White Rose University Consortium logo
University of Leeds logo University of Sheffield logo York University logo

Masked Conditional Neural Networks for Sound Recognition

Medhat, Fady (2018) Masked Conditional Neural Networks for Sound Recognition. PhD thesis, University of York.

This is the latest version of this item.

[img] Text
Masked Conditional Neural Networks for Sound Recognition.pdf - Examined Thesis (PDF)
Restricted until 31 December 2020.

Abstract

Sound recognition has been studied for decades to grant machines the human hearing ability. The advances in this field help in a range of applications, from industrial ones such as fault detection in machines and noise monitoring to household applications such as surveillance and hearing aids. The problem of sound recognition like any pattern recognition task involves the reliability of the extracted features and the recognition model. The problem has been approached through decades of crafted features used collaboratively with models based on neural networks or statistical models such as Gaussian Mixtures and Hidden Markov models. Neural networks are currently being considered as a method to automate the feature extraction stage together with the already incorporated role of recognition. The performance of such models is approaching handcrafted features. Current neural network based models are not primarily designed for the nature of the sound signal, which may not optimally harness distinctive properties of the signal. This thesis proposes neural network models that exploit the nature of the time-frequency representation of the sound signal. We propose the ConditionaL Neural Network (CLNN) and the Masked ConditionaL Neural Network (MCLNN). The CLNN is designed to account for the temporal dimension of a signal and behaves as the framework for the MCLNN. The MCLNN allows a filterbank-like behaviour to be embedded within the network using a specially designed binary mask. The masking subdivides the frequency range of a signal into bands and allows concurrent consideration of different feature combinations analogous to the manual handcrafting of the optimum set of features for a recognition task. The proposed models have been evaluated through an extensive set of experiments using a range of publicly available datasets of music genres and environmental sounds, where they surpass state-of-the-art Convolutional Neural Networks and several hand-crafted attempts.

Item Type: Thesis (PhD)
Related URLs:
Academic Units: The University of York > Electronics (York)
Depositing User: Fady Medhat
Date Deposited: 04 Dec 2018 11:03
Last Modified: 04 Dec 2018 11:03
URI: http://etheses.whiterose.ac.uk/id/eprint/21594

Available Versions of this Item

  • Masked Conditional Neural Networks for Sound Recognition. (deposited 04 Dec 2018 11:03) [Currently Displayed]

You can contact us about this thesis. If you need to make a general enquiry, please see the Contact us page.

Actions (repository staff only: login required)