Learn More
In the Speechdat-E project five medium large telephone speech databases have been collected for Czech, Hungarian, Polish, Russian, and Slovak. The project was recently concluded. This paper reports briefly on the contents of the databases, elaborates on experiences gained from the data recordings and from the validation of the databases. The availability of(More)
We investigated the brain mechanisms enabling one automatically discriminate phoneme category irrespective of the large inter-speaker variability in the acoustic features of the voices. For this purpose, subjects were presented with 450 different speech stimuli, each uttered by a different speaker, belonging to three vowel categories, while a 306-channel(More)
  • 1