Adaptation of children’s speech with limited data based on formant-like peak alignment

Automatic recognition of children’s speech using acoustic models trained by adults results in poor performance due to differences in speech acoustics. These acoustical differences are a consequence of children having shorter vocal tracts and smaller vocal cords than adults. Hence, speaker adaptation needs to be performed. However, in real-world applications, the amount of adaptation data available may be less than what is needed by common speaker adaptation techniques to yield reasonable performance. In this paper, we first study, in the discrete frequency domain, the relationship between frequency warping in the front-end and corresponding transformations in the back-end. Three common feature extraction schemes are investigated and their transformation linearity in the back-end are discussed. In particular, we show that under certain approximations, frequency warping of MFCC features with Mel-warped triangular filter banks equals a linear transformation in the cepstral space. Based on that linear transformation, a formant-like peak alignment algorithm is proposed to adapt adult acoustic models to children’s speech. The peaks are estimated by Gaussian mixtures using the Expectation-Maximization (EM) algorithm [Zolfaghari, P., Robinson, T., 1996. Formant analysis using mixtures of Gaussians, Proceedings of International Conference on Spoken Language Processing, 1229–1232]. For limited adaptation data, the algorithm outperforms traditional vocal tract length normalization (VTLN) and maximum likelihood linear regression (MLLR) techniques.     

An Efficient GCD-Based Cancelable Biometric Algorithm for Single and Multiple Biometrics

Cancelable biometrics are required in most remote access applications that need an authentication stage such as the cloud and Internet of Things (IoT) networks. The objective of using cancelable biometrics is to save the original ones from hacking attempts. A generalized algorithm to generate cancelable templates that is applicable on both single and multiple biometrics is proposed in this paper to be considered for cloud and IoT applications. The original biometric is blurred with two co-prime operators. Hence, it can be recovered as the Greatest Common Divisor (GCD) between its two blurred versions. Minimal changes if induced in the biometric image prior to processing with co-prime operators prevents the recovery of the original biometric image through a GCD operation. Hence, the ability to change cancelable templates is guaranteed, since the owner of the biometric can pre-determine and manage the minimal change induced in the biometric image. Furthermore, we test the utility of the proposed algorithm in the single- and multi-biometric scenarios. The multi-biometric scenario depends on compressing face, fingerprint, iris, and palm print images, simultaneously, to generate the cancelable templates. Evaluation metrics such as Equal Error Rate (EER) and Area and Receiver Operator Characteristic curve (AROC) are considered. Simulation results on single- and multi-biometric scenarios show high AROC values up to 99.59%, and low EER values down to 0.04%.     

NTRU_ SSS: Anew Method Signcryption Post Quantum Cryptography Based on Shamir’s Secret Sharing

With the advent of quantum computing, numerous efforts have been made to standardize post-quantum cryptosystems with the intention of (eventually) replacing Elliptic Curve Cryptography (ECC) and Rivets-Shamir-Adelman (RSA). A modified version of the traditional N-Th Degree Truncated Polynomial Ring (NTRU) cryptosystem called NTRU Prime has been developed to reduce the attack surface. In this paper, the Signcryption scheme was proposed, and it is most efficient than others since it reduces the complexity and runs the time of the code execution, and at the same time, provides a better security degree since it ensures the integrity of the sent message, confidentiality of the data, forward secrecy when using refreshed parameters for each session. Unforgeability to prevent the man-in-the-middle attack from being active or passive, and non-repudiation when the sender can’t deny the recently sent message. This study aims to create a novel NTRU cryptography algorithm system that takes advantage of the security features of curve fitting operations and the valuable characteristics of chaotic systems. The proposed algorithm combines the (NTRU Prime) and Shamir's Secret Sharing (SSS) features to improve the security of the NTRU encryption and key generation stages that rely on robust polynomial generation. Based on experimental results and a comparison of the time required for crucial exchange between NTRU-SSS and the original NTRU, this study shows a rise in complexity with a decrease in execution time in the case when compared to the original NTRU. It’s encouraging to see signs that the suggested changes to the NTRU work to increase accuracy and efficiency.     

Efficient Deep Learning Modalities for Object Detection from Infrared Images

For military warfare purposes, it is necessary to identify the type of a certain weapon through video stream tracking based on infrared (IR) video frames. Computer vision is a visual search trend that is used to identify objects in images or video frames. For military applications, drones take a main role in surveillance tasks, but they cannot be confident for long-time missions. So, there is a need for such a system, which provides a continuous surveillance task to support the drone mission. Such a system can be called a Hybrid Surveillance System (HSS). This system is based on a distributed network of wireless sensors for continuous surveillance. In addition, it includes one or more drones to make short-time missions, if the sensors detect a suspicious event. This paper presents a digital solution to identify certain types of concealed weapons in surveillance applications based on Convolutional Neural Networks (CNNs) and Convolutional Long Short-Term Memory (ConvLSTM). Based on initial results, the importance of video frame enhancement is obvious to improve the visibility of objects in video streams. The accuracy of the proposed methods reach 99%, which reflects the effectiveness of the presented solution. In addition, the experimental results prove that the proposed methods provide superior performance compared to traditional ones.     

Studies of Bone-Bonding Ability and Antibacterial Properties of Ag<Superscript>+</Superscript>, Cu<Superscript>2+</Superscript> or Zn<Superscript>2+</Superscript> ions Doping within Hench’s Bioglass and Glass-Ceramic Derivatives

Derived Hench’s bioglasses with specific ionic dopants Ag⁺, Cu²⁺, or Zn²⁺ have been prepared. The bone-boding ability or bioactivity behavior for the prepared glasses and their glass-ceramic derivatives has been investigated after immersion in phosphate solution for two weeks. Collective Fourier transform infrared absorption spectra (FTIR) and scanning electron microscopic (SEM) studies were conducted in order to study the in-vitro bioactivity behavior. X-ray diffraction (XRD) analysis was carried out to identify the crystallized phases upon thermal heat treatment through a two-step regime. The glasses and their glass-ceramic derivatives were tested to study their antibacterial or antifungal efficiency responding to the doped metal ions. FTIR spectra revealed the generation of two split peaks at about 560 and 605 cm^?1, after immersion in (0.2 M) sodium phosphate solution (Na₃PO₄), signifying the formation of a crystalline calcium phosphate phase, leading to hydroxyapatite formation. SEM examinations show characteristic rounded or nodular microcrystals for hydroxyapatite which support the FTIR data. X-ray diffraction analysis indicated crystallization of the main soda-lime silicate phase (1Na₂O.2CaO.3SiO₂) besides a secondary silicon phosphate phase (SiO₂.P₂O₅) in the studied glass ceramics. The route of crystallization is discussed on the basis of the presence of 6% P₂O_5; which facilitates the formation of phase separation and voluminous bulk crystallization of the main soda-lime silicate phase. The introduction of dopants is identified to cause no changes in the precipitated phases, with only minor changes in the percent of the crystalline phases. Experimental data indicate that the glass-ceramic samples are effective in bioactivity and antimicrobial efficiency.     

Compartmentalization Role of A-Kinase Anchoring Proteins (AKAPs) in Mediating Protein Kinase A (PKA) Signaling and Cardiomyocyte Hypertrophy

The Beta-adrenergic receptors (β-ARs) stimulation enhances contractility through protein kinase-A (PKA) substrate phosphorylation. This PKA signaling is conferred in part by PKA binding to A-kinase anchoring proteins (AKAPs). AKAPs coordinate multi-protein signaling networks that are targeted to specific intracellular locations, resulting in the localization of enzyme activity and transmitting intracellular actions of neurotransmitters and hormones to its target substrates. In particular, mAKAP (muscle-selective AKAP) has been shown to be present on the nuclear envelope of cardiomyocytes with various proteins including: PKA-regulatory subunit (RIIα), phosphodiesterase-4D3, protein phosphatase-2A, and ryanodine receptor (RyR2). Therefore, through the coordination of spatial-temporal signaling of proteins and enzymes, mAKAP controls cyclic-adenosine monophosphate (cAMP) levels very tightly and functions as a regulator of PKA-mediated substrate phosphorylation leading to changes in calcium availability and myofilament calcium sensitivity. The goal of this review is to elucidate the critical compartmentalization role of mAKAP in mediating PKA signaling and regulating cardiomyocyte hypertrophy by acting as a scaffolding protein. Based on our literature search and studying the structure–function relationship between AKAP scaffolding protein and its binding partners, we propose possible explanations for the mechanism by which mAKAP promotes cardiac hypertrophy.