Using Statistical Modeling, Rate of Change of Pitch and Inter-Onset Interval to Distinguish Between Restful and Restless Ragas

Abstract

Given that the strength of statistics lies in modelling, we are motivated to do a comparative statistical study between two types of ragas, one being aesthetically known to be restful and the other restless in nature. We first try to distinguish these two types through statistical modeling. To substantiate our findings, two more statistical features are considered in the paper to separate the two categories of ragas, namely the rate of change of pitch and inter-onset interval. The experimental results are encouraging.

Keywords

Raga / {Restful, restless} nature / Rate of pitch change / Inter Onset interval / Statistical modeling

References

[1] Holt, C.C.: Forecasting trends and seasonal by exponentially weighted averages. Off. Naval Res. Memorandum 52 (1957). Reprinted in Holt, C. C. (January–March 2004). Forecasting trends and seasonal exponentially weighted averages. Int. J. Forecasting 20(1), 5–10 (2004)

[2] Brown RG. Smoothing Forecasting and Prediction of Discrete Time Series. 1963 Englewood Cliffs: Prentice-all

[3] Chakraborty S, Mazzola G, Tewari S, Patra M. Computational Musicology in Hindustani Music. 2014 Berlin: Springer

[4] Chakraborty, S., Ranganayakulu, R., Chauhan, S., Solanki, S.S., Mahto, K.: A statistical analysis of Raga Ahir Bhairav. J. Music Meaning 8, sec. 4, (2009). http://www.musicandmeaning.net/issues/showArticle.php?artID=8.4

[5] Adiloglu K, Noll T, Obermayer K. A paradigmatic approach to extract the melodic structure of a musical piece. J. New Music Res.. 2006, 35 3 221-236