Deep neural network architectures for dysarthric speech analysis and recognition

Neural Computing and Applications - This paper investigates the ability of deep neural networks (DNNs) to improve the automatic recognition of dysarthric speech through the use of convolutional...     

The Solutions on One-Dimensional Dirac Oscillator with Energy-Dependent Potentials and Their Effects on the Shannon and Fisher Quantities of Quantum Information Theory

Journal of Low Temperature Physics - In this paper, we focus, at first, on the exact solutions on the one-dimensional Dirac oscillator with the energy-dependent potentials. Then, the influence of...     

Alternating current electrophoretic deposition of Saccharomyces cerevisiae cells and the viability of the deposited biofilm in ethanol production

In this work, we have explored the possibility of using asymmetrical alternating current electrophoretic deposition (AC-EPD) process, which we have previously reported for enzyme deposition, to immobilize Saccharomyces cerevisiae (S. cerevisiae) cells onto stainless steel substrates. The deposition of S. cerevisiae cells at 30 Hz and 200 V_p-p permits the formation of 89 ± 16 μm thick cell layers in 30 min. The mass of the deposited cells is shown to increase quasi-linearly with the deposition time and the applied amplitude. In order to increase the mechanical stability of the immobilized cells, a thin layer of polyurethane was applied after the AC-EPD of S. cerevisiae cells. The viability of the immobilized cells was tested in the production of ethanol. The results showed that the fermentation process with the immobilized S. cerevisiae cells is more efficient than the fermentation carried out with similarly treated free cells.     

Application of electrostatic precipitator in collection of smoke particles from hospital wastes combustion

The paper reports the development and implementation of a cost-effective electrostatic precipitator (ESP) prototype for the medical wastes incinerator of university hospital centre (CHU) of Sidi-Bel-Abbes, using a water washing system for cleaning electrodes. The impact of medical waste incineration on human health is a topical debate. The incineration process is a safe mode of disposal [OK] of such waste, but it is not an effective solution and needs a pollution control system. Generally, in Africa, cost is the major constraint for manufacturers and users. A half-scale ESP model was initially used for an experimental study in the laboratory. Thereafter, a full-scale model was produced and installed for the incinerator based on the optimal values obtained from this preliminary study.     

Performance Analysis of Retrial Queueing Systems Using Generalized Stochastic Petri Nets

We consider retrial queueing systems, in which an arriving customer finding the server busy, may repeat his call after a random duration. The consideration of repeated calls introduces great analytical difficulties. In fact, detailed analytical results exist for some special retrial queueing systems, while for many others, the performance evaluation is limited to numerical algorithms, approximation methods and simulation. Retrial queues have been widely used to model many problems in telephone switching systems, telecommunication and computer networks. In this paper, we show a method of modelling and analysing retrial queueing systems, using the Generalized Stochastic Petri nets (GSPNs).     

A noise-robust front-end for distributed speech recognition in mobile communications

This paper investigates a new front-end processing that aims at improving the performance of speech recognition in noisy mobile environments. This approach combines features based on conventional Mel-cepstral Coefficients (MFCCs), Line Spectral Frequencies (LSFs) and formant-like (FL) features to constitute robust multivariate feature vectors. The resulting front-end constitutes an alternative to the DSR-XAFE (XAFE: eXtended Audio Front-End) available in GSM mobile communications. Our results showed that for highly noisy speech, using the paradigm that combines these spectral cues leads to a significant improvement in recognition accuracy on the Aurora 2 task.     

State-dependent packet scheduling for QoS routing in a dynamically changing environment

The packet scheduling in router plays an important role in the sense to achieve QoS differentiation and to optimize the queuing delay, in particular when this optimization is accomplished on all routers of a path between source and destination. In a dynamically changing environment a good scheduling discipline should be also adaptive to the new traffic conditions. We model this problem as a multi-agent system in which each agent learns through continual interaction with the environment in order to optimize its own behaviour. So, we adopt the framework of Markov decision processes applied to multi-agent system and present a pheromone-Q learning approach which combines the Q-multi-learning technique with a synthetic pheromone that acts as a communication medium speeding up the learning process of cooperating agents.