ML Anthology

Use of Multi-Layered Networks for Coding Speech with Phonetic Features

Yoshua Bengio, Régis Cardin, Renato de Mori, Piero Cosi
NeurIPS 1988 pp. 224-231
/neurips/1988/bengio1988neurips-use/

Abstract

Preliminary results on speaker-independant speech recognition are reported. A method that combines expertise on neural networks with expertise on speech recognition is used to build the recognition systems. For transient sounds, event(cid:173) driven property extractors with variable resolution in the time and frequency domains are used. For sonorant speech, a model of the human auditory system is preferred to FFT as a front-end module.

PDF NeurIPS Semantic Scholar

Cite

Text

Bengio et al. "Use of Multi-Layered Networks for Coding Speech with Phonetic Features." Neural Information Processing Systems, 1988.

Markdown

[Bengio et al. "Use of Multi-Layered Networks for Coding Speech with Phonetic Features." Neural Information Processing Systems, 1988.](https://mlanthology.org/neurips/1988/bengio1988neurips-use/)

BibTeX

@inproceedings{bengio1988neurips-use,
  title     = {{Use of Multi-Layered Networks for Coding Speech with Phonetic Features}},
  author    = {Bengio, Yoshua and Cardin, Régis and de Mori, Renato and Cosi, Piero},
  booktitle = {Neural Information Processing Systems},
  year      = {1988},
  pages     = {224-231},
  url       = {https://mlanthology.org/neurips/1988/bengio1988neurips-use/}
}