Rozpoznávač izolovaných slov pro ovládání elektronických slovníků

This work is concerned with creation of isolated word recognizer for electronic dictionaires, testing its functionality on data sample and improvement by normalisation and speaker adaptation techniques. Word recognizer is built on HTK (Hidden Markov Model Toolkit). At the beginning of this document, the main aims of the work are set. In the next chapter is theoretical analysis, which describes process of recognition of isolated words with hidden Markov models. Next chapter specifies the speech data, which were used for testing. Other resources for building recognizer, like models, dictionary and grammar are described in next chapter. Before creation of recognizer, it was necessary to solve conversion between the phonemes set which was used in dictionary and set, which uses the recognizer. The recognizer was built with 8~kHz models first, than 16~kHz models were also used. Normalisation and speaker adaptation techniques were used. Obtained data were processed and results are analyzed in separate chapter. Finally is discussed, if the goals of the work were reached and what are the next steps of application development.

Speech recognition, HTK, VTLN, PLP, dictionary, phoneme