EffortNet: A Deep Learning Framework for Objective Assessment of Speech Enhancement Technologies Using EEG-Based Alpha Oscillations

TL;DR

EffortNet is a deep learning framework that decodes listening effort from EEG alpha oscillations, enabling personalized assessment of speech enhancement technologies with high accuracy and adaptability.

Contribution

This work introduces EffortNet, combining self-supervised, incremental, and transfer learning to improve EEG-based listening effort classification across individuals.

Findings

Alpha oscillations are valid biomarkers of listening effort.

EffortNet achieves 80.9% accuracy with limited new subject data.

Transformer-enhanced speech produces neural responses closer to clean speech.

Abstract

This paper presents EffortNet, a novel deep learning framework for decoding individual listening effort from electroencephalography (EEG) during speech comprehension. Listening effort represents a significant challenge in speech-hearing research, particularly for aging populations and those with hearing impairment. We collected 64-channel EEG data from 122 participants during speech comprehension under four conditions: clean, noisy, MMSE-enhanced, and Transformer-enhanced speech. Statistical analyses confirmed that alpha oscillations (8-13 Hz) exhibited significantly higher power during noisy speech processing compared to clean or enhanced conditions, confirming their validity as objective biomarkers of listening effort. To address the substantial inter-individual variability in EEG signals, EffortNet integrates three complementary learning paradigms: self-supervised learning to leverage unlabeled data, incremental learning for progressive adaptation to individual characteristics, and transfer learning for efficient knowledge transfer to new subjects. Our experimental results demonstrate that Effort- Net achieves 80.9% classification accuracy with only 40% training data from new subjects, significantly outperforming conventional CNN (62.3%) and STAnet (61.1%) models. The probability-based metric derived from our model revealed that Transformer-enhanced speech elicited neural responses more similar to clean speech than MMSEenhanced speech. This finding contrasted with subjective intelligibility ratings but aligned with objective metrics. The proposed framework provides a practical solution for personalized assessment of hearing technologies, with implications for designing cognitive-aware speech enhancement systems.