31-10-2016, 02:10 PM
1462451229-tttt.docx (Size: 1.87 MB / Downloads: 8)
Braille is a tactile method of writing and reading different languages by the visually challenged people across the globe as a method of raised dots or pores on a piece of paper or nowadays on three dimensional screens. [6]
Braille characters are small rectangular blocks called cells that contain tiny palpable bumps called raised dots. The number and arrangement of these dots distinguish one character from another. Since the various braille alphabets originated as transcription codes of printed writing systems, the mappings (sets of character designations) vary from language to language. Furthermore, in English Braille there are three levels of encoding: Grade 1 - a letter-by-letter transcription used for basic literacy; Grade 2 - an addition of abbreviations and contractions; and Grade 3 - various non-standardized personal short-hands. [7]
Braille cells are not the only thing to appear in braille text. There may be embossed illustrations and graphs, with the lines either solid or made of series of dots, arrows, bullets that are larger than braille dots, etc.
In the face of screen-reader software, braille usage has declined. However, braille education remains important for developing reading skills among blind and visually impaired children, and braille literacy correlates with higher employment rates.
Introduction & Motivation
Visually challenged individuals rely on their sense of touch for pattern perception, much as the rest of us depend on vision. The feel is reciprocated on paper by pores, and the pattern of the pores was initially developed into a tactile writing system called braille. This pattern perception can be electrically controlled by any microcontroller or embedded system, and the output pattern is recorded by the linear motion of a three by two braille character cell. We, during the course of our research have considered two main methods of controlling the braille pin cell, namely the electromagnet method and the more accurate method of linear actuation.
In this project we use the other method of linear motion, generated by a toy motor to a linear actuator setup, controlled by a ARDUINO development board pushes the exact same pins as that mentioned by the controller, creating a definite braille pattern as expected. The overall setup is a six actuator Braille cell upon aARDUINO ATMEGA CPU, powered by the device that has the PDF file. This creation, not yet compact, can be realized using the ARDUINO IDE and the 3 V toy motors.
Speaker Recognition: The theory
Speaker recognition is the process of automatically recognizing who is speaking on the basis of individual information included in speech waves. This technique makes it possible to use the speaker's voice to verify their identity and control access to services such as voice dialing, banking by telephone, telephone shopping, database access services, information services, voice mail, security control for confidential information areas, and remote access to computers.
Speaker recognition can be classified into identification and verification. Speaker identification is the process of determining which registered speaker provides a given utterance. Speaker verification, on the other hand, is the process of accepting or rejecting the identity claim of a speaker. Figure 1 shows the basic structures of speaker identification and verification systems. The system that we will describe is classified as text-independent speaker identification system since its task is to identify the person who speaks regardless of what is saying.
At the highest level, all speaker recognition systems contain two main modules (refer to Figure 1): feature extraction and feature matching. Feature extraction is the process that extracts a small amount of data from the voice signal that can later be used to represent each speaker. Feature matching involves the actual procedure to identify the unknown speaker by comparing extracted features from his/her voice input with the ones from a set of known speakers.
Feature Extraction (MFCC)
The extraction of the best parametric representation of acoustic signals is an important task to produce a better recognition performance. The efficiency of this phase is important for the next phase since it affects its behavior. MFCC is based on human hearing perceptions which cannot perceive frequencies over 1Khz. In other words, in MFCC is based on known variation of the human ear’s critical bandwidth with frequency [8-10]. MFCC has two types of filter which are spaced linearly at low frequency below 1000 Hz and logarithmic spacing above 1000Hz. A subjective pitch is present on Mel Frequency Scale to capture important characteristic of phonetic in speech.
Voice recognition methodology
Voice recognition works based on the premise that a person voice exhibits characteristics are unique to different speaker. The signal during training and testing session can be greatly different due to many factors such as people voice change with time, health condition (e.g. the speaker has a cold), speaking rate and also acoustical noise and variation recording environment via microphone.
Conception of the Idea
The basic idea of the project was conceived from weeks one-three, where initially we candidates considered the implementation of the dissertation of vibrators in the finger positions and one palm of a glove developed specially for the purpose of recreating the braille cell. The idea however had a major flow; the vibrations were for a fixed period of time and were inconsistent with the reading speeds and grasping abilities of all braille readers and interpreters. Hence the approach was dropped.
This approach was replaced with a more permanent and effective way of reading out braille; the linear actuator. It consisted of two methods: Electromagnet and motor method. The electromagnet method involved connecting pins to the solenoids similar to the electric bell, and causing linear motion by passing current through the solenoid wires. It was deemed inappropriate because the solenoid may cause linear motion in all the pins in its magnetic field, resulting in unpredicted relative displacement of the pin and thus causing an undesired Braille pattern.
Motor method of linear actuation involved converting the rotational motion of the DC motor into linear motion using micro-gears. Hence we compromised the size of the overall device at the advantage of accuracy.
4.2 Phase One Development: Text to Braille
Phase one as explained earlier involves the development of the Braille cell and the bringing of a character from PDF file and displaying its Braille equivalent on the cell. Achieved during the weeks 4-7[], before going into the heart of the idea, we took a trial experiment bringing a character from a text document into the arduino IDE and displaying the particular pattern of LEDs. This experiment helped us to study and verify character recognition from a basic text file.
Portable Document Formats (PDFs), unlike text files displays the images of the characters and a backend database stores the ASCII codes of the characters displayed as images. Hence to read out the PDF file, we use OCR or Optical Character Recognition software to convert the PDF into a .txt file, which in turn is compared character by character to generate its Braille equivalents on the Braille cell.