Researchers Develop 'Biocomputer' Capable of Voice Recognition

The system, dubbed 'Brainoware', combines lab-grown human brain tissue with electronic circuits, offering potential insights for AI computing and brain study.

Researchers have created a 'biocomputer', named 'Brainoware', made up of lab-grown human brain tissue and electronic circuits that can perform tasks including voice recognition.
The system works by translating information into a pattern of electric pulses that are delivered to the organoid. The brain tissue's response is picked up by a sensor and 'decoded' using a machine-learning algorithm.
In tests, Brainoware was able to perform voice recognition after being trained on 240 recordings of eight people speaking, identifying voices with an accuracy of 78%.
Brainoware could provide additional insights for AI computing as brain organoids can provide biological neural networks with complexity, connectivity, neuroplasticity, and neurogenesis, as well as low energy consumption and fast learning.
Despite the promising results, there are significant challenges to overcome, including keeping the organoids alive and healthy, and the peripheral equipment power consumption levels.