Feasibility Investigations of the Possibility of Measurements, of the Ultrasonic Transducer Power Output at Ultrasonic-Therapy-Devices, with Piezoceramic Sensors
The paper shows the essential results for the investigation of a new ultrasonic power measuring method, in articular for measuring the sonic pressure of ultrasonic therapy devices, by using piezoceramic sensors. The aim of this work is to develop a new measuring instrument for the fast performance measurement at ultrasonic-therapy-devices.
New Digital Architecture of CNN for Pattern Recognition
The paper deals with the design of a new digital CNN (Cellular Neural Network) architecture for pattern recognition. The main parameters of the new design were the area consumption of the chip and the speed of calculation in one iteration. The CNN was designed as a digital synchronous circuit. The largest area of the chip belongs to the multiplication unit. In the new architecture we replaced the parallel multiplication unit by a simple AND gate performing serial multiplication. The natural property of this method of multiplication is rounding. We verified some basic properties of the proposed CNN such as edge detection, filling of the edges and noise removing. At the end we compared the designed network with other two CNNs. The new architecture allows to save till 86% gates in comparison with CNN with parallel multipliers.
In the development of the voice conversion and personification of the text-to-speech (TTS) systems, it is very necessary to have feedback information about the users’ opinion on the resulting synthetic speech quality. Therefore, the main aim of the experiments described in this paper was to find out whether the classifier based on Gaussian mixture models (GMM) could be applied for evaluation of different storytelling voices created by transformation of the sentences generated by the Czech and Slovak TTS system. We suppose that it is possible to combine this GMM-based statistical evaluation with the classical one in the form of listening tests or it can replace them. The results obtained in this way were in good correlation with the results of the conventional listening test, so they confirm practical usability of the developed GMM classifier. With the help of the performed analysis, the optimal setting of the initial parameters and the structure of the input feature set for recognition of the storytelling voices was finally determined.
The contribution describes the effect of the fixed and removable orthodontic appliances on spectral properties of emotional speech. Spectral changes were analyzed and evaluated by spectrograms and mean Welch’s periodograms. This alternative approach to the standard listening test enables to obtain objective comparison based on statistical analysis by ANOVA and hypothesis tests. Obtained results of analysis performed on short sentences of a female speaker in four emotional states (joyous, sad, angry, and neutral) show that, first of all, the removable orthodontic appliance affects the spectrograms of produced speech.
Our environment is permeated by electrical and magnetic alternating waves in the frequency range above the AC voltage of 50 Hz and also in the radio frequency range. Much attention from the public is given to these waves. Through numerous studies and publications about this type of oscillations and waves it is largely known from which sources they occur and which impact they have. However, very little information could be found about electrical and magnetic alternating waves in the frequency range below 50 Hz. The aim of this research is to demonstrate that these signals exist and also to show how the signals look like and where and when they occur. This article gives an overview of the occurrence of these ELF (Extremely Low Frequencies) signals, their specific properties in view of the time domain and in view of the frequency domain and of the possible sources of these waves. Precise knowledge of the structures of the ELF signals allows conclusions about their potential to cause electromagnetic interference in electronic systems. Also other effects in our environment, eg on flora and fauna could be explained.
In this paper the intelligibility of ideal binary-masked noisy signal is evaluated for different signal to noise ratio (SNR), mask error, masker types, distance between source and receiver, reverberation time and local criteria for forming the binary mask. The ideal binary mask is computed from time-frequency decompositions of target and masker signals by thresholding the local SNR within time-frequency units. The intelligibility of separated signal is measured using different objective measures computed in frequency and perceptual domain. The present study replicates and extends the findings which were already presented but mainly shows impact of room acoustic on the intelligibility performance of IBM technique.
The paper describes our experiment with using the Gaussian mixture models (GMM) for classification of speech uttered by a person wearing orthodontic appliances. For the GMM classification, the input feature vectors comprise the basic and the complementary spectral properties as well as the supra-segmental parameters. Dependence of classification correctness on the number of the parameters in the input feature vector and on the computation complexity is also evaluated. In addition, an influence of the initial setting of the parameters for GMM training process was analyzed. Obtained recognition results are compared visually in the form of graphs as well as numerically in the form of tables and confusion matrices for tested sentences uttered using three configurations of orthodontic appliances.