ISCA Archive Eurospeech 1997
ISCA Archive Eurospeech 1997

Unsupervised HMM adaptation based on speech-silence discrimination

Ilija Zeljkovic, Shrikanth Narayanan, Alexandros Potamianos

An unsupervised, sentence-level, discriminative, HMM adaptation algorithm based on silence- speech classification is presented. Silence and speech regions are determined either using an end- pointer or using the segmentation obtained from the recognizer in a first pass. A unsupervised discriminative training procedure using the gradient descent algorithm, with N-best competing strings with word insertions is then used to improve the discrimination between silence and speech. Experiments on connected digits show about 40-80 % reduction in insertion errors, a small amount of reduction in substitution errors, and a negligible effect on deletion errors. In addition, experiments on noisy speech showed about 70% word error rate reduction, thus demonstrating the robustness of the proposed adaptation technique.


doi: 10.21437/Eurospeech.1997-544

Cite as: Zeljkovic, I., Narayanan, S., Potamianos, A. (1997) Unsupervised HMM adaptation based on speech-silence discrimination. Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997), 2055-2058, doi: 10.21437/Eurospeech.1997-544

@inproceedings{zeljkovic97b_eurospeech,
  author={Ilija Zeljkovic and Shrikanth Narayanan and Alexandros Potamianos},
  title={{Unsupervised HMM adaptation based on speech-silence discrimination}},
  year=1997,
  booktitle={Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997)},
  pages={2055--2058},
  doi={10.21437/Eurospeech.1997-544},
  issn={1018-4074}
}