Interpretable Convolutional Filters with SincNet
This work addresses the problem of interpretability in deep learning for speech processing, offering a more explainable model for researchers and practitioners, though it is incremental in improving existing CNN methods.
The authors tackled the lack of interpretability in neural networks by proposing SincNet, a CNN that uses parametrized sinc functions to learn meaningful filters from raw speech waveforms, resulting in faster convergence and better performance in speaker and speech recognition tasks.
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. Nevertheless, the internal "black-box" representations automatically discovered by current neural architectures often suffer from a lack of interpretability, making of primary interest the study of explainable machine learning techniques. This paper summarizes our recent efforts to develop a more interpretable neural model for directly processing speech from the raw waveform. In particular, we propose SincNet, a novel Convolutional Neural Network (CNN) that encourages the first layer to discover more meaningful filters by exploiting parametrized sinc functions. In contrast to standard CNNs, which learn all the elements of each filter, only low and high cutoff frequencies of band-pass filters are directly learned from data. This inductive bias offers a very compact way to derive a customized filter-bank front-end, that only depends on some parameters with a clear physical meaning. Our experiments, conducted on both speaker and speech recognition, show that the proposed architecture converges faster, performs better, and is more interpretable than standard CNNs.