The present invention is generally related to the field of the e-Exam pad.
More particularly, the present invention relates to the system of e-Exam for
visually impaired students.
BACKGROUND OF THE INVENTION
[0002] Nowadays, technology plays an important role in every field and makes
everyone’s life easier, better, faster, and more secure. The evolution of technology
is advantageous to humans for many reasons. It has paved the way for multifunctional devices like the smartwatch, smartphone, smart TV, laptop, tablet,
health monitoring devices, voice assistance devices, etc. Advancements in
technology have provided faster ways to communicate via social media platforms
and instant messaging apps. In the medical field, technology helps to treat more
patients and consequently saves many lives. Those who are struggling with
hearing loss can get benefit from technology (hearing aids). The medical field
makes discoveries regarding treatments, symptom and disease research, data
collection, human aiding devices, cure research, etc., by using technology.
[0003] The people who have lost their vision completely are struggling to do
everything on their own. Visually impaired people cannot read words or letters.
So, they learn letters, words, and numbers with the help of Braille. Thus, visually
impaired students can learn easily like ordinary students. Even though, they are
struggling to attend the written exam. However, scribes can help the students who
are completely lost their vision. During regular classes, colleges/schools used to
assign scribes for assisting visually impaired students in exam halls. With online
learning and exams becoming normal, visually impaired or blind students are
having difficulties in writing exams from homes and uploading the documents of
the answer papers. So, the present invention provides the e-exam pad for visually
impaired students who are completely lost their vision.
[0004] However, there were lots of efforts made to help the visually impaired
students to attend the exam. Some of the reference known to us is as follows:
Prior Arts:
[0005] Indian patent application 202041017650 describes the system and method
of speech recognition based automatic digital documentation inbuilt with wireless
mike, which comprises a wireless mike with coupler, amplifier, volume controller,
and voice recorder. The main purpose of this invention is to generate a digital
document automatically based on the recognized speech signal of the lecturer.
Initially, the microphone captures the speech signal of the lecturer and then, it
creates the documentation based on their lecturing notes.
[0006] Indian patent application 202141021584 describes the method and system
autonomous wheelchair-assisted speech recognition system for physically
challenged ones. The speech-assisted wheelchair device is controlled by the
speech signal of the user. It can either be controlled automatically or manually,
where the disabled person is placed over it. The movement of the wheelchair can
be made with the help of an accelerometer and the destination can be set with their
voice assistant.
[0007] Indian patent application 202041047439 describes the system and method
of lip movement based visual speech recognition device for automatic
documentation in built with digital camera, which comprises the visual speech
recognition. The main purpose of this present invention is to create the document
automatically by the lip movement of speakers in conferences or other seminar
events. Visual speech recognition recognizes the lip movement of the person and
converts it into text format. Finally, the created document will be stored and
managed by the document management system.
[0008] Indian patent application 202041037441 describes the method and system
of voice assistance system with inbuilt speech recognition, which comprises the
sound card, Bluetooth device, and speech recognition module. The main purpose
of this invention is to assist vehicle drivers with voice commands. This module
accepts seven voice commands at a time that making it user-friendly to the vehicle
drivers.
[0009] Indian patent application 202011040854 describes the system and method
of multipurpose exam writing pad with timer, which consists of a paper holder,
timer, start, and reset buttons. The main purpose of this invention is to help
students keep track of the time utilized during the exam, especially competitive
exams using the timer.
[0010] State of the art suffers from the following limitations:
[0011] State of the arts does not consider an e-exam pad for visually impaired
students. Usually, visually impaired students need assistance (scribes) to write
their exams. Writers write on the answer sheet the answers that the visually
impaired students say orally. But it is difficult for visually impaired students to
find out a scribe who helps the visually impaired students; especially in online
exams. So, the present invention provides the e-exam pad for visually impaired
students to read out the contents that are present on the device’s display. The
speech recognizer that is embedded within the device also recognizes the spoken
words and converts them into the text format. Finally, the document generator
generates a digital document based on the text format.
OBJECTIVES OF THE INVENTION
[0012] The main objective of the present invention is to provide an e-exam pad
for visually impaired students to attend the exam without the help of a scribe.
[0013] Another objective of the present invention is to provide the screen reader
to read the contents that show on the display of the e-exam pad by converting the
displayed content into synthesized speech using the text-to-speech converter. The
screen reader is controlled by the user’s voice command.
[0014] Yet another objective of the present invention is to generate the digital
document based on the recognized characters (answers given by the visually
impaired person) using a document generator.
SUMMARY OF THE INVENTION
[0015] The present invention summary is easy to understand before the hardware
and system enablement were illustrated in this present invention. There have been
multiple possible embodiments that do not expressly point up in this method's
present acknowledgment. Here, the conditions are used to explain the purpose of
exacting versions or embodiments for understanding the present invention.
[0016] The main aspect of the present invention is the e-exam pad, which
comprises the speech recognizer and document generator. Generally, visually
impaired students write their exams with the help of scribes. The scribes write the
answers that visually impaired students say orally on the answer sheet. So, the
present invention provides an e-exam for visually impaired people to attend the
exam without the help of the scribe.
[0017] Accordingly, one aspect of the present invention is the speech recognizer,
which is used to extract the speech signal and recognize the spoken words of the
visually impaired student and convert it into the text format based on the speech
model.
[0018] Another aspect of the present invention is the document generator, which
is used to generate a digital document based on converted text format. Thus,
visually impaired people can attend the exam without the help of scribes.
BRIEF DESCRIPTION OF THE DRAWINGS
[0019] The accompanying drawings, which are incorporated in, constitute a part
of the specification, illustrate the invention's embodiment, and the description
serves to explain the principles of the invention.
[0020] Various embodiments will be described under the appended drawings,
which are provided to illustrate the present invention.
[0021] Figure 1 illustrates the perspective view of the e-exam pad as provided in
the present invention.
[0022] Figure 2 illustrates the architecture of the e-exam pad as provided in the
present invention.
[0023] Figure 3 illustrates the entire process of the e-exam pad as provided in the
present invention.
DETAILED DESCRIPTION OF THE INVENTION
[0024] This present invention is easy to understand with the reference of detailed
figures and descriptions set forth herein. Here, various embodiments have been
discussed regarding the architecture and flow chart. Some embodiments of this
invention, illustrating its features, will now be discussed, and the disclosed
embodiments merely exemplary of the invention that may embody in various
forms.
[0025] Generally, visually impaired students write their exams with the help of
scribes. The scribes write the answers that visually impaired students say orally on
the answer sheet. But it is difficult for visually impaired students to find out a
scribe who helps the visually impaired students; especially in online exams. So,
the present invention provides the e-exam pad for visually impaired students.
[0026] Initially, when the visually impaired student turns on the e-exam pad for
the exam, the screen reader reads the question displayed on the screen. After that,
the visually impaired student has to answer the question that is asked in the exam.
Then, the microphone records the audio signal and recognizes the spoken
character. Subsequently, the recognized character will be passed to the document
generator and generate the spoken answer into a digital document.
[0027] The present invention shows the perspective view of the e-exam pad (100),
further detailed descriptions of the present invention are stated here about the
attached drawings. Thus, the detailed embodiments of the present invention are
disclosed here to describe the present invention.
[0028] In this embodiment of the present invention, as shown in figure 1(a),
which refers to the perspective view of the e-exam pad (100) for generating the
digital document based on the recognized spoken words of visually impaired
students, which comprises the speech recognizer (105) and document generator
(106).
[0029] The e-exam pad (101) is an exam device for visually impaired students. In
this device, the visually impaired student just has to give his/her answer orally and
it generates the digital document based on the spoken answers. Initially, when the
student turns on the e-exam pad (101), the microphone (104) that is embedded
within the e-exam pad (101) also turns on to record the speech signal of the
visually impaired student.
[0030] The camera (102) is used to capture the image of the student for
authentication verification. After that, the screen reader also turns on to read
questions that are displayed on the e-exam pad (101) by converting the text into
speech. Then, the converting speech signal will be passed to the speaker (103).
The visually impaired student can use his/her voice to control the e-exam pad
(101), which means the student can give orders such as re-reading question 2 or
moving on to the next question, etc.
[0031] Subsequently, the microphone (104) records the speech signal of the
visually impaired student and passes it to the speech recognizer (105). The speech
recognizer (105) is used to translate spoken words (exam answer) into text. It
recognizes the spoken words and converts them into the text format. After that,
the converted text format will be passed to the document generator (106). The
document generator (106) generates a digital document of the text format.
[0032] In another embodiment of the present invention, figure 2 illustrates the
architecture of the e-exam pad (200), which comprises the screen reader (211).
[0033] The power button (201) is used to turn on/off the e-exam pad. The battery
(202) is a device, which provides energy to the device by converting chemical
energy into electrical energy. The memory unit (203) is also known as internal
memory/primary memory, which is used to store data, information, and
instructions of the device. It includes Read-only-memory (ROM) & Read-access-
memory (RAM) (2031). A/D & D/A converters (204) stands for “Analog-toDigital converter” and “Digital-to-Analog converter”. An A/D converter is used to
convert analog signals into digital signals, which means converting an analog
input such as a speech signal into a digital signal.
[0034] The cellular baseband (205) processor is a chip in the e-exam pad, which is
used to handle a cellular transmission. It converts data into signals to modify the
carrier frequency for transmission. Application processor (206) is used to support
applications running in the e-exam pad operating system environment. Codec
(207) is used to encode or decode a signal or data stream. The purpose of the RF
part (208) is to transmit and receive radio signals for communicating with another
device wirelessly.
[0035] The camera (209) is used to capture the image of an object, which means it
captures the image of the student for authentication verification. The display (210)
is a projecting mechanism and computer output surface, which is used to show
text and often graphic images to the user. In this method, the screen reader (211)
is embedded within the display (210) of the e-exam pad. When the display of the
e-exam pad turns on, the screen reader (211) also starts and converts the text into
a speech signal (212). After that, the converted speech signal will be passed to the
speaker (213). Thus, the e-exam pad reads out the questions for visually impaired
students without the help of scribes.
[0036] Mic (214) is a microphone, which is used to record the speech signal of the
visually impaired student. When the user turns on the device, the microphone also
starts to record the speech signal of the visually impaired student for creating the
spoken words into a digital document. The recorded speech signal will be passed
to the speech recognizer (215) to recognize the spoken words and convert speech
into the text format (216). The converted text format will be passed to the
document generator (217) to generate a digital document. Thus, the visually
impaired student can attend the exam without the help of a scribe.
[0037] The GPS module (218) is used to track or find the location of the user.
Bluetooth module (219) is used for short-range and point-to-point wireless data
transmission and reception. Wi-Fi module (220) is used to connect the e-exam pad
to the internet for transmitting and receiving the data. USB port (221) is used for
both data transfer and charging the battery (202).
[0038] In another embodiment of the present invention, figure 3 illustrates the
entire process of the present invention (300), which comprises the text to speech
converter (304).
[0039] Initially, when the visually impaired student turns on the e-exam pad, the
microphone (301) that is embedded within the e-exam pad also records the
visually impaired student’s speech signal (3011). The screen reader (303) is
controlled by the voice command (302) of the visually impaired student. The
screen reader (303) reads the text and image that shows on the display using the
text to speech converter (304). The text to speech converter (304) is an assistive
technology, which is used to read digital text aloud, which comprises the steps of
text analysis (3041), phonetic analysis (3042), prosody generation (3043), and
synthesized speech (3044).
[0040] Text analysis (3041) is used to extract readable information from the text
(contents that show on the display of the e-exam pad) to enable data-driven
approaches for managing content. Phonetic analysis (3042) is used to recognize
the sound of the analyzed text to identify a word. The prosody generation (3043)
is used to predict the pitch, duration, and energy value in implicit form or explicit
form. Finally, the synthesized speech (3044), which means the artificial human
voice will be generated and the artificial human voice will be passed to the
speaker (305).
[0041] Once the screen reader (303) reads the questions that show on the e-exam
pad display, the visually impaired student has to answer orally. The microphone
(301) records the speech signal and passes it to the speech recognizer (306). The
speech recognizer (306) is used to convert the speech signal into the text format,
which comprises pre-processing (3061), feature extraction (3062), speech analysis
(3063), and character recognizer (3064).
[0042] The speech pre-processing (3061) method is used to differentiate the
voiced or unvoiced speech signal and create feature vectors. This process is
adjusting the speech signal so that the speech signal will be more suitable for
speech feature extraction (3062). In this method, feature extraction (3062) is used
to extract the different features such as vocal tract, pitch, and power configuration
from the speech signal. After that, the extracted information will be passed to the
speech analysis (3063). The speech analysis (3063) is used to analyze the speech
signal to obtain important information about the speech signal. Then, the character
recognizer (3064) recognizes the spoken words based on the speech model (307)
and converts them into the text format. Finally, the converted text format will be
passed to the document generator (308) to generate a digital document. Thus, the
virtually impaired students can attend the exam without the help of scribes. The eexam pad is very flexible to the user and user-friendly device.

We claim:
1. A system of an e-exam pad for visually impaired students (100), which
comprising:
a) Screen reader (211);
b) Speech recognizer (105); and
c) Document generator (106).
2. The system of an e-exam pad for visually impaired students (100) as claimed in
claim 1, wherein said the screen reader (211) reads the contents that show on
the display by converting the displayed content into synthesized speech using
the text-to-speech converter.
3. The system of an e-exam pad for visually impaired students (100) as claimed in
claim 1, wherein said the speech recognizer (105) recognizes the spoken words
and converts them into text format.
4. The system of an e-exam pad for visually impaired students (100) as claimed in
claim 1, wherein said the document generator (106) generates the digital
document based on the converted text format.