom, Taoyuan, TAIWAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Telecommunication Laboratories, Chunghwa Telecom Company Limited, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I92172085"]},{"raw_affiliation_string":"Telecommunication Laboratories, Chunghwa Telecom, Taoyuan, TAIWAN","institution_ids":["https://openalex.org/I92172085"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081460934","display_name":"I-Bin Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I92172085","display_name":"Chunghwa Telecom (Taiwan)","ror":"https://ror.org/04f786589","country_code":"TW","type":"company","lineage":["https://openalex.org/I92172085"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"I-Bin Liao","raw_affiliation_strings":["Telecommunication Laboratories, Chunghwa Telecom Company Limited, Taoyuan, Taiwan","Telecommunication Laboratories, Chunghwa Telecom, Taoyuan, TAIWAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Telecommunication Laboratories, Chunghwa Telecom Company Limited, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I92172085"]},{"raw_affiliation_string":"Telecommunication Laboratories, Chunghwa Telecom, Taoyuan, TAIWAN","institution_ids":["https://openalex.org/I92172085"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.952,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.88668516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"457","last_page":"460"},"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":0.9994000196456909,"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":0.9987000226974487,"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":0.7951880693435669},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.6658834218978882},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6568106412887573},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6550009250640869},{"id":"https://openalex.org/keywords/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.6499766111373901},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5941635966300964},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.5914260149002075},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4165474772453308},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.4115999937057495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3743233382701874},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3495904207229614},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.21359387040138245},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12050417065620422}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7951880693435669},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.6658834218978882},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6568106412887573},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6550009250640869},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.6499766111373901},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5941635966300964},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.5914260149002075},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4165474772453308},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.4115999937057495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3743233382701874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3495904207229614},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.21359387040138245},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12050417065620422},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6287915","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287915","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W144548647","https://openalex.org/W178932670","https://openalex.org/W2035852710","https://openalex.org/W2123169318","https://openalex.org/W2124232593","https://openalex.org/W2124539664","https://openalex.org/W2159113005","https://openalex.org/W2163468724","https://openalex.org/W2189429918","https://openalex.org/W2293399065","https://openalex.org/W3097096317","https://openalex.org/W6605891315","https://openalex.org/W6678415575","https://openalex.org/W6683626087","https://openalex.org/W6687632320"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2371528275","https://openalex.org/W2375454309","https://openalex.org/W2374135200","https://openalex.org/W2390487542"],"abstract_inverted_index":{"In":[0,67],"this":[1,68],"paper,":[2,69],"we":[3,70],"propose":[4],"a":[5,26,64,75],"hybrid":[6],"method":[7,84],"for":[8,85,105],"singing":[9],"pitch":[10,22,39,48,60],"extraction":[11,111],"from":[12],"polyphonic":[13],"audio":[14,109],"music.":[15],"We":[16,34],"have":[17,44],"observed":[18],"several":[19,59],"kinds":[20],"of":[21,47,58,108],"errors":[23],"made":[24],"by":[25],"previously":[27],"proposed":[28,99],"algorithm":[29,104],"based":[30],"on":[31],"trend":[32],"estimation.":[33],"also":[35],"noticed":[36],"that":[37,97],"other":[38,45],"tracking":[40],"methods":[41,73],"tend":[42],"to":[43,54,62,77],"types":[46],"error.":[49],"Then":[50],"it":[51],"becomes":[52],"intuitive":[53],"combine":[55],"the":[56,79,82,98,102,106],"results":[57,95],"trackers":[61],"achieve":[63],"better":[65],"accuracy.":[66],"adopt":[71],"3":[72],"as":[74],"committee":[76],"determine":[78],"pitch,":[80],"including":[81],"trend-estimation-based":[83],"forward":[86],"and":[87,90],"backward":[88],"signals,":[89],"training-based":[91],"HMM":[92],"method.":[93],"Experimental":[94],"demonstrate":[96],"approach":[100],"outperforms":[101],"best":[103],"task":[107],"melody":[110],"in":[112],"MIREX":[113],"2010.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
