The Tempo 2 Algorithm: Adjusting Time-Delays by Supervised Learning

Abstract

In this work we describe a new method that adjusts time-delays and the widths of time-windows in artificial neural networks automatically. The input of the units are weighted by a gaussian input-window over time which allows the learning rules for the delays and widths to be derived in the same way as it is used for the weights. Our results on a phoneme classification task compare well with results obtained with the TDNN by Waibel et al., which was manually optimized for the same task.

Cite

Text

Bodenhausen and Waibel. "The Tempo 2 Algorithm: Adjusting Time-Delays by Supervised Learning." Neural Information Processing Systems, 1990.

Markdown

[Bodenhausen and Waibel. "The Tempo 2 Algorithm: Adjusting Time-Delays by Supervised Learning." Neural Information Processing Systems, 1990.](https://mlanthology.org/neurips/1990/bodenhausen1990neurips-tempo/)

BibTeX

@inproceedings{bodenhausen1990neurips-tempo,
  title     = {{The Tempo 2 Algorithm: Adjusting Time-Delays by Supervised Learning}},
  author    = {Bodenhausen, Ulrich and Waibel, Alex},
  booktitle = {Neural Information Processing Systems},
  year      = {1990},
  pages     = {155-161},
  url       = {https://mlanthology.org/neurips/1990/bodenhausen1990neurips-tempo/}
}