EEG based Continuous Speech Recognition using Transformers
This work addresses speech recognition for individuals with speech impairments using EEG, but it is incremental as it compares existing methods on new data without major breakthroughs.
The paper tackled continuous speech recognition using EEG features by comparing transformer-based and RNN-based models, finding that transformers train faster and perform better on smaller vocabularies, but RNNs outperform on larger vocabularies in a limited English dataset.
In this paper we investigate continuous speech recognition using electroencephalography (EEG) features using recently introduced end-to-end transformer based automatic speech recognition (ASR) model. Our results demonstrate that transformer based model demonstrate faster training compared to recurrent neural network (RNN) based sequence-to-sequence EEG models and better performance during inference time for smaller test set vocabulary but as we increase the vocabulary size, the performance of the RNN based models were better than transformer based model on a limited English vocabulary.