Connect with us

News

Scientists use AI neural network to translate speech from brain activity

Published

on

Three recently published studies focused on using artificial intelligence (AI) neural networks to generate audio output from brain signals have shown promising results, namely by producing identifiable sounds up to 80% of the time. Participants in the studies first had their brain signals measured while they were either reading aloud or listening to specific words. All the data was then given to a neural network to “learn” how to interpret brain signals after which the final sounds were reconstructed for listeners to identify. These results represent hopeful prospects for the field of brain-computer interfaces (BCIs), where thought-based communication is quickly moving from the realm of science fiction to reality.

The idea of connecting human brains to computers is far from new. In fact, several relevant milestones have been made in recent years including enabling paralyzed individuals to operate tablet computers with their brain waves. Elon Musk has also famously brought attention to the field with Neuralink, his BCI company that essentially hopes to merge human consciousness with the power of the Internet. As brain-computer interface technology expands and develops new ways to foster communication between brains and machines, studies like these, originally highlighted by Science Magazine, will continue demonstrating the steady march of progress.

Functional areas of the human brain. | Credit: Blausen.com staff (2014) via CC BY 3.0.

In the first study conducted by researchers from Columbia University and Hofstra Northwell School of Medicine, both in New York, five epileptic participants had the brain signals from their auditory cortexes recorded as they listened to stories and numbers being read to them. The signal data was provided to a neural network for analysis which then reconstructed audio files that were accurately identified by participating listeners 75% of the time.

In the second study conducted by a team from the University of Bremen (Germany), Maastricht University (Netherlands), Northwestern University (Illinois), and Virginia Commonwealth University (Virginia), brain signal data was gathered from six patients’ speech planning and motor areas while undergoing tumor surgeries. Each patient read specific words aloud to target the data collected. After the brain data and audio data were given to their neural network for training, the program was given brain signals not included in the training set to recreate audio, the result producing words that were recognizable 40% of the time.

Finally, in a third study by a team at the University of California, San Francisco, three participants with epilepsy read text aloud while brain activity was captured from the speech and motor areas of their brains. The audio generated from their neural network’s analysis of the signal readings was presented to a group of 166 people who were asked to identify the sentences from a multiple choice test – some sentences were identified with 80% accuracy.

While the research presented in these studies shows serious progress towards connecting human brains to computers, there are still a few significant hurdles. For one, the way neuron signal patterns in the brain translate into sounds varies from person to person, so neural networks must be trained on each individual person. The best results require the best data possible, i.e., the most precise neuron signals possible, meaning this is something that can only be obtained by placing electrodes in the brain itself. The opportunities to collect data at this invasive level for research are limited, relying on voluntary participation and approval of experiments.

Advertisement

All three of the studies highlighted demonstrated an ability to reconstruct speech based on neural data in some significant capacity; however, also in all cases, the study participants were able to create audible sounds to use with the computer training set. In the case of patients unable to speak, the level of difficultly in interpreting the brain’s speech signals from other signals will be the biggest challenge. Also, the differences between brain signals during actual speech vs. thinking about speech will complicate matters further.

Accidental computer geek, fascinated by most history and the multiplanetary future on its way. Quite keen on the democratization of space. | It's pronounced day-sha, but I answer to almost any variation thereof.

Advertisement
Comments

Investor's Corner

Cantor Fitzgerald raises Tesla PT To $510, citing Cybercab, Semi, and AI momentum

The firm cited upcoming production milestones for the Cybercab, Semi, and Optimus as key drivers behind its revised valuation.

Published

on

Credit: Tesla Asia/X

Cantor Fitzgerald has boosted its Tesla (NASDAQ:TSLA) price target from $355 to $510 per share, maintaining an “Overweight” rating over its continued confidence in the company’s long-term growth. 

Analyst Andres Sheppard cited upcoming production milestones for the Cybercab, Semi, and Optimus as key drivers behind Cantor Fitzgerald’s revised valuation, as well as expanding opportunities in Tesla’s Energy and Full Self-Driving initiatives.

Major growth from multiple Tesla programs

According to Sheppard, Tesla disclosed that volume production for the Cybercab, Semi, and Megapack 3 is on track for fiscal year 2026, with Optimus production lines also targeted to launch next year. The analyst highlighted these updates as “significant,” noting that Tesla’s diverse roadmap continues to reinforce its position as a vertically integrated energy and AI company.

Cantor Fitzgerald now expects Tesla’s capital expenditures at approximately $9.2 billion for FY2025 and around $12 billion for FY 2026, a substantial increase tied to the company’s efforts to further scale its operations. The analyst noted that these investments align with Tesla’s push into robotics, autonomous driving, and energy storage.

Confidence in AI-driven expansion

Tesla shares closed at $433.72 last Friday, giving Cantor Fitzgerald’s $510 price target an implied upside of roughly 17.6%. The revised forecast reflects the firm’s expectation that Tesla’s long-term value extends far beyond vehicle sales, with strong upside from the company’s FSD, Robotaxi/Cybercab, Semi, and Optimus initiatives, as noted in a StreetInsider report.

Advertisement

“Overall, we remain bullish on TSLA over the medium to long term,” Sheppard wrote. “We continue to see meaningful future upside from Energy Storage & Deployment, FSD, Robotaxis/Cybercab, Semis, and Optimus Bots.”

Tesla highlighted these key initiatives in its Q3 2025 Update Letter. “We continue to evolve and augment our product lineup with a focus on cost, scale and future monetization opportunities via services powered by our AI software. Cybercab, Tesla Semi and Megapack 3 are on schedule for volume production starting in 2026,” the company wrote.

Continue Reading

News

Tesla is ramping its hiring for Cybercab vehicle manufacturing roles

A check of the company’s Careers website shows 30 open positions tied to the Cybercab project, with 25 focused directly on vehicle manufacturing.

Published

on

Credit: Tesla/YouTube

Tesla is accelerating preparations for its upcoming Cybercab by rapidly expanding its hiring efforts in Austin, Texas. 

A check of the company’s Careers website shows 30 open positions tied to the Cybercab project, with 25 focused directly on vehicle manufacturing. The spike in listings suggests that Tesla may be gearing up for a production ramp of its fully autonomous two-seater at Giga Texas.

New Cybercab job listings

Tesla’s Careers page now features several new roles that appear crucial to the Cybercab’s buildout. Among the most recent additions are openings for Engineering Technicians for the Cybercab’s drive units, battery pack, and general assembly, as well as positions for Equipment Technicians for the vehicle’s production lines.

Earlier this month, Tesla only had three openings related to the autonomous two-seater’s manufacturing. Even then, it was already exciting as the Cybercab would be produced using Tesla’s “Unboxed” manufacturing process. This process is designed to make the Cybercab easier and quicker to produce. 

Similar to previous Cybercab-related job listings, all of the openings are currently based in Austin, Texas. This suggests that for now, at least, the production of the Cybercab will really be focused on Giga Texas to start.

Advertisement

Ultra-fast Cybercab production targets

Tesla CEO Elon Musk has described the Cybercab as the company’s highest-volume vehicle yet, targeting an annual production rate of around 2 million units. He added that the Cybercab line will operate more like a “high-speed consumer electronics” assembly process than a conventional car factory.

“If you’ve seen the design of the Cybercab line, it doesn’t look like a normal car manufacturing line,” Musk said earlier this year. “It looks like a really high-speed consumer electronics line. In fact, the line will move so fast that actually people can’t even get close to it.”

Continue Reading

Elon Musk

Memphis to use xAI taxes for neighborhood improvements: “Truly a blessing”

City officials confirmed that the funds will be reinvested in local neighborhoods near xAI’s Colossus supercomputer.

Published

on

Credit: xAI/X

The City of Memphis has collected all taxes owed by Elon Musk’s xAI before the payment deadline, creating a $3.2 million special revenue fund to support communities affected by the company’s operations. 

City officials confirmed that the funds will be reinvested in local neighborhoods near xAI’s Colossus supercomputer.

Directing xAI funds toward community projects

Mayor Paul Young’s administration recently outlined how the funds will be allocated. The initiative was focused on improving infrastructure and quality of life in neighborhoods impacted by xAI’s construction and operations. 

Councilwoman Yolanda Cooper-Sutton emphasized that the process will include public input, with surveys already distributed to residents to guide spending priorities, according to ABC24.

“With that ordinance, we are in the near future getting ready to set up the committee because this is the people’s money,” Cooper-Sutton said. “We wanna make sure that it is used for the people.”

Advertisement

Officials noted that they are planning to present a final proposal to the entire council after reviewing community feedback. Cooper-Sutton added that the program represents a step toward ensuring businesses operating in Memphis treat residents “fairly and with equality.”

“It is truly, truly a blessing. What we are doing here at this body and this council, we wanna make sure that whatever business that comes here, that the people are treated fairly and with equality,” she stated. 

xAI partnership fuels local job opportunities

Beyond tax revenue, xAI’s growing presence is expected to bolster Memphis’ workforce development goals. Earlier this month, the artificial intelligence startup co-hosted a job fair at Crosstown Concourse with the American Job Center to connect residents with new employment pathways.

“We know that jobs are coming. We know that talent is here,” Melody Freemon, executive director of the Greater Memphis Workforce Development Board, stated. “We wanna make sure we’re not just putting people in any ole jobs. We wanna put people on a pathway to self-sustainability. We wanna put people on a pathway to self-sustainability and something they can rely on in the future.”

Freemon also noted that the Greater Memphis Workforce Development Board was able to make a favorable offer to xAI. “We promised that we can provide a pipeline. This is the central hub for connection. This is where job seekers are, so let us take the headache off of your hiring needs. Come here, let us source the people and make sure that we meet the demand,” Freeman stated.

Advertisement
Continue Reading

Trending