Boosting the Predictive Accurary of Singer Identification Using Discrete Wavelet Transform For Feature Extraction

no code implementations • 31 Jan 2021 • Victoire Djimna Noyum, Younous Perieukeu Mofenjou, Cyrille Feudjio, Alkan Göktug, Ernest Fokoué

We conclude that, for a dataset of 4 singers and 200 songs, the best identification system consists of the DWT (db4) feature extraction introduced in this work combined with a linear support vector machine for identification resulting in a mean accuracy of 83. 96%.

Singer Identification