The paper offers a comprehensive survey of machine translation approaches to coping with Slavic languages in different aspects of statistical machine translation. We observe that the interest of the community in research of more difficult languages is increasing and we believe that the translation quality of those languages will reach the level of practical use in the near future.
COBISS.SI-ID: 20561174
We researched the extension of hidden Markov model based recogniton od activities of daily living. We extended the the system with higher order Markov chains to include long term dependencies and an activity transition cost to reduce the number of activity transition in the recognition results.
COBISS.SI-ID: 22619414
A new method of binocular phase-coded visual stimulation for non-invasive direct brain computer interfaces was designed based on two-channel capture of electroencephalographic signals in the occiput region of the head at the left and right occipital lobes of the brain and further detection of rhythmic and less rhythmic cortical oscillations or visually evoked potentials as a consequence of visual stimuli. Binocular phase-coded visual stimulation was performed on the basis of phase modulation of several spatially distributed light sources as the back light of the left and right screen of the head-mounted displays for virtual or augmented reality. The results showed that it is possible to create a new hidden communication channel that does not have a direct impact on the displayed visual three-dimensional context within virtual or augmented reality applications. Thus we achieved a basis for establishing a new modality in order to achieve more intuitive interaction.
COBISS.SI-ID: 22315030
In the paper, a speech-based platform for intelligent ambience and/or supportive environment applications is presented. The platform has a distributed architecture, which enables extended connectivity and support for multiple intelligent ambience services. The mobile unit Genesis is an integral part of the distributed platform, enabling interaction between several users and the environment. Furthermore, the sophisticated client/server platform's architecture incorporates robust speech recognition and text-to-speech synthesis engines for more natural human-machine interaction between users and the mobile unit Genesis. Both engines are multilingual oriented. Although the whole system is developed for the Slovenian language, it can be quickly adapted for other languages when appropriate language resources are available. With high speaker independent speech recognition accuracy and low command-to-operation delay, Genesis proves to have good manoeuvrability and it is easy to operate even by a non-experienced operator.
COBISS.SI-ID: 20686358
A major drawback of corpus-based speech synthesis systems is the use of large acoustic inventories, and currently one of the main challenges is the optimal representation of concatenation costs associated with units in the acoustic inventory. These concatenation costs are used to evaluate spectral mismatches between the acoustic units to be concatenated. The combinatorics of costs grows exponentially with the size of the acoustic inventories and can result in hundreds of millions or even billions of concatenation costs to be processed. Therefore, in this paper, we represent a novel unit selection optimization algorithm, which minimizes the size of concatenation costs through the vector quantization-based compression technique and tuple structures. Furthermore, the proposed optimization algorithm is designed to be used as an objective measure to optimize the performance of the unit selection cost function regarding the quality of the speech output, and to evaluate the effect of the vector quantization-based compression technique on its performance. The results obtained show that even when data compression is above 50%, the effect on the quality of the synthesized speech is negligible.
COBISS.SI-ID: 22512150