{"id":"https://openalex.org/W2103218155","doi":"https://doi.org/10.1109/icme.2003.1220854","title":"A statistical multidimensional humming transcription using phone level hidden Markov models for query by humming systems","display_name":"A statistical multidimensional humming transcription using phone level hidden Markov models for query by humming systems","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2103218155","doi":"https://doi.org/10.1109/icme.2003.1220854","mag":"2103218155"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2003.1220854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1220854","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","Integrated Media Syst. Center, Southern California Univ., 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"]},{"raw_affiliation_string":"Integrated Media Syst. Center, Southern California Univ., 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","Integrated Media Syst. Center, Southern California Univ., 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"]},{"raw_affiliation_string":"Integrated Media Syst. Center, Southern California Univ., 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","Integrated Media Syst. Center, Southern California Univ., 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"]},{"raw_affiliation_string":"Integrated Media Syst. Center, Southern California Univ., 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":0.5926,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.68598078,"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":"I","last_page":"61"},"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":0.9980999827384949,"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":0.9947999715805054,"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/hum","display_name":"Hum","score":0.8995635509490967},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.844463586807251},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7001815438270569},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6255989074707031},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.6127460598945618},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5325962901115417},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4680088758468628},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.43936723470687866},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.43347036838531494},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3960813879966736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36196473240852356},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.302573561668396},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.231736958026886},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.167542964220047}],"concepts":[{"id":"https://openalex.org/C23161992","wikidata":"https://www.wikidata.org/wiki/Q2922301","display_name":"Hum","level":3,"score":0.8995635509490967},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.844463586807251},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7001815438270569},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6255989074707031},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.6127460598945618},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5325962901115417},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4680088758468628},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.43936723470687866},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.43347036838531494},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3960813879966736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36196473240852356},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.302573561668396},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.231736958026886},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.167542964220047},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"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/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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme.2003.1220854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1220854","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:10.1.1.203.1215","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.203.1215","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/publications/ICME03_shih.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W150213279","https://openalex.org/W1724148608","https://openalex.org/W1778811406","https://openalex.org/W1964219887","https://openalex.org/W2027518030","https://openalex.org/W2103257781","https://openalex.org/W2151155792","https://openalex.org/W2152324136"],"related_works":["https://openalex.org/W2153098279","https://openalex.org/W1510894296","https://openalex.org/W2134386692","https://openalex.org/W2082284720","https://openalex.org/W2194396582","https://openalex.org/W2116722627","https://openalex.org/W2379938888","https://openalex.org/W2537260108","https://openalex.org/W4233405330","https://openalex.org/W2176285001"],"abstract_inverted_index":{"A":[0,18],"new":[1],"phone":[2,79],"level":[3,80],"hidden":[4,81],"Markov":[5,82],"model":[6,108],"approach":[7],"applied":[8],"to":[9],"human":[10,129],"humming":[11,34,45,74],"transcription":[12],"is":[13,76,91,103,140],"proposed":[14,30],"in":[15,72],"this":[16,57],"research.":[17],"music":[19,54],"note":[20,71,89,102],"has":[21],"two":[22],"important":[23],"attributes,":[24],"i.e.":[25],"pitch":[26,39,99,107],"and":[27,40,56,131],"duration.":[28],"The":[29,67,85,98],"system":[31],"generates":[32],"multidimensional":[33],"transcriptions,":[35],"which":[36],"contain":[37],"both":[38],"duration":[41,86,96],"information.":[42],"Query":[43],"by":[44,78,94,105,124],"provides":[46,59],"a":[47,60,70,95,106,110],"natural":[48],"means":[49],"for":[50,63],"content-based":[51],"retrieval":[52],"from":[53,127],"databases,":[55],"research":[58],"robust":[61],"front-end":[62],"such":[64],"an":[65,132],"application.":[66],"segment":[68,90],"of":[69,87,100,137],"the":[73,88,101],"waveform":[75],"modeled":[77,104],"models":[83,122],"(HMM).":[84],"then":[92],"labeled":[93],"model.":[97,113],"using":[109],"Gaussian":[111],"mixture":[112],"Preliminary":[114],"real-time":[115],"recognition":[116,135],"experiments":[117],"are":[118],"carried":[119],"out":[120],"with":[121],"trained":[123],"data":[125],"obtained":[126],"eight":[128],"objects,":[130],"overall":[133],"correct":[134],"rate":[136],"around":[138],"84%":[139],"demonstrated.":[141]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}