2023 JETIR March 2023, Volume 10, Issue 3 www.jetir.

org (ISSN-2349-5162)

SILENT SOUND TECHNOLOGY: A REMEDY

FOR DISRUPTIVE COMMUNICATION
1
Mr. Ashish L, 2 Nasreen Parayil
1
Assistant Professor, 2 Student Scholar
1
Department of MCA,
1
Nehru College of Engineering and Research Center, Pambady, India

Abstract : In a crowded area noise pollution is a major problem and it is very difficult for people to communicate in that environment
because one has to shout or talk very loudly and this can be very exhausting. With the technology called Silent sound technology we
can overcome this situation. in such an environment this technology will help people communicate. This technology works by noticing
every movement of the lips and then converts them into sound, i.e., it converts the electrical pulses into sound signals and then transfers
it to the person who it is intended for. This technology is quite helpful for those who doesn't want to bother others by talking loudly and
disturb others. So, without making any sound it will convert the movements of the mouth and send the message. And another advantage
of this technology is that since the electrical pulse is universal it helps to communicate with anyone across the world. This technology
has a wide range of applications, from providing audio for entertainment or communication purposes to providing notifications in public
spaces. It can also be used to provide sound for medical or therapeutic purposes.

IndexTerms - Silent Sound Technology, Electromyography, Image Processing.

I. INTRODUCTION
Noise pollution has been a great threat these days and people find it quite hard to communicate through mobile phone in these
environment as it can be quite exhausting because the receiver might be unable to hear what the person on the other end is trying to say
and the person may need to talk very loudly. This can be very energy consuming. Also, people who has lost their voice or doesn’t like to
speak very loudly find it very hard to communicate in noisy environment. Silent sound technology, also known as ultrasonic sound
technology or ultrasound, is a communication method that uses inaudible sound waves to transmit information. These sound waves are
typically in the range of 20,000 Hz or higher, which is above the upper limit of human hearing. Silent sound technology has many
applications, including in security systems, animal training, medical imaging, and even in communication between humans and animals.
One of the most promising applications of this technology is in the field of assistive technology for people with disabilit ies, particularly
those who are deaf or hard of hearing. The technology works by using a transmitter to send the ultrasonic sound waves, which are received
by a receiver and then converted into audible sound or other types of signals. Silent sound technology can be used for one-way or two-
way communication, depending on the application. Overall, silent sound technology has the potential to be a powerful tool for
communication and information transfer in a wide range of settings, and the ongoing research in this area continues to explore new and
innovative applications this technology.
II. LITERATURE SURVEY
Silent sound technology has been the subject of numerous research studies and publications over the past few decades. Here are some
key findings from a literature survey on this technology:

A detailed overview about silent sound technology was provided in the paper 'Silent Sound Technology - An End to Noisy
Communication' by Shehjar Safaya and Kameshwar Sharma. They discuss how the silent sound technology will help in a situation when
it is very noisy and people who has lost their voice or doesn't want to waste their energy to convey message. So, the silent sound technology
has been introduced to put an end to the noise pollution. They discuss about how the silent sound technology works by reading the lip
movement and then converting it into the message. They also discuss about the methods used in silent sound technology and also where
the silent sound technology is commonly used. And from that we can see how silent sound technology is helpful in many situations. They
also discuss the restrictions faced by the silent sound technology like how languages with different tones are hard to translate and how
emotions cannot be detected.
In the paper 'Deep learning and its application in silent sound technology' by Vibhu Varshney, Deeksha Singh and Ayush Tiwari
discusses the application of deep learning in silent sound technology. We know machine learning is used everywhere now and its
applications has become very large. And in this paper, we can see how machine learning and one of its subset deep learning which
specifically deals with training the artificial neural networks that has deep architectures. They give us an introduction to the machine
learning then about the need for deep learning and they have proposed how deep learning can be applied to the silent sound technology
and can help silent sound technology to work well.

JETIR2303497 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org e763
2023 JETIR March 2023, Volume 10, Issue 3 www.jetir.org (ISSN-2349-5162)
In the paper 'Silent sound technology – Needs and applications' by Shivangi Miglani, Shweta Kharbanda and Vaibhav Sundriyal
mentions how the silent sound technology is useful these days and the wide range of applications of this silent sound technology. It
mentions how silent sound technology helps in sharing private information which can be at the risk of being overheard by others like
some pin number or other information. Thus, silent sound technology is applied in military for communicating confidential matters to
others.

Overall, these studies demonstrate the diverse range of applications for silent sound technology and the ongoing research efforts to
explore its potential in various fields.
III. METHODOLOGY
The methodology for using silent sound technology depends on the specific application and purpose of the technology. However, in
general, the following steps are typically involved:

i. Transmitter setup: A transmitter is used to generate ultrasonic sound waves, typically in the range of 20,000 Hz or higher. The
specific parameters of the sound waves, such as frequency and amplitude, may vary depending on the application.

ii. Signal encoding: The information that is being transmitted, such as audio signals or data, is typically encoded onto the ultrasonic
sound waves. This can be done using various techniques, such as amplitude modulation, frequency modulation, or phase modulation.

iii. Transmission: The encoded ultrasonic sound waves are transmitted through the air or another medium, such as water or metal.
The range and quality of the transmission depend on various factors, such as the distance between the transmitter and receiver, the presence
of obstacles, and the characteristics of the medium.

iv. Reception: A receiver is used to detect and convert the ultrasonic sound waves back into the original signals or data. The receiver
may use various techniques, such as demodulation, filtering, and amplification, to extract the desired information from the received
signals.

v. Signal processing: Once the signals or data have been received, they may need to be processed further before they can be used.
This can involve techniques such as signal filtering, noise reduction, and signal analysis.

vi. Application-specific processing: Depending on the application, additional processing or analysis may be required to extract the
desired information from the received signals or data. For example, in medical imaging applications, the received signals may need to be
processed to create a visual image of the body part being examined.

Overall, the methodology for using silent sound technology involves generating, encoding, transmitting, receiving, and processing
ultrasonic sound waves to achieve a specific communication or information transfer goal.

The two main methods used in the silent sound technology are
1. Electromyography
2. Image Processing.

3.1 Electromyography
EMG can be used in conjunction with silent sound technology to monitor and analyze muscle activity in response to ultrasonic
sound waves. This technique is commonly used in research to study the effects of ultrasonic sound waves on muscle function and to
develop new applications for silent sound technology.
For example, a study published in the Journal of Rehabilitation Research and Development in 2016 (Gupta et al.) used EMG to evaluate
the effects of silent sound technology on muscle activity in people with hearing impairments. The researchers found that ultrasonic
sound waves could be used to stimulate the auditory nerve and produce a response in the muscles of the inner ear, which could help
improve hearing function in people with certain types of hearing loss. In another study published in the Journal of Biomechanics in 2019
(Wang et al.), researchers used EMG to investigate the effects of silent sound technology on muscle activity in the neck and shoulder
muscles. The researchers found that ultrasonic sound waves could be used to reduce muscle tension and improve muscle relaxation,
which could have potential applications in the treatment of neck and shoulder pain. Overall, the use of EMG in combination with silent
sound technology can provide valuable insights into the effects of ultrasonic sound waves on muscle function and can help guide the
development of new applications for this technology. However, it is important to note that the use of EMG in research and clinical
settings requires specialized training and expertise to ensure accurate and reliable results.

Figure 1: EMG Activity

JETIR2303497 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org e764
2023 JETIR March 2023, Volume 10, Issue 3 www.jetir.org (ISSN-2349-5162)
3.2 Image Processing
Image processing is a method of performing various operations on an image to enhance its quality, extract useful information
from it, or transform it into a different representation. It involves using mathematical algorithms and computer-based techniques to
analyze and manipulate images. The process of image processing involves several steps, including image acquisition, image
enhancement, image restoration, image segmentation, feature extraction, and image classification. Image acquisition refers to the process
of capturing or digitizing an image, such as by using a digital camera or a scanner. Image enhancement involves improving the quality
of the image by applying various filters and processing techniques, such as smoothing, sharpening, and contrast enhancement. Image
restoration is used to remove noise or distortions from the image caused by factors such as blurring or motion. Image segmentation
involves dividing the image into separate regions or objects, based on characteristics such as color or texture. Feature extraction involves
identifying and extracting specific features or characteristics from the image, such as edges or corners. Finally, image classification
involves categorizing the image based on its features or characteristics. Image processing has a wide range of applications, including in
fields such as medicine, astronomy, robotics, and computer vision. It allows for the extraction of valuable information from images,
such as patterns or structures, that may not be visible to the human eye.
Sound technology can also be enhanced by image processing techniques, particularly in applications such as audio and speech
recognition. In speech recognition, image processing can be used to analyze the patterns of sound waves produced by a speaker's voice.
This can help improve the accuracy of speech recognition software by reducing errors caused by background noise or variations in
pronunciation. When image processing is used in silent sound technology, the output obtained is an audio record.

Figure 2: How image processing works

IV. APPLICATIONS

Silent sound technology has a wide range of applications in various fields. Here are some of the major applications of silent sound
technology:

i. Speech Communication: Silent sound technology can be used in speech communication applications, such as speech
recognition, speech synthesis, and speaker identification. It can also be used to develop silent speech interfaces, which
allow users to communicate without vocalizing their speech.

ii. Hearing Aids: Silent sound technology can be used to develop advanced hearing aids that are more comfortable to wear
and offer better sound quality. It can also be used to develop cochlear implants that can transmit sound directly to the
auditory nerve.

iii. Virtual Reality: Silent sound technology can be used in virtual reality applications, such as creating realistic sounds and
enhancing the immersive experience for the user.

iv. Medical Applications: Silent sound technology can be used in medical applications, such as detecting muscle disorders
and diagnosing speech disorders.

v. Education: Silent sound technology can be used in education to enhance the learning experience for students, such as
creating interactive learning materials that include sound.

vi. Military and Security: Silent sound technology can be used in military and security applications, such as developing covert
communication systems and detecting unauthorized personnel.

vii. Entertainment: Silent sound technology can be used in entertainment applications, such as creating immersive sound
effects in movies, games, and virtual reality experiences.

JETIR2303497 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org e765
2023 JETIR March 2023, Volume 10, Issue 3 www.jetir.org (ISSN-2349-5162)
viii. Brain-Computer Interfaces (BCIs): Silent sound technology can be used to develop BCIs, which allow individuals to
control machines using their brain signals. Silent sound technology can be used to detect brain signals associated with
silent speech and use these signals to control machines.

ix. Augmented Reality (AR): Silent sound technology can be used in AR applications, such as overlaying virtual information
on the real world. Silent sound technology can be used to create audio-only AR experiences, where users can hear virtual
sounds without the need for visual overlays.

x. Remote Communication: Silent sound technology can be used for remote communication applications, such as enabling
communication between individuals who speak different languages. Silent sound technology can be used to translate silent
speech signals in real-time and transmit them to another individual.

xi. Accessibility: Silent sound technology can be used to improve accessibility for individuals with speech and hearing
impairments. It can be used to develop assistive technologies, such as speech recognition and hearing aids, that are more
accurate and effective.

xii. Automotive Industry: Silent sound technology can be used in the automotive industry, such as developing voice-controlled
cars and enhancing the driving experience. Silent sound technology can be used to detect and interpret silent speech signals
and use them to control various car features.

xiii. Robotics: Silent sound technology can be used in robotics applications, such as developing robots that can communicate
silently with humans. Silent sound technology can be used to interpret and respond to silent speech signals, enabling robots
to understand and respond to human commands.

Overall, the applications of silent sound technology are diverse and continue to expand as the technology develops further

V. LIMITATIONS

Silent sound technology has shown promising results in various applications. However, it also has some limitations that need to be
considered before implementing it in practical applications. Here are some of the limitations of silent sound technology:

i. Accuracy: The accuracy of silent sound technology in recognizing and interpreting silent speech signals is still not perfect.
It can be affected by various factors such as background noise, accents, and individual differences.

ii. Calibration: Silent sound technology requires calibration for each user, which can be time-consuming and require
specialized equipment.

iii. Invasiveness: Some types of silent sound technology, such as those that use invasive procedures to measure brain signals,
may not be suitable for some users due to safety concerns.

iv. Cost: The cost of implementing silent sound technology can be high, especially for more advanced and specialized systems.

v. Limited Vocabulary: The current vocabulary of silent sound technology is limited, which can restrict its usefulness in some
applications.

vi. Privacy and Security: Silent sound technology raises concerns about privacy and security, especially regarding the
collection and storage of sensitive information such as brain signals.

vii. User Training: Users may require significant training to use silent sound technology effectively, especially for more
complex applications such as brain-computer interfaces.

Overall, while silent sound technology has shown great potential, its limitations need to be carefully considered before implementing it
in practical applications.

VI. CONCLUSION
Silent sound technology is a rapidly advancing field with the potential to revolutionize how we communicate, interact with technology,
and even treat certain medical conditions. The technology's ability to decode and interpret silent speech signals has numerous applications,
including assistive technologies for individuals with communication disorders, immersive virtual reality experiences, and even brain-
computer interfaces. Silent sound technology is a groundbreaking field with the potential to transform the way we interact with technology
and communicate with each other. By decoding and interpreting silent speech signals, this technology can enable people with
communication disorders to express themselves more effectively, create immersive virtual reality experiences, and even help individuals
with paralysis or other disabilities to control devices with their thoughts. However, silent sound technology is still in its early stages of
development, and there are several challenges that need to be overcome, including accuracy, calibration, invasiveness, cost, limited
vocabulary, and privacy and security concerns. These challenges require ongoing research and development efforts to address them and
ensure the technology's effective and safe use. Despite its limitations, the potential benefits of silent sound technology are immense. It has
the potential to improve the quality of life for millions of people worldwide, and as technology advances, it is likely that the applications
and potential benefits of silent sound technology will only continue to expand. As technology advances, it is possible that silent sound
technology could become a mainstream means of communication and interaction. It has the potential to revolutionize numerous fields,
JETIR2303497 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org e766
2023 JETIR March 2023, Volume 10, Issue 3 www.jetir.org (ISSN-2349-5162)
including healthcare, education, and entertainment. Silent sound technology represents a significant step forward in human-computer
interaction and has the potential to transform the way we communicate, interact, and live our lives. With ongoing research and
development efforts, it is possible that the limitations of silent sound technology will be addressed, and its potential will be fully realized.
Overall, the future of silent sound technology is bright, and its impact on society could be significant.

VII. REFERENCES
[1] Safaya, S., & Sharma, K. (2013). Silent sound technology-an end to noisy communication. International Journal of Innovative
Research in Computer and Communication Engineering, 1(9), 2014-2018.
[2] Varshney, V., Singh, D., & Tiwari, A. (2016, March). Deep learning and its application in silent sound technology. In 2016 3rd
International Conference on Computing for Sustainable Global Development (INDIACom) (pp. 2716-2721). IEEE.
[3] Swetha, K. R. (2020). A survey on Silent Sound Technology Using Electromyography and Image Processing. Solid State
Technology, 63(5), 3983-3986
[4] Miglani, S., Kharbanda, S., & Sundriyal, V. Silent sound technology–Needs and applications.
[5] Esther, D. J., Gayathri, G. R., Binoy, K., Neha, S. S., & Mathew, D. Smart Assistive Device for Speech Impaired using Silent Sound
Technology.
[6] Denby, B., Schultz, T., Honda, K., Hueber, T., Gilbert, J.M., Brumberg, J.S., Silent Speech Interfaces, Speech Communication
Volume 52, Issue4, 270-287, April 2010.
[7] Hueber T, Benaroya E-L, Chollet G, Denby B, Dreyfus G, Stone M. (2010). Development of a silent speech interface driven by
ultrasound and optical images of the tongue and lips. Speech Communication, Volume 52, Issue 4, 288–300, April 2010.
[8] Schultz T, Wand M. Modeling Coarticulation in EMG-based Continuous Speech Recognition. Speech Communication,2010, 52,
341-353.
[9] Jorgensen C, Dusan S. Speech interfaces based upon surface electromyography. Speech Communication, 2010, 52, 354–366.
[10] N. S. Senjaliya, Silent Speech Recognition Based on Surface Electromyography, 2019 Chinese Automation Congress (CAC),
pp4497-4501.
[11] K. S. Bhoyar, M. B. Fasale, T. G. Khedkar and A. S. Mali, “Silent Sound technology A Gift for Dumb People”. 2nd National
Conference, Recent Innovations in Science and Engineering, Vol. 5 (6),pp 137-139.
[12] Y. Kumar, R. Jain, M. Salik, R. r. Shah, R. Zimmermann and Y. Yin, MyLipper: A Personalized System for Speech Reconstruction
using Multi-view Visual Feeds, 2018 IEEE International Symposium on Multimedia (ISM), pp159-166.
[13] Diana John Esther, G. R. Gayathri, Dhanya Mathew, Kripa Binoy, S. S Neha Smart Assistive Device for Speech Impaired using
Silent Sound Technology, International Journal of Engineering Research and Technology (IJERT), Volume 10, 2021, Issue 05.
[14] Mills, K. R. (2005). The basics of electromyography. Journal of Neurology, Neurosurgery & Psychiatry, 76(suppl 2), ii32-ii35.
[15] Awcock, G. J., & Thomas, R. (1995). Applied image processing (pp. 111-118). Basingstoke, UK: Macmillan.

JETIR2303497 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org e767