Back to search

University of Glasgow

Interpreting intermediate feature representations of raw-waveform deep CNNs by sonification

Abstract

dc:description.abstract

The majority of the recent works that address the interpretability of raw waveform based deep neural networks (DNNs) for audio processing focus on interpreting spectral and frequency response information, often limiting to visual and signal theoretic means of interpretation, solely for the first layer. This work proposes sonification, a method to interpret intermediate feature representations of sound event recognition (SER) 1D-convolutional neural networks (1D-CNNs) trained on raw waveforms by mapping these representations back into the discrete-time input signal domain, highlighting substructures in the input that maximally activate a feature map as intelligible acoustic events. Sonification is used to compare supervised and contrastive self-supervised feature representations, observing how the latter learn more acoustically discernible representations, especially in the deeper layers. A metric to quantify acoustic similarity between the interpretations and their corresponding inputs is proposed, and a layer-by-layer analysis of the trained feature representations using this metric supports the observations made.

Degree

thesis:*
Level dc:type.qualificationlevel
MSc(R)
Grantor dc:publisher.institution
University of Glasgow
Year dc:date.issued
2022

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Yadav, Sarthak

Subjects

dc:subject × 1

Rights

Language dc:language
en

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
University of Glasgow
Base URL
theses.gla.ac.uk/cgi/oai2
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Yadav, Sarthak. Interpreting intermediate feature representations of raw-waveform deep CNNs by sonification. MSc(R) thesis, University of Glasgow, 2022. https://doi.org/10.5525/gla.thesis.82820