{"id":"https://openalex.org/W2151155792","doi":"https://doi.org/10.1109/icme.2001.1237713","title":"Content-based music retrieval using linear scaling and branch-and-bound tree search","display_name":"Content-based music retrieval using linear scaling and branch-and-bound tree search","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W2151155792","doi":"https://doi.org/10.1109/icme.2001.1237713","mag":"2151155792"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2001.1237713","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2001.1237713","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Multimedia and Expo, 2001. ICME 2001.","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/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":true,"raw_author_name":"J.-S.R. Jang","raw_affiliation_strings":["Multimedia Information Retrieval Laboratory Computer Science Department, National Tsing Hua University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Multimedia Information Retrieval Laboratory Computer Science Department, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016890751","display_name":"Hong-Ru Lee","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":"Hong-Ru Lee","raw_affiliation_strings":["Multimedia Information Retrieval Laboratory Computer Science Department, National Tsing Hua University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Multimedia Information Retrieval Laboratory Computer Science Department, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109219665","display_name":"Ming\u2010Yang Kao","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-Yang Kao","raw_affiliation_strings":["Multimedia Information Retrieval Laboratory Computer Science Department, National Tsing Hua University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Multimedia Information Retrieval Laboratory Computer Science Department, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5073451247"],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":3.9406,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.93796468,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"289","last_page":"292"},"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":0.9976999759674072,"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":0.991599977016449,"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":0.7147754430770874},{"id":"https://openalex.org/keywords/linear-scale","display_name":"Linear scale","score":0.5904337763786316},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5880456566810608},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5844034552574158},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.560144305229187},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.549565315246582},{"id":"https://openalex.org/keywords/search-tree","display_name":"Search tree","score":0.474122554063797},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4549602270126343},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44285792112350464},{"id":"https://openalex.org/keywords/hum","display_name":"Hum","score":0.4377908706665039},{"id":"https://openalex.org/keywords/multidimensional-scaling","display_name":"Multidimensional scaling","score":0.41461342573165894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3174692392349243},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.2967183589935303},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2025803029537201},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15626966953277588},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15447527170181274},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12779954075813293},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.11492714285850525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7147754430770874},{"id":"https://openalex.org/C170122806","wikidata":"https://www.wikidata.org/wiki/Q1914828","display_name":"Linear scale","level":2,"score":0.5904337763786316},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5880456566810608},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5844034552574158},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.560144305229187},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.549565315246582},{"id":"https://openalex.org/C207024777","wikidata":"https://www.wikidata.org/wiki/Q621673","display_name":"Search tree","level":3,"score":0.474122554063797},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4549602270126343},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44285792112350464},{"id":"https://openalex.org/C23161992","wikidata":"https://www.wikidata.org/wiki/Q2922301","display_name":"Hum","level":3,"score":0.4377908706665039},{"id":"https://openalex.org/C91682802","wikidata":"https://www.wikidata.org/wiki/Q620538","display_name":"Multidimensional scaling","level":2,"score":0.41461342573165894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3174692392349243},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.2967183589935303},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2025803029537201},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15626966953277588},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15447527170181274},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12779954075813293},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.11492714285850525},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2001.1237713","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2001.1237713","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Multimedia and Expo, 2001. ICME 2001.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8999999761581421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1481204283","https://openalex.org/W1493163583","https://openalex.org/W1527747256","https://openalex.org/W1594159577","https://openalex.org/W1778811406","https://openalex.org/W1964219887","https://openalex.org/W1966280390","https://openalex.org/W1970893633","https://openalex.org/W2027518030","https://openalex.org/W2046134527","https://openalex.org/W2071914178","https://openalex.org/W2078009352","https://openalex.org/W2088171019","https://openalex.org/W2097921974","https://openalex.org/W2110527478","https://openalex.org/W2144679084","https://openalex.org/W2158382912","https://openalex.org/W2160066518","https://openalex.org/W2161170734","https://openalex.org/W2169989102","https://openalex.org/W2239504576","https://openalex.org/W4245046554","https://openalex.org/W4285719527","https://openalex.org/W6638009197","https://openalex.org/W6674878074","https://openalex.org/W6690404994"],"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/W4399590736","https://openalex.org/W2612622548","https://openalex.org/W2768219367","https://openalex.org/W4251913501"],"abstract_inverted_index":{"paper":[0],"presents":[1],"the":[2,35,44,53,69,98,108],"use":[3],"of":[4,25,55,119],"linear":[5,89],"scaling":[6,90],"and":[7,32,76,91,106],"tree":[8,92],"search":[9,93],"in":[10,43],"a":[11,19,30,61,74,80,84],"content-based":[12,57],"music":[13,58],"retrieval":[14,59],"system":[15],"that":[16],"can":[17],"take":[18],"user's":[20,70],"acoustic":[21,71],"input":[22,72],"(8-second":[23],"clip":[24],"singing":[26,126],"or":[27],"humming)":[28],"via":[29],"microphone":[31,75],"then":[33],"retrieve":[34],"intended":[36],"song":[37],"from":[38,73,122],"over":[39],"3000":[40],"candidate":[41],"songs":[42],"database.":[45],"The":[46],"system,":[47],"known":[48],"as":[49],"Super":[50,65,104],"MBox,":[51],"demonstrates":[52],"feasibility":[54],"real-time":[56],"with":[60,115,124],"high":[62],"recognition":[63,110],"rate.":[64],"MBox":[66,105],"first":[67],"takes":[68],"converts":[77],"it":[78],"into":[79],"pitch":[81],"vector.":[82],"Then":[83],"fast":[85],"comparison":[86],"engine":[87],"using":[88],"is":[94,112],"employed":[95],"to":[96],"compute":[97],"similarity":[99],"scores.":[100],"We":[101],"have":[102],"tested":[103],"found":[107],"top-20":[109],"rate":[111],"about":[113,116],"73%":[114],"1000":[117],"clips":[118],"test":[120],"inputs":[121],"people":[123],"mediocre":[125],"skills.":[127]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}