STUDENT'S-t MIXTURE MODEL BASED MULTI-INSTRUMENT RECOGNITION IN POLYPHONIC MUSIC

Sundar, Harshavardhan and Ranjani, HG and Sreenivas, TV (2013) STUDENT'S-t MIXTURE MODEL BASED MULTI-INSTRUMENT RECOGNITION IN POLYPHONIC MUSIC. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), MAY 26-31, 2013, Vancouver, BC, Canada, pp. 216-220.

PDF ieee_int_con_aco_spe_sig_pro_216_2013.pdf - Published Version Restricted to Registered users only Download (352kB) | Request a copy

Abstract

We address the problem of multi-instrument recognition in polyphonic music signals. Individual instruments are modeled within a stochastic framework using Student's-t Mixture Models (tMMs). We impose a mixture of these instrument models on the polyphonic signal model. No a priori knowledge is assumed about the number of instruments in the polyphony. The mixture weights are estimated in a latent variable framework from the polyphonic data using an Expectation Maximization (EM) algorithm, derived for the proposed approach. The weights are shown to indicate instrument activity. The output of the algorithm is an Instrument Activity Graph (IAG), using which, it is possible to find out the instruments that are active at a given time. An average F-ratio of 0 : 7 5 is obtained for polyphonies containing 2-5 instruments, on a experimental test set of 8 instruments: clarinet, flute, guitar, harp, mandolin, piano, trombone and violin.

Item Type:	Conference Proceedings
Series.:	International Conference on Acoustics Speech and Signal Processing ICASSP
Publisher:	IEEE
Additional Information:	Copyright for this article belongs to the IEEE, USA
Keywords:	Student's-t Mixture Models; Latent Variable; Polyphony; Instrument Recognition; Instrument Activity Graph
Department/Centre:	Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited:	04 Mar 2014 11:33
Last Modified:	04 Mar 2014 11:34
URI:	http://eprints.iisc.ac.in/id/eprint/48482

Actions (login required)

View Item