2 code implementations • 25 May 2018 • Fady Medhat, David Chesmore, John Robinson
We have evaluated the MCLNN performance using the Urbansound8k dataset of environmental sounds.
1 code implementation • 8 Apr 2018 • Fady Medhat, David Chesmore, John Robinson
Neural network based architectures used for sound recognition are usually adapted from other application domains, which may not harness sound related properties.
1 code implementation • 6 Mar 2018 • Fady Medhat, David Chesmore, John Robinson
We present the ConditionaL Neural Network (CLNN) and the Masked ConditionaL Neural Network (MCLNN) designed for temporal signal recognition.
1 code implementation • 18 Feb 2018 • Fady Medhat, David Chesmore, John Robinson
MCLNN has achieved accuracies that are competitive to state-of-the-art handcrafted attempts in addition to models based on Convolutional Neural Networks.
1 code implementation • 15 Feb 2018 • Fady Medhat, David Chesmore, John Robinson
Deep neural network architectures designed for application domains other than sound, especially image recognition, may not optimally harness the time-frequency representation when adapted to the sound recognition problem.
1 code implementation • 7 Feb 2018 • Fady Medhat, David Chesmore, John Robinson
Automatic feature extraction using neural networks has accomplished remarkable success for images, but for sound recognition, these models are usually modified to fit the nature of the multi-dimensional temporal representation of the audio signal in spectrograms.
1 code implementation • 16 Jan 2018 • Fady Medhat, David Chesmore, John Robinson
Neural network based architectures used for sound recognition are usually adapted from other application domains such as image recognition, which may not harness the time-frequency representation of a signal.