Robust End-to-End Speaker Verification Using EEG
This addresses speaker verification robustness for noisy conditions, but is incremental as it applies existing deep learning methods to a new data combination.
The paper tackles speaker verification in noisy environments by combining EEG signal features with speech features or using EEG alone, showing improved robustness with concrete performance gains.
In this paper we demonstrate that performance of a speaker verification system can be improved by concatenating electroencephalography (EEG) signal features with speech signal features or only using EEG signal features. We use state-of-the-art end-to-end deep learning model for performing speaker verification and we demonstrate our results for noisy speech. Our results indicate that EEG signals can improve the robustness of speaker verification systems, especially in noiser environment.