Interpretable Convolutional Filters with SincNet

23 Nov 2018Mirco RavanelliYoshua Bengio

Deep learning is currently playing a crucial role toward higher levels of artificial intelligence. This paradigm allows neural networks to learn complex and abstract representations, that are progressively obtained by combining simpler ones... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Distant Speech Recognition DIRHA English WSJ SincNet-Raw waveform Word Error Rate (WER) 38.2 # 3