Spectrogram based features selection using multiple kernel learning for speech/music discrimination.

Autor: Nilufar, Sharmin, Ray, Nilanjan, Molla, M. K. Islam, Hirose, Keikichi

Publikováno v: 2012 IEEE International Conference on Acoustics, Speech & Signal Processing (ICASSP); 1/ 1/2012, p501-504, 4p