A Factored Language Model of Quantized Pitch and Duration.
Xiao Li, Gang Ji, Jeff Bilmes · University of Michigan Library Repository · 2006
This paper investigates a novel statistical approach to music classification that utilizes recent technology developed in the domain of natural language processing.Specifically, we investigate the use of factored language models (FLMs) for the task of producing conditional probability distributions to model origin-specific folk songs.In our model, pitch cluster and quantized duration are employed as the two fundamental factors in a musical unit.The structure of our FLM is empirically chosen from data to minimize perplexity.We apply this collection of FLMs to the task of folk song classification.Our experiments show classification accuracy of 72.5% on a data set of European folk songs from 6 different regions.