Abstract I have used the number of flex

Abstract
– Presently
the most appropriate way to express our thoughts and feelings with physically
challenged persons ( deaf and dumb ) the communication pays the only way.
Nevertheless , the number of issues are arising with common people who are not
well aware with sign languages making it difficult for the deaf and dumb people
to withstand in current generation . Here I develop a worthwhile system that
helps in providing speech to speechless person with aid of smart glove
assistance. Although the
market has some data gloves for some renowned gaming and other virtual reality
applications , there is no such complete system that is available for the
translation of sign language into speech . To attain this I have used the number of flex sensors fitted with the
glove. These sensors respectively then senses the finger movement that measures information arising from physical
interaction with its environment. According to the output generated from the
flex sensor, ATmega328 will display the corresponding message over LCD in which
the Analog signal is converted into the digital signal using ADC converter. The
generated text message is then converted into voice using speak jet and this
voice is heard with the help of speaker. Hence making the possibility of
achieving speech for speechless persons.

KEYWORDS :
Flex sensor,ATmega328,ADC converter,Speakjet.

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

I.                   
INTRODUCTION

Deaf
and mute people use sign language. This language is said to be a communication
skill that uses gestures rather than that of sound to convey any respective
messages. This gesture movement follows simultaneously combines the number of
hand shapes along with its orientations ,following the hand movements and
facial expressions to express  the
thoughts of the speaker fluidly. But most often, ordinary  people find it rather difficult to understand
these sign languages. The development of the most popular devices for hand
movement acquisition, glove-based systems, started about 30 years ago and
continues to emerge. In the recent years, there is a rapid increase in the
number of speech – disabled victims due to several reasons like by birth, oral
diseases, accidents, etc… A need for the Electronic Assistive Technology (EST)
increases among physically impaired persons as they are communicating by means
of sign language. Here I Propose a gesture in a sign language with movement
that is understandable. With the help of this hand gesture the corresponding
voice gets generated as well as the message gets displayed on LCD. This will be
useful for both speech-impaired and hearing-impaired patients by means of
aiding them with improved benefits. This system is compact, flexible and only
takes less power to operate making it more reliable to use.

 

II.                 
LITERATURE SURVEY

The need for the inventing a system such
as communicating hand glove has made the impaired people to live their life
comfortably with us. A Crafty Communicating Hand Glove is a portable device
which can be easily handled anywhere.

Author N. P.
Bhatti B. S . Chowdhry , presented design of Electronic hand glove for Speech
impaired and Paralyzed patients. Speech and Hearing impaired people generally
use hand sign language to communicate. The main idea is to translate this sign
language into speech. In this system RVM 01 is a parallel Mode based voice
recording and playback chip is used. It supports 32 Voice groups with a total
of 1800 minutes recording. Sampling is done at 10K sample rate and

 

 

the voice is record in the internal
memory. No external MEMORY is required for storing the voice data. Its voice
storage capacity is more therefore this system is more efficient .

Author T. H.
Speeter ,
presented implementation of electronic speaking glove for speechless patient.
This system is designed to facilitate an easy communication through synthesized
speech using Forward Positional Transformation(FPT) technique for the benefit of speechless patients. In this
author used Smart Phone with various gestures can be made on touch screen.
These can be convert to sound by various inbuilt software. This is not
convenient as user must be educated which is not possible all the time.
Therefore this system is less efficient than others.

Author Abjhijt
Auti, D. K. Sarji , described design of speaking gloves
for speechless persons. The main aim of this approach is to develop electronic
speaking glove which is designed to easy communication through synthesized
speech for the benefit of speechless patients using Mechanomyogram (MMG)
. A speechless person communicate through sign language which is not understood
by the any normal people. The proposed system is designed to solve this
problem. In this system used a IVR341N as a 8-bit MCU based Voice chip . It can
store 341sec voice message with 4-bit ADPCM compression at 6KHz sampling rate
and it required external memory for voice storing.

Author Jan Fizza
Bukhari,
named their prototype as Sign Speak which translated Indian Sign Language into
text and speech. The various part of module were glove design, data
acquisition, wireless link and android application. In glove design module,
selection of appropriate sensors and their location was finalized with the
contact of two finger . To detect a contact, connected to the input voltage
through pull-up resistors were used. Whenever any conductive plate connected to
ground was touched to positive plate, a contact was detected. Therefore,
whenever one finger was in contact with the other, value of contact sensors for
that particular fingers became 0. To detect and measure the acceleration of
hand ADXL 345 was used in I2C mode. By placing all these sensors on a glove at
appropriate location, the data glove as an input device to our main controller.
A Data Acquisition (DAQ) system was setup, which was a able to capture data
from the flex and contact sensor.

 

 

III.              
METHODOLOGY

3.1 BLOCK DIAGRAM OF SYSTEM

Fig 1. BLOCK DIAGRAM

 

THE PROPOSED SYSTEM CONSISTS OF PRIMARILY TWO SECTIONS:

1.  Transmitter section

2.  Receiver section

THE BLOCKS CONTAINED IN THE TRANSMITTER SECTION ARE:

1.  Flex sensors

2.  Accelerometer

3.  AVR microcontroller

4.  RF transmitter

THE BLOCKS CONTAINED IN THE RECEIVER SECTION ARE:

1.  RF receiver

2.  AVR microcontroleer

3.  voice module

4.  16×2 Lcd module and HC05 bluetooth module

 

 

 

 

 

Fig 2. TRANSMITTER – RECEIVER

3.2    
DESCRIPTION OF THE PROPOSED SYSTEM

 

A.     
HAND GESTURE
RECOGNITION

A Power Supply of about 5 volt that is maximum is
given to the microcontroller. The supplied power is then used to operate the
flex sensor that has 10ohms resistors that are in parallel with that sensor.
Component used to make power supply is LM7805. This series of fixed-voltage
integrated-circuit voltage regulators is designed for a wide range of
applications. An easy way to
remember the voltage output by a LM78XX series of voltage regulators is the
last two digits of the number. A LM7805 ends with “05”;
thus, it outputs 5 volts. The “78” part is
just the convention that the chip makers use to denote the series of regulators
that output positive voltage. The other series of    regulators, the LM79XX, is the series that
outputs negative voltage. Electrolytic
capacitors are used  for filtration.
In fig.2.it
shows the flex sensors are used as input and are placed on the glove. They
convert the bend into electrical resistance. If bending is more resistance
value will more. They are usually in the form of a thin strip having resistance
10K ohm to 15K ohm. It is very comfortable because of having less weight.
Inside the flex sensor there is a carbon resistive element within thin
substrate. When substrate is bend the sensor produces a resistance output
related to the bend radius.

                           Fig 2. Flex sensor

B.     
SIGNAL
CONDITIONING FOR DATA COMPATIBILITY

The high-performance Microchip 8-bit AVR
RISC-based microcontroller combines 32KB ISP flash memory with read-while-write
capabilities, 1KB EEPROM, 2KB SRAM, 23 general purpose I/O lines, 32 general
purpose working registers, three flexible timer/counters with compare modes,
internal and external interrupts, serial programmable USART, a byte-oriented
2-wire serial interface, SPI serial port, 6-channel 10-bit A/D converter
(8-channels in TQFP and QFN/MLF packages), programmable watchdog timer with
internal oscillator, and five software selectable power saving modes. The
device operates between 1.8-5.5 volts. The
outputs from the sensors are fed to the analog port pin of ATmega328 . The
inbuilt ADC of ATmega328 will convert analog voltage from sensors to the
digital voltage. The flash memory of ATmega328 is programmed in such way that
there is code corresponding to each of the digital value. This is done by ADC. If we expect high precision for our data processing it is of
primary importance to condition signals using the best products of the
industry. Series
Voltage References are
said to be XTR75010 whereas Shunt
Voltage References are
given using XTR431. The operation performed in the given
flex sensor signal is to compensate the imperfections present and to make them
compatible for interface with next stage element. The resistance of flex sensor will only change in one direction. When sensor is in not working i.e. unflexed
at that time its resistance upto 10K and for flexed sensor it will increase
upto 30k-40k. This change in resistance will be converted in to voltage change
by connecting flex sensor potential divider circuit. Voltage divider is used to
determine the output voltage levels. LM358 comparator is a voltage operational
amplifier which is as shown . It consists of two independent, high-gain,
frequency-compensated operational amplifiers that were designed specifically to
operate from a single supply over a wide range of voltages Voltage across two
resistances connected in series i.e. basically resistance to voltage converter.
The resistor and flex forms a voltage divider which divides the input voltage
by a ratio determined by the variable(R1) and fixed resistors(R2) for data
compatibility. The output from signal conditioning stage is given as input to
the processing stage.

 

 

 

 

 

Fig 3. LM358 comparator

C.     
TRANSPUTING VOICE FOR AUDIO RECORD

APR89341
one-time programmable speech IC is used here . The speech codes corresponding
to each gesture is initially recorded. A P89010
high performance Voice OTP is fabricated with Standard CMOS process with
embedded 256K bits EPROM.  It can store up to 10 sec voice message
with 4-bit ADPCM compression at 6KHz sampling rate.8-bit PCM is also available
as user   selectable option. Two trigger modes, simple Key
trigger mode and Parallel CPU trigger mode facilitate diffuser interface. User selectable triggering and output signal options
provide maximum flexibility to various applications. Built-in
resistor  controlled oscillator,
8-bit current mode D/A output and PWM direct speaker driving output minimize
the number of external components.  PC controlled programmer and
developing software are available. Port B pins
of the microcontroller are connected to s1 to s8 pins to address the memory
location. Output of speech IC is given to sound amplifier LM386 and is heard
via the speaker. User selectable triggering and output signal
options provide maximum flexibility to various applications. Built-in
resistor  controlled oscillator, 8-bit
current mode D/A output and PWM direct speaker driving output minimize the
number of external components.  PC controlled programmer and
developing software are available. Port B pins
of the microcontroller are connected to s1 to s8 pins to address the memory
location. Output of speech IC is given to sound amplifier LM386 and is heard
via the speaker. APLUS
integrated achieves these high levels of storage capability by using its
proprietary analog/multilevel storage technology implemented in an advanced
Flash non-volatile memory process, where each memory cell can store 256 voltage
levels. This technology enables the APR9600 device to reproduce voice signals
in their natural form. It eliminates the need for encoding and compression,
which often introduce distortion. The voice processing circuit in arduino shows
the number of switches connected at port A of APR 9600 which are used to record
or a

 

 

 

playback
IC. Voice filter and processing are on pin 17 and 18. On 14 and 15 there is a
speaker which speak up all the recorded voices. Electrolytic capacitor and
paper capacitor are used to filter analog and digital signal.

 

Fig
4 . VOICE PROCESSING SYSTEM

D.     
DISPLAY
MACHINATION FOR DATA

  User input
interface allows user to control a hardware device using natural gestures. This
gestures are intended to provide the required information for further
processing. The  simplest and most common
type of input interfacing device is the push button switch. It is a simple switch  mechanism for controlling some aspect of a machine or a process.
Buttons are typically made out of hard material, usually plastic or metal. Flex sensor , LCD and SpeakJet are also used to provide the interface. Flex
sensors  change in resistance depending
upon the amount of bend on the sensor . They convert the change in bend to
electrical resistance – the more the bend, the more will be the resistance
value. They are usually in the form of a thin strip from 1 “-5” long
that vary in resistance from approximately 10K? to 50K?.

 

Fig 5.INTERFACING
LCD WITH ARDUINO

 

 

 

Table 1 .RESISTANCE
VALUES FOR DIFFERENT FLEX SENSORS

 

FINGER

RESISTANCE

Thumb Finger

12k?

Index Finger

22k? + 2.2k?

Middle Finger

33k?

Ring Finger

27k? + 2.2k?

Pinky Finger

47k?

 

E.     
BOOSTING AUDIO
LEVEL             

     The SpeakJet is a completely self-contained,
single-chip voice and complex sound synthesizer. The SpeakJet is a completely self-contained, single-chip
voice and complex sound synthesizer. It uses a mathematical sound algorithm to
control an internal five channel sound synthesizer to generate on-the-fly,
unlimited vocabulary speech synthesis and complex sounds. The SpeakJet is
pre-configured with 72 speech elements (allophones), 43 sound effects, and 12
DTMF Touch Tones. Through the selection of these sounds, and in combination
with the control of the pitch, rate, bend, and volume parameters, the user has
the ability to produce unlimited phrases and sound effects, with thousands of
variations, at any time. The SpeakJet can be controlled simultaneously by logic
changes on any one of its eight Event Input lines, and by a single I/O serial
line, allowing for both CPU-controlled and stand-along operations.The SpeakJet can be controlled simultaneously
by logic changes on any one of its eight Event Input lines, and by a single I/O
serial line, allowing for both CPU-controlled and stand-along operations. To
connect a speaker to the board amplification circuit is  connected between the DAC0 pin and the speaker. The amplification circuit
will increase the volume of the speaker. There are many audio amplifiers
available, one of the most common is the LM386.
supply the LM386 connecting the Vs pin
with different voltages sources, like for example the +5 V present on the 5V
pin of the Arduino. Due or an external 9V battery.

 

 

 

 

The gain of the
amplifier is given by the capacitor connected to pin 1 and 8 of the LM386. With the 10 µF capacitor the gain is set to 200,
without the capacitor the gain is 50. With the potentiometer the volume of the
amplifier is controlled. It is configured at the gain of 200 that make it quite
natural to human ears; an 8? speaker is used to get the final output.

 

 Fig 6. LM386 MOUNTING ON BREADBOARD

F.        INTERFACING AT COMMANDS

The standard AT commands are used to control
the working of microcontroller. Power Supply of about 5 volt that is maximum is
given to the ATmega328 microcontroller. Facilitates the usage in GSM based
voice communications , SMS, GPRS, Bluetooth UART. The output from the sensing
stage is given to the signal conditioning stage for further processing.
Bluetooth UART enables US to wireless transmit & receive serial data.
Devices equipped with Bluetooth technology support wireless point-to-point
connections, as well as wireless access to mobile phones. We can simply use it
for serial port replacement to establish connection between MCU and PC for data
transfer. It delivers the received data and receives the data to be transmitted
to and from a host system through a host controller interface. It is a
technology that is said to be  standard
for exchanging data over short distances (using short-wavelength UHF radio
waves in the ISM band from 2.4 to 2.485 GHz) from fixed and mobile devices, and
building personal area networks (PANs).

 

 

 

Invented by telecom vendor Ericsson in 1994, it
was originally conceived as a wireless alternative to RS-232 data cables. It
can connect several devices, overcoming problems of synchronization. Fig 3 ,
shows the data flow diagram for seial connection setup and its output.

Fig 7.
Data Flow Diagram              

G. SERIAL
CONNECTION SETUP FOR OUTPUT

The
input to the ADC channels of the microcontroller Arduino ATmega328. The
processed ADC values from the microcontroller are then compared with the
threshold values for the recognition of a particular gesture. The particular
gesture that is recognized is given to the microcontroller which transmits them
through the RF module in a serial manner. For each value received at RF
receiver, the microcontroller gives corresponding commands to the LCD and the
Voice Module. The ATmega328 which transmits them through the RF module in a
serial manner that has the operations of both the RF transmitter and RF
receiver. Speak jet is connected to port D of controller ATmega328 to generate
the sound. The voice is generated accordingly to message which is displayed on
LCD. This device can be used to learn sign language
and helps bridge the communication barrier with which a mute or deaf person is
faced, when communicating with someone unfamiliar with the language. A
HC-05 Bluetooth module which is simple to use for Bluetooth Serial Port
Protocol (SPP) module and for the transparent wireless serial connection setup,
a Bluetooth HC-05 module is designed. With Serial Port Profile, HC-05 Bluetooth
module is a class-2 module, which is configure as either slave or master.

 

 

For
wired serial connection, there is possibility of a drop-in replacement. To
establish the connection, HC-05 used as a serial port replacement, between MCU,
PC. Bluetooth module HC-05 will be simplified our overall design. HC-05 module
has the footprint which is too small (12.7mm*27mm). With CMOS technology and
Adaptive Frequency Hopping Feature (AFH), HC-05 module will be used CSR
Bluecore04-External single chip Bluetooth system.

 

  
Fig 8. MOUNTING BLUETOOTH HC – 05

IV.               
RESULT

In
my proposed system, the person wearing the glove should keep it still for about
2 seconds for the appropriate detection of the particular gesture. Every
gesture consists of some degree of movement and bending of fingers following a
particular order with its specified angle respectively. The number of sensor
values that gets initiated by each of the Flex sensors along with that of an
accelerometer are fed to the ADC channel of the ATmega328 microcontroller. For
every bending of Flex sensors with given instant and manoeuvre of an accelerometer, based upon the positions of these
sensors they produce different analog values. The different gestures are
assigned with multiple unique numbers inorder to identify a particular gesture
that is being made. For the identified gestures, gets displayed on LCD and the
same is transmitted via wireless transceiver.

The comparison technique is
maintained at the receiver side of the system, such that for each value that is
received, the microcontroller generates output for each gesture with specific
commands to be displayed on LCD module at the receiver end. The Voice IC
simultaneously performs its action giving the speech signal and text
accordingly.