This presentation investigates the dynamics of discrete-time cellular neural networks (DT-CNN). In contrast to classical neural networks that are mostly gradient-like systems, DT-CNN possesses both complete stability and chaotic behaviors as different parameters are considered. An energylike function which decreases along orbits of DT-CNN as well as the existence of a globally attracting set ar...

Deep Neural Networks (DNN) have become a popular approach for speech enhancement, and singing voice separation. DNNs are typically trained to estimate a timefrequency mask using ground truth examples. In this submission, we combine DNN estimation as a first step with traditional refinement via F0 estimation, using the YINFFT algorithm.

In this paper, linear matrix inequality (LMI) approach for synchronization of chaotic fuzzy cellular neural networks (FCNNs) with discrete and unbounded distributed delays based on sampled-data controlis investigated. Lyapunov-Krasovskii functional combining with the input delay approach as well as the free-weighting matrix approach are employed to derive several sufficient criteria in terms of...

Accelerating deep neural networks (DNNs) has been attracting increasing attention as it can benefit a wide range of applications, e.g., enabling mobile systems with limited computing resources to own powerful visual recognition ability. A practical strategy to this goal usually relies on a two-stage process: operating on the trained DNNs (e.g., approximating the convolutional filters with tenso...

Brain tumor extraction and its analysis are challenging tasks in Medical image processing because brain image is complicated. Segmentation plays a very important role in the medical image processing .Image segmentation is used to take out the suspicious parts from MRI. In that way MRI (magnetic resonance imaging) has become a useful medical diagnostic tool for the diagnosis of brain. In this pr...

This work addresses the use of deep neural networks (DNNs) in automatic language identification (LID) focused on short test utterances. Motivated by their recent success in acoustic modelling for speech recognition, we adapt DNNs to the problem of identifying the language in a given utterance from the short-term acoustic features. We show how DNNs are particularly suitable to perform LID in rea...

In this paper we continue to investigate how the deep neural network (DNN) based acoustic models for automatic speech recognition can be trained without hand-crafted feature extraction. Previously, we have shown that a simple fully connected feedforward DNN performs surprisingly well when trained directly on the raw time signal. The analysis of the weights revealed that the DNN has learned a ki...