Search

Increased mortality rate for patients with mental disorders and their shorter lifespan compared to the general public is stated by numerous authors. Services on the Clinic for mental disorders 'Dr Laza Lazarević' were reorganized, by introducing intensive care units - level two, i.e. contemporary intensive care of patients was introduced, only without life support. Primary objective of the research was to determine if the introduction of intensive care to the Clinic led to a statistically significant change in the number of fatal outcomes of hospitalized patients. The research was designed as a cross-sectional study and it included 62 patients that have died while being hospitalized at the Clinic for mental disorders 'Dr Laza Lazarević' in Belgrade, in 2011 and 2012. Data were collected by retrospective insight in the histories of illnesses and treatment protocols of the Clinic and institutes for pathology and forensic medicine of the Faculty of Medicine in Belgrade. Obtained data were statistically analysed with Student's T-test and ANOVA test, with a significance level of 0.05. Statistically significant difference was determined in fatalities in 2011 compared to 2012 with p = 0.007, and there were significantly less fatalities in 2012. Statistically significant difference in frequency of fatal outcomes when comparing 2011 to 2012 was determined only when comparing the ward of previous intensive care on one side with the newly established psychiatric intensive care units - level two on the other. High level of significance was determined with p = 0.005. New organizational concept introduced in 2012 has led to more efficient twenty-four-hour care and monitoring of hospitalized patients, suppression of accompanying somatic illnesses which altogether led to a significant reduction of fatal outcomes.

Postulate of our research issue is based on the argumentation the correlation diffuse damage of neuronical and non neuronical subcortical structures weakened vascularization during the longer premorbid period with the clinical manifestation of cognitive dysfunction. The main aim of our researching is argumentation the atrophy subcortical brains structures and connection with cognitive dysfunction by the extent to the demented and brain mnestic deterioration. Research was carried out in the two researched groups of patients treated in hospital, A and B, that controlled themselves as well. Both groups consisted of 40 patients both sexes aged 50 to 70 years. Results of our research confirmed that cognitive functioning was damaged to all patients with determined subcortical brain, s ischemia and reduction of the neuronical and non neuronical subcortical structures diagnosed by the visualised imaging diagnostic methods. Dysfunction of cognition according to difficulty is the reciprocal psychometric confirmed scope of subcortical atrophy, or the reduction of the brain, s structures.

This paper presents the results on whispered speech recognition using gammatone filterbank cepstral coefficients for speaker dependent mode. The isolated words used for this experiment are taken from the Whi-Spe database. Whispered speech recognition is based on dynamic time warping and hidden Markov models methods. The experiments are focused on the following modes: normal speech, whispered speech and their combinations (normal/whispered and whispered/normal). The results demonstrated an important improvement in recognition after application of cepstral mean subtraction, especially in mixed train/test scenarios. [ABSTRACT FROM AUTHOR]

This article presents an analysis of different cepstral normalization techniques in automatic recognition of whispered and bimodal speech (speech+whisper). In these experiments, conventional GMM-HMM speech recognizer was used as speaker-dependant automatic speech recognition system with special Whi-Spe corpus containing utterance recordings in normally phonated speech and whisper. The following normalization techniques were tested and compared: CMN (Cepstral Mean Normalization), CVN (Cepstral Variance Normalization), MVN (Cepstral Mean and Variance Normalization), CGN (Cepstral Gain Normalization) and quantile-based dynamic normalization techniques such as QCN and QCN-RASTA. The experimental results show to what extent each of these cepstral normalization techniques can improve whisper recognition accuracy in mismatched train/test scenario. The best result is obtained using CMN in combination with inverse filtering which provides an average 39.9 percent improvement in whisper recognition accuracy for all tested speakers.