Multimodal speech and speaker modeling and recognition are widely accepted as vital aspects of state of the art human-machine interaction systems. While correlations between speec...
Mehmet Emre Sargin, Oya Aran, Alexey Karpov, Ferda...
We present a method of grounded word learning that is powerful enough to learn the meanings of first and second person pronouns. The model uses the understood words in an utteran...
With the overwhelming volume of online news available today, there is an increasing need for automatic techniques to analyze and present news to the user in a meaningful and effi...
Ramesh Nallapati, Ao Feng, Fuchun Peng, James Alla...
A sound source separation technique based on a bio-inspired neural network, capable of functioning in more than two-source mixtures, is proposed. Separation results are compared wi...
During odour recognition, excitatory and inhibitory groups of neurons in the second stage of the locust olfactory system, the antennal lobe (AL), fire alternately. There is little...