The goal of this work is to introduce an architecture to automatically detect the amount of stress in the speech signal close to real time. For this an experimental setup to recor...
Neural networks are a useful alternative to Gaussian mixture models for acoustic modeling; however, training multilayer networks involves a difficult, nonconvex optimization that...
In an attempt to overcome problems associated with articulatory limitations and generative models, this work considers the use of phonological features in discriminative models fo...
Many real-world sequence learning tasks require the prediction of sequences of labels from noisy, unsegmented input data. In speech recognition, for example, an acoustic signal is...
Artificial neural networks have already shown their success in face recognition and similar complex pattern recognition tasks. However, a major disadvantage of the technique is th...
Mrinal Kanti Bhowmik, Debotosh Bhattacharjee, Mita...