Unsupervised training for Farsi-English speech-to-speech translation

Speech-to-speech translation has evolved into an attractive area in recent years with significant progress made by various research groups. However, the translation engines usually suffer from the lack of bilingual training data, especially for low-resource languages. In this paper we present an unsupervised training technique to alleviate this problem by taking advantage of available source language data. Different approaches are proposed and compared through extensive experiments conducted on a speech-to-speech translation task between Farsi and English. The translation performance is significantly improved in both directions with the enhanced translation model. A state-of-the-art Farsi automatic speech recognition system is also established in this work.