Search

Total laryngectomy (TL) is as a well-established treatment for advanced laryngeal malignancies, entailing the complete removal of the larynx. Speech rehabilitation following TL is crucial for improving the quality of life and facilitating social reintegration. Electrolaryngeal (EL) speech, a widely used voice restoration technique utilizing external excitation signals, often produces artificial and monotonous sound quality. Efforts to enhance EL speech include the application of statistical voice conversion and neural approaches to speech enhancement. These approaches typically aim to map spectral features into acoustic characteristics, including the fundamental frequency ( $F_{0}$ ). However, challenges arise owing to substantial discrepancies and pattern differences between extracted features for EL and normal speech, compounded by limited clinical training data. To address this issue, we explored $F_{0}$ pattern prediction based on frame-wise phoneme information using bidirectional long short-term memory recurrent neural networks. Beyond direct predictions based on phoneme labels, we expanded our analysis to include real-valued phoneme embeddings and conducted predictions for clustered embeddings representing low-dimensional input representations. Our findings demonstrate that both regression and classification predictive modeling can map frame-wise phoneme information into natural $F_{0}$ patterns. Additionally, phoneme labels can be considered as shared features between EL and normal speech, allowing for improved prediction accuracies by incorporating phoneme information from normal speech into the training sets for EL speech. Furthermore, by learning phoneme embeddings and creating input features for $F_{0}$ prediction based on the clustering of these embeddings, accurate $F_{0}$ patterns can be predicted, and the challenge of finding a strategy to reduce the dimensionality of the input features can be effectively alleviated.

Background: The Electrocardiogram (ECG) is an important measure for diagnosing the presence or absence of heart arrhythmias. Premature ventricular contractions (PVC) is a relatively large arrhythmia occurring outside the normal tract and being triggered outside the Sino atrial (SA) node of heart. Objective: This study has focused on tunable Q-factor wavelet transform (TQWT) algorithm and statistical methods to detect PVC.Material and Methods: In this analytical and statistical study, 22 ECGs records were selected from the MIT/BIH arrhythmia database. In the first stage the noise of signal remove and then five sub-bands create by TQWT. In the second stage nine features (minimum, maximum, root mean square, mean, interquartile range, standard deviation (SD), skewness, and variance) extracted of ECG and then the best features selected by using analysis of variance (ANOVA) test. Finally, the system is evaluated by using the learning machines of support vector machine (SVM), the K-Nearest Neighbor (KNN), and artificial neural network (ANN). Results: The best results were verified with KNN learning machine: the sensitivity Se= 98.23% and accuracy Ac= 97.81%. Conclusion: A comparative analysis with the related existing methods shows the method proposed in this study is higher than the other method for classification PVC and can help physicians to classify normal and PVC heart signals in the screening of the patients with coronary artery diseases (CADs).

In this paper, a new 32-bit ASIP-based crypto processor for AES, IDEA, and MD5 is designed. The instruction-set consists of both general purpose and specific instructions for the above cryptographic algorithms. The proposed architecture has nine function units and two data buses. It has also two types of 32-bit instruction formats for executing Memory Reference (M.R.), Register Reference (R.R.), and Input/Output Reference (I/O R.) instructions. The maximum achieved frequency is 166.916 MHz. The encoded output results of the encryption process of a 128-bit input block are obtained after 122, 146 and 170 clock cycles for AES-128, AES-192, and AES-256, respectively. Moreover, it takes 95 clock cycles to encrypt or decrypt a 64-bit input block by using IDEA. Finally, the MD5 hash algorithm requires 469 clock cycles to generate the coded outputs for a block of 512 bits. The performance of the proposed processor is compared to some previous and state-of-the-art implementations in terms of speed, latency, throughput, and flexibility.

Ischemic heart disease is one of the leading causes of death in the world, and includes a wide range of transient forms, including incomplete blood supply to the heart muscle, which cause heart attacks and eventually sudden death. Identifying the main area of the myocardial infarction (MI) is a priority for the treatment of myocardial infarction. Electrocardiogram signal recording is a common method for monitoring cardiac function and widely used for detecting heart attack. In this study, using 10-part sections of the standard 12-lead electrocardiogram signal taken from the PhysioNet database, the diagnosis of the infarction was made possible. First, after removing the electrocardiogram (ECG) signal noises, by applying the Principal Component Analysis (PCA), the dimensions of the 12-lead electrocardiogram signal were reduced. Then the characteristic vector was created using the statistical properties of the wavelet cross spectrum (WCS) and the resulting wavelet coherence (WCOH) by the cross-wavelet transformation (XWT) method. In the next step, using a support vector machine, which is used as a classifier, the location of the heart attack is detected. The results show that the designed system to detect the incidence of MI has a sensitivity of 96.7% and a precision of 99%.

In this paper, a new algorithm for image encryption using chaotic tent map and Arnold cat map is proposed. This algorithm consists of two major phases, permutation and substitution. In the permutation phase, Arnold cat transform is used. A pseudo random image is produced using the chaotic tent map. In the substitution phase, the permuted image is Exclusively ORed to this pseudo random image in order to generate encrypted images. A computer simulation is used to evaluate the proposed algorithm and to compare its results to encrypted images of other methods. The criteria for these comparisons are chi-square test of histogram, correlation coefficients of pixels, NPCR (number of pixel change rate), UACI (unified average changing intensity), MSE (mean square error) and MAE (mean absolute error). These comparisons show that the proposed chaotic image encryption method has a high performance and security.