JANUS: Speech-to-Speech Translation Using Connectionist and Non-Connectionist Techniques

Abstract

We present JANUS, a speech-to-speech translation system that utilizes diverse processing strategies, including connectionist learning, tradi(cid:173) tional AI knowledge representation approaches, dynamic programming, and stochastic techniques. JANUS translates continuously spoken English and German into German, English, and Japanese. JANUS cur(cid:173) rently achieves 87% translation fidelity from English speech and 97% from German speech. We present the JANUS system along with com(cid:173) parative evaluations of its interchangeable processing components, with special emphasis on the connectionist modules.

Cite

Text

Waibel et al. "JANUS: Speech-to-Speech Translation Using Connectionist and Non-Connectionist Techniques." Neural Information Processing Systems, 1991.

Markdown

[Waibel et al. "JANUS: Speech-to-Speech Translation Using Connectionist and Non-Connectionist Techniques." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/waibel1991neurips-janus/)

BibTeX

@inproceedings{waibel1991neurips-janus,
  title     = {{JANUS: Speech-to-Speech Translation Using Connectionist and Non-Connectionist Techniques}},
  author    = {Waibel, Alex and Jain, Ajay N. and McNair, Arthur E. and Tebelskis, Joe and Osterholtz, Louise and Saito, Hiroaki and Schmidbauer, Otto and Sloboda, Tilo and Woszczyna, Monika},
  booktitle = {Neural Information Processing Systems},
  year      = {1991},
  pages     = {183-190},
  url       = {https://mlanthology.org/neurips/1991/waibel1991neurips-janus/}
}