AI built from living brain cells can recognise voices

Brainoware computer can identify people by their voice

Anthony Cuthbertson
Tuesday 12 December 2023 07:33 EST
Comments
Brain organoids grown from stem cells have raised ethical concerns about how they are used
Brain organoids grown from stem cells have raised ethical concerns about how they are used (Stanford University)

Your support helps us to tell the story

From reproductive rights to climate change to Big Tech, The Independent is on the ground when the story is developing. Whether it's investigating the financials of Elon Musk's pro-Trump PAC or producing our latest documentary, 'The A Word', which shines a light on the American women fighting for reproductive rights, we know how important it is to parse out the facts from the messaging.

At such a critical moment in US history, we need reporters on the ground. Your donation allows us to keep sending journalists to speak to both sides of the story.

The Independent is trusted by Americans across the entire political spectrum. And unlike many other quality news outlets, we choose not to lock Americans out of our reporting and analysis with paywalls. We believe quality journalism should be available to everyone, paid for by those who can afford it.

Your support makes all the difference.

Scientists have used living brain cells to build an artificial intelligence system capable of recognising different people’s voices.

The hybrid biocomputer integrated electronics into laboratory-grown human brain tissue in order to perform voice recognition tasks with an accuracy of 78 per cent.

The success of the AI experiment could lead to a new era powerful “Brainoware” computers, according to the team from Indiana University Bloomington in the US who built it.

“Brain-inspired computing hardware aims to emulate the structure and working principles of the brain and could be used to address current limitations in artificial intelligence technologies,” the researchers wrote in a paper, titled ‘Brain organoid reservoir computing for artificial intelligence’, published in the journal Nature Electronics on Monday.

“Due to the high plasticity and adaptability of organoids, Brainoware has the flexibility to change and reorganise in response to electrical stimulation, highlighting its ability for adaptive reservoir computing.”

The approach could also vastly reduce the energy demands of modern artificial intelligence systems, with current AI hardware consuming around 8 million watts to drive a neural network that the human brain could power with just 20 watts.

One of the brain organoids used in the AI study
One of the brain organoids used in the AI study (Indiana University Bloomington)

Brain organoids are cultivated from stem cells and grown in a lab, offering ways to investigate everything from how the human brain works, to potential methods for treating neural diseases.

The increasingly complex nature of these lab-grown brain parts has led to ethical concerns about what constitutes a human, and at which point brain tissue can be considered a person.

Earlier this year, researchers in Japan and Taiwan proposed creating a legal framework for clarifying issues like informed consent, which could determine how brain organoids can be used and treated.

“Although human brain organoids do not constitute natural persons at present, the likelihood of their potential to become natural persons in the near future requires more thorough consideration in advance of that reality occurring,” said Hiroshima University researcher Masanori Kataoka, who led the research.

The latest Brainoware research remains a long way from touching on such concerns, with the AI-infused brain organoids capable of identifying a speaker but not understanding what they say.

Join our commenting forum

Join thought-provoking conversations, follow other Independent readers and see their replies

Comments

Thank you for registering

Please refresh the page or navigate to another page on the site to be automatically logged inPlease refresh your browser to be logged in