A brain implant using artificial intelligence was able to turn a paralyzed woman's thoughts into speech almost simultaneously, US researchers said.

Though still at the experimental stage, the latest achievement using an implant linking brains and computers raised hopes that these devices could allow people who have lost the ability to communicate to regain their voice.

The California-based team of researchers had previously used a brain-computer interface, or BCI, to decode the thoughts of Ann - a 47-year-old with quadriplegia who has not been able to speak since suffering a stroke 18 years ago - and translate them into speech.

However there was an eight-second delay between her thoughts and the speech being read aloud by a computer.

But the team's new model, revealed in the journal Nature Neuroscience on Monday, turned Ann's thoughts into a version of her old speaking voice in 80-millisecond increments.

For the research, Ann was shown sentences on a screen which she would say to herself in her mind. Then her thoughts would be converted into her voice, which the researchers built up from recordings of her speaking before she was injured.

Meanwhile, a tie-up between a Chinese research institute and tech company said on Monday that it aims to implant its brain chip into 13 people by the end of this year, in a move that could see it overtake Elon Musk's Neuralink in collecting patient data.

The Beijing-based Chinese Institute for Brain Research and NeuCyber NeuroTech has inserted Beinao No 1, a semi-invasive wireless brain chip, into three patients in the past month and has 10 more lined up for this year.

The acceleration of human trials by CIBR and NeuCyber could make Beinao No 1 the brain chip with the highest number of patients in the world.

US BCI company Synchron is currently the global leader in terms of human trials with 10 patients, while Musk's Neuralink currently has three people with its implant.

Agence France-Presse, Reuters Reuters

Reuters

Brain implant using AI turns thoughts into speech almost simultaneously