{"id":"https://openalex.org/W2152200372","doi":"https://doi.org/10.1109/icme.2003.1221716","title":"HMM-based music retrieval using stereophonic feature information and framelength adaptation","display_name":"HMM-based music retrieval using stereophonic feature information and framelength adaptation","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2152200372","doi":"https://doi.org/10.1109/icme.2003.1221716","mag":"2152200372"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2003.1221716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221716","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":true,"oa_status":"green","oa_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/76936/76936.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"B. Schuller","raw_affiliation_strings":["Institute for Human-Computer Communication, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Human-Computer Communication, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039092855","display_name":"Gerhard Rigoll","orcid":"https://orcid.org/0000-0003-1096-1596"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"G. Rigoll","raw_affiliation_strings":["Institute for Human-Computer Communication, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Human-Computer Communication, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088367992","display_name":"M. Lang","orcid":"https://orcid.org/0009-0001-8080-0010"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"M. Lang","raw_affiliation_strings":["Institute for Human-Computer Communication, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Human-Computer Communication, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5043060302"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.2964,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.6058236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"II","last_page":"713"},"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":0.9980000257492065,"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":0.9926999807357788,"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":0.826565682888031},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5936426520347595},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.5864987969398499},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.5711873769760132},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.562700092792511},{"id":"https://openalex.org/keywords/stereophonic-sound","display_name":"Stereophonic sound","score":0.532903254032135},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.4861685633659363},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48497438430786133},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4507078528404236},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.448616623878479},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4325904846191406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3465989828109741},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.1191551685333252},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08855900168418884}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.826565682888031},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5936426520347595},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.5864987969398499},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5711873769760132},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.562700092792511},{"id":"https://openalex.org/C140631703","wikidata":"https://www.wikidata.org/wiki/Q34678","display_name":"Stereophonic sound","level":3,"score":0.532903254032135},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.4861685633659363},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48497438430786133},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4507078528404236},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.448616623878479},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4325904846191406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3465989828109741},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.1191551685333252},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08855900168418884},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icme.2003.1221716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221716","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:uni-augsburg.opus-bayern.de:76936","is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/76936","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/76936/76936.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.364.5746","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.364.5746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mmk.ei.tum.de/publ/pdf/03/03sch3.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:uni-augsburg.opus-bayern.de:76936","is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/76936","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/76936/76936.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"},"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2152200372.pdf"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2024411421","https://openalex.org/W2099568056","https://openalex.org/W2125838338","https://openalex.org/W2169821300","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W1481643945","https://openalex.org/W2153275212","https://openalex.org/W2402674073","https://openalex.org/W2205029322","https://openalex.org/W126167045","https://openalex.org/W2328848613","https://openalex.org/W4298140471","https://openalex.org/W2152200372","https://openalex.org/W2757523791"],"abstract_inverted_index":{"Music":[0],"retrieval":[1,29],"methods":[2,26],"are":[3],"in":[4,20,45,55,82,226],"the":[5,12,21,34,39,52,75,78,89,96,148,172,176,180,194,207],"focus":[6],"of":[7,15,33,80,91,144,150,154,165,175,182,196,214],"recent":[8],"interest":[9],"due":[10],"to":[11,37,59,73,113,158,179,206],"increasing":[13],"size":[14],"music":[16,56,84],"databases":[17],"as":[18,51,125],"e.g.":[19],"Internet.":[22],"Among":[23],"different":[24],"query":[25,61],"content-based":[27],"media":[28],"analyzing":[30],"intrinsic":[31],"characteristics":[32],"source":[35],"seems":[36],"form":[38],"most":[40],"intuitive":[41],"access.":[42],"The":[43,141,191],"key-melody":[44],"a":[46,60,151,159,183,197],"song":[47],"can":[48],"be":[49],"regarded":[50],"major":[53],"characteristic":[54],"and":[57,77,138,201,220],"leads":[58],"by":[62,163],"humming":[63,104,112,129,132],"or":[64,103],"singing.":[65],"In":[66,117],"this":[67,118],"paper":[68,192],"we":[69,120],"turn":[70],"our":[71,145],"attention":[72],"both,":[74],"features":[76],"algorithm":[79],"matching":[81,97,111,131,189],"audio":[83,115,216],"retrieval.":[85],"Nowadays":[86],"approaches":[87],"propagate":[88],"use":[90,164],"dynamic":[92],"time":[93],"warping":[94],"for":[95,128],"process.":[98],"As":[99],"reference":[100],"mostly":[101],"midi-data":[102],"itself":[105],"is":[106,147,224],"used.":[107],"However,":[108],"first":[109],"attempts":[110],"polyphonic":[114,139,215],"exist.":[116],"contribution":[119],"introduce":[121],"hidden":[122],"Markov":[123],"models":[124],"an":[126,169],"alternative":[127],"queries":[130],"itself,":[133],"mobile":[134],"phone":[135],"ring":[136,218],"tones":[137],"audio.":[140],"second":[142],"object":[143],"research":[146],"introduction":[149],"new":[152],"way":[153],"melody":[155],"enhancement":[156],"prior":[157],"latter":[160],"feature":[161],"extraction":[162,173],"stereophonic":[166],"information.":[167],"Further":[168],"adaptation":[170],"throughout":[171],"process":[174],"frame":[177],"length":[178],"tempo":[181],"musical":[184],"piece":[185],"helps":[186],"improving":[187],"similarity":[188],"performance.":[190],"addresses":[193],"design":[195],"working":[198],"recognition":[199],"engine":[200],"results":[202],"achieved":[203],"with":[204],"respect":[205],"alluded":[208],"methods.":[209],"A":[210],"test":[211],"database":[212],"consisting":[213],"clips,":[217],"tones,":[219],"sung":[221],"user":[222],"data":[223],"described":[225],"detail.":[227]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
