Search papers, labs, and topics across Lattice.
This paper introduces an end-to-end Markov AAD framework that leverages conditional random fields (CRF) to improve auditory attention decoding from EEG signals by treating logits as Markov emissions. By jointly optimizing cross-entropy and CRF objectives, the approach enhances temporal continuity in attention state learning, outperforming traditional post-hoc HMM smoothing techniques. The proposed ESCNet backbone achieves significant accuracy improvements on both dynamic and static datasets, demonstrating the effectiveness of learning attention states as sequences rather than isolated classifications.
CRF-based training for auditory attention decoding boosts accuracy by up to 5.6% over traditional methods, revealing the power of temporal context in neural signal interpretation.
Auditory attention decoding (AAD) identifies the speaker a listener attends to from neural responses like electroencephalography (EEG), making it a key algorithm in neuro-steered hearing aids. However, most neural AAD models are trained as independent short-window classifiers, despite auditory attention being a temporally persistent cognitive state and short-window EEG--audio evidence often being noisy and ambiguous. We propose an end-to-end Markov AAD framework based on conditional random field (CRF) that trains window-level neural emissions under a two-state attention prior. The framework treats the logits of any AAD backbone as Markov emissions, learns the transition rate from a standard HMM initialization, and jointly optimizes cross-entropy and CRF objectives, allowing temporal continuity to guide representation learning rather than merely smoothing predictions after training. We also introduce ESCNet, an EEG--speech correlation backbone that preserves time-aligned features and converts the difference between two mean Pearson correlations into state logits. We evaluate the framework with four emission backbones spanning correlation-based, convolutional, recurrent, and attention-based designs. On the dynamic AVGC dataset, CRF training generally outperforms post-hoc HMM smoothing; with ESCNet, it achieves $86.5\%$ causal and $92.4\%$ non-causal accuracy using $1$s windows. On the static KUL and USTC datasets, it improves causal decoding over fixed-rate post-hoc HMM baselines by $5.6\%$ and $2.0\%$, respectively, showing the superiority of learning AAD as attention state sequence over isolated-window classification.
