Distant speech processing for smart home: comparison of ASR approaches in scattered microphone network for voice command

Voice command in multi-room smart homes for assisting people in loss of autonomy in their daily activities faces several challenges, one of them being the distant condition which impacts ASR performance. This paper presents an overview of multiple techniques for fusion of multi-source audio (pre, middle, post fusion) for automatic speech recognition for in-home voice command. The robustness of the models of speech is obtained by adaptation to the environment and to the task. Experiments are based on several publicly available realistic datasets with participants enacting activities of daily life. The corpora were recorded in natural condition, meaning background noise is sporadic, so there is no extensive background noise in the data. The smart home is equipped with one or two microphones in each room, the distance between them being larger than 1 m. An evaluation of the most suited techniques improves voice command recognition at the decoding level, by using multiple sources and model adaptation. Although Word Error Rate (WER) is between 26 and 40%, Domotic Error Rate (identical to the WER, but at the level of the voice command) is less than 5.8% for deep neural network models, the method using Feature space Maximum Likelihood Linear Regression (fMLLR) with speaker adaptation training and Subspace Gaussian Mixture Model (SGMM) exhibits comparable results.     

Parallel synchronous and asynchronous coupled simulated annealing

The Journal of Supercomputing - We propose a parallel synchronous and asynchronous implementation of the coupled simulated annealing (CSA) algorithm in a shared-memory architecture. The original...     

Similarity measures of bipolar neutrosophic sets and their application to multiple criteria decision making

In this paper, we introduced some similarity measures for bipolar neutrosophic sets such as; Dice similarity measure, weighted Dice similarity measure, Hybrid vector similarity measure and weighted Hybrid vector similarity measure. Also we examine the propositions of the similarity measures. Furthermore, a multi-criteria decision-making method for bipolar neutrosophic set is developed based on these given similarity measures. Then, a practical example is shown to verify the feasibility of the new method. Finally, we compare the proposed method with the existing methods in order to demonstrate the practicality and effectiveness of the developed method in this paper.

     

Relationship among Facebook jealousy,aggression, and personal and relationship variables

In the last decade, jealousy research has focused on the Facebook jealousy; however, few studies have identified its relationship to aggression. The purpose of this study is to investigate the relationship between Facebook jealousy and aggression, and some personal and relational variables. A sample of 846 participants (516 females, 330 males) aged 18–66 years from Turkey completed the Facebook Jealousy Questionnaire, Rosenberg Self-Esteem Scale, and Buss–Perry Aggression Questionnaire. From an evolutionary perspective, gender differences in jealousy could be explained through evolution-based differences in parental investment, and that males exhibit increased jealousy in response to sexual infidelity, whereas females become jealous in response to emotional infidelity. A forced-choice question (with a choice of sexual infidelity or emotional infidelity as the more jealousy evoking) was asked to the participants in order to determine gender differences on sexual and emotional jealousy. Results indicated no significant gender differences in Facebook Jealousy scores. Self-esteem and age negatively predicted Facebook jealousy. All aggression sub-types significantly predicted Facebook jealousy. Consistent with the evolutionary perspective and previous evidence, chi-square analysis showed that males’ and females’ responses to the forced-choice question differ significantly.     

Simultaneous optimization of piezoelectric actuator topology and polarization

This article addresses the problem of piezoelectric actuator design for active structural vibration control. The topology optimization method using the Piezoelectric Material with Penalization and Polarization (PEMAP-P) model is employed in this work to find the optimum actuator layout and polarization profile simultaneously. A coupled finite element model of the structure is derived assuming a two-phase material, and this structural model is written into the state-space representation. The proposed optimization formulation aims to determine the distribution of piezoelectric material which maximizes the controllability for a given vibration mode. The optimization of the layout and poling direction of embedded in-plane piezoelectric actuators are carried out using a Sequential Linear Programming (SLP) algorithm. Numerical examples are presented considering the control of the bending vibration modes for a cantilever and a fixed beam. A Linear-Quadratic Regulator (LQR) is synthesized for each case of controlled structure in order to compare the influence of the polarization profile.     

Effect of Annealing on the Surface Morphology and Current–Voltage Characterization of a CZO Structure Prepared by RF Magnetron Sputtering

Semiconductors - In this study, we investigated the Cu-doped ZnO (CZO) structure. This structure was deposited on the Si and glass substrates using the RF magnetron sputtering technique....     

A mixed-integer programming approach for solving university course timetabling problems

Journal of Scheduling - This article presents a mixed-integer programming model for solving the university timetabling problem which considers the allocation of students to classes and the...     

On Two‐Player Interval‐Valued Fuzzy Bayesian Games

Game theory is an important basis to simulate several situations where multiple agents interact strategically for decision making and support. In many applications, such as auctions, frequently used for resource management involving two or more agents competing for the resources, the interacting agents only know their own characteristics and must make decisions while having to estimate the characteristics of the others. When probabilities are assigned for the different types of the interacting agents, this kind of strategic interaction constitutes a Bayesian game. In cases in which it is very difficult to characterize the private information of each agent, the payoffs can be given by approximate (not probabilistic) values, but the concept of Bayesian Nash equilibrium cannot be applied in this context. Fuzzy set theory is an excellent basis for studying this type of game, where the payoffs are represented by fuzzy numbers. When it is the case that there is also uncertainty about such fuzzy numbers, the use of interval fuzzy numbers appears as a good modeling alternative. This paper introduces an approach for interval‐based fuzzy Bayesian games, based on interval‐valued fuzzy probabilities for modeling the types of agents involved in the interaction. We present two different case studies, namely the (Interval) Fuzzy Bayesian Hiring Game and (Interval) Fuzzy Bayesian Prisoner's Dilemma with Moral Standards, comparing the results obtained with the crisp, fuzzy and interval fuzzy approaches, highlighting a particular case in which the interval fuzzy approach presents a solution although the two other do not.