cisc-867 deep learning course project. speech emotion recognition (ser) on ravdess using a lightweight 1d cnn on log-mel-spectrograms, compared against a classical mfcc + svm baseline. optimized for ...
FRS/GMRS and pager show minor confusion (3 FRS→ISM, 2 pager→APRS) due to similar bursty transmission patterns. This is authentic ML behavior reflecting real signal similarity.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results