In a musical signals, the spectral and temporal contents of instruments often overlap. If the number of channels is at least the same as the number of instruments, it is possible to apply statistical tools to highlight the characteristics of each instrument, making their identification possible. However, in the underdetermined case, in which there are fewer channels than sources, the task becomes challenging. One possible way to solve this problem is to seek for regions in the time and/or frequency domains in which the content of a given instrument appears isolated. The strategy presented in this paper explores the spectral disjointness among instruments by identifying isolated partials, from which a number of features are extracted. The information contained in those features, in turn, is used to infer which instrument is more likely to have generated that partial. Hence, the only condition for the method to work is that at least one isolated partial exists for each instrument somewhere in the signal. If several isolated partials are available, the results are summarized into a single, more accurate classification. Experimental results using 25 instruments demonstrate the good discrimination capabilities of the method. © 2010 IEEE.191111122Agostini, G., Longari, M., Pollastri, E., Musical instrument timbres classification with spectral features (2003) EURASIP J. Appl. Signal Process., 2003, pp. 5-14Benetos, E., Kotti, M., Kotropoulos, C., Musical instrument classification using non-negative matrix factorization algorithms and subset feature selection (2006) Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., pp. 221-224Chetry, N., Sandler, M., Linear predictive models for musical instrument identification (2009) Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., pp. 173-176Eronen, A., Klapuri, A., Musical instrument recognition using cepstral coefficients and temporal features (2000) Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., pp. 753-756Essid, S., Richard, G., David, B., Musical instrument recognition by pairwise classification strategies (2006) IEEE Trans. Audio, Speech, Lang. Process., 14 (4), pp. 1401-1412. , JulFanelli, A.M., Caponetti, L., Castellano, G., Buscicchio, C.A., Content-based recognition of musical instruments (2004) Proc. IEEE Int. Symp. Signal Process. Inf. Tech., pp. 361-364Ihara, M., Maeda, S.-I., Ishii, S., Instrument identification in monophonic music using spectral information (2007) Proc. IEEE Int. Symp. Signal Process. Inf. Tech., pp. 595-599Joder, C., Essid, S., Richard, G., Temporal integration for audio classification with application to musical instrument classification (2009) IEEE Trans. Audio, Speech, Lang. Process., 17 (1), pp. 174-186. , JanKrishna, A.G., Sreenivas, T.V., Music instrument recognition: From isolated notes to solo phrases (2004) Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., pp. 265-268Martin, K.D., Kim, Y.E., Musical instrument identification: A pattern-recognition approach (1998) Proc. Meeting Acoust. Soc. Amer.Pruysers, C., Schnapp, J., Kaminskyj, I., Wavelet analysis in musical instrument sound classification (1998) Proc. Int. Symp. Signal Process. Applicat.Brown, J.C., Computer identification of musical instruments using pattern recognition with cepstral coefficients as features (1999) J. Acoust. Soc. Amer., 105, pp. 1933-1941Brown, J.C., Houix, O., McAdams, S., Feature dependence in the automatic identification of musical woodwind instruments (2001) J. Acoust. Soc. Amer., 109, pp. 1064-1072Fragoulis, D., Papaodysseus, C., Exarhos, M., Roussopoulos, G., Panagopoulos, T., Kamarotos, D., Automated classification of piano-guitar notes (2006) IEEE Trans. Audio, Speech, Lang. Process., 14 (3), pp. 1040-1050. , MayBurred, J.J., Robel, A., Sikora, T., Polyphonic musical instrument recognition based on a dynamic model of the spectral envelope (2009) Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., pp. 173-176Jincahitra, P., Polyphonic instrument identification using independent subspace analysis (2004) Proc. IEEE Int. Conf. Multimedia Expo, pp. 1211-1214Kashino, K., Murase, H., A sound source identification system for ensemble music based on template adaptation and music stream extraction (1999) Speech Commun., 27, pp. 337-349Kitahara, T., Goto, M., Komatani, K., Ogata, T., Okuno, H.G., Instrument identification in polyphonic music: Feature weighting to minimize influence of sound overlaps (2007) EURASIP J. Appl. Signal Process., 2007, pp. 1-15Martins, L.G., Burred, J.J., Tzanetakis, G., Lagrange, M., Polyphonic instrument recognition using spectral clustering (2007) Proc. Int. Conf. Music Inf. RetrievalVincent, E., Rodet, X., Instrument identification in solo and ensemble music using independent subspace analysis (2004) Proc. Int. Conf. Music Inf. Retrieval, pp. 576-581Eggink, J., Brown, G.J., Application of missing feature theory to the recognition of musical instruments in polyphonic audio (2003) Proc. Int. Conf. Music Inf. Retrieval, pp. 1-7Eggink, J., Brown, G.J., Instrument recognition in accompanied sonatas and concertos (2004) Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., pp. 217-220Leveau, P., Sodoyer, D., Daudet, L., Automatic instrument recognition in a polyphonic mixture using sparse representations (2007) Proc. Int. Conf. Music Inf. RetrievalEssid, S., Richard, G., David, B., Instrument recognition in polyphonic music based on automatic taxonomies (2006) IEEE Trans. Audio, Speech, Lang. Process., 14 (1), pp. 68-80. , JanSomerville, P., Uitdenbogerd, A.L., Multitimbral musical instrument classification (2008) Proc. Int. Symp. Comp. Science Applic., pp. 269-274Eggink, J., Brown, G.J., A missing feature approach to instrument identification in polyphonic music (2003) Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., pp. 553-556Kostek, B., Musical instrument classification and duet analysis employing music information retrieval techniques (2004) Proc. IEEE, 92 (4), pp. 712-729. , AprThornburg, H., Leistikow, R.J., Berger, J., Melody extraction and musical onset detection via probabilistic models of framewise STFT peak data (2007) IEEE Trans. Audio, Speech, Lang. Process., 15 (4), pp. 1257-1272. , MayHu, G., Wang, D., Auditory segmentation based on onset and offset analysis (2007) IEEE Trans. Audio, Speech, Lang. Process., 15 (2), pp. 396-405. , FebZhou, R., Mattavelli, M., Zoia, G., Music onset detection based on resonator time frequency image (2008) IEEE Trans. Audio, Speech, Lang. Process., 16, pp. 1685-1695Barbedo, J.G.A., Lopes, A., Wolfe, P.J., Empirical methods to determine the number of sources in single-channel musical signals (2009) IEEE Trans. Audio, Speech, Lang. Process., 17 (8), pp. 1435-1444. , NovBarbedo, J.G.A., Lopes, A., Wolfe, P.J., High time-resolution estimation of multiple fundamental frequencies (2007) Proc. Int. Conf. Music Inf. Retrieval, pp. 399-403Rauhala, J., Lehtonen, H.-M., Valimaki, V., Fast automatic inharmonicity estimation algorithm (2007) J. Acoust. Soc. Amer., 121, pp. EL184-EL189Brown, J.C., Frequency ratios of spectral components of musical sounds (1996) J. Acoust. Soc. Amer., 99, pp. 1210-1218Oppenheim, A.V., Schafer, R.W., (1975) Digital Signal Processing, , Englewood Cliffs, NJ: Prentice-HallSmith III, J.O., Spectral Audio Signal Processing, , https://ccrma.stanford.edu/~jos/sasp, Online. AvailableEronen, A., Comparison of features for music instrument recognition (2001) Proc. IEEE Workshop Applicat. Signal Process Audio Acoust., pp. 19-22Every, M.R., Discriminating between pitched sources in music audio (2008) IEEE Trans. Audio, Speech, Lang. Process., 16 (2), pp. 267-277. , FebDeng, J.D., Simmermacher, C., Cranefield, S., A study on feature analysis for musical instrument classification (2008) IEEE Trans. Syst., Man. Cybern. B: Cybern., 38 (2), pp. 429-438. , AprGoto, M., Development of the RWC music database (2004) Proc. Int. Cong. Acoustics, pp. 553-556http://theremin.music.uiowa.edu, University of Iowa Musical Instrument Samples Database. Online. AvailableElliott, C., Attacks and releases as factors in instrument identification (1975) J. Res. Music Educat., 23, pp. 35-40Kendall, R.A., The role of acoustic signal partitions in listener categorization of musical phrases (1986) Music Percep., 4, pp. 185-214Martin, K.D., (1999) Sound-source Recognition: Atheory and Computational Model, , Ph. D. dissertation, Mass. Inst. of Technol., Cambridge, U. KSrinivasan, A., Sullivan, D., Fujinaga, I., Recognition of isolated instrument tones by conservatory students (2002) Proc. Int. Conf. Music Percept. Cogn., pp. 17-21Livshin, A., Rodet, X., The importance of cross database evaluation in sound classification (2003) Proc. Int. Conf. Music Inf. RetrievalEronen, A., (2001) Automatic Musical Instrument Recognition, , Ph. D. dissertation, Tampere Univ. of Technol., Tampere, FinlandEvery, M.R., (2006) Separation of Musical Sources and Structure From Single-channel Polyphonic Recordings, , Ph. D. dissertation, Univ. of York, York, U. KWu, M., Wang, D.L., Brown, G.J., A multi-pitch tracking algorithm for noisy speech (2003) IEEE Trans. Speech Audio Process., 11 (3), pp. 229-241. , May