|
|
Human Machine Interface Systems(HUMIS)
These systems
aim at a better Human-machine interaction which envisages
the use of other modes of communication with the computer
namely: speech and vision. Speech input/output and Optical
Character Recognition (OCR) Systems are still at nascent
stages even in developed countries. They are successful
only in specialized domains and restricted environments.
These can serve
as test-bed for all application developments in the area
of Speech syntComprehensive databases of the different
units of speech such as phonemes, words etc. for various
Indian Languages need to be developed which hesis and
Speech Recognition.
Speech signals
for 1000 selected words of Hindi have been recorded for
two utterances of about 50 speakers. PC based algorithms
have been designed for speech signal processing, acoustic
analysis of speech sounds and phoneme labelling. An acoustic
phonetic database for these words has been created. This
is useful for speech synthesis and recognition. This has
been developed at CEERI, Delhi.
Theses systems
are useful for direct transfer of large data into
the computer with the help of scanner. The hard copy is
fed into a scanner, the image file is then analysed and
image processing are applied for transforming into ASCII
file. Efforts are underway to develop OCR for Hindi.
Alpha version
of Speech synthesis system for Hindi language has been
developed. The prosodic rules are under development for
further improving the quality of the speech. It is being
developed at CEERI, Delhi.
Various image
processing algorithms have been developed for obtaining
the image matrices of the characters and identifying the
Devanagari characters and words for laser printed text.
This development is being carried out at C-DAC, Pune.
 |
HindiVani – Central Electronics Engineering Research
Institute, N.Delhi |
It is a PC based
Unlimited Vocabulary Text-to-Speech Conversion Software
for Hindi (Alpha Version) for DOS platform. The text document
is generated using a Hindi Editor which supports ISCII
standard. The input words are split into syllables, using
a parser. An acoustic-phonetic database of all these syllables
is available in the database, which is subsequently used
to create words. The concatenation of syllables into words
and the superimposition of quality features is done by
developing rules. The quality features of speech such
as intonation, stress and timing patterns are then improved.
A cascade-parallel formant synthesizer is used to synthesize
the speech. The major components of the system are(Block
Schematic Diagram):
|
Word Parser |
|
Concatenator |
|
Parametric Database |
|
Knowledge Base (Frequency & Durational Rules) |
|
Voice Quality Manager |
|
Klatt Synthesizer |
|
D/A Converter |
The s/w can be used
as an aid for the visually handicapped and for information
retrieval. The system is being ported to Windows environment
and prosody rules are being incorporated for better quality
speech output.
|
Devanagari Optical Character Recognition - C-DAC Pune |
OCR s/w has
been developed with following input design parameters:
|
Laser printed raster scan image file using 300 and 600
dpi resolution |
|
DV - Natraj and DV – Surekh Fonts |
|
Font Sizes 12, 14, 16, 18, 20, 24, 28, 32, 36, 40 &
48 |
|
Scanning at 300 & 600 dpi using HP Desk Scan - 4C
Scanner, black & white, 8 bit, .bmp file format |
Shiro-rekha based
approach has been adopted. Based on which, Algorithms
have been devised for segmentation, tilt correction and
Feature Extraction to generate three sets of databases
namely Top, Middle and Bottom modifiers. Approximately
95% accuracy has been obtained.
|
Pocket translator C-DAC Pune |
Pocket Translator
is a tool for the foreign tourists to communicate with
the locals. It offers instant translation in both script
and voice from one language to another selected language.
It stores standard phrases that are commonly used by travellers
at various public utility places. It looks like calculator/casio
diary having a miniature keyboard and LCD display unit
that will runwith pencil cell.Language phrases have been
selected in categories of Automobile, Restaurant, help/emergency,
shopping, home/housekeeper, greetings, telephone/postal,
directions/signs, socialising, tours/leisure, travel/hotel,
medical, legal, business, technical terms. It will cover
major Indian Languages viz. Hindi, Tamil, Malayalam, Kannada,
Telugu, Bengali, Oriya with English as the interface.The
features of the Pocket Translator are:
|
Language Translation |
|
Language Phrases |
|
Personal data with security lock |
|
Address and Phone diary |
|
Currency convertor |
|
World Time Clock |
|
Consumer Information |
|
Games |
A prototype pocket
translator for Hindi with 30,000 bi-lingual dictionary
and 300 phrases has been developed to establish the feasibility
of technology.
|
|
