elektronický časopis
- Conspectus
- Počítačová věda. Výpočetní technika. Informační technologie
- NML Fields
- lékařská informatika
- NML Publication type
- elektronické časopisy
elektronický časopis
- Conspectus
- Počítačová věda. Výpočetní technika. Informační technologie
- NML Fields
- lékařská informatika
- NML Publication type
- elektronické časopisy
The impact of the classification method and features selection for the speech emotion recognition accuracy is discussed in this paper. Selecting the correct parameters in combination with the classifier is an important part of reducing the complexity of system computing. This step is necessary especially for systems that will be deployed in real-time applications. The reason for the development and improvement of speech emotion recognition systems is wide usability in nowadays automatic voice controlled systems. Berlin database of emotional recordings was used in this experiment. Classification accuracy of artificial neural networks, k-nearest neighbours, and Gaussian mixture model is measured considering the selection of prosodic, spectral, and voice quality features. The purpose was to find an optimal combination of methods and group of features for stress detection in human speech. The research contribution lies in the design of the speech emotion recognition system due to its accuracy and efficiency.
- MeSH
- Algorithms * MeSH
- Databases, Factual MeSH
- Emotions physiology MeSH
- Voice Quality MeSH
- Humans MeSH
- Neural Networks, Computer MeSH
- Signal Processing, Computer-Assisted instrumentation MeSH
- Speech physiology MeSH
- ROC Curve MeSH
- Pattern Recognition, Automated * MeSH
- Pattern Recognition, Physiological physiology MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
- MeSH
- Immune Tolerance MeSH
- Immunologic Techniques MeSH
- Isoantigens MeSH
- Rats MeSH
- Leukocytes MeSH
- Check Tag
- Rats MeSH
Cílem sdělení je porovnání vyšetřovacího postupu pro určení parametrů, které se užívají při hodnocení percepce řeči pomocí slovní audiometrie. Většina testů v zahraničí používá spondejová slova. Položili jsme si otázku, zda lze hledat závislost mezi PTA a SRT, pokud použijeme pro stanovení SRT test české slovní audiometrie. Využili jsme výsledky 34 pacientů s percepční nedoslýchavostí. Z výpočtů je nejpřínosnější určení hodnoty SRT6. Z naší studie je patrné, že vztah mezi PTA a SRT lze sledovat.
The aim of our study is the comparison of examinational process for determination of parameters, which are being used by the evaluation of speech recognition, by the help of speech audiometry. We have asked ourselves the question whether there is a dependency between PTA and SRT, if we use for determination SRT a test of Czech speech audiometry. We have used the results of 34 patients suffering sensorineural hearing loss. The determination of SRT6 from our results is the most profitable. It is clear from our study that the relationship between PTA and SRT is possible.
