1. SEMINAR BY: GUIDED BY:
JEEVITHA R Ms VIDYA S BENNUR
1ec08ec018
2. CONTENTS
•Introduction
•What is speech?
•Sources of information
•Brain computer interface (BCI)
•Speech synthesis
•speech synthesis technologies
•Block diagram
•Features
• Methods of producing
Electromyography
Image processing
• Applications
•In fiction
•Reference
3. •You are in a theatre or a noisy restaurant or a bus etc., where there is lot of
noise around is a big issue while talking on a mobile phone. But in future this
problem is eliminated with “silent sound technology”, a new technology
unveiled at the CeBIT fare. It transforms lip movements into a computer
generated voice for the listener at the other end of the listener
• Silent speech is a device that allows speech communication without using
the sound made when people vocalize their speech sounds. As such it is a
type of electronic lip reader. It works by computer identifying phonemes that
an individual pronounces from non auditory sources of information about
their speech movements. These are then used to recreate the speech using
speech synthesis
4. •The device uses electromyography, monitoring tiny muscular movements
that occur when we speak and converting them into electrical pulses that
can be turned into speech without a sound uttered. It also uses image
processing technique that converts digital data into a film image with
minimal corrections and calibration.
5. Speech is the vocalized form of human communication. It is based upon the
syntactic combination of lexical and names that are drawn from very large
(usually to about 10,000 different words) vocabularies.
A gestural form of human communication exists for the deaf in the form of
sign language. Speech in some cultures has become the basis of a written
language, often one that differs in its vocabulary, syntax and phonetics from its
associated spoken one, a situation called diglossia
7. The vocal tract is the cavity in human beings and in
animals where sound that is produced at the sound source (larynx in mammals;
syrinx in birds) is filtered.
8. Bone conduction is the conduction of sound to the inner ear through the bones
of the skull.
Some hearing aids employ bone conduction, achieving an effect equivalent to
hearing directly by means of the ears. A headset is ergonomically positioned on the
temple and cheek and the electromechanical transducer, which converts electric
signals into mechanical vibrations, sends sound to the internal ear through the
cranial bones. Likewise, a microphone can be used to record spoken sounds via
bone conduction. The first description, in 1923, of a bone conduction hearing aid
was Hugo Gernsback’s "Osophone", which he later elaborated on with his
"Phonosone".
9. Categories:
•Ordinary products
•Hearing aids
•Specialized communication products
Advantages:
Ears free
High sound clarity in very noisy environment
Can have a perception of stereo sound
Disadvantages:
Some implementations require more power than headphones.
Less clear recording and playback than headphones.
10. A brain computer interface is often called as mind machine interface(MMI)or
sometimes called direct neural interface is a direct communication pathway
between the brain and an external device
The field of BCI research and development has since focused primarily on
neuroprosthetics applications that aim at restoring damaged hearing, sight and
movement. Thanks to the remarkable cortical plasticity of the brain, signals from
implanted prostheses can, after adaptation, be handled by the brain like natural
sensor or effecter channels. Following years of animal experimentation, the first
neuroprosthetic devices implanted in humans appeared in the mid- 90s
11. Speech synthesis is the artificial production of human speech. A
computer system used for this purpose is called a speech
synthesizer, and can be implemented in software or hardware.
Synthesized speech can be created by concatenating pieces of
recorded speech that are stored in a database. Systems differ in the
size of the stored speech units; a system that stores phones or
di phones provides the largest output range, but may lack clarity.
12. Speech synthesizing process:
The quality of a speech synthesizer is judged by its it’s similarity to the human
voice and by its ability to be understood. An intelligible text-to-speech program
allows people with visual impairments or reading disabilities to listen to written
works on a home computer. Many computer operating systems have included
speech synthesizers since the early 1980’s.
13. The most important qualities of speech synthesis system are naturalness and
intelligibility . Naturalness describes how closely the output sounds like human
speech, while intelligibility is the ease with which the output is understood.
There are 8 types of Synthesizing technologies such that they are :
a) Concatenative synthesis
b) Unit selection synthesis
c) Di phone synthesis
d) Domain-specific synthesis
e) Formant synthesis
f) Articulatory synthesis
g) HMM-based synthesis
h) Sine wave synthesis
14. CONCATENATIVE SYNTHESIS:
Concatenative synthesis is based on the concatenation (or stringing
together) of segments of recorded speech. Generally, Concatenative synthesis
produces the most natural-sounding synthesized speech.
UNIT SELECTION SYNTHESIS:
Unit selection synthesis uses large databases of recorded speech. During
database creation, each recorded utterance is segmented into some or all of the
following: individual phones, di phones, half-
phones, syllables, morphemes, words, phrases, and sentences.
DI PHONE SYNTHESIS:
Di phone synthesis uses a minimal speech database containing all the di
phones(sound-to-sound transitions) occurring in a language. The number of di
phones depends on the phonotactics of the language: for example, Spanish has
about 800 di phones and German about 2500. In di phone synthesis, only one
example of each di phone is contained in the speech database.
15. Domain specific synthesis:
Domain-specific synthesis concatenates prerecorded words and
phrases to create complete utterances. It is used in applications where the
variety of texts the system will output is limited to a particular domain, like
transit schedule announcements or weather reports.
Format synthesis:
Format synthesis does not use human speech samples at runtime.
Instead the synthesized speech output is created using additive synthesis
and an acoustic model (physical modeling synthesis). Parameters such as
fundamental frequency, voicing, and noise levels are varied over time to
create a waveform of artificial speech. This method is sometimes called
rules-based synthesis
16. ARTICULATORY SYNTHESIS:
Articulatory synthesis refers to computational techniques for
synthesizing speech based on models of the human vocal tract and the
articulation processes occurring there. Until recently, articulatory synthesis
models have not been incorporated into commercial speech synthesis
systems.
HMM BASED SYNTHESIS:
HMM-based synthesis is a synthesis method based on hidden Markov
models, also called Statistical Parametric Synthesis. In this system, the
frequency spectrum (vocal tract), fundamental frequency (vocal
source), and duration (prosody) of speech are modeled simultaneously by
HMMs. Speech waveforms are generated from HMMs themselves based on
the maximum likelihood criterion.
17. SINE WAVE SYNTHESIS:
Sine wave synthesis is a technique for synthesizing
speech by replacing the formants (main bands of energy) with
pure tone whistles.
19. FEATURES:
AUDIO SPOTLIGHT:
The Audio Spotlight transmitters generate a column of sound between
three and five degrees wider than the transmitter. It converts ordinary
audio into high-frequency ultrasonic signals that are outside the range of
normal hearing. As these sound waves push out from the source, they
interact with air pressure to create audible sounds.
Sound field distribution is shown with equal loudness contours for a
standard 1 KHz tone. The center area is louder at 100% amplitude, while
the sound level just outside the illustrated beam area is less than 10%.
Audio spotlight systems are much sensitive to listener distance than
traditional loudspeakers, but maximum performance is attained at roughly
1-2m (3-6feet) from the listener.
Typical levels are 80dB SPL at 1 KHz for As-16 and 85dB SPL for AS-24
models. The larger AS-24 can output about twice the power and twice low
frequency range.
20. This simulation is fixed for fixed source size(0.4m/16”) with varying wavelength.
From the statements above, we expect to see an unidirectional response for a large
wavelength relative to source, and higher directivity as wavelength decreases.
22. ELECTROMYOGRAPHY:
It is a technique for evaluating and recording the electrical activity
produced by skeletal muscles. EMG is performed using an instrument
called an electromyography, to produce a record called an
electromyogram. An electromyography detects the electrical potential
generated by muscle cells when these cells are electrically or
neurologically activated.
23. Electromyographic sensors attached to the face records the electric signals
produced by the facial muscles, compare them with pre recorded signal
pattern of spoken words .
When there is a match that sound is transmitted on to the other end of the
line and person at the other end listen to the spoken words.
24. For such an interface ,we should use 4 kinds of TRANSDUCERS . They are as
follows :-
1.Vibration sensors
2.Pressure sensor
3.Electromagnetic sensor
4.Motion sensor
IMAGE POCESSING:
•The simplest form of image processing converts the data tape into a film image
with minimal corrections and calibrations.
25. Digital data
Pre processing
Feature extraction
Image enhancement Selection of training
data
Manual interpretation
Decision and classification Ancillary data
Supervised Unsupervised
Classification output
Post processing operation
Assess memory
Maps and imageries Reports Data
26. As we know in space there is no medium for sound to travel therefore this
technology can be best utilized by astronauts.
We can make silent calls even if we are standing in a crowded place.
This technology is helpful for people without vocal cord or those who are
suffering from Aphasia (speaking disorder ).
This technology can be used for communication In nasty environment.
To tell a secret PIN no. , or credit card no. on the phone now be easy as there is
no one eavesdrop anymore.
Since the electrical signals are universal they can be translated into any language.
Native speakers can translate it before sending it to the other side. Hence it can be
converted into any language of choice currently being German, English & French.
27. Translation into majority of languages but for languages such as Chinese
different tone holds different meaning, facial movements being the same. Hence
this technology is difficult to apply in such situations.
From security point of view recognizing who you are talking to gets complicated.
Even differentiating between people and emotions cannot be done. This means
you will always feel you are talking to a robot.
This device presently needs nine leads to be attached to our face which is quite
impractical to make it usable.
28. Silent sound technology gives way to a bright future to speech recognition
technology from simple voice commands to memorandum dictated over the phone
all this is fairly possible in noisy public places.
Without having electrodes hanging all around your face, these electrodes will be
• It may have features like lip reading based on image recognition & processing
rather than electromyography.
• Nano technology will be a mentionable step towards making the device handy.
29. Engineers claim that the device is working with 99 percent efficiency.
It is difficult to compare SSI technologies directly in a meaningful way. Since many
of the systems are still preliminary, it would not make sense, for example, to
compare speech recognition scores or synthesis quality at this stage.
With a few abstractions, however, it is possible to shed light on the range of
applicability and the potential for future commercialization of the different
methods.