News
Scientists use AI neural network to translate speech from brain activity
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.
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.
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.
Tesla Board Chair Robyn Denholm met with Bloomberg this morning to discuss a variety of topics, but perhaps one of the most interesting was her comments on what is being done to protect company CEO Elon Musk.
After the assassination of right-wing political commentator Charlie Kirk this week, there have been concerns about Musk’s safety, as well as that of other high-profile business leaders and political figures.
Earlier this week, Musk said himself that his security detail would be increased significantly following Kirk’s death, a move that many investors and fans of the company had requested because of political violence.
Elon Musk assures Tesla investors he will enhance his security detail
“Definitely need to enhance security,” Musk said. Tesla spent $3.3 million on Musk’s security in 2024 and January and February 2025. For reference, Meta spent over $27 million on Mark Zuckerberg’s security last year, which is higher than any other tech CEO.
During Denholm’s appearance on Bloomberg TV earlier today, she stated that the company has been focused on Musk’s security detail for “many years,” especially considering he is one of the richest people on Earth and holds an incredible amount of influence.
“It is something that we take very seriously; he takes it very seriously as well. So, again, from a board perspective, it is something we’ve discussed at length,” Denholm said.
Tesla Board Chair Robyn Denholm on increased security for CEO Elon Musk:
— TESLARATI (@Teslarati) September 12, 2025
Denholm added that she believes “there is not anyone in a boardroom that is not touched by what has happened with Charlie Kirk.”
Although Musk’s political involvement has toned down significantly in the past, he still has enemies, especially based on groups that oppose him and the company specifically. Based on this week’s events, it feels that increased security is a necessary expense Tesla must account for.
Investor's Corner
Tesla bear turns bullish for two reasons as stock continues boost
“I think from a trading perspective, it looks very interesting,” Nathan said, citing numerous signs of strength, such as holding its 200-day moving average and holding against its resistance level.
A Tesla bear is changing his tune, turning bullish for two reasons as the company’s stock has continued to get a boost over the past month.
Dan Nathan, a notorious skeptic of Tesla shares, said he is changing his tune, at least in the short term, on the company’s stock because of “technicals and sentiment,” believing the company is on track for a strong Q3, but also an investment story that will slowly veer away from its automotive business.
“I think from a trading perspective, it looks very interesting,” Nathan said, citing numerous signs of strength, such as holding its 200-day moving average and holding against its resistance level.
He also said he believes a rally for the stock could continue as it heads into the end of the quarter, especially as the $7,500 electric vehicle tax credit is coming to an end at the end of the month.
With that being said, he believes the consensus for Q3 deliveries is “probably low,” as he believes Wall Street is likely underestimating what Tesla will bring to the table on October 1 or 2 when it reports numbers for the quarter.
Tesla bear Dan Nathan has flipped his script on Tesla $TSLA shares, citing “technicals and sentiment”
— TESLARATI (@Teslarati) September 12, 2025
Tesla shares are already up over five percent today, with gains exceeding nine percent over the past five trading days, and more than fourteen percent in the past month.
While some analysts are looking at the performance of other Mag 7 stocks, movement on rates from the Federal Reserve, and other broader market factors as reasoning for Tesla’s strong performance, it appears some movement could be related to the company’s recent developments instead.
Over the past week, Tesla has made some strides in its Robotaxi program, including a new license to test the platform in the State of Nevada, which we reported on.
Tesla lands regulatory green light for Robotaxi testing in new state
Additionally, the company is riding the tails of the end of the EV tax credit, as inventory, both new and used, is running extremely low, generally speaking. Many markets do not have any vehicles to purchase as of right now, making delivery by September 30 extremely difficult.
However, there has been some adjustments to the guidelines by the IRS, which can be read here:
Tesla is trading at around $389 at 10:56 a.m. on the East Coast.
News
Tesla lands regulatory green light for Robotaxi testing in new state
This will be the third state in total where Tesla is operating Robotaxi, following Austin and California.
Tesla has landed a regulatory green light to test its Robotaxi platform in a new state, less than three months after the ride-hailing service launched in Texas.
Tesla first launched its driverless Robotaxi suite in Austin, Texas, back on June 22. Initially offering rides to a small group of people, Tesla kept things limited, but this was not to be the mentality for very long.
It continued to expand the rider population, the service area, and the vehicle fleet in Austin.
The company also launched rides in the Bay Area, but it does use a person in the driver’s seat to maintain safety. In Austin, the “Safety Monitor” is present in the passenger’s seat during local rides, and in the driver’s seat for routes that involve highway driving.
Tesla is currently testing the Robotaxi platform in other states. We reported that it was testing in Tempe, Arizona, as validation vehicles are traveling around the city in preparation for Robotaxi.
Tesla looks to make a big splash with Robotaxi in a new market
Tesla is also hoping to launch in Florida and New York, as job postings have shown the company’s intention to operate there.
However, it appears it will launch in Nevada before those states, as the company submitted its application to obtain a Testing Registry certification on September 3. It was processed by the state’s Department of Motor Vehicles Office of Business Licensing on September 10.
NEWS: Tesla has officially received approval from the Nevada DMV to start testing autonomous vehicles (robotaxis) on public roads.
Today, I confirmed directly with the Nevada DMV that @Tesla‘s application to obtain a Testing Registry certification was approved by the DMV Office… pic.twitter.com/hx5JhHBFiD
— Sawyer Merritt (@SawyerMerritt) September 11, 2025
It will then need to self-certify for operations, essentially meaning they will need to comply with various state requirements.
This will be the third state in total where Tesla is operating Robotaxi, following Austin and California.
CEO Elon Musk has stated that he believes Robotaxi will be available to at least half of the U.S. population by the end of the year. Geographically, Tesla will need to make incredible strides over the final four months of the year to achieve this.
Tesla Board Chair discusses what is being done to protect CEO Elon Musk
Tesla bear turns bullish for two reasons as stock continues boost
Tesla lands regulatory green light for Robotaxi testing in new state
-
News2 weeks agoTesla is overhauling its Full Self-Driving subscription for easier access
-
Elon Musk2 weeks agoElon Musk shares unbelievable Starship Flight 10 landing feat
-
Elon Musk1 week agoTesla’s next-gen Optimus prototype with Grok revealed
-
News6 days agoTesla launches new Supercharger program that business owners will love
-
Elon Musk6 days agoTesla Board takes firm stance on Elon Musk’s political involvement in pay package proxy
-
News2 weeks agoTesla appears to be mulling a Cyber SUV design
-
News1 week agoTesla deploys Unsupervised FSD in Europe for the first time—with a twist
-
News2 weeks agoTesla expands crazy new lease deal for insane savings on used inventory