We present a recurrent neural net (RNN) model of text normalization — defined as the mapping of written text to its spoken form, and a description of the open-source dataset that we used in our experiments. We show that while the RNN model achieves very high overall accuracies, there remain errors that would be unacceptable in a speech application like TTS.We then show that a simple FST-based f...

A modiied Recurrent Neural Network (RNN) is used to learn a Self-Routing Interconnection Network (SRIN) from a set of routing examples. The RNN is modiied so that it has several distinct initial states. This is equivalent to a single RNN learning multiple diierent synchronous sequential machines. We deene such a sequential machine structure as augmented and show that a SRIN is essentially an Au...

In today’s affective databases speech turns are often labelled on a continuous scale for emotional dimensions such as valence or arousal to better express the diversity of human affect. However, applications like virtual agents usually map the detected emotional user state to rough classes in order to reduce the multiplicity of emotion dependent system responses. Since these classes often do no...

Recent advances in recurrent neural nets (RNNs) have shown much promise in many applications in natural language processing. For most of these tasks, such as sentiment analysis of customer reviews, a recurrent neural net model parses the entire review before forming a decision. We argue that reading the entire input is not always necessary in practice, since a lot of reviews are often easy to c...

We improve previous end-to-end differentiable neural networks (NNs) with fast weight memories. A gate mechanism updates fast weights at every time step of a sequence through two separate outer-product-based matrices generated by slow parts of the net. The system is trained on a complex sequence to sequence variation of the Associative Retrieval Problem with roughly 70 times more temporal memory...

Echo State Networks are a special class of recurrent neural networks, that are well suited for attractor-based learning of motor patterns. Using structural multi-objective optimization, the trade-off between network size and accuracy can be identified. This allows to choose a feasible model capacity for a follow-up full-weight optimization. Both optimization steps can be combined into a nested,...

in this study, an image backlight compensation method using adaptive luminance modification is proposed for efficiently obtaining clear images.the proposed method combines the fuzzy c-means clustering method, a recurrent functional neural fuzzy network (rfnfn), and a modified differential evolution.the proposed rfnfn is based on the two backlight factors that can accurately detect the compensat...

Living organisms have ingenious control mechanisms in which many molecular interactions work for keeping their normal activities against disturbances inside and outside of them. However, at the same time, the control mechanism has debacle points at which the stability can be broken easily. This paper proposes a new method which uses recurrent neural network for predicting debacle points in an h...