Text Input in Indic Scripts

Slides:



Advertisements
Similar presentations
Keyboard Training Instruction by: Connie Hutchison & Christopher McCoy.
Advertisements

KeTra.
Alphabetic Cheerleaders! An activity for Students learning English Grammar Press Space Bar to continue.
Language Model for Cyrillic Mongolian to Traditional Mongolian Conversion Feilong Bao, Guanglai Gao, Xueliang Yan, Hongwei Wang
FIRE 2013 By:- Hardik Joshi 1, Apurva Bhatt 1, Honey Patel 2 1 Department of Computer Science, Gujarat.
Intelligent Information Retrieval CS 336 –Lecture 2: Query Language Xiaoyan Li Spring 2006 Modified from Lisa Ballesteros’s slides.
1/25 Writing Character sets Unicode Input methods.
Lecture4 1 Wide character vs. Multi-byte characters Text information needs to be represented by the right data types. –Multi byte characters: data are.
Professional Learning Reference: Key conceptsVELS Levels 1&2 Early Language Development.
Performing User Interface Design
Text-To-Speech System for Marathi Miss. Deepa V. Kadam Indian Institute of Technology, Bombay.
Presenter: Dung Thi Nguyen Date: September 15, 2011.
1 SSML Extensions for TTS in Indian Languages II workshop on Internationalizing SSML May 2006, Greece Nixon Patel and Kishore Prahallad Bhrigus.
Module 1: Introduction to Teaching IELTS
Computer System Examples? Input Output Devices System Unit Devices
Digital Learning Material (e-Content) Development Process Senthil Kumar 24 th June 2008 transforming education, empowering communities, promoting development.
Review for 1 st Quiz. How to listen properly Stop what you are doing.
1 Ideas for Future Research Anirudha Joshi Industrial Design Centre, IIT Bombay February 2013.
News On The Go! How NewsHunt reached 1 Crore Downloads ? INDIAN LANGUAGES!!
Nurturing Living Languages © C-DAC Mahesh D. Kulkarni C-DAC GIST Group Electronics and Information Technology Exposition - ELITEX 2005 India.
Step 1 1. Go to Start-> Control Panel > Regional & Language Options > Click on Languages Tab Tick the Check box to Install files for complex.
Chapter 11 An Introduction to Visual Basic 2008 Why Windows and Why Visual Basic How You Develop a Visual Basic Application The Different Versions of Visual.
India In the Midst of Change. Goals Learn about key features of India’s population Examine the state of India’s economy Understand the major challenges.
Implementation Issues Mark Davis Properties.
Kishore Prahallad IIIT-Hyderabad 1 Unit Selection Synthesis in Indian Languages (Workshop Talk at IIT Kharagpur, Mar 4-5, 2009)
Mel & Hot Keys Review. What’s MEL?  Maya Embedded Language  Most of Maya's interface is built using MEL commands and scripts.
Sorting it all out: An introduction to collation Cathy Wissink Michael Kaplan Globalization Infrastructure and Font Technology Windows International Microsoft.
Designing a Handwriting Recognition Based Writing Environment J C Read, S J MacFarlane, C Casey Department of Computing, University of Central Lancashire,
Tongue movement kinematics in speech: Task specific control of movement speed Anders Löfqvist Haskins Laboratories New Haven, CT.
Closing Session  FIRE shared task  Results of yesterday’s experiments  Open discussion and Your Feedback.
Script Writing Vocabulary. 2 Character direction Information that tells characters how to move or speak Copyright © Texas Education Agency, All.
Essential Programming Skills CSE 340 – Principles of Programming Languages Spring 2016 Adam Doupé Arizona State University
A Level Computing#BristolMet Session Objectives#U2S11 MUST identify built-in string manipulation functions SHOULD correctly use string manipulation functions.
Vidya Narayan LIS 385T.6 PDA Usability Vidya Narayan The University of Texas at Austin School of Information LIS 382L.15.
Lesson 2. NEEDS ANALYSIS Student want to work on: Speaking about complex topics Speaking on the phone (companies) Speaking with doctors Practicing for.
1.4 Keyboard Training.
IT Strategy Roadmap Template
Essential Programming Skills
an Introduction to English

Manner of Articulation
The dvorak keyboard History The dvorak layout Testing it
SYSTEM APPROACH TO EDUCATION
Project timeline # 3 Step # 3 is about x, y and z # 2
1.4 Keyboard Training Keyboard Training.
Zone Identification in the Printed Gujarati Text
التدريب الرياضى إعداد الدكتور طارق صلاح.


Industrial Training Provider ,

Velar (`guttural') consonants:

êF> (Devanàgarã) `climbed' råóhaþ (Roman transliteration)
Year 9 Entry Level Computing
Text for section 1 1 Text for section 2 2 Text for section 3 3
Text for section 1 1 Text for section 2 2 Text for section 3 3
Text for section 1 1 Text for section 2 2 Text for section 3 3
Text for section 1 1 Text for section 2 2 Text for section 3 3

Text for section 1 1 Text for section 2 2 Text for section 3 3
Text for section 1 1 Text for section 2 2 Text for section 3 3
Text for section 1 1 Text for section 2 2 Text for section 3 3
Put the on A on the keyboard.
What is the QWERTY Keyboard?
Text for section 1 1 Text for section 2 2 Text for section 3 3
Text for section 1 1 Text for section 2 2 Text for section 3 3
Text for section 1 1 Text for section 2 2 Text for section 3 3
Project timeline # 3 Step # 3 is about x, y and z # 2

Presentation transcript:

Text Input in Indic Scripts Anirudha Joshi Industrial Design Centre, IIT Bombay

Tele-density Share Urban 148% 62% Rural 40% 38% (Jan 2013, TRAI) Illiterate (26%) Illiterate (35%) Primary school (14%) Middle school (9%) Metric (8%) HSC / Diploma (4%) Graduates (3.7%)

Source: The Times of India

How many people in India speak English?

How many people in India prefer to speak in English?

Source: Top 10 Publications 2012 Q1, Hansa Research, MRUS, IRS

Source: An Installation in IDC

Structure of the Devanagari Script 4/20/2017 Structure of the Devanagari Script Vowels अ आ इ ई उ ऊ ए ऐ ओ औ अं अः Vowels Vowel modifiers ◌ ा ि ी ु ू े ै ो ौ ं ः Gutturals क ख ग घ ङ Palatals च छ ज झ ञ Linguals ट ठ ड ढ ण ट ठ ड ढ ण त थ द ध न Consonants Dentals त थ द ध न च छ ज झ ञ Vowels can all be recited in a sing-song manner without break Vowel modifiers appear only when vowels are combined with consonants. प फ ब भ म Labials प फ ब भ म क ख ग घ ङ Semi-vowels य र ल व श ष स ह ळ क्ष ज्ञ 12

Challenges in Text Input in Indian Languages 4/20/2017 Challenges in Text Input in Indian Languages Large number of characters ~660 frequent glyphs 2+ keystrokes = glyph क + ो = को (C + V) क + ो + ं = कों (C + V + V) Difference in pronunciation and visual sequence क + ि = कि Conjuncts (halant ् between two consonants) ट + ् + व = ट्व (C + C) Varying similarity between conjuncts and consonants स + ् + त = स्त क + ् + र = क्र र + ् + क = र्क क + ् + ष = क्ष Vowels अ आ इ ई उ ऊ ए ऐ ओ औ अं अः Vowels Vowel modifiers ◌ ा ि ी ु ू े ै ो ौ ं ः Gutturals क ख ग घ ङ Palatals च छ ज झ ञ Linguals ट ठ ड ढ ण Consonants Dentals त थ द ध न 34+11+10+8 chars req to form the 660 freq occuring glyphs Complex script More than one keystroke ex. Other challenges add to the complexity of input in Devanagari Labials प फ ब भ म Semi-vowels य र ल व श ष स ह ळ क्ष ज्ञ

Text Input in Indic Languages QWERTY keyboard for Devanagari input Devanagari needs 52 keys (13 vowels, 34 consonants, 4 conjuncts, 1 halant) QWERTY has 26 un-shifted keys Leads to cognitive load on users Complex structure of Indic scripts (G > K) Large number of glyphs Need much training and practice 30-50 hours to reach 25 wpm Slow starts Only professional typists put in the effort QWERTY is not suitable

Source: Anshuman Kumar

Task Success /5 Users Without help Total p (one tailed) p (one tailed) Nokia (0.208) Samsung (0.195) Sony (0.001) Total p (one tailed) Nokia (0.000) Samsung (0.010) Sony (0.000)

Disha

Swarachakra

Inscript

Oct 2013 Jun 2013 Aug 2013 Jan 2014