Structural maximum a posteriori linear regression for fast HMM adaptation

@article{Siohan2002StructuralMA,
  title={Structural maximum a posteriori linear regression for fast HMM adaptation},
  author={Olivier Siohan and Tor Andr{\'e} Myrvoll and Chin-Hui Lee},
  journal={Computer Speech & Language},
  year={2002},
  volume={16},
  pages={5-24}
}
Transformation-based model adaptation techniques like maximum likelihood linear regression (MLLR) rely on an accurate selection of the number of transformations for a given amount of adaptation data. If too many transformations are used, the transformation parameters may be poorly estimated, can overfit the adaptation data, and offer poor generalization. On the other hand, if the number of transformations is too small, the adapted models can only provide a moderate improvement over the baseline… CONTINUE READING
Highly Influential
This paper has highly influenced 19 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 136 citations. REVIEW CITATIONS
96 Citations
18 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 96 extracted citations

136 Citations

01020'00'03'07'11'15
Citations per Year
Semantic Scholar estimates that this publication has 136 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 18 references

Adaptive classification and decision strategies for robust speech recognition. In Workshop on Robust Methods for Speech Recognition in Adverse Conditions

  • C.-H. Lee
  • 1999
1 Excerpt

Hidden Markov model adaptation using maximum a posteriori linear regression

  • O. Siohan Chesta
  • Workshop on Robust Methods for Speech Recognition…
  • 1999

Similar Papers

Loading similar papers…