The IBM speech-to-speech translation system for smartphone: Improvements for resource-constrained tasks

This paper describes our recent improvements to IBM TRANSTAC speech-to-speech translation systems that address various issues arising from dealing with resource-constrained tasks, which include both limited amounts of linguistic resources and training data, as well as limited computational power on mobile platforms such as smartphones. We show how the proposed algorithms and methodologies can improve the performance of automatic speech recognition, statistical machine translation, and text-to-speech synthesis, while achieving low-latency two-way speech-to-speech translation on mobiles.

► We describe the IBM TRANSTAC speech-to-speech mobile translation system. ► Address issues arising from linguistically and computationally constrained tasks. ► Presented methods that improved the performance of key components. ► Enabled the low-latency two-way speech-to-speech translation on smartphones.