We present a model of speech perception which takes into account effects of correlations between sounds. Words in this model correspond to the attractors of a suitably chosen descent dynamics. The resulting lexicon is rich in short words, and much less so in longer ones, as befits a reasonable word length distribution. We separately examine the decryption of short and long words in the presence of mishearings. In the regime of short words, the algorithm either quickly retrieves a word, or proposes another valid word. In the regime of longer words, the behaviour is markedly different. While the successful decryption of words continues to be relatively fast, there is a finite probability of getting lost permanently, as the algorithm wanders round the landscape of suitable words without ever settling on one.

Question: A friend of mine who has a connection to the Asheville Citizen Times told me that because of the staff shortage in the newsroom, the paper has purchased a software program using artificial intelligence that researches and then generates the answers to about half of the Answer Man columns. From what I've heard, this is being done to provide the Answer Man more time to work on other writing assignments. Apparently, the only part of the AI questions that are actually addressed by the real Answer Man are the smart aleck answers, because the AI program is not that developed. Could you please provide some additional information on how this is going? My answer: You've got to admit it would be nice to have some intelligence in this column.

We propose a mixed deep neural network strategy, incorporating parallel combination of Convolutional (CNN) and Recurrent Neural Networks (RNN), cascaded with deep autoencoders and fully connected layers towards automatic identification of imagined speech from EEG. Instead of utilizing raw EEG channel data, we compute the joint variability of the channels in the form of a covariance matrix that provide spatio-temporal representations of EEG. The networks are trained hierarchically and the extracted features are passed onto the next network hierarchy until the final classification. Using a publicly available EEG based speech imagery database we demonstrate around 23.45% improvement of accuracy over the baseline method. Our approach demonstrates the promise of a mixed DNN approach for complex spatial-temporal classification problems.