On Learning Interpretable CNNs with Parametric Modulated Kernel-based Filters

Research output: Chapter in Book/Report/Conference proceedingConference contribution


We investigate the problem of direct waveform modelling using parametric kernel-based filters in a convolutional neural network (CNN) framework, building on SincNet, a CNN employing the cardinal sine (sinc) function to implement learnable bandpass filters. To this end, the general problem of learning a filterbank consisting of modulated kernel-based baseband filters is studied. Compared to standard CNNs, such models have fewer parameters, learn faster, and require less training data. They are also more amenable to human interpretation, paving the way to embedding some perceptual prior knowledge in the architecture. We have investigated the replacement of the rectangular filters of SincNet with triangular, gammatone and Gaussian filters, resulting in higher model flexibility and a reduction to the phone error rate. We also explore the properties of the learned filters learned for TIMIT phone recognition from both perceptual and statistical standpoints. We find that the filters in the first layer, which directly operate on the waveform, are in accord with the prior knowledge utilised in designing and engineering standard filters such as mel-scale triangular filters. That is, the networks learn to pay more attention to perceptually significant spectral neighbourhoods where the data centroid is located, and the variance and Shannon entropy are highest.
Original languageEnglish
Title of host publicationProceedings Interspeech 2019
PublisherInternational Speech Communication Association
Number of pages5
Publication statusPublished - 19 Sep 2019
EventInterspeech 2019 - Graz, Austria
Duration: 15 Sep 201919 Sep 2019

Publication series

PublisherInternational Speech Communication Association
ISSN (Electronic)1990-9772


ConferenceInterspeech 2019
Internet address


  • Interpretable CNN
  • SincNet
  • parametric modulated kernel-based filters
  • speech phone recognition

Fingerprint Dive into the research topics of 'On Learning Interpretable CNNs with Parametric Modulated Kernel-based Filters'. Together they form a unique fingerprint.

Cite this