We introduce FFTNet, a deep learning approach synthesizing audio waveforms. Our approach builds on the recent WaveNet project, which showed that it was possible to synthesize a natural sounding audio waveform directly from a deep convolutional neural network. FFTNet offers two improvements over WaveNet. First it is substantially faster, allowing for real-time synthesis of audio waveforms. Secon...

This paper is the follow on to a previous publication by the authors, which investigated the relationship between the level of neutral buoyancy (LNB) determined from the ambient sounding and the actual outflow levels using mainly CloudSat observations. The goal of the current study is to provide a more complete characterization of LNB, deep convective outflow, and convective core, and the relat...

We present tutorial dialogue systems in two different domains that demonstrate the use of dialogue management and deep natural language processing techniques. Generation techniques are used to produce natural sounding feedback adapted to student performance and the dialogue history, and context is used to interpret tentative answers phrased as questions.

We present tutorial dialogue systems in two different domains that demonstrate the use of dialogue management and deep natural language processing techniques. Generation techniques are used to produce natural sounding feedback adapted to student performance and the dialogue history, and context is used to interpret tentative answers phrased as questions.

The interpretation of simultaneous ionospheric Doppler sounding and ground magnetometer observations of low-latitude Pi2 waves is revised. We compare the theoretical estimates of the ionospheric Doppler velocity for the same amplitude of the ground magnetic disturbances produced by a large-scale compressional mode and an Alfvén mode. The plasma vertical displacement caused by the wave electric ...

Abstract Conventional linear iterative methods for magnetotelluric sounding (MT) suffer from considerable limitations related to difficulties in selecting the initial model and local optima. On other hand, conventional intelligent nonlinear exhibit slow convergence low accuracy. In this study, we propose an inversion strategy based on deep learning (DL) belief network (DBN) realise instantaneou...

Introduction: Investigation of the internal structure of martian polar caps, being a challenging task during past decades [1], is now going to be solved with the ground penetrating radar (GPR) instruments, both orbital and landed. In the present report the propagation of ultra wide band (UWB) chirp pulse in martian polar ice caps is investigated. The specific nature of the problem is that rathe...

Initialization of model parameters is crucial in the conventional 1D inversion of DC electrical data, since a poor guess may result in undesired parameter estimations. In the present work, we investigate the performance of neural networks in the direct inversion of DC sounding data, without the need of a priori information. We introduce a two-step network approach where the first network identi...