alterego is a AI intelligent headset developed by MIT media lab that picks up on neuromuscular signals that trigger when you subvocalize – that’s talking in your head in layman’s terms. the system consists of a wearable device and an associated computing system that can transcribe words that the user verbalizes internally but does not speak aloud.
electrodes in the device pick up neuromuscular signals in the jaw and face that are triggered by internal verbalizations — saying words ‘in your head’ — but are undetectable to the human eye. the signals are then fed to a machine-learning system that has been trained to correlate particular signals with particular words.
video by MIT media lab
the idea seems like pure science fiction but in fact, internal verbalizations and their physical correlations s have been a serious thought and study since the 19th centure. one of the goals of the speed-reading movement of the 1960s was to eliminate internal verbalization, or ‘subvocalization,’ as it’s known.
‘the motivation for this was to build an IA device — an intelligence-augmentation device,’ says arnav kapur, a graduate student at the MIT media lab, who led the development of the new system. ‘our idea was: could we have a computing platform that’s more internal, that melds human and machine in some ways and that feels like an internal extension of our own cognition?‘
artificial intelligence (67 articles)
google demonstrates 'quantum supremacy', a major computing breakthrough
lexus unveils electric LF-30 concept with drone-deploying capabilities
extremely dextrous robot arm uses AI to solve rubik's cube one-handed
the toyota LQ features an air-purifying layer that reduces ozone emissions
AI created a ‘portrait of hunger' by scanning the faces of 1,000 people in need
refik anadol induces a 'machine hallucination' at ARTECHOUSE in new york's chelsea market
MIT media lab (48 articles)
MIT researchers find new approach suggesting path to emissions-free cement
MIT creates robotic thread designed to crawl through the human brain
autonomous boats connect to form movable bridges in amsterdam
wearable technology (213 articles)
virgin galactic unveils under armour astronaut suits for future tourist flights
a brain-controlled exoskeleton helps paralysed man walk again
the sound shirt lets deaf people feel music on their skin
technology news
aston martin's first motorcycle is 'automotive art for the motorbike connoisseur'
#technology
the bike – strictly limited to just 100 examples – features a strong, sculptural body form, accented by a carbon fiber fin.
the bike – strictly limited to just 100 examples – features a strong, sculptural body form, accented by a carbon fiber fin.
chevrolet unveils retro E-10 electric pickup based on 1962 model
#technology
the E-10 concept is based on a 1962 C-10 pickup truck, imagining a retro-vintage future for hot rodding.
the E-10 concept is based on a 1962 C-10 pickup truck, imagining a retro-vintage future for hot rodding.
CAKE's ösa electric motorcycle doubles as a customizable workbench on wheels
#technology
the modular design comes with over 1,000 possible combinations to power various on- and off-grid pursuits.
the modular design comes with over 1,000 possible combinations to power various on- and off-grid pursuits.
the ocean cleanup unveils floating garbage truck that catches plastic in rivers
#technology
the solar-powered floating device is designed to scoop plastic out of rivers before it reaches oceans.
the solar-powered floating device is designed to scoop plastic out of rivers before it reaches oceans.
So…remote cameras can already translate the vibration of houseplant leaves into conversations in a distant apartment. Looks like a short hop, using this tech, to reading our unexpressed thoughts next?
My son had a stroke is now non-verbal – where & when can I get this???
@Paul – The device reads “intended” subvocalized speech i.e. when you read words in your head but don’t vocalize. It does not read your thoughts. In fact reading thoughts is noise and from what I understand, the researchers went ahead with this modality to avoid reading the noise and capture voluntary intentions.
@Laura – This is still in early stages of development, but hopefully will reach a level when it starts make a more tangible impact and help people who have undergone strokes etc to “speak”