The paper describes an experiment with using the Gaussian mixture models (GMM) for automatic classification of the speaker age and gender. It analyses and compares the influence of different number of mixtures and different types of speech features used for GMM gender/age classification. Dependence of the computational complexity on the number of used mixtures is also analysed. Finally, the GMM classification accuracy is compared with the output of the conventional listening tests. The results of these objective and subjective evaluations are in correspondence.
The paper deals with the photoplethysmographic (PPG) optical sensor usage for non-invasive acquisition of vital information about the cardiovascular system from different parts of the human skin surface. Finger-ring and ear-clip realizations of the transmission-type PPG sensor were tested first. For the next PPG signal recording, the reflection PPG sensor was placed on fingers and on a wrist. PPG signal properties were described by energetic and temporal parameters and their statistical parameters together with determined instantaneous heart rate values. Our final aim was to find conditions, limitations, and recommendations for development of a wearable PPG sensor working in a magnetic field environment.
The paper describes first-step experiments with parallel measurement of cardiovascular parameters using a photoplethysmographic optical sensor and standard portable blood pressure monitors in different situations of body relaxation and stimulation. Changes in the human cardiovascular system are mainly manifested by differences in the Oliva–Roztocil index, the instantaneous heart rate, and variations in blood pressure. In the auxiliary experiments, different physiological and psychological stimuli were applied to test whether relaxation and activation phases produce different measured parameters suitable for further statistical analysis and processing. The principal investigation is aimed at analysis of vibration and acoustic noise impact on a physiological and psychological state of a person lying inside the low-field open-air magnetic resonance imager (MRI). The obtained results will be used to analyze, quantify, and suppress a possible stress factor that has an impact on the speech signal recorded during scanning in the MRI device in the research aimed at 3D modeling of the human vocal tract.
24 April 2013 in EURASIP Journal on Audio, Speech, and Music Processing
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.
26 September 2013 in Elektronika ir Elektrotechnika
The paper describes analysis and comparison of formant features comprising the first three formant positions together with their 3 -dB bandwidths and the formant tilts. These features were determined from the smoothed spectral envelopes or directly calculated from the complex roots of the LPC polynomial. Subsequently, statistical analysis and comparison of the formant features from emotional speech representing joy, sadness, anger, and a neutral state was performed. In this experiment we use the speech material in the form of sentences uttered by male and female professional speakers in Czech and Slovak languages. For detailed analysis, the derived speech database consisting of manually selected sounds corresponding to the stationary parts of five vowels and two nasals was created. The determined formant positions and their value ranges are in correspondence with the general knowledge for male and female voices. Obtained statistical results and values of parameter ratios will be used for emotional speech conversion or they can also be applied for extension of the text-to-speech system enabling expressive speech production. DOI: http://dx.doi.org/10.5755/j01.eee.19.8.1739