In this paper, we describe our work on the creation of a voice model using a speech synthesis system for the Hindi Language. We use preexisting “voices”, use publicly available speech corpora to create a “voice” using the Festival Speech Synthesis System (Black, 1997). Our contribution is two-fold: (1) We scrutinize multiple speech synthesis systems and provide an extensive report on the curren...

We took part in the Corporacion Favorita Grocery Sales Forecasting competition[1] hosted on Kaggle and achieved the 2nd place. In this abstract paper, we present an overall analysis and solution to the underlying machine-learning problem based on time series data, where major challenges are identified and corresponding preliminary methods are proposed. Our approach is based on the adaptation of...

Expressive efficiency is a concept that allows formally reasoning about the representational capacity of deep network architectures. A network architecture is expressively efficient with respect to an alternative architecture if the latter must grow super-linearly in order to represent functions realized by the former. A well-known example is the exponential expressive efficiency of depth, name...

Sequential models achieve state-of-the-art results in audio, visual and textual domains with respect to both estimating the data distribution and generating high-quality samples. Efficient sampling for this class of models has however remained an elusive problem. With a focus on text-to-speech synthesis, we describe a set of general techniques for reducing sampling time while maintaining high o...

This paper presents a deep learning network that performs automatic detection of defects by inspecting full ultrasonic guided wave signals excited in plate structures. The findings show the algorithm, which is an adaptation WaveNet, and hence based on causal dilated convolutional neural networks, effectively able to learn features and/or patterns related presence waves scattered from damage, th...

Predictions of stock and foreign exchange (Forex) have always been a hot profitable area study. Deep learning applications proven to yield better accuracy return in the field financial prediction forecasting. In this survey, we selected papers from Digital Bibliography & Library Project (DBLP) database for comparison analysis. We classified according different deep methods, which included C...

Traffic forecasting is attracting considerable interest due to its widespread application in intelligent transportation systems. Given the complex and dynamic traffic data, many methods focus on how establish a spatial-temporal model express non-stationary patterns. Recently, latest Graph Convolution Network (GCN) has been introduced learn spatial features while time neural networks are used te...

In this paper we introduce wavelet video processing of proximity sensor signals. Proximity sensing is required for a wide range of military and commercial applications, including weapon fuzing, robotics, and automotive collision avoidance. While our proposed method temporarily increases signal dimension, it eventually performs data compression through the extraction of salient signal features. ...

This paper presents the system identification and design of a neural network based Proportional, Integral and Derivative (PID) controller for a two degree of freedom (2DOF), quarter-car active suspension system. The controller design consists of a PID controller in a feedback loop and a neural network feedforward controller for the suspension travel to improve the vehicle ride comfort and handl...