Learn More
In this paper the assistive multimodal system is presented, which is aimed for the disabled people, which need other kinds of interfaces than ordinary people. The group of users of this system is persons with hands disabilities. The interaction between a user and a machine is performed by voice and head movements. It gives the opportunity for disabled(More)
In this paper, we present a word-based very large vocabulary automatic speech recognition system for Russian. Some novel methods are proposed for organization of the lexicon and the language model. Two-level morpho-phonemic prefix graph that uses some information on morphemic structure of lexical units is suggested for a compact representation of the(More)
Speech is the most natural way of human communication and in order to achieve convenient and efficient human–computer interaction implementation of state-of-the-art spoken language technology is necessary. Research in this area has been traditionally focused on In this paper, we describe our efforts to build an automatic speech recognition (ASR) system for(More)
The paper presents the results of recent experiments with audiovisual speech recognition for two popular Slavonic languages: Russian and Czech. The description of test applied tasks, the process of multimodal databases collection and data pre-processing, methods for visual features extraction (geometric shape-based features; DCT and PCA pixel-based visual(More)
This paper describes the developed multimodal system intended for assistance to people with disabilities of hands. It combines automatic speech recognition and head tracking in one multimodal system. The structure of the system, the methods for recognition and tracking, information fusion and synchronization, the obtained results and testing conditions are(More)