Technology

AI system restores speech for paralyzed patients using own voice

Published

8 months ago

April 16, 2025

AI system restores speech for paralyzed patients using own voice

Researchers in California have achieved a significant breakthrough with an AI-powered system that restores natural speech to paralyzed individuals in real time, using their own voices, specifically demonstrated in a clinical trial participant who is severely paralyzed and cannot speak.

This innovative technology, developed by teams at UC Berkeley and UC San Francisco, combines brain-computer interfaces (BCI) with advanced artificial intelligence to decode neural activity into audible speech.

Compared to other recent attempts to create speech from brain signals, this new system is a major advancement.

STAY PROTECTED & INFORMED! GET SECURITY ALERTS & EXPERT TECH TIPS – SIGN UP FOR KURT’S ‘THE CYBERGUY REPORT’ NOW

AI-powered system (Kaylo Littlejohn, Cheol Jun Cho, et al. Nature Neuroscience 2025)

How it works

The system uses devices such as high-density electrode arrays that record neural activity directly from the brain’s surface. It also works with microelectrodes that penetrate the brain’s surface and non-invasive surface electromyography sensors placed on the face to measure muscle activity. These devices tap into the brain to measure neural activity, which the AI then learns to transform into the sounds of the patient’s voice.

The neuroprosthesis samples neural data from the brain’s motor cortex, the area controlling speech production, and AI decodes that data into speech. According to study co-lead author Cheol Jun Cho, the neuroprosthesis intercepts signals where the thought is translated into articulation and, in the middle of that, motor control.

AI-powered system (Kaylo Littlejohn, Cheol Jun Cho, et al. Nature Neuroscience 2025)

AI ENABLES PARALYZED MAN TO CONTROL ROBOTIC ARM WITH BRAIN SIGNALS

Key advancements

Real-time speech synthesis: The AI-based model streams intelligible speech from the brain in near-real time, addressing the challenge of latency in speech neuroprostheses. This “streaming approach brings the same rapid speech decoding capacity of devices like Alexa and Siri to neuroprostheses,” according to Gopala Anumanchipalli, co-principal investigator of the study. The model decodes neural data in 80-ms increments, enabling uninterrupted use of the decoder, further increasing speed.
Naturalistic speech: The technology aims to restore naturalistic speech, allowing for more fluent and expressive communication.
Personalized voice: The AI is trained using the patient’s own voice before their injury, generating audio that sounds like them. In cases where patients have no residual vocalization, the researchers utilize a pre-trained text-to-speech model and the patient’s pre-injury voice to fill in the missing details.
Speed and accuracy: The system can begin decoding brain signals and outputting speech within a second of the patient attempting to speak, a significant improvement from the eight-second delay in a previous study from 2023.

WHAT IS ARTIFICIAL INTELLIGENCE (AI)?

AI-powered system (Kaylo Littlejohn, Cheol Jun Cho, et al. Nature Neuroscience 2025)

EXOSKELETON HELPS PARALYZED PEOPLE REGAIN INDEPENDENCE

Overcoming challenges

One of the key challenges was mapping neural data to speech output when the patient had no residual vocalization. The researchers overcame this by using a pre-trained text-to-speech model and the patient’s pre-injury voice to fill in the missing details.

AI-powered system (Kaylo Littlejohn, Cheol Jun Cho, et al. Nature Neuroscience 2025)

HOW ELON MUSK’S NEURALINK BRAIN CHIP WORKS

Impact and future directions

This technology has the potential to significantly improve the quality of life for people with paralysis and conditions like ALS. It allows them to communicate their needs, express complex thoughts and connect with loved ones more naturally.

“It is exciting that the latest AI advances are greatly accelerating BCIs for practical real-world use in the near future,” UCSF neurosurgeon Edward Chang said.

The next steps include speeding up the AI’s processing, making the output voice more expressive and exploring ways to incorporate tone, pitch and loudness variations into the synthesized speech. Researchers also aim to decode paralinguistic features from brain activity to reflect changes in tone, pitch and loudness.

SUBSCRIBE TO KURT’S YOUTUBE CHANNEL FOR QUICK VIDEO TIPS ON HOW TO WORK ALL OF YOUR TECH DEVICES

Kurt’s key takeaways

What’s truly amazing about this AI is that it doesn’t just translate brain signals into any kind of speech. It’s aiming for natural speech, using the patient’s own voice. It’s like giving them their voice back, which is a game changer. It gives new hope for effective communication and renewed connections for many individuals.

What role do you think government and regulatory bodies should play in overseeing the development and use of brain-computer interfaces? Let us know by writing us at Cyberguy.com/Contact.

For more of my tech tips and security alerts, subscribe to my free CyberGuy Report Newsletter by heading to Cyberguy.com/Newsletter.

Ask Kurt a question or let us know what stories you’d like us to cover.

Follow Kurt on his social channels:

Answers to the most-asked CyberGuy questions:

New from Kurt:

Kurt “CyberGuy” Knutsson is an award-winning tech journalist who has a deep love of technology, gear and gadgets that make life better with his contributions for Fox News & FOX Business beginning mornings on “FOX & Friends.” Got a tech question? Get Kurt’s free CyberGuy Newsletter, share your voice, a story idea or comment at CyberGuy.com.

Technology

TikTok ban: all the news on the app’s shutdown and return in the US

Published

5 hours ago

December 18, 2025

Press Room

TikTok ban: all the news on the app’s shutdown and return in the US

After briefly going dark in the US to comply with the divest-or-ban law targeting ByteDance that went into effect on January 19th, TikTok quickly came back online. It eventually reappeared in the App Store and Google Play as negotiations between the US and China continued, and Donald Trump continued to sign extensions directing officials not to apply the law’s penalties.

Finally, in mid-December, TikTok CEO Shou Zi Chew told employees that the agreements to create TikTok USDS Joint Venture LLC, which includes Oracle, Silver Lake, and MGX as part owners, have been signed, and the deal is expected to close on January 22nd, 2026. His letter said that for users in the US, the new joint venture will oversee data protection, the security of a newly-retrained algorithm, content moderation, and the deployment of the US app and platform.

Read on for all the latest news on the TikTok ban law in the US.

Technology

Secret phrases to get you past AI bot customer service

Published

5 hours ago

December 18, 2025

Press Room

Secret phrases to get you past AI bot customer service

NEWYou can now listen to Fox News articles!

You’re gonna love me for this.

Say you’re calling customer service because you need help. Maybe your bill is wrong, your service is down or you want a refund. Instead of a person, a cheerful AI voice answers and drops you into an endless loop of menus and misunderstood prompts. Now what?

That’s not an accident. Many companies use what insiders call “frustration AI.” The system is specifically designed to exhaust you until you hang up and walk away.

Not today. (Get more tips like this at GetKim.com)

FOX NEWS POLL: VOTERS SAY GO SLOW ON AI DEVELOPMENT — BUT DON’T KNOW WHO SHOULD STEER

Here are a few ways to bypass “frustration” AI bots. (Sebastian Kahnert/picture alliance via Getty Images)

Use the magic words

You want a human. For starters, don’t explain your issue. That’s the trap. You need words the AI has been programmed to treat differently.

Nuclear phrases: When the AI bot asks why you’re calling, say, “I need to cancel my service” or “I am returning a call.” The word cancel sets off alarms and often sends you straight to the customer retention team. Saying you’re returning a call signals an existing issue the bot cannot track. I used that last weekend when my internet went down, and, bam, I had a human.

Power words: When the system starts listing options, clearly say one word: “Supervisor.” If that doesn’t work, say, “I need to file a formal complaint.” Most systems are not programmed to deal with complaints or supervisors. They escalate fast.

Technical bypass: Asked to enter your account number? Press the pound key (#) instead of numbers. Many older systems treat unexpected input as an error and default to a human.

OPENAI ANNOUNCES UPGRADES FOR CHATGPT IMAGES WITH ‘4X FASTER GENERATION SPEED’

“Supervisor” is one magic word that can get you a human on the other end of the line. (Neil Godwin/Future via Getty Images)

Go above the bots

If direct commands fail with AI, be a confused human.

The Frustration Act: When the AI bot asks a question, pause. Wait 10 seconds before answering. These systems are built for fast, clean responses. Long pauses often break the flow and send your call to a human.

The Unintelligible Bypass: Stuck in a loop? Act like your phone connection is terrible. Say garbled words or nonsense. After the system says, “I’m having trouble understanding you” three times, many bots automatically transfer you to a live agent.

The Language Barrier Trick: If the company offers multiple languages, choose one that’s not your primary language or does not match your accent. The AI often gives up quickly and routes you to a human trained to handle language issues.

Use these tricks when you need help. You are calling for service, not an AI bot.

CLICK HERE TO DOWNLOAD THE FOX NEWS APP

Long pauses and garbled language can also get you referred to a human. (iStock)

Get tech-smarter on your schedule

National radio: Airing on 500-plus stations across the U.S. Find yours or get the free podcast.
Daily newsletter: Join 650,000 people who read the Current (free!)
Watch: On Kim’s YouTube channel

Award-winning host Kim Komando is your secret weapon for navigating tech.

Technology

The latest iPad Air is $400 for the first time and arrives by Christmas

Published

17 hours ago

December 18, 2025

Press Room

The latest iPad Air is 0 for the first time and arrives by Christmas

If you have $400 and want an iPad, your options are usually kind of limited to either just the base iPad, or better yet, the latest iPad Mini — if it happens to be on sale when you’re shopping (it is now, but that’s not always the case). But right now, you should consider getting the 128GB version of Apple’s 11-inch iPad Air with the capable M3 processor. At Target, multiple colors of this model are $399.99, beating the previous low of $449.99 we’ve seen during large-scale deal events. Currently, no other retailer is matching this price. This sale ends Saturday night.

$400 is a sweet price for this model, as it debuted in early 2025 for $600. In terms of how it stacks up to other iPad models, Verge editor-at-large David Pierce said in his impressions that the M3 Air is “exactly what you think it is. Which is fine.” I know, that sounds like a back-handed compliment, but it’s been a while since iPads peaked in terms of utility, design, and fast performance. This one carries the torch in Apple’s tablet dominance, and its M3 processor means it’ll be a fantastic tablet for longer than any other iPad at the $400 price point. Read our in-depth impressions.