Development of a Real-time Asr System for Slovak Speechdat Database

This paper describes development of a real-time speech recognition system in Slovak for the voice-operated telephone services. The system is based on SPHINX2 platform. The decoder using Hidden Markov Models was trained on the SpeechDat-E Slovak database. It is speaker independent, large vocabulary, continuous speech real-time automatic speech recognition system. Test results are given for the test groups of isolated digits, connected isolated digits, application words, phonetically rich words, and city (plus proper) names. Achieved word error rates are in the interval from 3.73% (connected isolated digits, vocabulary of 11 words) to 15.72% (city names, vocabulary of 927 words).