Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
VOICE CONTROLLED WHEELCHAIR using Amharic.pdf
1. BAHIR DAR INSTITUTE OF TECHNOLOGY
SCHOOL OF ELECTRICAL ENGINEERING
FINAL YEAR PROJECT PRESENTATION :
VOICE CONTROLLED WHEELCHAIR
Members:
Matebie Gashu (500/02)
Mengistu Baye (1307/03)
Mignot Ayana (1373/03)
Mubarek Kebede (14bb/03)
Supervisor :
Mr. : Enyachewu
2. PRESENTATION OUTLINE
introduction mengistu
Voice recognition Mubarek
Speaker recognition
control system Mignot
Result and conclusion matebie
3. INTRODUCTION
Controlling device with speech is used for many
application
To recognize speech and speaker first the
feature of the speech must be extracted
the best way to extract speech feature is
MFCC
o After feature extraction we classify the speech
and speaker using artificial neural net work
4. OBJECTIVE OF THE PROJECT
General Objective
Design control system of voice controlled
wheelchair.
Specific Objectives
To develop speech and speaker recognition
system
To develop c code for Arduino which control
motor
To interface Ultrasonic sensor to Arduino
7. Voice recognition part of our project mainly done
in semester project
what we did is improving efficiency
8. Ways of efficacy improvement
extracting additional feature
short time energy
Zero crossing point
Adjusting good recording time
And adjusting suppling frequency
10. The speaker recognition part is used for change
the system from speaker independent to speaker
dependent
11. CAPTURE AND PREPROCESSING
Get the audio signal.
Make suitable for feature extraction
Capture
Silence
Removal
Pre-Emphasis
Framing
Windowing
12. FEATURE EXTRACTION
Transform the input audio signal into a
sequence of acoustic feature vectors
MFCC : Mel Filter Cepstral Coefficients
as Feature
Perceptual approach
Human Ear processes audio signal in Mel
scale
Mel scale : linear up to 1KHz and
logarithmic after 1KHz
MFCC gives distribution of energy in Mel
frequency band
Calculated for each frame
Fourier Transform
Mel Filter
Log
IFT : DCT
Energy and Deltas
15. DESIGN CONSIDERATION OF ANN
Sigmoid activation function
Activation function
Number of input unit
Number of hidden
layer
Number of units per
layer
Number of out put
16. DESIGN CONSIDERATION OF ANN
The number of input units are the
the size of the external tigers
in our case the input units are
40 coeffecentes
Activation function
Number of input unit
Number of hidden
layer
Number of units per
layer
Number of out put
17. DESIGN CONSIDERATION
The number of hidden layer affect
learning acurecy
High number hidden layer lead
over fit
High mathematical cost
Small number of hidden layer may
unable to learn
Activation function
Number of input unit
Number of hidden
layer
Number of units per
layer
Number of out put
18. DESIGN CONSIDERATION
Number of units per layer
High number of unit per layer
running cost increase
It may lead over fit
o Small number of units per layer
Leads under fit
Activation function
Number of input unit
Number of hidden
layer
Number of units per
layer
Number of out put
19. DESIGN CONSIDERATION
number of out put unit
the number of the out put unit
in our case 2
default and
User
Activation function
Number of input unit
Number of hidden
layer
Number of units per
layer
Number of out put
22. COST
The root mean square error (RMSE) is
a frequently-used measure of the
differences between values predicted by a
model or an estimator and the values
actually observed from the thing being
modelled or estimated
23. BACK PROPAGATION AND GRADIENT
Backpropagation is used for propagating the
error from out put to input
Backpropagation performs a gradient descent
within the solution's vector space towards a
global minimum.
The gradient from the backpropagation given to
the fimncg bulletin fanction
Fmincg updating the weights according to the
cost and out put the optimized weights
27. PARTS OF THE SYSTEM
In our real system we will use
HM2007 DSP KIT
It has external interface circuit
It is dual processing unit
Good relatively in its speed
Since can't found in local market
We use normal pc
VOICE RECOGNITION
IC
CONTROL UNIT
OBSTACLE
SENSOR
MOTOR
DIRECTION
CONTROL
MOTOR SPEED
CONTROL
28. Control unit are the hart of all
control system
In our case we use Arduino uno
It has 6 analog input and
14 digital i/o
It has serial communication pin
from external device
VOICE RECOGNITION
IC
CONTROL UNIT
OBSTACLE
SENSOR
MOTOR
DIRECTION
CONTROL
MOTOR SPEED
CONTROL
29. Obstacle sensor detect presence or
absence of obstacle
In our case we use ultrasonic sensor
VOICE RECOGNITION
IC
CONTROL UNIT
OBSTACLE
SENSOR
MOTOR
DIRECTION
CONTROL
MOTOR SPEED
CONTROL
30. H-bridge used to control the
direction of the motor
VOICE RECOGNITION
IC
CONTROL UNIT
OBSTACLE
SENSOR
MOTOR
DIRECTION
CONTROL
MOTOR SPEED
CONTROL
31. Current
• One switch is closed in each leg of the "H"
• One switch is open in each leg of the "H"
32. Current
• One switch is closed in each leg of the "H"
• One switch is open in each leg of the "H”
turn in the Other Direction
33. The speed of the dc motor can
be controlled using PWM from
Arduino
VOICE RECOGNITION
IC
CONTROL UNIT
OBSTACLE
SENSOR
MOTOR
DIRECTION
CONTROL
MOTOR SPEED
CONTROL
35. RESULT AND DESICCATION
We develop speech and speaker recognition system
In last we train our data set and gate good accuracy
Voice recognition 97 for training 88% for test
Speaker 99 % for training 94 for test
And we design the control system
Final we stimulate and we do well
36. PROBLEM FACED
In this project time we face many problems
there was no lab which for doing the project so
there was deficiency of computer
Adviser even if their is there is no follow up
bad view of the staff member towards as
37. we will implement the hard ware
properly
It can improved its efficacy by using
vector machine learning
Additional value can be added like
RF transceiver to control remotely
38. CONCLUSION
From this work we conclude that
MFCC is fine for speech feature extraction
Neural network is good for isolated word recognition
In general we conclude that our project is feasible for
control wheelchair movement control.