![\"A](\"https:\/\/www.europesays.com\/us\/wp-content\/uploads\/2025\/08\/d41586-025-02589-5_51335518.jpg\"\/)
<\/p>\n <\/p>\n
A brain scan (artificially coloured) produced by magnetic resonance imaging. Credit: K H Fung\/Science Photo Library<\/p>\n
A brain implant<\/a> can decode a person\u2019s internal chatter \u2013 but the device works only if the user thinks of a preset password1<\/a>.<\/p>\n The mind-reading device, or brain\u2013computer interface<\/a> (BCI), accurately deciphered up to 74% of imagined sentences. The system began decoding users\u2019 internal speech \u2013 the silent dialogue in people\u2019s minds \u2014 only when they thought of a specific keyword. This ensured that the system did not accidentally translate sentences that users would rather keep to themselves.<\/p>\n The study, published in Cell on 14 August, represents a \u201ctechnically impressive and meaningful step\u201d towards developing BCI devices that accurately decode internal speech, says Sarah Wandelt, a neural engineer at the Feinstein Institutes for Medical Research in Manhasset, New York, who was not involved in the work. The password mechanism also offers a straightforward way to protect users\u2019 privacy, a crucial feature for real-world use<\/a>, adds Wandelt.<\/p>\n Avoiding eavesdropping<\/p>\n BCI systems translate brain signals into text or audio and have become promising tools for restoring speech in people with paralysis or limited muscle control. Most devices require users to try to speak out loud, which can be exhausting and uncomfortable. Last year, Wandelt and her colleagues developed the first BCI for decoding internal speech<\/a>, which relied on signals in the supramarginal gyrus, a brain region that plays a major part in speech and language2<\/a>.<\/p>\n A study participant who has trouble speaking clearly because of a stroke uses the brain\u2013computer interface.Credit: Emory BrainGate Team<\/p>\n But there\u2019s a risk that these internal-speech BCIs could accidentally decode sentences users never intended to utter, says Erin Kunz, a neural engineer at Stanford University in California. \u201cWe wanted to investigate this robustly,\u201d says Kunz, who co-authored the new study.<\/p>\n First, Kunz and her colleagues analysed brain signals collected by microelectrodes placed in the motor cortex<\/a> \u2014 the region involved in voluntary movements \u2014 of four participants. All four have trouble speaking, one because of a stroke and three because of motor neuron disease, a degeneration of the nerves that leads to loss of muscle control. The researchers instructed participants to either attempt to say a set of words or imagine saying them. <\/p>\n Recordings of the participants\u2019 brain activity showed that attempted and internal speech originated in the same brain region and generated similar neural signals, but those associated with internal speech were weaker.<\/p>\n![\"A](\"https:\/\/www.europesays.com\/us\/wp-content\/uploads\/2025\/08\/d41586-025-02589-5_51335516.jpg\"\/)
<\/p>\n
![\"\"](\"https:\/\/www.europesays.com\/us\/wp-content\/uploads\/2025\/08\/d41586-025-02589-5_51086678.jpg\"\/)
<\/p>\n