ISCA Archive ICSLP 2000
ISCA Archive ICSLP 2000

Rival training: efficient use of data in discriminative training

Carsten Meyer, Georg Rose

We evaluate a simple extension of the corrective training algorithm for reestimation of the acoustic parameters, using | in addition to misrecognized sentences - also a selection of correctly recognized sentences for discrimination. Our approach (called "rival training") is implementationally much less expensive than lattice{based discriminative training methods, since we apply a \hard" threshold criterion to select a subset of sentences for which a single competitor is used for discrimination. Still, significant performance gains are obtained compared to maximum likelihood and corrective training even for triphone models with 61 densities per mixture (on a digit string and a large vocabulary isolated word recognition task). Further, the hard selection scheme may be used to accelerate the training process due to faster convergence and by restricting the training process to a fixed subset of training utterances.


Cite as: Meyer, C., Rose, G. (2000) Rival training: efficient use of data in discriminative training. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 4, 632-635

@inproceedings{meyer00_icslp,
  author={Carsten Meyer and Georg Rose},
  title={{Rival training: efficient use of data in discriminative training}},
  year=2000,
  booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
  pages={vol. 4, 632-635}
}