Assignment on Speech Recognition Using Shallow Neural Network Classification

Running head: Speech Recognition Using Shallow Neural Network Classification
Speech Recognition Using Shallow Neural Network Classification
Name of the Student
Name of the University
Author Note

Speech Recognition Using Shallow Neural Network Classification1
Table of Contents
Introduction:...............................................................................................................................2
Problem definition:.....................................................................................................................3
Methodology:.............................................................................................................................3
Experiments and discussion:..................................................................................................5
Bayesian regularization algorithm:........................................................................................6
MATLAB code:.....................................................................................................................9
Neural network architecture view:.......................................................................................11
Network training summary:.................................................................................................11
Plot of training state:............................................................................................................12
Error histogram for test set:..................................................................................................13
ROC plot for test classes:.....................................................................................................14
Plot of confusion matrix:......................................................................................................15
Conclusion:..............................................................................................................................16
References:...............................................................................................................................17

Speech Recognition Using Shallow Neural Network Classification2
Introduction:
Speech recognition is a subfield of computer linguistics by which methodologies are
developed by which enables the machines to recognize the spoken language by human by
converting into text. This is also known as the automatic speech recognition, speech to text
conversion or computer speech recognition. The typical speech recognition works by training
a machine by isolated words or vocabulary as spoken by a person with proper accent. The
system typically analyse the voice of the particular person and then fine tune’s voice for
increasing the accuracy of recognition. This type of speech recognition system is known as
speaker dependent speech recognition where a sample voice is used for training and the
systems with no training voice are known as speaker independent speech recognition system
(Yu and Deng 2016). There are different applications of speech recognition that includes
voice user interfaces like voice dialling, call routing, domotic appliance control and key word
searching. However, in this particular research a different type of speech recognition
application is performed where the by different attributes of speech a person is identified as a
healthy or diseased. In particular the recognition software will be able to recognize when a
diseased person (for a particular disease) speaking to the system by analysing its attributes or
when a healthy person is speaking. Now, instead of considering multiple disease detection the
software will be implemented for only one disease which is chosen to be Parkinson’s disease
where the patient goes through voice change with other change in physical attribute change.
Hence, for this project a relevant data will be used that contains the voice sample attributes of
Parkinson’s disease patients and voice sample of healthy patient which will be analysed using
neural networks in the software that outputs whether a person/s is diseased or normal. Hence,
this is a speaker dependent speech recognition system where the voice sample of healthy and
diseased patients will be used for training the algorithm with neural network and then will be
tested on a set of people combining both healthy and diseased subjects (Archive.ics.uci.edu.

Speech Recognition Using Shallow Neural Network Classification3
2020). Now, for a better version of classification with increased accuracy of prediction,
artificial neural networks are used and thus in this project the identification of the subjects by
analysing speech samples is performed with shallow neural network with customized
parameters and training algorithm. A neural network is basically a network of nodes or
artificial neurons than are originally inspired from the pattern recognition ability of neural
network in the human brain. The neural network learns to perform the tasks by considering
some examples which are the provided data to the network. There are no rules specified in
the networks to the perform tasks but as they learn the weights of the different interconnected
nodes are updated. The weights of the neurons are updated by ‘signal’ input to it which is
modelled by the real numbers and the output of each neurons is a non-linear function of
addition of inputs. The weights increase or decrease based on the strength of the signal input
to it and typically in neural networks there is some pre-specified threshold of the signal which
when crossed then the signal is not sent from a neuron to next neuron. There are many layers
in the network which contains series of neurons and more the number of layers more complex
patterns can be recognized by the network (Bouwmans 2019). Now, in MATLAB there are
bunch of neural network libraries which enables to solve simple to complex pattern
recognition problems and the MATLAB functions which are used to perform classification
for the problem are given in the later sections.
Problem definition:
The particular problem of this research to build an automatic artificial intelligence
system that can classify a person as health or affected by Parkinson’s disease when the key
attributes of the voice sample is given as input to the system in appropriate format.