Discriminative adaptive training with VTS and JUD

  title={Discriminative adaptive training with VTS and JUD},
  author={Federico Flego and Mark J. F. Gales},
  journal={2009 IEEE Workshop on Automatic Speech Recognition & Understanding},
Adaptive training is a powerful approach for building speech recognition systems on non-homogeneous training data. Recently approaches based on predictive model-based compensation schemes, such as Joint Uncertainty Decoding (JUD) and Vector Taylor Series (VTS), have been proposed. This paper reviews these model-based compensation schemes and relates them to factor-analysis style systems. Forms of Maximum Likelihood (ML) adaptive training with these approaches are described, based on both second… CONTINUE READING
Highly Cited
This paper has 45 citations. REVIEW CITATIONS
19 Citations
19 References
Similar Papers


Publications citing this paper.


Publications referenced by this paper.
Showing 1-10 of 19 references

Similar Papers

Loading similar papers…