Towards language portability in statistical speech translation
Lists
Only you see this
Abstract
Speech translation has made significant advances over the last years. We believe that we can overcome today's limits of language and domain portable conversational speech translation systems by relying more radically on learning approaches and by the use of multiple layers of reduction and transformation to extract the desired content in another language. Therefore, we cascade stochastic source-channel models that extract an underlying message from a corrupt observed output. The three models effectively translate: (1) speech to word lattices (automatic speech recognition, ASR); (2) ill-formed fragments of word strings into a compact well-formed sentence (Clean); (3) sentences in one language to sentences in another (machine translation, MT). We present results of our research efforts towards rapid language portability of all these components. The results on translation suggest that MT systems can be successfully constructed for any language pair by cascading multiple MT systems via English. Moreover, end-to-end performance can be improved, if the interlingua language is enriched with additional linguistic information that can be derived automatically and monolingually in a data-driven fashion.
BibTeX
@inproceedings{waibel2004towards,
author = {Alex Waibel and Tanja Schultz and Stephan Vogel and Christian Fügen and Matthias Honal and Muntsin Kolss and Jürgen Reichert and Sebastian Stüker},
title = {{Towards language portability in statistical speech translation}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2004},
url = {https://openreview.net/forum?id=X0dIQ6bubj},
}Loading related content...