Back to News

Breaking the Barrier of Silent Speech with AI: The Revolutionary EchoSpeech Eyeglasses

Aug 2 2023

When we hear about new breakthroughs in artificial intelligence, we often think of AI-powered chatbots like ChatGPT or AI generators for creatives like Midjourney. However, these are just a few examples of what AI can provide. AI is also making significant strides in other areas to help society, and one of the most recent technological breakthroughs is AI-equipped eyeglasses that can read silent speech.

Meet EchoSpeech, an AI tool developed by Cornell University's Smart Computer Interfaces for Future Interactions (SciFi) Lab which can recognize up to 31 unvocalized commands.

How is EchoSpeech able to recognize silent speech? In this blog article, we'll delve into the role that AI plays in making these glasses possible, explore their benefits, and take a look at what the future holds for this groundbreaking technology.

Let's begin by defining what silent speech is and how technology interprets it

Silent speech, also known as subvocalization, is when you internally articulate words or thoughts without speaking them aloud. Even when people silently speak, their tongue, lips, and vocal cords still move slightly, resulting in small muscle contractions which can be detected by sensors placed on the neck or face. Unlike reading, silent speech does not rely on visual cues from written language.

Sensors such as electromyography (EMG) electrodes, accelerometers, and other wearable devices can detect the subtle muscle movements in the face or neck that occur during internal speech, which can then be translated into text or speech. These sensors can be integrated into glasses or headsets to help develop glasses that can read silent speech.

AI plays a vital role in this development of glasses that read silent speech, as machine learning algorithms and other AI techniques analyze the muscle movements detected by the sensors and translate them into text or speech. AI can also enhance the overall performance of the glasses through personalized speech recognition and noise cancellation, improving the accuracy and speed of the translation.

One of the main advantages of silent speech technology is that it offers people the opportunity to communicate silently without needing to vocalize. This can be particularly useful for individuals with speech disorders, people who are deaf or hard of hearing, and military or law enforcement personnel who need to communicate covertly.

What is the technology behind EchoSpeech?

EchoSpeech is an AI-powered eyeglass that detects and interprets subtle movements involved in silent speech, such as lip and mouth movements. It uses speakers and microphones embedded in a glass frame to send and receive sound waves across the face while sensing mouth movements, similar to a wearable sonar system.

Additionally, EchoSpeech has a deep learning algorithm that analyzes the echo profiles in real time and stores the detections on the user's smartphone. According to Ruidong Zhang, the lead author of “EchoSpeech: Continuous Silent Speech Recognition on Minimally-obtrusive Eyewear Powered by Acoustic Sensing”, this technology can be particularly beneficial for those who cannot vocalize sound, as it can be an excellent input for a voice synthesizer.

Furthermore, EchoSpeech could be used to help people communicate via a smartphone in places where speaking may be inappropriate or difficult, such as a library or concert. And this technology also removes the need for cameras and requires less bandwidth to process and be relayed to a smartphone via Bluetooth than image or video data.

One of the most interesting features of EchoSpeech, due to its acoustic sensing, is its low power consumption, which can run for up to 10 hours. Whereas other experimental camera-based systems can only run up to 30 minutes after charging. Additionally, EchoSpeech’s data is processed on the user’s smartphone instead of a cloud, making it privacy sensitive.

What’s in store with this technology?

The team behind EchoSpeech is exploring the potential of this groundbreaking technology and is working towards commercializing it. Once this technology becomes widely available to the public, it has the potential to break down barriers to communication for people with speech disabilities and hearing impairments, enabling fluid and seamless communication like never before.

In addition, researchers at SciFi Lab are investigating smart-glass applications to track facial, eye, and upper body movements, which could potentially be integrated into virtual reality helmets to animate users' avatars.

In conclusion, EchoSpeech is an innovative technology that has the potential to revolutionize the way we communicate, and we can't wait to see what the future holds for this exciting development.

At Ultim Marketing, we're always at the forefront of the latest technological advancements and include the use of AI in all of our services. Whether you're looking to integrate AI into your marketing strategy or explore the possibilities of emerging technologies, we have the expertise to help you achieve your goals. Contact us today to learn more about how we can help your business grow within your market with the use of AI.

Share socially