# CA-TCN: A Causal-Anticausal Temporal Convolutional Network for Direct Auditory Attention Decoding Source: [CA-TCN: A Causal-Anticausal Temporal Convolutional Network for Direct Auditory Attention Decoding]() Collection index: [llms.txt]() Data updated: 2026-06-09T05:00:07.006Z Authors: I\\~nigo Garc\\'ia-Ugarte, Rub\\'en Eguinoa, Ricardo San Mart\\'in, Daniel Paternain, Carmen Vidaurre Published: 2026-03-27T13:21:28.000Z ## Abstract A promising approach for steering auditory attention in complex listening environments relies on Auditory Attention Decoding (AAD), which aim to identify the attended speech stream in a multiple speaker scenario from neural recordings. Entrainment-based AAD approaches, typically assume access to clean speech sources and electroencephalography (EEG) signals to exploit low-frequency correlations between the neural response and the attended stimulus. In this study, we propose CA-TCN, a Causal-Anticausal Temporal Convolutional Network that directly classifies the attended speaker. The proposed architecture integrates several best practices from convolutional neural networks in sequence processing tasks. Importantly, it explicitly aligns auditory stimuli and neural responses by employing separate causal and anticausal convolutions respectively, with distinct receptive fields operating in opposite temporal directions. Experimental results, obtained through comparisons with three baseline AAD models, demonstrated that CA-TCN consistently improved decoding accuracy across datasets and decision windows, with gains ranging from 0.5% to 3.2% for subject-independent models and from 0.8% to 2.9% for subject-specific models compared with the next best-performing model, AADNet. Moreover, these improvements were statistically significant in four of the six evaluated settings when comparing Minimum Expected Switch Duration distributions. Beyond accuracy, the model demonstrated spatial robustness across different conditions, as the EEG spatial filters exhibited stable patterns across datasets. Overall, this work introduces an accurate and unified AAD model that outperforms existing methods while considering practical benefits for online processing scenarios. These findings contribute to advancing the state of AAD and its applicability in real-world systems. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Auditory Attention Decoding on Jaulab Subject-Specific](): Auditory Attention Decoding; Jaulab Subject-Specific; Accuracy (1s): 60.4. - [Auditory Attention Decoding on DTU Subject-Specific](): Auditory Attention Decoding; DTU Subject-Specific; Accuracy (1s): 60.5. - [Auditory Attention Decoding on KULeuven (Subject-Specific)](): Auditory Attention Decoding; KULeuven (Subject-Specific); Accuracy (1s): 59.1. - [Auditory Attention Decoding on Jaulab Subject-Independent (val)](): Auditory Attention Decoding; Jaulab Subject-Independent (val); Accuracy (1s): 58. - [Auditory Attention Decoding on DTU Subject-Independent (val)](): Auditory Attention Decoding; DTU Subject-Independent (val); Accuracy (1s): 58.3. - [Auditory Attention Decoding on KULeuven Subject-Independent (val)](): Auditory Attention Decoding; KULeuven Subject-Independent (val); Accuracy (1s): 56.8. ## Original sources and implementation [Original paper]() [PDF]()