Discriminative training for continuous speech recognition

@inproceedings{Reichl1995DiscriminativeTF,
  title={Discriminative training for continuous speech recognition},
  author={Wolfgang Reichl and G{\"u}nther Ruske},
  booktitle={EUROSPEECH},
  year={1995}
}
Discriminative training techniques for Hidden Markov Models were recently proposed and successfully applied for automatic speech recognition In this paper a discussion of the Minimum Classi cation Error and the Maximum Mu tual Information objective is presented An extended reesti mation formula is used for the HMM parameter update for both objective functions The discriminative training me thods were utilized in speaker independent phoneme reco gnition experiments and improved the phoneme… CONTINUE READING

From This Paper

Topics from this paper.