Object tracking is useful in applications like computer-aided medical diagnosis, video editing, visual surveillance etc. Commonly used approaches usually involve the use of filter (e.g. Kalman filter) to predict the location of the object in next image frame. Such approaches actually borrow ideas from signal theory and are limited to applications where dynamic model is known. In this paper, a f...

En aplicaciones de control inteligente, uno los problemas es determinar el número capas y neuronas en cada capa. Esto se vuelve más complejo con ciertos tipos redes neuronales como las basadas wavelets donde traslaciones dilataciones son parámetros adicionales. Este artículo presenta un estudio comparativo para tipo wavelet que muestran mejor desempeño controlar helicóptero Quanser dos grados l...

In this paper, an automatic text–independent Arabic word speaker identification system is presented using Fuzzy Wavelet Neural Network terminology (FWNN). The approach is combining wavelet theory to fuzzy logic and neural network which lead to fabricate a Fuzzy Wavenet . Position and dilation of the fuzzy wavenets are fixed and the weights are optimized according to learning algorithm in the ne...

This paper introduces the details of the speech synthesis system developed by the USTC team for Blizzard Challenge 2017. A 6.5-hour corpus of highly expressive children’s audiobook was released to the participants this year. A parametric system that modeling speech waveforms was built for the task. Firstly, long short term memory (LSTM)-based recurrent neural networks (RNN) were adopted for the...

Normalizing flows and autoregressive models have been successfully combined to produce state-of-the-art results in density estimation, via Masked Autoregressive Flows (MAF) (Papamakarios et al., 2017), and to accelerate stateof-the-art WaveNet-based speech synthesis to 20x faster than real-time (Oord et al., 2017), via Inverse Autoregressive Flows (IAF) (Kingma et al., 2016). We unify and gener...

A novel method for learning optimal, orthonormal wavelet bases for representing 1and 2D signals, based on parallels between the wavelet transform and fully connected artificial neural networks, is described. The structural similarities between these two concepts are reviewed and combined to a “wavenet”, allowing for the direct learning of optimal wavelet filter coefficient through stochastic gr...

We recently presented a new model for singing synthesis based on a modified version of the WaveNet architecture. Instead of modeling raw waveform, we model features produced by a parametric vocoder that separates the influence of pitch and timbre. This allows conveniently modifying pitch to match any target melody, facilitates training on more modest dataset sizes, and significantly reduces tra...