Sorry, you need to enable JavaScript to visit this website.

Diversity plays a vital role in many text generating applications. In recent years, Conditional Variational Auto Encoders (CVAE) have shown promising performances for this task. However, they often encounter the so called KL-Vanishing problem. Previous works mitigated such problem by heuristic methods such as strengthening the encoder or weakening the decoder while optimizing the CVAE objective function. Nevertheless, the optimizing direction of these methods are implicit and it is hard to find an appropriate degree to which these methods should be applied.

The generalized command response (GCR) model represents intonation as a
superposition of muscle responses to spike command signals. We have previously
shown that the spikes can be predicted by a two-stage system, consisting of a recurrent neural network and a post-processing procedure, but the responses themselves were fixed dictionary atoms. We propose an end-to-end
neural architecture that replaces the dictionary atoms with trainable
second-order recurrent elements analogous to recursive filters. We demonstrate

1D Convolutional Neural Networks (CNNs) have recently become the state-of-the-art technique for crucial signal processing applications such as patient-specific ECG classification, structural health monitoring, anomaly detection in power electronics circuitry and motor-fault detection. This is an expected outcome as there are numerous advantages of using an adaptive and compact 1D CNN instead of a conventional (2D) deep counterparts.

Speech-related Brain Computer Interfaces (BCI) aim primarily at finding an alternative vocal communication pathway for
people with speaking disabilities. As a step towards full decoding of imagined speech from active thoughts, we present a
BCI system for subject-independent classification of phonological categories exploiting a novel deep learning based

Road traffic forecasting systems are in scenarios where sensor or system failure occur. In those scenarios, it is known that missing values negatively affect estimation accuracy although it is being often underestimate in current deep neural network approaches. Our assumption is that traffic data can be generated from a latent space. Thus, we propose an online unsupervised data imputation method based on learning the data distribution using a variational autoencoder (VAE).

Recent work on acoustic parameter estimation indicates that geometric room volume can be useful for modeling the character of an acoustic environment. However, estimating volume from audio signals remains a challenging problem. Here we propose using a convolutional neural network model to estimate the room volume blindly from reverberant single-channel speech signals in the presence of noise. The model is shown to produce estimates within approximately a factor of two to the true value, for rooms ranging in size from small offices to large concert halls.

We propose a deep semantic segmentation-based layered image compression (DSSLIC) framework in which the segmentation map of the input image is obtained and encoded as the base layer of the bit-stream. Experimental results show that the proposed framework outperforms the H.265/HEVC-based BPG and other codecs in both PSNR and MS-SSIM metrics in RGB domain. Besides, since semantic map is included in the bit-stream, the proposed scheme can facilitate many other tasks such as image search and object-based adaptive image compression.

Special high-end sensors with expensive hardware are usually needed to measure shock signals with high accuracy. In this paper, we show that cheap low-end sensors calibrated by deep neural networks are also capable to measure high-g shocks accurately. Firstly we perform drop shock tests to collect a dataset of shock signals measured by sensors of different fidelity. Secondly, we propose a novel network to effectively learn both the signal peak and overall shape.