Deep Neural Networks (DNNs) are powerful models that have achieved excellent performance on difficult learning tasks. Although DNNs work well whenever large labeled training sets are available, they cannot be used to map sequences to sequences. In this paper, we present a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure. Our method uses a...

Prior work in this domain has focused on modeling errors at the phonetic level, while using a lexicon to convert phones words, usually accompanied by an FST Language model. We present novel end-to-end models directly predict hallucinated ASR word sequence outputs, conditioning input as well corresponding phoneme sequence. This improves prior published results for recall of from in-domain system...

This thesis explores the application of ensemble methods to sequential learning tasks. The focus is on the development and the critical examination of new methods or novel applications of existing methods, with emphasis on supervised and reinforcement learning problems. In both types of problems, even after having observed a certain amount of data, we are often faced with uncertainty as to whic...

In this article, we present an isotropic unsupervised algorithm for temporal sequence learning. No special reward signal is used such that all inputs are completely isotropic. All input signals are bandpass filtered before converging onto a linear output neuron. All synaptic weights change according to the correlation of bandpass-filtered inputs with the derivative of the output. We investigate...

Recurrent neural networks (RNNs) in combination with a pooling operator and the neighbourhood components analysis (NCA) objective function are able to detect the characterizing dynamics of sequences and embed them into a fixed-length vector space of arbitrary dimensionality. Subsequently, the resulting features are meaningful and can be used for visualization or nearest neighbour classification...

What do tying shoelaces, hitting a golf ball, and square dancing have in common? Each can be learned by imitation, a major way that people of all ages acquire and master important skills. Imitation has been widely studied in infants, children and young adults, but until now, not in older adults. In fact, imitation learning is especially important in the everyday activities of older adults as th...

Sequential behavior and sequence learning is essential to intelligence. Often the elements of sequences exhibit an internal structure that can elegantly be represented using relational atoms. Applying traditional sequential learning techniques to such relational sequences requires either to ignore the internal structure or to put up with a combinatorial explosion in the model complexity. This c...

We present Deep Voice 3, a fully-convolutional attention-based neural textto-speech (TTS) system. Deep Voice 3 matches state-of-the-art neural speech synthesis systems in naturalness while training an order of magnitude faster. We scale Deep Voice 3 to dataset sizes unprecedented for TTS, training on more than eight hundred hours of audio from over two thousand speakers. In addition, we identif...

We present two approaches that use unlabeled data to improve sequence learning with recurrent networks. The first approach is to predict what comes next in a sequence, which is a conventional language model in natural language processing. The second approach is to use a sequence autoencoder, which reads the input sequence into a vector and predicts the input sequence again. These two algorithms...