English speaking proficiency assessment using speech and electroencephalography signals

<p>In this paper, the English speaking proficiency level of non-native speakers<br />was automatically estimated as high, medium, or low performance. For purpose, speech 142 speakers was recorded and electroencephalography (EEG) signals 58 them were while in English. Two systems proposed for estimating speaker; one used 72 audio features, extracted from signals, other 112 features EEG signals. Multi-class support vector machines (SVM) training testing both using a cross-validation strategy. The speech-based system outperformed with 68% accuracy on 60 recordings, compared 56% 30 recordings.</p>