Sound event detection for music signals using gaussian processes
Keywords:
Gaussian processes classification, supervised machine learning, spectrogram, event detection, music signals.
Abstract
In this paper we present a new methodology for detecting sound events in music signals using Gaussian Processes. Our method firstly takes a time-frequency representation, i.e. the spectrogram, of the input audio signal. Secondly the spectrogram dimension is reduced translating the linear Hertz frequency scale into the logarithmic Mel frequency scale using a triangular filter bank. Finally every short-time spectrum, i.e. every Mel spectrogram column, is classified as “Event” or “Not Event” by a Gaussian Processes Classifier. We compare our method with other event detection techniques widely used. To do so, we use MATLAB® to program each technique and test them using two datasets of music with different levels of complexity. Results show that the new methodology outperforms the standard approaches, getting an improvement by about 1.66 % on the dataset one and 0.45 % on the dataset two in terms of F-measure.
How to Cite
[1]
P. A. Alvarado-Durán, M. A. Álvarez-López, and Álvaro A. Orozco-Gutiérrez, “Sound event detection for music signals using gaussian processes”, TecnoL., no. 31, pp. 93–122, Nov. 2011.
Downloads
Download data is not yet available.