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.
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.
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.
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.
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.
Follow Kurt on his social channels:
Answers to the most-asked CyberGuy questions:
New from Kurt:
Copyright 2025 CyberGuy.com. All rights reserved.
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Business Upturn
3 hours ago
- Business Upturn
PromptQL Partners with UC Berkeley to Develop New Data Agent Benchmark for Reliability of Enterprise AI Agents
BERKELEY, Calif., June 04, 2025 (GLOBE NEWSWIRE) — PromptQL , a platform for reliable AI, today announced a strategic research collaboration with the University of California, Berkeley to develop the first comprehensive data agent benchmark for enterprise reliability specifically designed to evaluate general-purpose AI data agents in enterprise environments. A recent McKinsey study revealed that 78% of organizations use AI in at least one business function, however, more than 80% say their organization hasn't seen a tangible impact on enterprise-level Earnings Before Interest and Taxes (EBIT). The partnership – led by Aditya Parameswaran, Professor and Co-Director of UC Berkeley's EPIC Data Lab , along with his students – addresses this fundamental challenge organizations face when deploying AI systems in business-critical environments. While existing agentic data benchmarks like GAIA, Spider, and FRAMES test specific AI tasks, they overlook the complexity, reliability demands, and messy, siloed data that define real business environments. The forthcoming data agent benchmark aims to offer a solution by creating a framework that reflects real-world complexities. 'Our customer conversations reveal a clear pattern—they're ready to move from proof-of-concepts to production AI, yet they lack the evaluation tools to make confident deployment decisions,' said Tanmai Gopal, CEO of PromptQL. 'The data agent benchmark changes that by using representative datasets from our work in telecom, healthcare, finance, retail, and anti-money laundering to reflect the real complexity of enterprise AI.' UC Berkeley's EPIC Data Lab brings expertise to this collaboration. Professor Parameswaran is a leading authority on the use of AI for next-gen usable data analysis tools and has received numerous prestigious awards. His research group has created widely-adopted data tools with tens of millions of downloads. 'Current benchmarks suffer from what I call the '1% problem'—they're built for tech giants and ignore the 99% of organizations grappling with real-world data complexity,' Parameswaran said. 'The data agent benchmark marks a shift toward evaluating AI based on the reliability, transparency, and practical value enterprises actually need. This collaboration bridges academic rigor with the production insights PromptQL brings from real deployments.' The data agent benchmark beta will be revealed later this year. Organizations interested in early access or contributing use-cases or datasets can reach out to the research team at [email protected] . PromptQL will be at AI Engineer World's Fair , June 3-6 in San Francisco. Tanmai Gopal, PromptQL's co-founder and CEO, will present a session, 'Al Automation that Actually Works: $100M Impact on Messy Data with Zero Surprises,' on June 4 at 11:15 a.m. PT. To learn more or schedule a demo at the PromptQL booth, visit . About PromptQL PromptQL is a next-generation AI platform from the makers of Hasura, the company behind the pioneering GraphQL Engine. Built for enterprise-grade reliability, PromptQL enables natural language analysis and automation on internal business data — with an industry-first accuracy SLA. By learning the unique language of your business and planning tasks before executing them deterministically, PromptQL brings human-level precision to AI agents. About UC Berkeley EPIC Data Lab The EPIC Data Lab at UC Berkeley develops low-code and no-code interfaces for data work, powered by Gen AI. Co-Led by Professor Aditya Parameswaran, the lab follows Berkeley's tradition of multidisciplinary systems research with emphasis on real-world impact and practical deployment. The lab's tools, including DocETL and other widely-adopted systems, demonstrate Berkeley's leadership in democratizing data science capabilities. Media Contact:Erica Anderson Offleash for PromptQL [email protected]
Yahoo
3 hours ago
- Yahoo
PromptQL Partners with UC Berkeley to Develop New Data Agent Benchmark for Reliability of Enterprise AI Agents
New benchmark to address critical gap in evaluating AI systems for mission-critical business operations BERKELEY, Calif., June 04, 2025 (GLOBE NEWSWIRE) -- PromptQL, a platform for reliable AI, today announced a strategic research collaboration with the University of California, Berkeley to develop the first comprehensive data agent benchmark for enterprise reliability specifically designed to evaluate general-purpose AI data agents in enterprise environments. A recent McKinsey study revealed that 78% of organizations use AI in at least one business function, however, more than 80% say their organization hasn't seen a tangible impact on enterprise-level Earnings Before Interest and Taxes (EBIT). The partnership – led by Aditya Parameswaran, Professor and Co-Director of UC Berkeley's EPIC Data Lab, along with his students – addresses this fundamental challenge organizations face when deploying AI systems in business-critical environments. While existing agentic data benchmarks like GAIA, Spider, and FRAMES test specific AI tasks, they overlook the complexity, reliability demands, and messy, siloed data that define real business environments. The forthcoming data agent benchmark aims to offer a solution by creating a framework that reflects real-world complexities. "Our customer conversations reveal a clear pattern—they're ready to move from proof-of-concepts to production AI, yet they lack the evaluation tools to make confident deployment decisions,' said Tanmai Gopal, CEO of PromptQL. 'The data agent benchmark changes that by using representative datasets from our work in telecom, healthcare, finance, retail, and anti-money laundering to reflect the real complexity of enterprise AI.' UC Berkeley's EPIC Data Lab brings expertise to this collaboration. Professor Parameswaran is a leading authority on the use of AI for next-gen usable data analysis tools and has received numerous prestigious awards. His research group has created widely-adopted data tools with tens of millions of downloads. "Current benchmarks suffer from what I call the '1% problem'—they're built for tech giants and ignore the 99% of organizations grappling with real-world data complexity,' Parameswaran said. 'The data agent benchmark marks a shift toward evaluating AI based on the reliability, transparency, and practical value enterprises actually need. This collaboration bridges academic rigor with the production insights PromptQL brings from real deployments.' The data agent benchmark beta will be revealed later this year. Organizations interested in early access or contributing use-cases or datasets can reach out to the research team at epic-support@ PromptQL will be at AI Engineer World's Fair, June 3-6 in San Francisco. Tanmai Gopal, PromptQL's co-founder and CEO, will present a session, 'Al Automation that Actually Works: $100M Impact on Messy Data with Zero Surprises,' on June 4 at 11:15 a.m. PT. To learn more or schedule a demo at the PromptQL booth, visit About PromptQLPromptQL is a next-generation AI platform from the makers of Hasura, the company behind the pioneering GraphQL Engine. Built for enterprise-grade reliability, PromptQL enables natural language analysis and automation on internal business data — with an industry-first accuracy SLA. By learning the unique language of your business and planning tasks before executing them deterministically, PromptQL brings human-level precision to AI agents. About UC Berkeley EPIC Data LabThe EPIC Data Lab at UC Berkeley develops low-code and no-code interfaces for data work, powered by Gen AI. Co-Led by Professor Aditya Parameswaran, the lab follows Berkeley's tradition of multidisciplinary systems research with emphasis on real-world impact and practical deployment. The lab's tools, including DocETL and other widely-adopted systems, demonstrate Berkeley's leadership in democratizing data science capabilities. Media Contact:Erica Anderson Offleash for PromptQLpromptql@ Research Contact:Professor Aditya ParameswaranUC Berkeley EPIC Data Labepic-support@ in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data
Yahoo
4 hours ago
- Yahoo
Mark Cuban Makes Major Donation To Jeff Cannonball ALS GoFundMe Campaign
Mark Cuban came through in a big way. Jeff Cannonball is an independent wrestler based in the New Jersey area. You might also know him from his humorous 'Short Soda Reviews' or his brief run in MLW. Cannonball recently announced some unfortunate news, as he was recently diagnosed with ALS (Amyotrophic Lateral Sclerosis). ALS is more commonly known as 'Lou Gehrig's Disease,' and it is a neurodegenerative disease that leads to eventual paralysis and death. Cannonball's family, which includes his wife, former indie wrestler Terra Calaway, organized a GoFundMe campaign to help offset the costs of all of the changes in his life. This includes him being unable to work, incoming medical bills, and other adjustments, like needing to find a single-story home that accommodates his needs. The campaign has gotten a lot of support so far. Former Dallas Mavericks owner Mark Cuban made a huge donation to the campaign on Tuesday night by contributing $10,000. Cuban did not comment on the donation, but he has been active in fighting for better healthcare options and prescription costs through his Cost Plus Drugs company. The GoFundMe campaign is currently at 84% of its $100,000 funding goal. However, you can continue to share the campaign and make a donation if you are able to here. There is currently no cure for ALS. People with ALS have a typical lifespan of 3-5 years after diagnosis. However, that timespan can vary and some individuals can live longer. You can learn more about ALS on the Mayo Clinic website or through the ALS Assocation. The post Mark Cuban Makes Major Donation To Jeff Cannonball ALS GoFundMe Campaign appeared first on Wrestlezone.
