Decoding the Unintelligible: Neural Speech Tracking in Low Signal-to-Noise Ratios

Understanding speech in noisy environments is challenging for both human listeners and technology, with significant implications for hearing aid design and communication systems. Auditory attention decoding (AAD) aims to decode the attended talker from neural signals to enhance their speech and improve intelligibility. However, whether this decoding remains reliable when speech intelligibility is severely degraded in real-world listening conditions remains unclear. In this study, we investigated selective neural tracking of the attended speaker under adverse listening conditions. Using EEG recordings in a multi-talker speech perception task with varying SNR, participants’ speech perception was assessed through a repeated-word detection task, while neural responses were analyzed to decode the attended talker. Despite substantial degradation in intelligibility, we found that neural tracking of attended speech persists, suggesting that the brain retains sufficient information for decoding. These findings demonstrate that even in highly challenging conditions, AAD remains feasible, offering a potential avenue for enhancing speech intelligibility in brain-informed audio technologies, such as hearing aids, that leverage AAD to improve speech perception in real-world noisy environments.