{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T05:12:16Z","timestamp":1740028336398,"version":"3.37.3"},"publisher-location":"Berlin, Heidelberg","reference-count":66,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642116735"},{"type":"electronic","value":"9783642116742"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-11674-2_4","type":"book-chapter","created":{"date-parts":[[2010,3,10]],"date-time":"2010-03-10T10:30:47Z","timestamp":1268217047000},"page":"65-91","source":"Crossref","is-referenced-by-count":3,"title":["Mid-level Representations of Musical Audio Signals for Music Information Retrieval"],"prefix":"10.1007","author":[{"given":"Tetsuro","family":"Kitahara","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"4_CR1","unstructured":"Good, M.: MusicXML: An internet-friendly format for sheet music. In: The XML 2001 Conf. Proc. (2001)"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Bellini, P., Nesi, P.: WEDELMUSIC format: An XML music notation format for emerging applications. In: Proc. Int\u2019l Conf.WEB Delivering of Music, pp. 79\u201386 (2001)","DOI":"10.1109\/WDM.2001.990161"},{"volume-title":"Signal Processing Methods for Music Transcription","year":"2006","key":"4_CR3","unstructured":"Klapuri, A., Davy, M. (eds.): Signal Processing Methods for Music Transcription. Springer, Heidelberg (2006)"},{"key":"4_CR4","first-page":"257","volume-title":"Computational auditory scene analysis","author":"D. Ellis","year":"1998","unstructured":"Ellis, D., Rosenthal, D.F.: Mid-level representations for computational auditory scene analysis. In: Rosenthal, D.F., Okuno, H.G. (eds.) Computational auditory scene analysis, ch. 17, pp. 257\u2013272. Lawrence Erlbaum, Mahwah (1998)"},{"issue":"4","key":"4_CR5","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1016\/j.specom.2004.07.001","volume":"43","author":"M. Goto","year":"2004","unstructured":"Goto, M.: A real-time music-scene-description system: Predominant-F0 estimation for detecting melody and bass lines in real-world audio signals. Speech Comm.\u00a043(4), 311\u2013329 (2004)","journal-title":"Speech Comm."},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Goto, M.: A robust predominant-f0 estimation method for real-time detection of melody and bass lines in CD recordings. In: Proc. ICASSP, vol.\u00a0II, pp. 757\u2013760 (2000)","DOI":"10.1109\/ICASSP.2000.859070"},{"key":"4_CR7","unstructured":"Marolt, M.: A mid-level melody-based representation for calculating audio similarity. In: Proc. ISMIR (2006)"},{"key":"4_CR8","unstructured":"Sagayama, S., Takahashi, K., Kameoka, H., Nishimoto, T.: Specmurt anasylis: A piano-roll-visualization of polyphonic music by deconvolution of log-frequency spectrum. In: Proc. SAPA (2004)"},{"key":"4_CR9","unstructured":"Abdallah, S.A., Plumbley, M.D.: Polyphonic music transcription by non-negative sparse coding of power spectra. In: Proc. ISMIR, pp. 318\u2013325 (2004)"},{"key":"4_CR10","volume-title":"Signal Processing Methods for Music Transcription","author":"T. Virtanen","year":"2006","unstructured":"Virtanen, T.: Unsupervised learning methods for source separation in monaural music signals. In: Klapuri, A., Davy, M. (eds.) Signal Processing Methods for Music Transcription. Springer, Heidelberg (2006)"},{"key":"4_CR11","unstructured":"Saito, S., Kameoka, H., Nishimoto, T., Sagamaya, S.: Specmurt analysis of multi-pitch music signals with adaptive estimation of common harmonic structure. In: Proc. ISMIR, pp. 84\u201391 (2005)"},{"issue":"1","key":"4_CR12","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1109\/TASL.2007.910786","volume":"16","author":"P. Leveau","year":"2008","unstructured":"Leveau, P., Vincent, E., Richard, G., Daudet, L.: Instrument-specific harmonic atoms for mid-level music representation. IEEE Trans., Audio, Speech, Lang., Process.\u00a016(1), 116\u2013128 (2008)","journal-title":"IEEE Trans., Audio, Speech, Lang., Process."},{"key":"4_CR13","unstructured":"Fujishima, T.: Realtime chord recognition of musical sound: a system using common Lisp music. In: Proc. ICMC, pp. 464\u2013467 (1999)"},{"key":"4_CR14","unstructured":"Sheh, A., Ellis, D.P.W.: Chord segmentation and recognition using EM-trained hidden Markov models. In: Proc. ISMIR (2003)"},{"key":"4_CR15","unstructured":"Yoshioka, T., Kitahara, T., Komatani, K., Ogata, T., Okuno, H.G.: Automatic chord transcription with concurrent recognition of chord symbols and boundaries. In: Proc. ISMIR, pp. 100\u2013105 (2004)"},{"key":"4_CR16","unstructured":"Bello, J.P., Pickens, J.: A robust mid-level representation for harmonic content in music signals. In: Proc. ISMIR (2005)"},{"key":"4_CR17","unstructured":"Cabral, G., Pachet, F., Briot, J.-P.: Automatic X traditional descriptor extraction: The case of chord recognition. In: Proc. ISMIR (2005)"},{"key":"4_CR18","unstructured":"Lee, K., Slaney, M.: A unified system for chord transcription and key extraction using hidden Markov models. In: Proc. ISMIR (2007)"},{"key":"4_CR19","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1007\/0-387-32845-9_11","volume-title":"Signal Processing Method for Music Transcription","author":"M. Goto","year":"2006","unstructured":"Goto, M.: Music scene description. In: Klapuri, A., Davy, M. (eds.) Signal Processing Method for Music Transcription, ch. 11, pp. 327\u2013359. Springer, Heidelberg (2006)"},{"issue":"12","key":"4_CR20","doi-asserted-by":"publisher","first-page":"2346","DOI":"10.1121\/1.1919362","volume":"36","author":"R.N. Shepard","year":"1964","unstructured":"Shepard, R.N.: Circularity in judgments of relative pitch. J. Acoust. Soc. Am.\u00a036(12), 2346\u20132353 (1964)","journal-title":"J. Acoust. Soc. Am."},{"key":"4_CR21","unstructured":"Fujisawa, T.X., Tani, M., Nagata, N., Katayose, H.: Music mood visualization based on quantitative model of chord perception. IPSJ Journal\u00a050(3) (2009) (in Japanese)"},{"issue":"2","key":"4_CR22","doi-asserted-by":"crossref","first-page":"106","DOI":"10.18061\/1811\/24080","volume":"1","author":"N.D. Cook","year":"2006","unstructured":"Cook, N.D., Fujisawa, T.X.: The psychophysics of harmony perception: Harmony is a three-tone phenomenon. Empirical Musicology Review\u00a01(2), 106\u2013126 (2006)","journal-title":"Empirical Musicology Review"},{"issue":"5","key":"4_CR23","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1109\/TSA.2002.800560","volume":"10","author":"G. Tzanetakis","year":"2002","unstructured":"Tzanetakis, G., Cook, P.: Musical genre classification of audio signals. IEEE Trans. Speech Audio Process.\u00a010(5), 293\u2013302 (2002)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Lu, L., Liu, D., Zhang, H.-J.: Automatic mood detection and tracking of music audio signals. IEEE Trans. Audio, Speech, Lang. Process.\u00a014(1) (2006)","DOI":"10.1109\/TSA.2005.860344"},{"key":"4_CR25","unstructured":"Pampalk, E.: Computational Models of Music Similarity and their Application in Music Information Retrieval. PhD thesis, Technischen Universitat Wien (2006)"},{"key":"4_CR26","unstructured":"Aucouturier, J.-J., Pachet, F.: Improving timbre similarity: How high\u2019s the sky? Journal of Negative Results in Speech and Audio Sciences (2004)"},{"key":"4_CR27","volume-title":"Signal Processing Methods for Music Transcription","author":"P. Herrera-Boyer","year":"2006","unstructured":"Herrera-Boyer, P., Klapuri, A., Davy, M.: Automatic classification of pitched instrument sounds. In: Klapuri, A., Davy, M. (eds.) Signal Processing Methods for Music Transcription. Springer, Heidelberg (2006)"},{"key":"4_CR28","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1486.001.0001","volume-title":"Auditory Scene Analysis: The Perceptual Organization of Sound","author":"A.S. Bregman","year":"1990","unstructured":"Bregman, A.S.: Auditory Scene Analysis: The Perceptual Organization of Sound. MIT Press, Cambridge (1990)"},{"issue":"11","key":"4_CR29","first-page":"823","volume":"49","author":"S. Namba","year":"1993","unstructured":"Namba, S.: Definition of timbre. J. Acoust. Soc. Jpn.\u00a049(11), 823\u2013831 (1993) (in Japanese)","journal-title":"J. Acoust. Soc. Jpn."},{"key":"4_CR30","unstructured":"Martin, K.D.: Sound-Source Recognition: A Theory and Computational Model. PhD thesis, MIT (1999)"},{"issue":"3","key":"4_CR31","doi-asserted-by":"publisher","first-page":"1933","DOI":"10.1121\/1.426728","volume":"103","author":"J.C. Brown","year":"1999","unstructured":"Brown, J.C.: Computer identification of musical instruments using pattern recognition with cepstral coefficients as features. J. Acoust. Soc. Am.\u00a0103(3), 1933\u20131941 (1999)","journal-title":"J. Acoust. Soc. Am."},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Eronen, A., Klapuri, A.: Musical instrument recognition using cepstral coefficients and temporal features. In: Proc. ICASSP, pp. 735\u2013756 (2000)","DOI":"10.1109\/ICASSP.2000.859069"},{"key":"4_CR33","unstructured":"Fujinaga, I., MacMillan, K.: Realtime recognition of orchestral instruments. In: Proc. ICMC, pp. 141\u2013143 (2000)"},{"key":"4_CR34","unstructured":"Marques, J., Moreno, P.J.: A study of musical instrument classification using Gaussian mixture models and support vector machines. CRL Technical Report Series CRL\/4, Compaq Cambridge Research Laboratory (1999)"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Kitahara, T., Goto, M., Okuno, H.G.: Musical instrument identification based on F0-dependent multivariate normal distribution. In: Proc. ICASSP, vol.\u00a0V, pp. 421\u2013424 (2003)","DOI":"10.1109\/ICME.2003.1221335"},{"key":"4_CR36","unstructured":"Livshin, A.A., Peeters, G., Rodet, X.: Studies and improvements in automatic classification of musical sound samples. In: Proc. ICMC, pp. 171\u2013174 (2003)"},{"issue":"4","key":"4_CR37","doi-asserted-by":"publisher","first-page":"1401","DOI":"10.1109\/TSA.2005.860842","volume":"14","author":"S. Essid","year":"2006","unstructured":"Essid, S., Richard, G., David, B.: Musical instrument recognition by pairwise classification strategies. IEEE Trans. Audio, Speech, Lang. Process.\u00a014(4), 1401\u20131412 (2006)","journal-title":"IEEE Trans. Audio, Speech, Lang. Process."},{"key":"4_CR38","first-page":"115","volume-title":"Computational Auditory Scene Analysis","author":"K. Kashino","year":"1998","unstructured":"Kashino, K., Nakadai, K., Kinoshita, T., Tanaka, H.: Application of the Bayesian probability network to music scene analysis. In: Rosenthal, D.F., Okuno, H.G. (eds.) Computational Auditory Scene Analysis, pp. 115\u2013137. Lawrence Erlbaum Associates, Mahwah (1998)"},{"key":"4_CR39","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/S0167-6393(98)00078-8","volume":"27","author":"K. Kashino","year":"1999","unstructured":"Kashino, K., Murase, H.: A sound source identification system for ensemble music based on template adaptation and music stream extraction. Speech Comm.\u00a027, 337\u2013349 (1999)","journal-title":"Speech Comm."},{"key":"4_CR40","unstructured":"Kinoshita, T., Sakai, S., Tanaka, H.: Musical sound source identification based on frequency component adaptation. In: Proc. IJCAI CASA Workshop, pp. 18\u201324 (1999)"},{"key":"4_CR41","doi-asserted-by":"crossref","unstructured":"Eggink, J., Brown, G.J.: A missing feature approach to instrument identification in polyphonic music. In: Proc. ICASSP, vol.\u00a0V, pp. 553\u2013556 (2003)","DOI":"10.1109\/ICASSP.2003.1200029"},{"key":"4_CR42","unstructured":"Eggink, J., Brown, G.J.: Application of missing feature theory to the recognition of musical instruments in polyphonic audio. In: Proc. ISMIR (2003)"},{"key":"4_CR43","unstructured":"Vincent, E., Rodet, X.: Instrument identification in solo and ensemble music using independent subspace analysis. In: Proc. ISMIR, pp. 576\u2013581 (2004)"},{"issue":"1","key":"4_CR44","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1109\/TSA.2005.860351","volume":"14","author":"S. Essid","year":"2006","unstructured":"Essid, S., Richard, G., David, B.: Instrument recognition in polyphonic music based on automatic taxonomies. IEEE Trans. Audio, Speech, Lang. Process.\u00a014(1), 68\u201380 (2006)","journal-title":"IEEE Trans. Audio, Speech, Lang. Process."},{"issue":"51979","key":"4_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2007\/51979","volume":"2007","author":"T. Kitahara","year":"2007","unstructured":"Kitahara, T., Goto, M., Komatani, K., Ogata, T., Okuno, H.G.: Instrument identification in polyphonic music: Feature weighting to minimize influence of sound overlaps. EURAIP J. Adv. Signal Processing\u00a02007(51979), 1\u201315 (2007)","journal-title":"EURAIP J. Adv. Signal Processing"},{"key":"4_CR46","doi-asserted-by":"crossref","unstructured":"Kitahara, T., Goto, M., Komatani, K., Ogata, T., Okuno, H.G.: Instrogram: A new musical instrument recognition technique without using onset detection nor F0 estimation. In: Proc. ICASSP, vol.\u00a0V, pp. 229\u2013232 (2006)","DOI":"10.1109\/ICASSP.2006.1661254"},{"issue":"1","key":"4_CR47","first-page":"214","volume":"48","author":"T. Kitahara","year":"2007","unstructured":"Kitahara, T., Goto, M., Komatani, K., Ogata, T., Okuno, H.G.: Instrogram: Probabilistic representation of instrument existence for polyphonic music. IPSJ Journal\u00a048(1), 214\u2013226 (2007); (also published in IPSJ Digital Courier, vol.3, pp.1\u201313)","journal-title":"IPSJ Journal"},{"key":"4_CR48","unstructured":"Kitahara, T.: Computational Musical Instrument Recognition and Its Application to Content-based Music Information Retrieval. PhD thesis, Kyoto University (2006)"},{"key":"4_CR49","unstructured":"Tzanetakis, G.: Manipulation, Analysis and Retrieval Systems for Audio Signals. PhD thesis, Princeton University (2002)"},{"issue":"5","key":"4_CR50","doi-asserted-by":"publisher","first-page":"1035","DOI":"10.1109\/TSA.2005.851998","volume":"13","author":"J.P. Bello","year":"2005","unstructured":"Bello, J.P., Daudet, L., Abdallah, S., Duxbury, C., Davies, M., Sandler, M.B.: A tutorial on onset detection in music signal. IEEE Trans. Audio, Speech, Lang. Process.\u00a013(5), 1035\u20131047 (2005)","journal-title":"IEEE Trans. Audio, Speech, Lang. Process."},{"issue":"2","key":"4_CR51","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1076\/jnmr.30.2.159.7114","volume":"30","author":"M. Goto","year":"2001","unstructured":"Goto, M.: An audio-based real-time beat tracking system for music with or without drums. J. New Music Res.\u00a030(2), 159\u2013171 (2001)","journal-title":"J. New Music Res."},{"key":"4_CR52","unstructured":"Davies, M.E.P., Plumbley, M.D.: Comparing mid-level representations for audio based beat tracking. In: Proc. DMRN Summer Conf., pp. 36\u201341 (2005)"},{"key":"4_CR53","unstructured":"Dixon, S., Pampalk, E., Widmer, G.: Classification of dance music by periodicity patterns. In: Proc. ISMIR (2003)"},{"key":"4_CR54","unstructured":"Dixon, S., Gouyon, F., Widmer, G.: Towards characteristics of music via rhythmic patterns. In: Proc. ISMIR, pp. 509\u2013516 (2004)"},{"key":"4_CR55","unstructured":"Paulus, J., Klapuri, A.: Measuring the similarity of rhythmic patterns. In: Proc. ISMIR (2002)"},{"key":"4_CR56","doi-asserted-by":"crossref","unstructured":"Tsunoo, E., Ono, N., Sagayama, S.: Rhythm map: Extraction of unit rhythmic patterns and analysis of rhythmic structure from music acoustic signals. In: Proc. ICASSP, pp. 185\u2013188 (2009)","DOI":"10.1109\/ICASSP.2009.4959551"},{"issue":"1","key":"4_CR57","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1162\/comj.2005.29.1.34","volume":"29","author":"F. Gouyon","year":"2005","unstructured":"Gouyon, F., Dixon, S.: A review of automatic rhythm description systems. Computer Music Journal\u00a029(1), 34\u201354 (2005)","journal-title":"Computer Music Journal"},{"issue":"2","key":"4_CR58","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"L.R. Rabiner","year":"1989","unstructured":"Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE\u00a077(2), 257\u2013286 (1989)","journal-title":"Proc. IEEE"},{"key":"4_CR59","unstructured":"Eggink, J., Brown, G.J.: Extracting melody lines from complex audio. In: Proc. ISMIR, pp. 84\u201391 (2004)"},{"key":"4_CR60","unstructured":"Totani, N., Kitahara, T., Katayose, H.: Music player with music thumbnailing and playlist generation functions based on instrumentation. In: Proc. Interaction (2008) (in Japanese)"},{"key":"4_CR61","doi-asserted-by":"crossref","unstructured":"Itoyama, K., Goto, M., Komatani, K., Ogata, T., Okuno, H.G.: Integration and adaptation of harmonic and inharmonic models for separating polyphonic musical signals. In: Proc. ICASSP, vol.\u00a0I (2007)","DOI":"10.1109\/ICASSP.2007.366615"},{"key":"4_CR62","first-page":"251","volume-title":"Computational Auditory Scene Analysis","author":"M. Goto","year":"2006","unstructured":"Goto, M.: Analysis of musical audio signals. In: Wang, D., Brown, G.J. (eds.) Computational Auditory Scene Analysis, ch. 8, pp. 251\u2013295. Wiley Interscience, Hoboken (2006)"},{"key":"4_CR63","unstructured":"Gomez, E., Bonada, J.: Tonality visualization of polyphonic audio. In: Proc. ICMC (2005)"},{"key":"4_CR64","unstructured":"Mardirossian, A., Chew, E.: Visualizing music: Tonal progressions and distributions. In: Proc. ISMIR (2007)"},{"key":"4_CR65","unstructured":"Yoshii, K., Goto, M.: Music thumbniler: Visualizing musical pieces in thumbnail images based on acoustic features. In: Proc. ISMIR, pp. 212\u2013216 (2008)"},{"key":"4_CR66","doi-asserted-by":"publisher","DOI":"10.1002\/0470093366","volume-title":"MPEG-7 Audio and Beyond","author":"H.-G. Kimi","year":"2005","unstructured":"Kimi, H.-G., Moreau, N., Sikora, T.: MPEG-7 Audio and Beyond. Wiley, Chichester (2005)"}],"container-title":["Studies in Computational Intelligence","Advances in Music Information Retrieval"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-11674-2_4.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,19]],"date-time":"2025-02-19T10:51:06Z","timestamp":1739962266000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-11674-2_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642116735","9783642116742"],"references-count":66,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-11674-2_4","relation":{},"ISSN":["1860-949X","1860-9503"],"issn-type":[{"type":"print","value":"1860-949X"},{"type":"electronic","value":"1860-9503"}],"subject":[],"published":{"date-parts":[[2010]]}}}