{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:30:36Z","timestamp":1781886636854,"version":"3.54.5"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2012,12,5]],"date-time":"2012-12-05T00:00:00Z","timestamp":1354665600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Multimed Info Retr"],"published-print":{"date-parts":[[2013,3]]},"DOI":"10.1007\/s13735-012-0026-0","type":"journal-article","created":{"date-parts":[[2012,12,4]],"date-time":"2012-12-04T20:30:57Z","timestamp":1354653057000},"page":"45-58","source":"Crossref","is-referenced-by-count":54,"title":["Tonal representations for music retrieval: from version identification to query-by-humming"],"prefix":"10.1007","volume":"2","author":[{"given":"Justin","family":"Salamon","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joan","family":"Serr\u00e0","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emilia","family":"G\u00f3mez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2012,12,5]]},"reference":[{"issue":"2","key":"26_CR1","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1162\/014892604323112257","volume":"28","author":"A Berenzweig","year":"2004","unstructured":"Berenzweig A, Logan B, Ellis DPW, Whitman B (2004) A large scale evaluation of acoustic and subjective music similarity measures. Comput Music J 28(2):63\u201376","journal-title":"Comput Music J"},{"issue":"3","key":"26_CR2","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1145\/328939.328959","volume":"24","author":"T Bozkaya","year":"1999","unstructured":"Bozkaya T, Ozsoyoglu M (1999) Indexing large metric spaces for similarity search queries. ACM Trans Database Syst 24(3):361\u2013404","journal-title":"ACM Trans Database Syst"},{"key":"26_CR3","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1486.001.0001","volume-title":"Auditory scene analysis","author":"A Bregman","year":"1990","unstructured":"Bregman A (1990) Auditory scene analysis. MIT Press, Cambridge"},{"key":"26_CR4","unstructured":"Bryan NJ, Wang G (2011) Musical influence network analysis and rank of sampled-based music. In: Proceedings of the 12th International Society for Music Information Retrieval Conference. Miami, Florida"},{"key":"26_CR5","unstructured":"Dahlhaus C Harmony (2012) Grove Music Online. Oxford Music Online. http:\/\/www.oxfordmusiconline.com\/subscriber\/article\/grove\/mus"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Dannenberg RB, Birmingham WP, Pardo B, Hu N, Meek C, Tzanetakis G (2007) A comparative evaluation of search techniques for query-by-humming usig the musart testbed. J Am Soc Inf Sci Technol","DOI":"10.1002\/asi.20532"},{"key":"26_CR7","unstructured":"Duda A, N\u00fcrnberger A, Stober S (2007) Towards query by singing\/humming on audio databases. In: 8th international conference on music information retrieval. Vienna, Austria"},{"key":"26_CR8","doi-asserted-by":"crossref","first-page":"1493","DOI":"10.1002\/j.1538-7305.1966.tb01706.x","volume":"45","author":"JL Flanagan","year":"1966","unstructured":"Flanagan JL, Golden RM (1966) Phase vocoder. Bell Syst Tech J 45:1493\u20131509","journal-title":"Bell Syst Tech J"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Foucard R, Durrieu JL, Lagrange M, Richard G (2010) Multimodal similarity between musical streams for cover version detection. In: Proceedings of the IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 5514\u20135517","DOI":"10.1109\/ICASSP.2010.5495217"},{"key":"26_CR10","unstructured":"G\u00f3mez E (2006) Tonal description of music audio signals. Ph.D. thesis, Universitat Pompeu Fabra, Barcelona, Spain. http:\/\/mtg.upf.edu\/node\/472"},{"issue":"3","key":"26_CR11","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1287\/ijoc.1040.0126","volume":"18","author":"E G\u00f3mez","year":"2006","unstructured":"G\u00f3mez E (2006) Tonal description of polyphonic audio for music content processing. INFORMS J Comput Spec Cluster Comput Music 18(3):294\u2013304","journal-title":"INFORMS J Comput Spec Cluster Comput Music"},{"key":"26_CR12","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1016\/j.specom.2004.07.001","volume":"43","author":"M Goto","year":"2004","unstructured":"Goto M (2004) A real-time music-scene-description system: predominant-f0 estimation for detecting melody and bass lines in real-world audio signals. Speech Commun 43:311\u2013329","journal-title":"Speech Commun"},{"issue":"1","key":"26_CR13","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1145\/1656274.1656278","volume":"11","author":"M Hall","year":"2009","unstructured":"Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH (2009) The WEKA data mining software: an update. ACM SIGKDD Explor Newsl 11(1):10\u201318","journal-title":"ACM SIGKDD Explor Newsl"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Hanna P, Robine M (2009) Query by tapping system based on alignment algorithm. In: IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 1881\u20131884","DOI":"10.1109\/ICASSP.2009.4959975"},{"issue":"3","key":"26_CR15","doi-asserted-by":"crossref","first-page":"521","DOI":"10.2307\/851047","volume":"20","author":"DL Harwood","year":"1976","unstructured":"Harwood DL (1976) Universals in music: a perspective from cognitive psychology. Ethomusicology 20(3):521\u2013533","journal-title":"Ethomusicology"},{"key":"26_CR16","unstructured":"Hyer B (2012) Tonality. Grove Music Online. Oxford Music Online. http:\/\/www.oxfordmusiconline.com\/subscriber\/article\/grove\/mus"},{"key":"26_CR17","volume-title":"Nonlinear time series analysis","author":"H Kantz","year":"2004","unstructured":"Kantz H, Schreiber T (2004) Nonlinear time series analysis, 2nd edn. Cambridge University Press, Cambridge","edition":"2"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Kotsifakos A, Papapetrou P, Hollm\u00e9n J, Gunopulos D, Athitsos V (2012) A survey of query-by-humming similarity methods. In: Conference on pervasive technologies related to assistive environments (PETRA)","DOI":"10.1145\/2413097.2413104"},{"key":"26_CR19","unstructured":"Liem CCS, Hanjalic A (2009) Cover song retrieval: a comparative study of system component choices. In: Proceedings of the International Society for Music Information Retrieval conference (ISMIR), pp 573\u2013578"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Liu D, Hua KA (2009) Transfer non-metric measures into metric for similarity search. In: 17th ACM international conference on Multimedia, MM \u201909. ACM, New York, pp 693\u2013696. doi: 10.1145\/1631272.1631390","DOI":"10.1145\/1631272.1631390"},{"issue":"4","key":"26_CR21","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1111\/j.1467-9280.1990.tb00213.x","volume":"1","author":"MP Lynch","year":"1990","unstructured":"Lynch MP, Eilers RE, Oller DK, Urbano RC (1990) Innateness, experience and music perception. Psychol Sci 1(4):272\u2013276","journal-title":"Psychol Sci"},{"key":"26_CR22","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to information retrieval","author":"CD Manning","year":"2008","unstructured":"Manning CD, Raghavan P, Sch\u00fctze H (2008) Introduction to information retrieval. Cambridge University Press, Cambridge"},{"issue":"8","key":"26_CR23","doi-asserted-by":"crossref","first-page":"1617","DOI":"10.1109\/TMM.2008.2007293","volume":"10","author":"M Marolt","year":"2008","unstructured":"Marolt M (2008) A mid-level representation for melody-based retrieval in audio collections. IEEE Trans Multimedia 10(8):1617\u20131625","journal-title":"IEEE Trans Multimedia"},{"key":"26_CR24","unstructured":"Ong BS, G\u00f3mez E, Streich S (2006) Automatic extraction of musical structure using pitch class distribution features. In: Workshop on learning the semantics of audio signals (LSAS), pp 53\u201365"},{"key":"26_CR25","volume-title":"Encyclopedia of knowledge management","author":"F Pachet","year":"2005","unstructured":"Pachet F (2005) Knowledge management and musical metadata. In: Schwartz D (ed) Encyclopedia of knowledge management. Idea Group, Harpenden"},{"key":"26_CR26","unstructured":"Pardo B, Birmingham W (2003) Query by humming: how good can it get? In: Workshop on Music Information Retrieval. Toronto, Canada, pp 107\u2013109"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Pardo B, Little D, Jiang R, Livni H, Han J (2008) The vocalsearch music search engine. ACM\/IEEE-CS Joint Conference on Digital Libraries (JCDL)","DOI":"10.1145\/1378889.1378977"},{"key":"26_CR28","unstructured":"Ratzan L (2004) Understanding information systems: what they do and why we need them. American Library Association"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Ravuri S, Ellis DPW (2010) Cover song detection: from high scores to general classification. In: Proceedings of the IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 65\u201368","DOI":"10.1109\/ICASSP.2010.5496214"},{"key":"26_CR30","doi-asserted-by":"crossref","unstructured":"Ryynanen M, Klapuri A (2008) Query by humming of midi and audio using locality sensitive hashing. In: IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 2249\u20132252","DOI":"10.1109\/ICASSP.2008.4518093"},{"key":"26_CR31","unstructured":"Salamon J, G\u00f3mez E (2011) Melody extraction from polyphonic music: Mirex 2011. In: 5th music information retrieval evaluation eXchange (MIREX). extended abstract, Miami, USA"},{"issue":"6","key":"26_CR32","doi-asserted-by":"crossref","first-page":"1759","DOI":"10.1109\/TASL.2012.2188515","volume":"20","author":"J Salamon","year":"2012","unstructured":"Salamon J, G\u00f3mez E (2012) Melody extraction from polyphonic music signals using pitch contour characteristics. IEEE transactions on audio, speech, and language processing 20(6):1759\u20131770","journal-title":"IEEE transactions on audio, speech, and language processing"},{"key":"26_CR33","unstructured":"Salamon J, G\u00f3mez E, Bonada J (2011) Sinusoid extraction and salience function design for predominant melody estimation. In: Proceedings 14th international conference on digital audio effects (DAFX-11). Paris, France"},{"key":"26_CR34","unstructured":"Salamon J, Rohrmeier M (2009) A quantitative evaluation of a two stage retrieval approach for a melodic query by example system. In: 10th International Society for Music Information Retrieval Conference. Kobe, Japan, pp 255\u2013260"},{"key":"26_CR35","unstructured":"Serr\u00e0 J (2011) Identification of versions of the same musical composition by processing audio descriptions. Ph.D. thesis, Universitat Pompeu Fabra, Barcelona, Spain"},{"key":"26_CR36","doi-asserted-by":"crossref","unstructured":"Serr\u00e0 J, G\u00f3mez E, Herrera P (2010) Audio cover song identification and similarity: background, approaches, evaluation, and beyond. In: Ra\u015b ZW, Wieczorkowska AA (eds) Advances in music information retrieval, studies in computational intelligence, vol 274, chap 14. Springer, Berlin, pp 307\u2013332","DOI":"10.1007\/978-3-642-11674-2_14"},{"issue":"4","key":"26_CR37","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1080\/09298210902894085","volume":"37","author":"J Serr\u00e0","year":"2008","unstructured":"Serr\u00e0 J, G\u00f3mez E, Herrera P, Serra X (2008) Statistical analysis of chroma features in western music predicts human judgments of tonality. J New Music Res 37(4):299\u2013309","journal-title":"J New Music Res"},{"issue":"2","key":"26_CR38","first-page":"514","volume":"20","author":"J Serr\u00e0","year":"2012","unstructured":"Serr\u00e0 J, Kantz H, Serra X, Andrzejak RG (2012) Predictability of music descriptor time series and its application to cover song detection. IEEE Trans Audio Speech Language Process 20(2):514\u2013525","journal-title":"IEEE Trans Audio Speech Language Process"},{"issue":"9","key":"26_CR39","doi-asserted-by":"crossref","first-page":"093017","DOI":"10.1088\/1367-2630\/11\/9\/093017","volume":"11","author":"J Serr\u00e0","year":"2009","unstructured":"Serr\u00e0 J, Serra X, Andrzejak RG (2009) Cross recurrence quantification for cover song identification. New J Phys 11(9):093017","journal-title":"New J Phys"},{"key":"26_CR40","unstructured":"Skalak M, Han J, Pardo B (2008) Speeding melody search with vantage point trees. In: 9th International Society for Music Information Retrieval Conference, Philadelphia, USA"},{"key":"26_CR41","unstructured":"Song J, Bae SY, Yoon K (2002) Mid-level music melody representation of polyphonic audio for query-by-humming system. In: 3rd international conference on music information retrieval, Paris, France"},{"issue":"6","key":"26_CR42","first-page":"1669","volume":"24","author":"WH Tsai","year":"2008","unstructured":"Tsai WH, Yu HM, Wang HM (2008) Using the similarity of main melodies to identify cover versions of popular songs for music document retrieval. J Inf Sci Eng 24(6):1669\u20131687","journal-title":"J Inf Sci Eng"},{"key":"26_CR43","unstructured":"Typke R (2007) Music retrieval based on melodic similarity. Ph.D. thesis, Utrecht University, The Netherlands"},{"key":"26_CR44","unstructured":"Typke R, Walczak-Typke A (2008) A tunneling-vantage indexing method for non-metrics. In: 9th international conference on music information retrieval. Philadelphia, USA, pp 683\u2013688"},{"key":"26_CR45","unstructured":"Vickers E (2001) Automatic long-term loudness and dynamics matching. In: Proceedings of the Conversion of the Audio Engineering Society (AES)"},{"key":"26_CR46","volume-title":"All of statistics: a concise course in statistical inference","author":"L Wasserman","year":"2003","unstructured":"Wasserman L (2003) All of statistics: a concise course in statistical inference. Springer, Berlin"},{"key":"26_CR47","volume-title":"Data mining: practical machine learning tools and techniques","author":"IH Witten","year":"2005","unstructured":"Witten IH, Frank E (2005) Data mining: practical machine learning tools and techniques, 2nd edn. Morgan Kaufmann, Waltham","edition":"2"}],"container-title":["International Journal of Multimedia Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-012-0026-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13735-012-0026-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-012-0026-0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,6]],"date-time":"2019-07-06T16:05:05Z","timestamp":1562429105000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13735-012-0026-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,12,5]]},"references-count":47,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2013,3]]}},"alternative-id":["26"],"URL":"https:\/\/doi.org\/10.1007\/s13735-012-0026-0","relation":{},"ISSN":["2192-6611","2192-662X"],"issn-type":[{"value":"2192-6611","type":"print"},{"value":"2192-662X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,12,5]]}}}