Removing timing clues improves brain-to-text speech decoding
Removing Timing Shortcuts Improves Non-Invasive Brain-to-Text
Machine Learning
Summary
Decoding words directly from brain signals when hearing speech is very challenging. The authors found previous methods partly guessed words by noticing the time gaps between spoken words, not the brain activity itself. By processing each word’s brain data independently, this timing shortcut is removed, making the decoding rely more on real brain signals. This change notably improves the accuracy of predicting heard words, bringing non-invasive brain decoding closer to invasive methods.
What this means in practice
- •For brain-computer interface developers: Build more accurate speech decoding systems using non-invasive brain signals by eliminating timing-related shortcuts in data processing.$Commercial implications: This technique enables speech prosthetics companies to offer improved communication aids for people with speech impairments.
- •For assistive technology engineers: Improve assistive devices that translate brain activity into text, making text generation from perceived speech more reliable without invasive methods.
Authors
Dulhan Jayalath, Oiwi Parker Jones
Abstract
We find that major reported improvements in decoding words from non-invasive brain recordings are largely reproducible without any brain data. In the influential work of d'Ascoli et al. (2025), time series of brain activity from subjects perceiving continuous speech are segmented into fixed-length windows starting at each word. A neural network then generates predictions for all of the words in a sentence together. Neighbouring windows partially overlap, implicitly revealing the interval between words. Since these intervals indicate the duration of the words spoken, and different words tend to have different durations - for example, "the" is much shorter than "supercalifragilisticexpialidocious" - the neural network can improve its predictions of words without relying on the underlying brain activity. Consistent with this, the method reaches 22.0% balanced accuracy on synthetic signals containing no brain information, compared with 22.3% on real brain recordings. To prevent the network from learning this shortcut, we make a single, simple change. Instead of jointly encoding all windows in a sentence, we process each independently. As a result, the neural network achieves better performance by learning underlying word-specific information from brain recordings. This makes two existing strategies become much more effective than before. Both aggregating predictions from distinct neural responses to the same word and using a pretrained LLM as a linguistic prior now substantially improve results. On our perceived speech benchmark, this simple recipe (SimpleB2T) achieves a word error rate of 36.6% with five observations per word, approaching past invasive speech decoding performance, albeit under different conditions. The results in this work expose an important shortcut in brain-to-text decoding and show that removing it leads to a simple and considerably more effective strategy.