Previous work on speech-to-speech translation has suffered from problems of brittleness and low quality (rule-based approaches), or from excessive data requirements and linguistic ineciency (analogical or example-based approaches). In this paper, we present a probabilistic approach to analogical speech translation, and describe its integration with linguistic processing. The evaluation results show that this approach results in high-accuracy translations in limited domains.
Cite as: Horiguchi, K., Franz, A. (1997) A probabilistic approach to analogical speech translation. Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997), 2687-2690, doi: 10.21437/Eurospeech.1997-678
@inproceedings{horiguchi97_eurospeech, author={Keiko Horiguchi and Alexander Franz}, title={{A probabilistic approach to analogical speech translation}}, year=1997, booktitle={Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997)}, pages={2687--2690}, doi={10.21437/Eurospeech.1997-678} }