Neural network can be used to “remember” speech patterns by encoding speech statistical regularity in network parameters. Clean speech can be “recalled” when noisy speech is input to the network. Adding more hidden layers can increase network capacity. But when the hidden layer size increases (deep network), the network is easily to be trapped to a local solution when traditional training strat...

In this paper, we study the challenging problem of tracking the trajectory of a moving object in a video with possibly very complex background. In contrast to most existing trackers which only learn the appearance of the tracked object online, we take a different approach, inspired by recent advances in deep learning architectures, by putting more emphasis on the (unsupervised) feature learning...

Denoising autoencoder (DAE) is effective in restoring clean speech from noisy observations. In addition, it is easy to be stacked to a deep denoising autoencoder (DDAE) architecture to further improve the performance. In most studies, it is supposed that the DAE or DDAE can learn any complex transform functions to approximate the transform relation between noisy and clean speech. However, for l...

Recently, researchers have begun to investigate Deep Neural Network (DNN) architectures as mapping functions in voice conversion systems. In this study, we propose a novel StackedJoint-Autoencoder (SJAE) architecture, which aims to find a common encoding of parallel source and target features. The SJAE is initialized from a Stacked-Autoencoder (SAE) that has been trained on a large general-purp...

Intelligent fault diagnosis techniques play an important role in improving the abilities of automated monitoring, inference, and decision making for repair maintenance machinery processes. In this article, a modified stacked autoencoder (MSAE) that uses adaptive Morlet wavelet is proposed to automatically diagnose various types severities rotating machinery. First, activation function utilized ...

In order to improve the condition monitoring and fault diagnosis of wind turbines, a stacked noise reduction autoencoding network based on group normalization is proposed in this paper. The SCADA data turbine operation, firstly, (GN) algorithm added solve problems stack training slow convergence speed, RMSProp used update weight bias autoenccoder, which further optimizes problem that loss funct...