Description:Field of the Invention
IOT Based Communications for Disable Persons
Background of the Invention.
Communication between deaf-mute persons and hearing people is more difficult because hearing people cannot understand deaf-mute people's speculations and feelings. Knowing different sorts of sign languages, such as sign language, can help people communicate more effectively. Here there is a need for devices, which can translate signs or gestures to voice statements. There are other inventions which limited to voice to text, gestures to text, and there is no innovation which combines all these methods to perform both ways of communication and also parallel which combines emotions also into communication which is having high priority .
Adeyanju[1] did his study titled “Machine learning methods for sign language recognition: A critical review and analysis” in the journal ‘Intelligent Systems with Applications” which represents research on sign language translators , but very less work done on developing a device which can be easily used by both communicating parties , also recognizes voice emotions, and facial emotions while translation occurs from both ends

Objectives of the Invention
The main objective of the design is to create a device which can recognise gestures of the deaf and dumb people and translates them with the combination of emotions reocgnized on face, in gestures, and produces voice directly which can be used in remote or direct communications.
Another objective of the device is convert the normal person's voice into sign language and display on smart glasses weared by the deaf and dumb person.

Intelligent translator works in 2 modes based on the user
For Deaf and Dumb.
–Takes the voice input from from opposite person and converts into Signs + text which will be displayed on Smart glasses
For Normal person who want to communicate with Deaf and Dumb
– Captures the signs and facial expressions from Deaf and Dumb Person and translates them in to voice messages added with emotional sounds.
Summary of the Invention

With motto of giving an optimal communication channel for deaf and dumb person with normal person the product invention is sone. In this invention NLP( natural Language Processing tools , Machine learning algorithms , image processing, Smart glasses, micro controller are Main software and hardware components for the design and implementation.

The Two main components of ITDD Device are
Smart glasses containing,
Display screen, microphone, Camara,
ITDD hub containing,
Speaker, Microcontroller, Battery, Bluetooth.

Here the ITDD Device takes the input from the normal user in terms of voice communications, also embeds the emotions of other person by capturing facial expressions and tone in voice and translates into sign language and also as text which will be displayed on the Smart glasses wared by the Deaf and dumb person.
And when The Deaf and Dumb perosn want to communicates he changes the mode
Then the device captures the signs made by him. And converts the Signs into voice messages and sends them to the opposite person through the Speaker.
The device mainly very advantageous for deaf and dumb person and also very use full for the people who want to communicate with deanf and dumb person.

Brief Description of accompanying Drawings

The present invention is illustrated in figure 1 to 10 of the drawings accompanying this specification. In the drawings like reference numbers/letters indicate corresponding parts in the various figures which are Drawn in a separate with Figure numbers.
Figure 1 represents the architecture of the total main system which mainly contains two modules one is Eyewear and the second is ITDD hub which contains controller ,speaker.
Figure 2 represents Eyewear which contains display , camera , microphone, and connecter for power and data transmission. The main purpose is display information to Deaf and dumb person. And capturing gestures and facial images using camera , capturing voice from microphone
Figure 3 represents ITDD hub box which can be kept in pocket and it contains micro controller, speaker, battery unit, Display, bluetooth device, connector.
This device acts as heart of total operation , Mcirocontroller performs the translation of dat capture and give the output
Figure 4 represents a TTGO T-Call V1.4 ESP32 which is used as main device to perform all translations and also this device isWireless Module SIM Antenna SIM Card SIM800L Module Unsoldered. The module is used for wireless communication. The ESP V1.4 ESP32 Serial WIFI Wireless Transceiver Module is a self-contained SOC with an integrated TCP/IP protocol stack that can give any microcontroller access to your WiFi network.
This module has a powerful enough onboard processing and storage capability that allows it to be integrated with the sensors and other application-specific devices through its GPIOs with minimal development up-front and minimal loading during runtime.
Figure 5 represents Speakers which are used to give voice sound to the end user
Figure 6 represents display which is used to display the functionalities of module
Figure 7 represents rechargeable Battery which can be used to give power supply to all modules
Figure 8 represents Bluetooth device which is used to communicate when user opt the for bluetooth communication
Figure 9 represents audiojack which can be used for connect other audio system
Figure 10 represents Switches which are used to control the Hub

Detail Description of the Invention
The invented model is for the Deaf and Dumb, which should be taken along with him. He should wear the Smart Glasses which is having mike and camera in it. And these smart glasses are connected with hub of the device which can be kept in pocket. The hub and smart glasses will be connected with wire as to elimate data transfer issues if go through wifi or bluetooth.
When the Deaf and Dumb person wears the smart glasses and Swich ons the functionality. The camera captures the hand signs made by him and sends them to the hub device and they are translated into voice which will be announced through speakers located in the hub.

This hub contains the micro controller which is coded for translating images with signs into voice. This voice is given as output through the Speaker.
In another mode where the deaf and dumb person wants to receive information. When a normal person starts talking, the mike which is kept in smart glasses will be capturing voice from the opposite person, the camera will capture the emotions, and the model will combine both voice and emotions and give a gesture output.
The gesture output will be transferred to smart glasses and displayed on them.
Here the voice to sign conversion NLP models are used. And for emotion recognitions image processing is used.
The following example illustrates how it works

EXAMPLE
● The Deaf and Dumb person stand opposite to the person with whom he wants to communicate in a distance less than or equal to 4 feet.
● Deaf and Dumb person wears the smart glasses and switche ons the hub.
● Deaf person makes signs exactly before his chest, so that signs are clearly visible to the camera on his smart glasses and waits for the sentence to be processed and the translated sentence will be given as output on both smart glasses as text and with speaker as voice.
● And he informs the opposite person to speak and mode of the hub is changed to listening.
● The opposite person will say the full sentence at a time and wait.
● The mike records the sentence.
● The camera records emotion on the opposite face.
● Both are processed using NLP and ML Models
● The output is translated in sign language and transferred to smart glasses.

The main advantages of the present invention are:

1. The best Communicating device between Deaf and dumb and Normal person
2. Eliminates social distance between Deaf and Dumb and normal people
3. It can be used for remote communication with symbol
4. Deaf and Dumb can also participate in online meeting
5. Emotions are included in communication.
, C , C , Claims:1. An Intelligent Translator for the deaf and dumb (ITDD) comprising:
i. An Eye Wear;
ii. An ITDD Hub;
iii. A TTGO-TCALL-ESP32; and
iv. A speaker;
Characterized in that the integrated system of (i), (ii), (iii) and (iv) helps in the communication of a normal person with deaf and dumb person in terms of both general communication and emotional communication using gestures, voice and facial expression.

2. The ITDD as claimed in claim1, wherein Eyewear (2) contains display, camera , microphone, and connecter for power and data transmission, when a normal person starts talking, the mic which is kept in smart glasses will be capturing voice from the opposite person, the camera will capture the emotions, and the model will combine both voice and emotions and give a gesture output, then the gesture output will be transferred to smart glasses and displayed on them and here the voice to sign conversion NLP models are used and for emotion recognitions image processing is used.

3. The ITDD as claimed in claim1, wherein ITDD Hub (3) contains micro controller, speaker, battery unit, Display, bluetooth device, connector.

4. The ITDD as claimed in claim1, wherein TTGO T-Call V1.4 ESP329(4) which is used as main device to perform all translations and also this device is Wireless Module SIM Antenna SIM Card SIM800L Module Unsoldered. The module is used for wireless communication. The ESP V1.4 ESP32 Serial WIFI Wireless Transceiver Module is a self-contained SOC with an integrated TCP/IP protocol stack that can give any microcontroller access to your WiFi network.

5. The ITDD as claimed in claim1, contains speaker(5) which are used to give voice sound to the end user when communicating with the other person.