Correctness-Adjusted Unsupervised Discriminative Acoustic Model Adaptation

@article{Gibson2012CorrectnessAdjustedUD,
  title={Correctness-Adjusted Unsupervised Discriminative Acoustic Model Adaptation},
  author={Matthew Gibson and Thomas Hain},
  journal={IEEE Transactions on Audio, Speech, and Language Processing},
  year={2012},
  volume={20},
  pages={2648-2656}
}
Unsupervised acoustic model adaptation for large vocabulary speech recognition is typically accomplished by using an estimated transcription of the adaptation data. The effectiveness of the technique is limited by errors in the estimated transcription. Previous work has mitigated this negative effect by using only those sections of the adaptation data which are transcribed with relatively high confidence. In this work, phoneme correctness predictions are integrated into a discriminative… CONTINUE READING

Citations

Publications citing this paper.
Showing 1-2 of 2 extracted citations

Unsupervised discriminative adaptation using differenced maximum mutual information based linear regression

2013 IEEE International Conference on Acoustics, Speech and Signal Processing • 2013
View 9 Excerpts
Highly Influenced

Discriminative recognition rate estimation for N-best list and its application to N-best rescoring

2013 IEEE International Conference on Acoustics, Speech and Signal Processing • 2013
View 2 Excerpts

References

Publications referenced by this paper.
Showing 1-10 of 27 references

MPE-based discriminative linear transforms for speaker adaptation

Computer Speech & Language • 2008
View 7 Excerpts
Highly Influenced

Unsupervised Minimum Bayes Risk Acoustic Model Adaptation

M. Gibson, T. Hain, Confidence-Informed
Sheffield Univ. Dept. of Comput. Sci., • 2011
View 2 Excerpts

Error Approximation and Minimum Phone Error Acoustic Model Estimation

IEEE Transactions on Audio, Speech, and Language Processing • 2010
View 2 Excerpts

Discriminative cluster adaptive training

IEEE Transactions on Audio, Speech, and Language Processing • 2006
View 1 Excerpt

MPE-based discriminative linear transform for speaker adaptation

2004 IEEE International Conference on Acoustics, Speech, and Signal Processing • 2004

Similar Papers

Loading similar papers…