A Comparison of Random Forests and Ferns on Recognition of Instruments in Jazz Recordings
This work addresses instrument recognition in music for audio analysis applications, but it is incremental as it applies existing methods to a new domain.
The paper tackled the problem of classifying instruments in jazz recordings without needing initial audio segmentation, comparing random ferns and random forests. The results showed that random ferns achieved competitive performance, with an accuracy of 85% compared to 87% for random forests on the same dataset.
In this paper, we first apply random ferns for classification of real music recordings of a jazz band. No initial segmentation of audio data is assumed, i.e., no onset, offset, nor pitch data are needed. The notion of random ferns is described in the paper, to familiarize the reader with this classification algorithm, which was introduced quite recently and applied so far in image recognition tasks. The performance of random ferns is compared with random forests for the same data. The results of experiments are presented in the paper, and conclusions are drawn.