MIMVOGUE: modeling Indian music using a variable order gapped HMM

Abstract

The computer-assisted music composition is an active research area since mid-1900. In this paper, we have applied the VOGUE model for designing musical sequence of bandish notations of raga Bhairav, a classical Indian music. Variable Order and Gapped hidden Markov model for unstructured elements can capture variable length dependencies with variable gaps in sequential data. In most of raga pattern, a particular pattern repeats itself which may be separated by variable length gaps. VOGUE mines the frequent patterns in raga having different length gaps. These mined patterns are used to model VOGUE for Indian music ragas. Furthermore, we analyzed the benefits of VOGUE model over the standard HMM. To the best of author’s knowledge, this is the very first attempt to model Indian classical music with variable order gapped HMM.