Towards Ultrasonic whispering over distances of 30 meters
An experimental device lets you whisper in the ear of someone up to 30 meters away. The wearable tech uses ultrasound to beam a speaker's words directly to a targeted individual without anyone else overhearing what is being said. It currently requires a large speaker mounted on your forehead and the electrodes stuck around your mouth.
There is further investigation in increasing its reach with more powerful directional speakers and make it work underwater with water-coupled ultrasonic transducers.
The accuracy in discriminating words still has to be improved if these systems had to be used in real scenarios, they hope that further progress in wearable transparent electrodes such as Second Skin will improve the signals and make the system less cumbersome. The advances in smart textiles and wearable computing will also improve this aspect.
The directivity of the speakers could be improved but not by increasing their size since they have to be wearable, one possible solution would be manufacturing custom transducers that operate in air at higher frequencies.
Abstract
Speech is our innate way of communication. However, it has limitation such as being a broadcast process, it has limited reach and it only works in air. Here, we explore the combination of two technologies for realizing natural targeted communication with potential applications in coordination of tasks or private conversations. For detecting words, we measure the bioelectric signals produced by facial muscles during speech. An electromyographic system composed of 4 surface electrodes had an accuracy of 80% when discriminating between 10 words. More importantly, the system was equally effective in discriminating spoken and silently mouthed words. For transferring the words, we used the sound-through-ultrasound phenomenon to generate audible sound within a narrow beam. We built a phased array of ultrasonic emitters, capable of emitting sound that can be steered electronically without physically moving the array. Two prototypes that combine detection and transfer of words are presented and their limitations analysed.
Later versions of the system could help soldiers communicate without alerting anyone to their presence. Ultrasound travels particularly well underwater so it could also be used to help divers communicate over long distances.
To use Marzo's device, a person first attaches a speaker to their forehead or chest and four electrodes to their lips and jaw. Using a technology known as electromyography, the electrodes capture the electrical signals produced by the facial muscles as a person talks.
Marzo and his colleagues then used a machine learning algorithm trained to recognise which electrical muscle signals were associated with 10 words, including "back", "stop", "yes" and "no". When tested, the system could recognise the correct word more than 80 per cent of the time, even if the person wearing the electrodes was only mouthing them.
The word-recognition system was then paired with wearable speakers that played an ultrasonic recording of the words that a person whispered or mouthed. The speakers emit ultrasound in a narrow beam, at a six-degree angle, so that only people directly in its path would hear the words being spoken.
