Nesting hierarchical phrase-based model for speech-to-speech translation

Hierarchical phrase-based (HPB) translation has been introduced to speech-to-speech (S2S) translation system on mobile terminals, such as smartphones. However, it suffers from the explosive growth in the number of rules along with the increment in decoding time for S2S translation system when the memory and decoding speed is restricted. In this paper, we propose a nesting HPB model to capture the topological structure of hierarchical rules on the source language side, which will not only filter out the redundant rules in HPB model but also speed up the decoder. Experiments on the HPB translation system show that our approach can greatly reduce the rule table size by 75% with a faster decoder, and yield the same translation quality (measured by using BLEU) as the state-of-art HPB model.