Braille Printer. Department of Computer Engineering, Late G.N. Sapkal C.O.E., Nasik, India. 1.

Similar documents
LOS ANGELES CITY COLLEGE (LACC) ALTERNATE MEDIA PRODUCTION POLICY EQUAL ACCESS TO INSTRUCTIONAL AND COLLEGE WIDE INFORMATION

Circuit Simulators: A Revolutionary E-Learning Platform

SOFTWARE EVALUATION TOOL

On Human Computer Interaction, HCI. Dr. Saif al Zahir Electrical and Computer Engineering Department UBC

Automating the E-learning Personalization

Calibration of Confidence Measures in Speech Recognition

Word Segmentation of Off-line Handwritten Documents

On-Line Data Analytics

re An Interactive web based tool for sorting textbook images prior to adaptation to accessible format: Year 1 Final Report

University of Toronto Physics Practicals. University of Toronto Physics Practicals. University of Toronto Physics Practicals

GACE Computer Science Assessment Test at a Glance

SAM - Sensors, Actuators and Microcontrollers in Mobile Robots

International Journal of Computational Intelligence and Informatics, Vol. 1 : No. 4, January - March 2012

HiSET TESTING ACCOMMODATIONS REQUEST FORM Part I Applicant Information

Speech Recognition at ICSI: Broadcast News and beyond

MINISTRY OF EDUCATION

Computer Science. Embedded systems today. Microcontroller MCR

Modeling function word errors in DNN-HMM based LVCSR systems

WHEN THERE IS A mismatch between the acoustic

Human Emotion Recognition From Speech

A Variation-Tolerant Multi-Level Memory Architecture Encoded in Two-state Memristors

Learning Methods in Multilingual Speech Recognition

SIE: Speech Enabled Interface for E-Learning

PREDICTING SPEECH RECOGNITION CONFIDENCE USING DEEP LEARNING WITH WORD IDENTITY AND SCORE FEATURES

ENEE 302h: Digital Electronics, Fall 2005 Prof. Bruce Jacob

GRE and TOEFL Tests, the PRAXIS Tests and SCHOOL LEADERSHIP SERIES Assessments. Bulletin Supplement

OFFICIAL DOCUMENT. Foreign Credits, Inc. Jawaharlal Nehru Technological University

SER CHANGES~ACCOMMODATIONS PAGES

AGENDA LEARNING THEORIES LEARNING THEORIES. Advanced Learning Theories 2/22/2016

Specification and Evaluation of Machine Translation Toy Systems - Criteria for laboratory assignments

Eli Yamamoto, Satoshi Nakamura, Kiyohiro Shikano. Graduate School of Information Science, Nara Institute of Science & Technology

SARDNET: A Self-Organizing Feature Map for Sequences

BUILD-IT: Intuitive plant layout mediated by natural interaction

Computerized Adaptive Psychological Testing A Personalisation Perspective

Document number: 2013/ Programs Committee 6/2014 (July) Agenda Item 42.0 Bachelor of Engineering with Honours in Software Engineering

What s in a Step? Toward General, Abstract Representations of Tutoring System Log Data

Special Educational Needs and Disabilities

Using EEG to Improve Massive Open Online Courses Feedback Interaction

Designing a Rubric to Assess the Modelling Phase of Student Design Projects in Upper Year Engineering Courses

Use and Adaptation of Open Source Software for Capacity Building to Strengthen Health Research in Low- and Middle-Income Countries

Physics 270: Experimental Physics

OPTIMIZATINON OF TRAINING SETS FOR HEBBIAN-LEARNING- BASED CLASSIFIERS

Module 12. Machine Learning. Version 2 CSE IIT, Kharagpur

Listening and Speaking Skills of English Language of Adolescents of Government and Private Schools

have to be modeled) or isolated words. Output of the system is a grapheme-tophoneme conversion system which takes as its input the spelling of words,

OCR for Arabic using SIFT Descriptors With Online Failure Prediction

LEGO MINDSTORMS Education EV3 Coding Activities

CIS 121 INTRODUCTION TO COMPUTER INFORMATION SYSTEMS - SYLLABUS

STUDIES WITH FABRICATED SWITCHBOARD DATA: EXPLORING SOURCES OF MODEL-DATA MISMATCH

Computer Organization I (Tietokoneen toiminta)

Modeling function word errors in DNN-HMM based LVCSR systems

A Practical Approach to Embedded Systems Engineering Workforce Development

FUZZY EXPERT. Dr. Kasim M. Al-Aubidy. Philadelphia University. Computer Eng. Dept February 2002 University of Damascus-Syria

Unit purpose and aim. Level: 3 Sub-level: Unit 315 Credit value: 6 Guided learning hours: 50

On the Combined Behavior of Autonomous Resource Management Agents

A study of speaker adaptation for DNN-based speech synthesis

MinE 382 Mine Power Systems Fall Semester, 2014

Five Challenges for the Collaborative Classroom and How to Solve Them

Seminar - Organic Computing

Parsing of part-of-speech tagged Assamese Texts

Running Head: STUDENT CENTRIC INTEGRATED TECHNOLOGY

Development of an IT Curriculum. Dr. Jochen Koubek Humboldt-Universität zu Berlin Technische Universität Berlin 2008

Designing a Computer to Play Nim: A Mini-Capstone Project in Digital Design I

EEAS 101 BASIC WIRING AND CIRCUIT DESIGN. Electrical Principles and Practices Text 3 nd Edition, Glen Mazur & Peter Zurlis

Application of Virtual Instruments (VIs) for an enhanced learning environment

Using SAM Central With iread

The Impact of the Multi-sensory Program Alfabeto on the Development of Literacy Skills of Third Stage Pre-school Children

Class-Discriminative Weighted Distortion Measure for VQ-Based Speaker Identification

Software Security: Integrating Secure Software Engineering in Graduate Computer Science Curriculum

A Neural Network GUI Tested on Text-To-Phoneme Mapping

Modeling user preferences and norms in context-aware systems

Mandarin Lexical Tone Recognition: The Gating Paradigm

QuickStroke: An Incremental On-line Chinese Handwriting Recognition System

COMPUTER INTERFACES FOR TEACHING THE NINTENDO GENERATION

Lectora a Complete elearning Solution

Reinforcement Learning by Comparing Immediate Reward

AQUA: An Ontology-Driven Question Answering System

Perspectives of Information Systems

A MULTI-AGENT SYSTEM FOR A DISTANCE SUPPORT IN EDUCATIONAL ROBOTICS

Understanding and Supporting Dyslexia Godstone Village School. January 2017

Multi-sensory Language Teaching. Seamless Intervention with Quality First Teaching for Phonics, Reading and Spelling

FY16 UW-Parkside Institutional IT Plan Report

Innovative Methods for Teaching Engineering Courses

AUTOMATIC DETECTION OF PROLONGED FRICATIVE PHONEMES WITH THE HIDDEN MARKOV MODELS APPROACH 1. INTRODUCTION

Bluetooth mlearning Applications for the Classroom of the Future

Competition in Information Technology: an Informal Learning

Computer Science 141: Computing Hardware Course Information Fall 2012

Virtual Seminar Courses: Issues from here to there

EECS 571 PRINCIPLES OF REAL-TIME COMPUTING Fall 10. Instructor: Kang G. Shin, 4605 CSE, ;

Infrared Paper Dryer Control Scheme

Software Maintenance

Evolutive Neural Net Fuzzy Filtering: Basic Description

Problems of the Arabic OCR: New Attitudes

Process to Identify Minimum Passing Criteria and Objective Evidence in Support of ABET EC2000 Criteria Fulfillment

Courses in English. Application Development Technology. Artificial Intelligence. 2017/18 Spring Semester. Database access

Multidisciplinary Engineering Systems 2 nd and 3rd Year College-Wide Courses

A Pipelined Approach for Iterative Software Process Model

REVIEW OF CONNECTED SPEECH

21st Century Community Learning Center

Teaching Algorithm Development Skills

Transcription:

Vol-0, Issue 0, APR 205. Braille Printer Harshali Gangurde, 2 Sayali Pingale, 3 Dipali Pawar, 4 Jyoti Aher,2,3,4 Department of Computer Engineering, Late G.N. Sapkal C.O.E., Nasik, India. harshaligangurde3@gmail.com, 2 sayalipingale9@gmail.com, 3 pawardipali6@gmail.com, 4 aherjyoti69@gmail.com Abstract: Generally, user interface is improved by considering only normal people, however this improvement affects reversely on blind people. Currently available systems are either used by normal person or blind person therefore there is a need of such system which will provide a common interface to blind as well as normal person. Now here we can use Braille Printer to provide such common interface. Braille is an important language used by the visually impaired to read and write. It is vital for communication and educational purposes. Braille Printer takes an input as a speech through microphone which is then converted to text using speech recognition and the recognized text is embossed in its respective Braille code. Here speech is the way of common interface through which blind person as well as normal person can interact with our system. Keywords Braille, Braille Code, Speech Recognition. I. INTRODUCTION Computer is the way through which human can interact with the digital world. Computer access is provided through graphical user interface, textual notifications. However this access is useful only for normal user. To provide such access to visual impaired people, speech is the way through which they can interact with the system. Braille Printer is a system useful for visually impaired people. It is developed to provide the common interface to the blind person as well as normal person. Normally user interface is improved by considering only normal people, however this improvement affects reversely on blind people. Thus, there is a need of such system which will provide common interface to blind as well as normal person. Our system takes an input as a speech through microphone which is embossed in Braille using speech recognition. Here speech is the way of common interface through which blind person as well as normal person can interact with our system. The embossed Braille printouts are very important in intellectual progress of blind and weak sighted people. These printouts are very important in education, developing their perception. It allows recording the information in a way, which is understandable for every blind person. II. LITERATURE SURVEY We have referred this paper and the new separate words search and recognition approach is proposed in this article. It is based on successive application of acoustic models. This evaluates the probability of the corresponding phoneme observation along the signal. The received noisy phoneme sequence is used to spot the most probable recognised word. The comparison with the baseline algorithm "Token Passing" has used which provides simplicity and effectiveness for the system. This system requires pre-processing evaluation which is computationally challenging. [] The system given here is automatic speech recognition (ASR), which converts speech from a recorded audio signal to text. A speech signal has a certain probability. Therefore, assuming a word x was spoken; they compute a probability for matching these words with the speech signal. This probability is calculated from the some properties of speech sub-units (phonemes in the acoustic model), linguistic knowledge about words. It requires additional information about pronunciation which requires more storage [3]. Among the developed systems for blind people, some systems use a standard braille keyboard or speech for giving input to a computer, with speech or braille being used for output. In those systems, there is a requirement to convert the braille codes into standard codes. This system has finite number of states which can hold the current context. These states have capabilities for both left and right context matching. However there are some limitations of this system such as some of the old system abbreviations, isolated letters without letter s sign (For example, the braille equivalent of Mr M. Jones ) are not converted correctly. [4] The system given here is a missing data recognition system. To improve the speech recognition, there are different methods which distinguish reliable and unreliable data. The performance of automatic speech recognizers degrades rapidly in the presence of noise and other distortions.

Speech recognizers requires clean speech and face a problem of mismatch when speech other sound sources (noise). They proposed a system to mitigate the effect of this mismatch on recognition; noisy speech is pre-processed by speech enhancement algorithms. However there are certain numbers of errors present due to additive noise. [7] By referring these various papers and various techniques we came to conclusion that there are number of algorithms for speech recognition, braille conversion however feasibility of such systems is less. And hence there must be a system where speech is given as an input and braille code will be embossed, and this system is more feasible as it can be used by blind as well as normal person. A. Printer III. EXISTING SYSTEM Braille is one way in which the visually impaired can communicate with the world. Printer output can be obtained concurrently with Braille output. Fant developed a method to allow brailing on a standard line printer. He used a strip of specially prepared cellophane tape. So it is not necessary to remove the ribbon or adjust the impact force. [6] approximately seventy dollars to develop. The expensiveness of Braille displays forces many to develop the skill using synthetic speech. As the Braille keyboard is only used by blind persons. Hence it is less feasible. [6] E. Need of System Computer access is necessary for blind users who can utilize computers as speech-enabled training programs, Braille training programs, Braille translators, interfaces with other equipment, and dynamic Braille displays. The major barrier for computer use for the visually impaired is the display of screen. The raised use of graphics on computers have resulted in a less accessibility to the computers and to the information presented through them to blind people. Compensation for the display can be in an tactile mode, auditory mode or a combination. For people with low vision, there is a need to enlarge the text and graphics to various degrees: 27% of individuals identified as legally blind use primarily visual means to access text while 0% use primarily auditory means. The remainder uses a combination of techniques. Thus a variety of means needs to be available to create access to computers for the visually impaired. [6] B. Braille Displays In addition to the use of Braille printers, refreshable Braille displays are segregate devices that connect to a computer. Each Braille cell consists of six solenoids. The Braille codes are formed by sets of pins being raised and lowered electro-mechanically. As the input is typed, the user can review it on the line display. It can display 20, 40, or 80 characters of text. [6] C. Braille Keyboards The keyboard consists of six standard keys that allow the user to produce a standard 6-dot Braille symbol. Braille note takers are small battery-powered devices that allow the user to enter the information on a Braille keyboard and then review the information through the use of synthetic speech or through a Braille display. These keyboards can be used as input devices that interface with personal computers. [6] D. Disadvantages of Existing Systems Printers are slower and noisier than ink printers as they are driven by solenoids that emboss Braille dots on a page as an output. Depending on the cost, the printers produce 0 or more characters per second. In braille display, each refreshable cell displays one character and costs IV. PROPOSED SYSTEM To overcome the disadvantages of existing systems, we are going to develop the system Braille Printer. This system is useful for visually impaired people. It is developed to provide the common interface to the blind person as well as normal person. Initially user has to give the input (speech) through microphone. Step algorithm converts chopped input into its equivalent binary code. This binary code is used to select the appropriate data line of the port for embossing. These data lines are connected to six bobbins of the printer. According to binary code, corresponding data line is activated. Then circuit is get completed and corresponding dot is get embossed on the paper. The embossed Braille printouts are very important in intellectual progress of blind and weak sighted people. These printouts are very important in education, developing their perception.

Vol-0, Issue 0, APR 205. 3 V. SYSTEM ARCHITECTURE Fig. shows the block diagram of Braille printer. The input given to the system is in the form of speech through microphone. This speech is given to the computer for speech recognition. Recognized speech is given to the interface card which contains transistors and relays. Then the generated bits with respect to the input speech are given to the printer to emboss the Braille code. The block diagram of Braille Printer consists of: System performing speech recognition Transistor Relay Printer A. Relay Fig. 3 Electronic Symbol of Relay An electrically operated switch is called as Relay. To mechanically operate a switch many relays use an electromagnet, however other operating principles are also used, as the solid-state relays. Relays are used where it is necessary to control a circuit by a low-power signal or where several circuits must be controlled by one signal. C. Printer Fig. Block diagram of Braille Printer A. Speech Recognition Speech Recognition is the process of converting spoken input to text. Speech recognition is sometimes referred to as speech-to-text conversion. Speech recognition allows us to provide input to an application with our voice. The speech recognition process is performed by a software component known as the speech recognition engine. Speech recognition fundamentally functions as pipeline that converts PCM (Pulse Code Modulation) digital audio from sound card into recognized speech. B. Transistor Fig. 4 Printer A printer consists of 6 dots equivalent to the Braille language dots. Internally these six dots are made up of door bell s (Ding-Dong bells) solenoid mechanism. Metal wires are connected to each ding-dong bell. After recognizing the speech, its equivalent binary code is given as input to printer. According to binary code, dots are get embossed on paper using metal wires. Fig. 2 Electronic Symbol of Transistor A transistor is a semiconductor device used to amplify and switch electronic signals and electrical power. It is consists of semiconductor material with at least three terminals for connection to an external circuit. A current or a voltage applied to one pair of the transistor s terminals and it changes the current through another pair of terminals. Because the controlled [output] power can be higher than the controlling [input] power thus a transistor can amplify a signal. Where R= Register, T= Transistor Fig. 5 Internal View of Embossing

Initially user has to give the input (speech) through microphone. Step algorithm converts chopped input into its equivalent binary code. This binary code is used to select the appropriate data line of the port for embossing. These data lines are connected to six bobbins of the printer. According to binary code, corresponding data line is activated. Then circuit is get completed and corresponding dot is get embossed on the paper. VI. ALGORITHMS As proposed system accepts an input as a speech, so we require a microphone. An input taken through this microphone is processed further as given in following algorithm. A. Algorithm of speech processing Initially user has to give the input (speech) through microphone. Steps in algorithm. Accept the input (speech) through microphone. 2. For (i= to speech_length) { Chop the given input. /* Using the concept of sound hypothesis, input speech is chopped in small units for recognition. */ } 3. For (i= to speech_length) { code is given as input to this algorithm. According to binary code, equivalent dots are embossed using metal wire. Steps in algorithm. Accept the input i.e. binary code. (Braille has six dots, hence six bit binary code is considered.) 2. According to binary code, data lines of port are selected. i. If (bit is high), Then equivalent data line is selected. ii. After selecting the data line, circuit get completed. iii. Using selected data line, corresponding dot is embossed using metal wire. These embossed dots on paper are considered as an output of proposed system. VII. RESULTS AND ANALYSIS Braille Printer is the system which is used for embossing the Braille code by accepting speech as an input. As we speak through micro-phone, it get recognized using sound hypothesis and get converted to binary code. This 6 bit binary code is equivalent to the braille code of recognized word. According to binary code, dots are getting embossed using metal wire. For example, binary code for alphabet A is 00000, then output will be as shown in fig. 6. A. Analysis There are various existing systems which are referred during developing the proposed system. However, these existing systems have some disadvantages which are overcome in proposed system. Compare input with library file. Return result of comparison. /* Chopped input is compared with library file which is already stored in our system. Comparing is done to determine spoken word. */ } 4. By comparing, appropriate word is recognized. B. Algorithm of printing The output of speech processing algorithm is recognised word. This word is converted into binary form. This binary Fig. 6 Examples of Embossed braille codes

Vol-0, Issue 0, APR 205. 5 Table. : Analysis of existing and proposed system Parameters Existing system Proposed system Less feasible as it can be More feasible as it can only used by blind be used by blind people because these people as well as system uses braille normal people because Feasibility keyboards and braille it takes speech as displays which are only input and it can be used by blind people as given by blind as well they have knowledge as normal people. about braille. Cost Input Output More expensive as the Braille Displays consist of refreshable cells. These cells require approximately 60-70 dollars to refresh. Input must be given in textual form through keyboard which can be either used by normal person by using normal keyboard or by blind person by using Braille Keyboard. It converters the given text into Braille Code and only displays braille form of that input. VIII. CONCLUSION Less expensive as it required the low cost components to develop. Input is given in speech form through microphone which can be easily given by normal person or blind person. It converts the given speech to text and then that text into its respective braille form and then embosses that Braille Code on paper. Proposed system describes course and results of work on development of new hardware aiding blind people and use new technologies in well-known hardware. An increasing number of computer based systems are becoming available to assist people with disabilities. Proposed system is useful for blind and visually impaired persons. This system permits blind person to enter information using speech, there is requirement of convert speech into Braille codes. These converted Braille codes are then embossed on paper in text format. These printouts are very important in intellectual progress of blind and weak sighted people. These printouts are very important in education, developing their perception. It allows recording the information in a way, which is understandable for every blind person. IX. ACKNOWLEDGEMENT It gives us great pleasure to acknowledge our topic titled: Braille Printer. This topic is presented as we are interested in the field of Artificial Intelligence and social welfare. With deep sense of gratitude we would like to thanks all the people who have lit our path with their kind guidance. We are very grateful to these intellectuals who did their best to help during our research work. It is our proud privilege to express great gratitude to, Prof (Dr). V.J. Gond Principal of Late G. N. Sapkal College of Engineering, We remain indebted to Prof. N.R. Wankhade, HOD Computer Engineering. And the special gratitude goes to our project coordinator and project guide Prof. B. R. Nandwalkar. We are also thankful to our parents for providing their wishful support for completion of our work successfully. And lastly we are thankful to all friends and the people who are directly or indirectly related to our project work. REFERENCES [] Igor Cheydorov, Aliaksei Kuzmin, Two Step Algorithm Of Separate Words Recognition In Continuous Speech Based On Usage Of Acoustic And Language Models, IJERT, ISSN: 2278-08, Vol. 2 Issue 7, July 203. [2] Dr.B.L.Shivakumar M.Rajasena thipathi, English to Braille Conversion Tool using Client Server Architecture Model, International Journal of Advanced Research in Computer Science and Software Engineering 3(8), pp. 295-299, August 203. [3] E. Gruhn et al., Statistical Pronunciation Modelling for Non- Native Speech Processing, Signals and Communication Technology, DOI:0.007/978-3-642-9586-0_2, Springer- Verlag Berlin Heidelberg 20. [4] Soundararajan Srinivasan, DeLiang Wang, Robust speech recognition by integrating speech separation and hypothesis testing, Speech Communication (52), pp. 72-8, (200). [5] R. Barczyk, L. Buczynski, D. Jasinska-Choromanska, Development of Braille s Printers, (a) Institute of Micromechanics and Photonics, Warsaw University of Technology, Sw. A. Boboli 8 Warsaw, 02-525, Poland, pp. 406-40, 2007. [6] Manouchehr Tabatabaei, Information Technology for Protected Individuals: A Survey of Current Status, Disability Studies Quarterly, Spring, Volume 22, No. 2 pages 59-74, 2002. [7] Paul Blenkhorn, A System for Converting Braille into Print, IEEE Transactions on Rehabilitation Engineering, Vol. 3, No. 2, June 995.