Informatica

This paper presents the Croatian context-dependent acoustic modelling used in speech recognition and in speech synthesis. The proposed acoustic model is based on context-dependent triphone hidden Markov models and Croatian phonetic rules. For speech recognition and speech synthesis system modelling and testing the Croatian speech corpus VEPRAD was used. The experiments have shown that Croatian speech corpus, Croatian phonetic rules and hidden Markov models as the modelling formalism can be used to develop speech recognition and speech synthesis systems in parallel for a highly flective and free order language like Croatian. We propose an evaluation procedure for speech synthesis, which combines an objective and a subjective evaluation approach and we present the achieved evaluation results. The proposed procedures for Croatian acoustic modelling were developed as parts of speech interfaces in a spoken dialog system for a limited weather forecast domain.

This paper presents a bimodal biometric verification system based on the fusion of palmprint and face features at the matching-score level. The system combines a new approach to palmprint principal lines recognition based on hypotheses generation and evaluation and the well-known eigenfaces approach for face recognition. The experiments with different matching-score normalization techniques have been performed in order to improve the performance of the fusion at the matching-score level. A “chimerical” database consisting of 1488 palmprint and face image pairs of 241 persons was used in the system design (440 image pairs of 110 persons) and testing (1048 image pairs of 131 persons). The experimental results show that system performance is significantly improved over unimodal subsystems.