Silent Sound technology allows communication without using vocal cords by monitoring muscular and lip movements, transforming them into computer-generated sound, and transmitting the information as audio to a receiver. It uses sensors and techniques like electromyography and image processing. EMG detects electrical signals from facial muscle movements when speaking silently, which are converted into electrical pulses and then speech. Image processing analyzes remotely sensed data. This technology could benefit vocally impaired people and allow covert communication in situations requiring discretion.
3. Contents
• INTRODUCTION
• NEED FOR SILENT SOUND
• ORIGINATION
• SENSORS NEEDED
• METHODS
• EMG
• IMAGE PROCESSING
• SILENT FEATURES
• APPLICATION
• CONCLUSION
4. Introduction
Silent Sound is a technology which makes it possible to
make calls/transmit information without using vocal
cords just in 4 steps.
Monitoring muscular & lip movements
Transforming them into a computer generated sound
Transmit them over a phone
Receiver receives the information in audio
5. Need for Silent
Sound To overcome with embarrassed situation such as-
To reply urgent call while meeting
For a better way of communication in noisy place
To be helpful for-
Vocally challenged People
Sharing secret information
6. Origination
Origination of idea
1968- Stanley Kubrick science-fiction film 2001 – A Space Odyssey
First demonstration
2010 -At CeBIT(Centrum fiir Biiroautomation, Informationstechnologie
und Telekommunikation)
Under development
scientists of Karlsruhe Institute Of Technology (KIT), Germany
7. Sensors Needed
These are the sensors that are used in Silent Sound Technology :
Pressure sensor
Vibration sensors
Motion sensor
Electromagnetic sensor
8. Methods
Silent Sound Technology is mainly processed through following methods. They are :
Electromyography (EMG) Image Processing
10. Electromyography
• EMG is a technique for evaluating & recording electrical activity
produced by skeletal muscles
• The silent sound technology uses electromyography for monitoring
muscular movements while speaking
• EMG detects electrical potential generated by muscle cells when they
are electrically or neurologically activated
• Detected signals are converted into electrical pulses
• Electrical signals are converted into speech, without utterance of sound
11. History of EMG
YEAR OBSERVER OBSERVATION
1666 First documented experiments dealing with EMG started
1666 Francesco Redi
Highly specialized muscle of the Electric Eel
generates electricity
1849 Dubois-Raymond
It’s possible to record electrical activity during a
voluntary muscle contraction
1890 Marey
Recorded the first actual muscular activity
Coined the term “Electromyography”
12. Principle of
operationIn general speaking aloud
Air passes through larynx & the tongue
Words are produced by articulator muscle
But when we are about to speak
Articulate muscle becomes active irrespective of passage of
air
Even by saying words without producing sound weak
electric currents are sent from brain to speech muscles.
13. EMG -
Procedure– A Needle electrode is inserted through the skin into the
muscle tissue.
– Valuable information about the state of the muscle and its
innervating nerve is observed
– The electrical activity when the muscle is at rest is
observed.
– Because skeletal muscles differ in the inner structure,
the electrode has to be placed at various locations to
obtain an accurate signal
– Shape, size, and frequency of the resulting motor unit are
judged.
15. Functioning
STEPS UNITS FUNCTIONS
I
Monitoring Unit Monitors tiny muscular movements
II
Electromyographic Sensors Records electric signals produced by the facial muscles
III
Transducers Converts the pulses into electric signals .
IV
Vocoder Converts electrical signal into speech pattern
V
Matching Unit
Compare them with pre recorded signal pattern of spoken words
17. Image Processing
• Converting digital data tape into a film image with minimal correction
& calibrations
• In silent sound technology its output is an audio record
18. Image Processing
techniques
Analysis of remotely sensed data is done using various
image processing techniques and methods that includes:
Analog image processing
Digital image processing
19. Data collection&
processingStimuli and Procedure
A list of frequently used sentences were prepared
Electromagnetic articulograph AG500 is used to register 3-D MOVEMENTS of the
tongue, lip and jaw when subject was talking
Articulograph records the movement by establishing calibrated electromagnetic
field
20. Data processing
Head movements were subtracted from tongue and lip locations
A zero phase low pass filter is applied for removing signal
noise
All sequences were segmented and annoted with sentences
21. EMA based silence
speech interface
Electromagnetic
Articulograph
Trained mode (SVM)
Online recognition
Sound database
Sound playback
Recognition
Data
segment
Probable
Sentences
Data
acquisition
Lip
movem
ent
Output
request
Sound
waveform
Senten
ce
sequenc
e
Speech
Acoustic
s
22. Silent Features
• Allow people to make silent calls without
bothering others.
• Helps to interpret foreign language
23. Applications
• In Military for communicating secret/confidential matters
• A hope for people who have lost their voice due to illness
or accident
• Sharing secrets like pin, password to trusted one
24. Conclusion
Thus Silent Sound Technology,
one of the recent trends in the
field of Information technology
implements ‘Talking Without
Talking’.
It will be one of the innovative
and useful technology and in
mere future this technology will