RecNorm: Simultaneous Normalisation and Classification Applied to Speech Recognition

Abstract

A particular form of neural network is described, which has terminals for acoustic patterns, class labels and speaker parameters. A method of training this network to "tune in" the speaker parameters to a particular speaker is outlined, based on a trick for converting a supervised network to an unsupervised mode. We describe experiments using this approach in isolated word recognition based on whole-word hidden Markov models. The results indicate an improvement over speaker-independent perfor(cid:173) mance and, for unlabelled data, a performance close to that achieved on labelled data.

Cite

Text

Bridle and Cox. "RecNorm: Simultaneous Normalisation and Classification Applied to Speech Recognition." Neural Information Processing Systems, 1990.

Markdown

[Bridle and Cox. "RecNorm: Simultaneous Normalisation and Classification Applied to Speech Recognition." Neural Information Processing Systems, 1990.](https://mlanthology.org/neurips/1990/bridle1990neurips-recnorm/)

BibTeX

@inproceedings{bridle1990neurips-recnorm,
  title     = {{RecNorm: Simultaneous Normalisation and Classification Applied to Speech Recognition}},
  author    = {Bridle, John S. and Cox, Stephen J.},
  booktitle = {Neural Information Processing Systems},
  year      = {1990},
  pages     = {234-240},
  url       = {https://mlanthology.org/neurips/1990/bridle1990neurips-recnorm/}
}