Spoken Speech Enhancement using EEG
This work addresses speech enhancement for noisy recordings, but it is incremental as it applies existing neural network methods to a new EEG-based approach.
The paper tackled the problem of enhancing spoken speech in noisy environments by using EEG signals, achieving significant improvement in speech quality compared to a traditional log MMSE algorithm.
In this paper we demonstrate spoken speech enhancement using electroencephalography (EEG) signals using a generative adversarial network (GAN) based model, gated recurrent unit (GRU) regression based model, temporal convolutional network (TCN) regression model and finally using a mixed TCN GRU regression model. We compare our EEG based speech enhancement results with traditional log minimum mean-square error (MMSE) speech enhancement algorithm and our proposed methods demonstrate significant improvement in speech enhancement quality compared to the traditional method. Our overall results demonstrate that EEG features can be used to clean speech recorded in presence of background noise. To the best of our knowledge this is the first time a spoken speech enhancement is demonstrated using EEG features recorded in parallel with spoken speech.