Deep learning approaches for speech emotion recognition: state of the art and research challenges

Speech emotion recognition (SER) systems identify emotions from the human voice in the areas of smart healthcare, driving a vehicle, call centers, automatic translation systems, and human-machine interaction. In the classical SER process, discriminative acoustic feature extraction is the most important and challenging step because discriminative features influence the classifier performance and decrease the computational time. Nonetheless, current handcrafted acoustic features suffer from limited capability and accuracy in constructing a SER system for real-time implementation. Therefore, to overcome the limitations of handcrafted features, in recent years, variety of deep learning techniques have been proposed and employed for automatic feature extraction in the field of emotion prediction from speech signals. However, to the best of our knowledge, there is no in-depth review study is available that critically appraises and summarizes the existing deep learning techniques with their strengths and weaknesses for SER. Hence, this study aims to present a comprehensive review of deep learning techniques, uniqueness, benefits and their limitations for SER. Moreover, this review study also presents speech processing techniques, performance measures and publicly available emotional speech databases. Furthermore, this review also discusses the significance of the findings of the primary studies. Finally, it also presents open research issues and challenges that need significant research efforts and enhancements in the field of SER systems.

     

Light weight model for intra mode selection in HEVC

Multimedia Tools and Applications - The High Efficiency Video Coding (HEVC) efficiently reduces the size of the multimedia contents, but at the cost of high computation complexity. In order to make...     

Color image DNA encryption using mRNA properties and non-adjacent coupled map lattices

This paper proposes a novel algorithm for encrypting color images. The innovation in this study is the use of messenger ribonucleic acid (mRNA) encoding to import into Deoxyribonucleic acid (DNA) encoding. For permutation of the plain image bits, we use Arnold’s Cat Map at the bit-level. Then, using Non-Adjacent Coupled Map Lattices (NCML), we apply diffusion operations to the permuted color channels. We also provide the upgrade of the diffusion phase with DNA encoding. In the proposed algorithm, the choices are random depending on the secret key, which is implemented using a simple logistic map. Hashing the string entered by the user, the secret key, parameters, and initial values are generated by the Double MD5 method. The results of tests and security analysis showed that the results of encryption with this scheme are effective, and the key space is large enough to withstand common attacks.

     

A study on melt recycling of bio-based polypropylene/thermoplastic starch compound

The compulsion to use bioplastics has increased significantly today. One of the important aspects of plastics is their recyclability. Therefore, the important question of this research is that although bio-based compounds containing starch are sensitive to thermal-mechanical recycling processes, are such products thermally recyclable? To answer the question, polypropylene (PP)/thermoplastic starch (TPS) compound granules were extruded up to five times, and in the other part, single-extruded granules were blended at different ratios with virgin granules by extrusion. In order to characterize these samples, Fourier transform infrared spectroscopy, thermogravimetric analysis, differential scanning calorimetry, rotational disc rheometry, tensile properties, and appearance evaluation were used. The results showed that it is possible to recycle PP/TPS granules up to four times repetition of the extrusion operation and the fifth repetition also showed slight changes. There was also a blend of single-extruded granules with virgin material up to a 50:50% composition without significant variation.     

Robust face recognition against expressions and partial occlusions

Facial features under variant-expressions and partial occlusions could have degrading effect on overall face recognition performance. As a solution, we suggest that the contribution of these features on final classification should be determined. In order to represent facial features contribution according to their variations, we propose a feature selection process that describes facial features as local independent component analysis(ICA) features. These local features are acquired using locally lateral subspace(LLS) strategy.Then, through linear discriminant analysis(LDA) we investigate the intraclass and interclass representation of each local ICA feature and express each feature s contribution via a weighting process. Using these weights, we define the contribution of each feature at local classifier level. In order to recognize faces under single sample constraint, we implement LLS strategy on locally linear embedding(LLE) along with the proposed feature selection. Additionally, we highlight the efficiency of the implementation of LLS strategy. The overall accuracy achieved by our approach on datasets with different facial expressions and partial occlusions such as AR, JAFFE,FERET and CK+ is 90.70%. We present together in this paper survey results on face recognition performance and physiological feature selection performed by human subjects.     

Privacy Preserving Geo-Linkage in the Big Urban Data Era

Big data technologies and a range of Government open data initiatives provide the basis for discovering new insights into cities; how they are planned, how they managed and the day-to-day challenges they face in health, transport and changing population profiles. The Australian Urban Research Infrastructure Network (AURIN – www.aurin.org.au) project is one example of such a big data initiative that is currently running across Australia. AURIN provides a single gateway providing online (live) programmatic access to over 2000 data sets from over 70 major and typically definitive data-driven organizations across federal and State government, across industry and across academia. However whilst open (public) data is useful to bring data-driven intelligence to cities, more often than not, it is the data that is not-publicly accessible that is essential to understand city challenges and needs. Such sensitive (unit-level) data has unique requirements on access and usage to meet the privacy and confidentiality demands of the associated organizations. In this paper we highlight a novel geo-privacy supporting solution implemented as part of the AURIN project that provides seamless and secure access to individual (unit-level) data from the Department of Health in Victoria. We illustrate this solution across a range of typical city challenges in localized contexts around Melbourne. We show how unit level data can be combined with other data in a privacy-protecting manner. Unlike other secure data access and usage solutions that have been developed/deployed, the AURIN solution allows any researcher to access and use the data in a manner that meets all of the associated privacy and confidentiality concerns, without obliging them to obtain ethical approval or any other hurdles that are normally put in place on access to and use of sensitive data. This provides a paradigm shift in secure access to sensitive data with geospatial content.     

Coordinated design of TCSC and PSS controllers using VURPSO and Genetic algorithms for multi-machine power system stability

Thyristor controlled series capacitor (TCSC) can regulate line impedance and therefore increase transferred power of the system. On the other hand power system stabilizer (PSS) increases dynamic stability of generator. To enhance the stability, combination of TCSC and PSS can be applied, and in such a case coordination of TCSC and PSS is essential. This paper applies this combined controller in order to enhance the stability of multi-machine system. Parameters of these controllers are optimized by velocity update relaxation particle swarm optimization (VURPSO) algorithm and Genetic algorithm (GA). The simulation results show that the combination of VURPSO algorithm and GA leads to a better design and stability.     

Fast implementation of dense stereo vision algorithms on a highly parallel SIMD architecture

In this paper, we present faster than real-time implementation of a class of dense stereo vision algorithms on a low-power massively parallel SIMD architecture, the CSX700. With two cores, each with 96 Processing Elements, this SIMD architecture provides a peak computation power of 96 GFLOPS while consuming only 9 Watts, making it an excellent candidate for embedded computing applications. Exploiting full features of this architecture, we have developed schemes for an efficient parallel implementation with minimum of overhead. For the sum of squared differences (SSD) algorithm and for VGA (640 × 480) images with disparity ranges of 16 and 32, we achieve a performance of 179 and 94 frames per second (fps), respectively. For the HDTV (1,280 × 720) images with disparity ranges of 16 and 32, we achieve a performance of 67 and 35 fps, respectively. We have also implemented more accurate, and hence more computationally expensive variants of the SSD, and for most cases, particularly for VGA images, we have achieved faster than real-time performance. Our results clearly demonstrate that, by developing careful parallelization schemes, the CSX architecture can provide excellent performance and flexibility for various embedded vision applications.     

A Model for Locating Park-and-Ride Facilities on Urban Networks Based on Maximizing Flow Capture: A Case Study of Isfahan, Iran

Traffic congestion is one of the main problems in large cities for which several approaches have been proposed. Park-and-ride is one of the best approaches that can remove traffic from the traffic network. Park-and-ride facilities are an important part of urban mass transit systems, effectively extending the service area and attracting commuters and other people who may not otherwise have used mass transit. However, its efficiency depends on its location in the urban network. In this research, we focus on travel time of shortest paths instead of the distance criterion for computing network traffic and develop a model for finding the best location(s) for siting park-and-ride systems so as to minimize the network traffic. The model is formulated based on population points, potential sites for park-and-ride establishment, and several Central Business District (CBDs). Then we present a Genetic algorithm that has been proved to be efficient in solving large size problems. Finally, the proposed model is used to locate park-and-ride facilities in the city of Isfahan, Iran.     

Regularized continuous estimation of distribution algorithms

Regularization is a well-known technique in statistics for model estimation which is used to improve the generalization ability of the estimated model. Some of the regularization methods can also be used for variable selection that is especially useful in high-dimensional problems. This paper studies the use of regularized model learning in estimation of distribution algorithms (EDAs) for continuous optimization based on Gaussian distributions. We introduce two approaches to the regularized model estimation and analyze their effect on the accuracy and computational complexity of model learning in EDAs. We then apply the proposed algorithms to a number of continuous optimization functions and compare their results with other Gaussian distribution-based EDAs. The results show that the optimization performance of the proposed RegEDAs is less affected by the increase in the problem size than other EDAs, and they are able to obtain significantly better optimization values for many of the functions in high-dimensional settings.