Leveraging Multiple Speech Enhancers for Non-Intrusive Intelligibility Prediction for Hearing-Impaired Listeners
This addresses the gap between lab-based and real-world assessments for hearing aid performance evaluation, though it is incremental as it builds on existing enhancer methods.
The paper tackled the problem of speech intelligibility prediction for hearing-impaired listeners without requiring clean reference signals, by proposing a non-intrusive framework that leverages speech enhancers and a 2-clips augmentation strategy, resulting in consistent outperformance of the non-intrusive baseline CPC2 Champion across multiple datasets.
Speech intelligibility evaluation for hearing-impaired (HI) listeners is essential for assessing hearing aid performance, traditionally relying on listening tests or intrusive methods like HASPI. However, these methods require clean reference signals, which are often unavailable in real-world conditions, creating a gap between lab-based and real-world assessments. To address this, we propose a non-intrusive intelligibility prediction framework that leverages speech enhancers to provide a parallel enhanced-signal pathway, enabling robust predictions without reference signals. We evaluate three state-of-the-art enhancers and demonstrate that prediction performance depends on the choice of enhancer, with ensembles of strong enhancers yielding the best results. To improve cross-dataset generalization, we introduce a 2-clips augmentation strategy that enhances listener-specific variability, boosting robustness on unseen datasets. Our approach consistently outperforms the non-intrusive baseline, CPC2 Champion across multiple datasets, highlighting the potential of enhancer-guided non-intrusive intelligibility prediction for real-world applications.