Classification of Chinese Popular Songs Using a Fusion Scheme of GMM Model Estimate and Formant Feature Analysis

Abstract

In this paper, a fusion scheme that combines Gaussian mixture model (GMM) calculations and formant feature analysis, called GMM-Formant, is proposed for classification of Chinese popular songs. Generally, automatic classification of popular music could be performed by two main categories of techniques, model-based and feature-based approaches. In model-based classification techniques, GMM is widely used for its simplicity. In feature-based music recognition, the formant parameter is an important acoustic feature for evaluation. The proposed GMM-Formant method takes use of linear interpolation for combining GMM likelihood estimates and formant evaluation results appropriately. GMM-Formant will effectively adjust the likelihood score, which is derived from GMM calculations, by referring to certain degree of formant feature evaluation outcomes. By considering both model-based and feature-based techniques for song classification, GMM-Formant provides a more reliable recognition classification result and therefore will maintain a satisfactory performance in recognition accuracy. Experimental results obtained from a musical data set of numerous Chinese popular songs show the superiority of the proposed GMM-Formant. Keywords: Song classification; Gaussian mixture model; Formant feature; GMM-Formant.