Jiří Přibil

Evaluation of influence of spectral and prosodic features on GMM classification of Czech and Slovak emotional speech

This article analyzes and compares influence of different types of spectral and prosodic features for Czech and Slovak emotional speech classification based on Gaussian mixture models (GMM). Influence of initial setting of parameters (number of mixture components and used number of iterations) for GMM training process was analyzed, too. Subsequently, analysis was performed to find how correctness of emotion classification depends on the number and the order of the parameters in the input feature vector and on the computation complexity. Another test was carried out to verify the functionality of the proposed two-level architecture comprising the gender recognizer and of the emotional speech classifier. Next tests were realized to find dependence of some negative aspect (processing of the input speech signal with too short time duration, the gender of a speaker incorrectly determined, etc.) on the stability of the results generated during the GMM classification process. Evaluations and tests were realized with the speech material in the form of sentences of male and female speakers expressing four emotional states (joy, sadness, anger, and a neutral state) in Czech and Slovak languages. In addition, a comparative experiment using the speech data corpus in other language (German) was performed. The mean classification error rate of the whole classifier structure achieves about 21% for all four emotions and both genders, and the best obtained error rate was 3.5% for the sadness style of the female gender. These values are acceptable in this first stage of development of the GMM classifier. On the other hand, the test showed the principal importance of correct classification of the speaker gender in the first level, which has heavy influence on the resulting recognition score of the emotion classification. This GMM classifier should be used for evaluation of the synthetic speech quality after applied voice conversion and emotional speech style transformation.

Measurement and imaging of planar electromagnetic phantoms based on NMR imaging methods

Measurement and Imaging of Planar Electromagnetic Phantoms Based on NMR Imaging Methods Planar electromagnetic phantom design for measurement and imaging using NMR has been performed. Electromagnetic phantom computation and testing on a NMR 0.178 Tesla Esaote Opera imager were accomplished. The classical geometrical and chemical phantoms are generally used for testing of NMR imaging systems. They are simple cylindrical or rectangular objects with different dimensions and shapes with holes filled with specially prepared water solutions. In our experiments a homogeneous phantom (reference medium) - a container filled with water - was used. The resultant image represents the magnetic field distribution in the homogeneous phantom. An image acquired by this method is actually a projection of the sample properties onto the homogeneous phantom. The goal of the paper is to map and image the magnetic field deformation using NMR imaging methods. We are using a double slender rectangular vessel with constant thickness filled with specially prepared water solution in our experiments. For detection a carefully tailored gradient-echo imaging method, susceptible to magnetic field homogeneity, was used.

Two Methods of Mechanical Noise Reduction of Recorded Speech During Phonation in an MRI device

Two Methods of Mechanical Noise Reduction of Recorded Speech During Phonation in an MRI device The paper presents two methods of noise reduction of speech signal recorded in an MRI device during phonation for the human vocal tract modelling. The applied approach of noise speech signal cleaning is based on cepstral speech analysis and synthesis because the noise is mainly produced by gradient coils, has a mechanical character, and can be processed in spectral domain. Our first noise reduction method is using real cepstrum limitation and clipping the peaks corresponding to the harmonic frequencies of mechanical noise. The second method is coming out from substation of the short-time spectra of two signals recorded withal: the first includes speech and noise, and the second consists of noise only. The resulting speech quality was compared by spectrogram and mean periodogram methods.

Circular Samples as Objects for Magnetic Resonance Imaging - Mathematical Simulation, Experimental Results

Abstract Circular samples are the frequent objects of in-vitro investigation using imaging method based on magnetic resonance principles. The goal of our investigation is imaging of thin planar layers without using the slide selection procedure, thus only 2D imaging or imaging of selected layers of samples in circular vessels, eppendorf tubes,.. compulsorily using procedure slide selection. In spite of that the standard imaging methods was used, some specificity arise when mathematical modeling of these procedure is introduced. In the paper several mathematical models were presented that were compared with real experimental results. Circular magnetic samples were placed into the homogenous magnetic field of a low field imager based on nuclear magnetic resonance. For experimental verification an MRI 0.178 Tesla ESAOTE Opera imager was used.

Quantum Imaging X-ray CT Systems Based on GaAs Radiation Detectors Using Perspective Imaging Reconstruction Techniques

Quantum Imaging X—ray CT Systems Based on GaAs Radiation Detectors Using Perspective Imaging Reconstruction Techniques The work presents two generations of developed portable quantum X—CT mini-systems which utilize monolithic semi-insulating GaAs detectors. This contribution describes the present status of the assembling of the new portable X—ray CT mini system. Developed modification of the X—ray image reconstruction based on perspective imaging techniques has been experimentally verified on testing phantoms and practically implemented for processing images of real test objects. Performed measurement of the performance of the SI GaAs detectors and the integral spectra of ASIC DX64 readout chips are also mentioned.

Design, Realization and Experiments with a new RF Head Probe Coil for Human Vocal Tract Imaging in an NMR device

Design, Realization and Experiments with a new RF Head Probe Coil for Human Vocal Tract Imaging in an NMR device Magnetic resonance imaging (MRI) is nowadays widely used in medicine for diagnostic imaging and in research studies. The modeling of the human vocal tract acoustics has recently attracted considerable interest. This paper describes the design, realization and first MR scan experiments with a new head probe coil for vocal tract imaging in the open-air MRI equipment working in a weak magnetic field up to 0.2 T. The paper also describes an experimental setting for sound recording during the MR imaging.

GMM-Based Evaluation of Emotional Style Transformation in Czech and Slovak

AbstractnIn the development of the voice conversion and the emotional speech style transformation in the text-to-speech systems, it is very important to obtain feedback information about the users’ opinion on the resulting synthetic speech quality. For this reason, the evaluations of the quality of the produced synthetic speech must often be performed for comparison. The main aim of the experiments described in this paper was to find out whether the classifier based on Gaussian mixture models (GMMs) could be applied for evaluation of male and female resynthesized speech that had been transformed from neutral to four emotional states (joy, surprise, sadness, and anger) spoken in Czech and Slovak languages. 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. For verification of our working hypothesis, a simple GMM emotional speech classifier with a one-level structure was realized. The next task of the performed experiment was to investigate the influence of different types and values (mean, median, standard deviation, relative maximum, etc.) of the used speech features (spectral and/or supra-segmental) on the GMM classification accuracy. The obtained GMM evaluation scores are compared with the results of the conventional listening tests based on the mean opinion scores. In addition, correctness of the GMM classification is analyzed with respect to the influence of the setting of the parameters during the GMM training—the number of mixture components and the types of speech features. The paper also describes the comparison experiment with the reference speech corpus taken from the Berlin database of emotional speech in German language as the benchmark for the evaluation of the performance of our one-level GMM classifier. The obtained results confirm practical usability of the developed GMM classifier, so we will continue in this research with the aim to increase the classification accuracy and compare it with other approaches like the support vector machines.

Statistical Analysis of Spectral Properties and Prosodic Parameters of Emotional Speech

Statistical Analysis of Spectral Properties and Prosodic Parameters of Emotional Speech The paper addresses reflection of microintonation and spectral properties in male and female acted emotional speech. Microintonation component of speech melody is analyzed regarding its spectral and statistical parameters. According to psychological research of emotional speech, different emotions are accompanied by different spectral noise. We control its amount by spectral flatness according to which the high frequency noise is mixed in voiced frames during cepstral speech synthesis. Our experiments are aimed at statistical analysis of cepstral coefficient values and ranges of spectral flatness in three emotions (joy, sadness, anger), and a neutral state for comparison. Calculated histograms of spectral flatness distribution are visually compared and modelled by Gamma probability distribution. Histograms of cepstral coefficient distribution are evaluated and compared using skewness and kurtosis. Achieved statistical results show good correlation comparing male and female voices for all emotional states portrayed by several Czech and Slovak professional actors.