Unsupervised discriminative adaptation using discriminative mapping transforms

  title={Unsupervised discriminative adaptation using discriminative mapping transforms},
  author={Kai Yu and Mark J. F. Gales and Philip C. Woodland},
  journal={2008 IEEE International Conference on Acoustics, Speech and Signal Processing},
The most commonly used approaches to speaker adaptation are based on linear transforms, as these can be robustly estimated using limited adaptation data. Although significant gains can be obtained using discriminative criteria for training acoustic models, maximum likelihood (ML) estimated transforms are used for unsupervised adaptation. This is because discriminatively trained transforms are highly sensitive to errors in the adaptation hypothesis. This paper describes a new framework for… CONTINUE READING