Vytautas Rudzionis

  • Citations Per Year
Learn More
Better discrimination of phonemic units still remains one of the most important problems in automatic speech recognition. Direct phoneme recognition in speaker independent automatic speech recognition systems is unable to provide good enough recognition results. There is made an assumption that better results could be achieved through the recognition of(More)
In this paper, we propose a computational architecture for multimodal comprehension of text and graphics. A theoretical account of the integrated conceptual structures induced by linguistic and graphical entities is presented. We exemplify these structures with the analysis of an excerpt from a report published by Point Reyes Bird Observatory (PRBO).(More)
The paper deals with the problem of improving speech recognition by combining outputs of several different recognizers. We are presenting our results obtained by experimenting with different classification methods which are suitable to combine outputs of different speech recognizers. Methods which were evaluated are: k-Nearest neighbors (KNN), Linear(More)
The Lithuanian speech database LTDIGITS was developed. Some details of this database could be of more general interest. These features are related with collected set of nasal consonant realizations in different vowel contexts. First, LTDIGITS contains nasal – vowel syllables where nasal is before open, middle and closed vowels. Second, the database includes(More)
Activities to develop Lithuanian Web pages for speech-enabled access from telephone are presented. After the integration of Lithuanian text-to-speech synthesizers “Aistis” and LtMBR to SAPI 5 (Speech Application Programming Interface), some Lithuanian speech-enabled Web pages were prepared (www.speech.itpi.ktu.lt). Two methods of SALT (Speech Application(More)