Jan Macek

Learn More
HMMs are the dominating technique used in speech recognition today since they perform well in overall phone recognition. In this paper, we show the comparison of HMM methods and machine learning techniques, such as neural networks, decision trees and ensemble classifiers with boosting and bagging in the task of articulatory-acoustic feature classification.(More)
Generally speech recognition systems make use of acoustic features as a representation of speech for further processing. These acoustic features are usually based on human auditory perception or signal processing. More recently, Articulatory Feature (AF) based speech representations have been investigated by a number of speech technology researchers.(More)
Generally speech recognition systems make use of acoustic features as a representation of speech for further processing. These acoustic features are usually based on human auditory perception or signal processing. More recently , Articulatory Feature (AF) based speech representations have been investigated by a number of speech technology researchers.(More)
A typical speech recognition system uses acoustic features to represent speech for its processing. Recently, articulatory features were introduced to serve the same purpose. They are motivated by linguistic knowledge and may therefore provide better or complementary representation of speech signal. We present research on recognition of such articulatory(More)
  • Rudolf Kadlec, Jindřich Libovick´y, Jan Macek, Jan Kleindienst
  • 2014
Accurate dialog state tracking is crucial for the design of an efficient spoken dialog system. Until recently, quantitative comparison of different state tracking methods was difficult. However the 2013 Dialog State Tracking Challenge (DSTC) introduced a common dataset and metrics that allow to evaluate the performance of trackers on a standardized task. In(More)
We present an interactive system for physical exercise of older people and provide results of a usability study with target user group. The system motivates an elderly person to do regular physical activity based on an easy exercise in a monitored environment without a direct supervision from care-givers. Our system employs multi-modal interface including(More)
This paper compares two different approaches to computer-aided analysis of ECG signals. ECG records are preprocessed by the wavelet transform, and the machine learning method of decision trees and fuzzy rules induction are used for classification. The wavelet transform allows good localisation of QRS complexes, P and T waves in time and amplitude. The(More)
Gravel-sand river terraces were nearly eliminated from central European landscape by river channelization. Monotypic stands of common reed (Phragmites australis) growing on such terraces are often stressed by drought, which makes them vulnerable to Lipara spp. (Diptera: Chloropidae) gallmakers. Although Lipara are considered ecosystem engineers, only(More)