{"id":"https://openalex.org/W2220016360","doi":"https://doi.org/10.1109/icme.2003.1221329","title":"Multidimensional humming transcription using a statistical approach for query by humming systems","display_name":"Multidimensional humming transcription using a statistical approach for query by humming systems","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2220016360","doi":"https://doi.org/10.1109/icme.2003.1221329","mag":"2220016360"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2003.1221329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","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/A5062391400","display_name":"Hsuan-Huei Shih","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hsuan-Huei Shih","raw_affiliation_strings":["Integrated Media Systems Center and Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Integrated Media Systems Center and Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S.S. Narayanan","raw_affiliation_strings":["Integrated Media Systems Center and Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Integrated Media Systems Center and Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001082656","display_name":"C.\u2010C. Jay Kuo","orcid":"https://orcid.org/0000-0001-9474-5035"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C.-C.J. Kuo","raw_affiliation_strings":["Integrated Media Systems Center and Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Integrated Media Systems Center and Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062391400"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":1.4815,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.84379122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"III","last_page":"385"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.9937000274658203,"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":0.993399977684021,"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/hum","display_name":"Hum","score":0.9323360919952393},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7039942145347595},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7006800174713135},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.603217601776123},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5961287021636963},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5010514259338379},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.49932336807250977},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4783991575241089},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41172492504119873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37168461084365845},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14915800094604492},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.06864520907402039}],"concepts":[{"id":"https://openalex.org/C23161992","wikidata":"https://www.wikidata.org/wiki/Q2922301","display_name":"Hum","level":3,"score":0.9323360919952393},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7039942145347595},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7006800174713135},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.603217601776123},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5961287021636963},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5010514259338379},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.49932336807250977},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4783991575241089},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41172492504119873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37168461084365845},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14915800094604492},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.06864520907402039},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C554144382","wikidata":"https://www.wikidata.org/wiki/Q213156","display_name":"Performance art","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme.2003.1221329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.124.6405","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.124.6405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sail.usc.edu/music/papers/icassp03-maverick.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W150213279","https://openalex.org/W1778811406","https://openalex.org/W1964219887","https://openalex.org/W2027518030","https://openalex.org/W2071914178","https://openalex.org/W2103257781","https://openalex.org/W2151155792","https://openalex.org/W2152324136","https://openalex.org/W6605983381","https://openalex.org/W6638009197","https://openalex.org/W6675600572"],"related_works":["https://openalex.org/W4244401456","https://openalex.org/W4253003836","https://openalex.org/W2612570103","https://openalex.org/W826845752","https://openalex.org/W2198680435","https://openalex.org/W1992491376","https://openalex.org/W2612622548","https://openalex.org/W2768219367","https://openalex.org/W2348837382","https://openalex.org/W9972820"],"abstract_inverted_index":{"A":[0,16],"new":[1],"statistical":[2],"pattern":[3],"recognition":[4,100,119],"approach":[5],"applied":[6],"to":[7],"human":[8,113],"humming":[9,32,43,71],"transcription":[10],"is":[11,73,87,124],"proposed":[12,28],"in":[13,69],"this":[14,55],"research.":[15],"music":[17,52],"note":[18,68,86],"has":[19],"two":[20],"important":[21],"attributes,":[22],"i.e.":[23],"pitch":[24,37,83,91],"and":[25,38,54,115],"duration.":[26],"The":[27,64],"algorithm":[29],"generates":[30],"multidimensional":[31],"transcriptions,":[33],"which":[34],"contain":[35],"both":[36],"duration":[39],"information.":[40],"Query":[41],"by":[42,75,89,108],"provides":[44,57],"a":[45,58,67,76,90,94],"natural":[46],"means":[47],"for":[48,61],"content-based":[49],"retrieval":[50],"from":[51,111],"databases,":[53],"research":[56],"robust":[59],"front-end":[60],"such":[62],"application.":[63],"segment":[65],"of":[66,84,121],"the":[70,82,85],"waveform":[72],"modeled":[74,88],"hidden":[77],"Markov":[78],"model":[79,92],"(HMM)":[80],"while":[81],"using":[93],"Gaussian":[95],"mixture":[96],"model.":[97],"Preliminary":[98],"real-time":[99],"experiments":[101],"are":[102],"carried":[103],"out":[104],"with":[105],"models":[106],"trained":[107],"data":[109],"obtained":[110],"eight":[112],"objects,":[114],"an":[116],"overall":[117],"correct":[118],"rate":[120],"around":[122],"80%":[123],"demonstrated.":[125]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}