BasicAudioSignal1DCNN
Basic Audio Signal Processing and 1-D CNN
Audio Library is Librosa and 1-D CNN is done by Keras.
Audio signal features are Zero Crossing Rate (ZCR), Spectral Centroid (SC), and Spectral Roll off (SR).
The dataset is 60 samples of wav files for three classes of musical instruments.
Each sample is one second and each class has 20 samples.