ARTICLE Dines_CSL_2011/IDIAP Personalising speech-to-speech translation: Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis Dines, John Liang, Hui Saheer, Lakshmi Gibson, Matthew Byrne, William Oura, Keiichiro Tokuda, Keiichi Yamagishi, Junichi King, Simon Wester, Mirjam Hirsimäki, Teemu Karhila, Reima Kurimo, Mikko cross-lingual speaker adaptation Machine Translation speech recognition speech synthesis EXTERNAL http://publications.idiap.ch/attachments/papers/2011/Dines_CSL_2011.pdf PUBLIC Computer Speech and Language 2011 http://www.sciencedirect.com/science/article/pii/S0885230811000441 URL doi:10.1016/j.csl.2011.08.003 doi In this paper we present results of unsupervised cross-lingual speaker adaptation applied to text-to-speech synthesis. The application of our research is the personalisation of speech-to-speech translation in which we employ a HMM statistical framework for both speech recognition and synthesis. This framework provides a logical mechanism to adapt synthesised speech output to the voice of the user by way of speech recognition. In this work we present results of several different unsupervised and cross-lingual adaptation approaches as well as an end-to-end speaker adaptive speech-to-speech translation system. Our experiments show that we can successfully apply speaker adaptation in both unsupervised and cross-lingual scenarios and our proposed algorithms seem to generalise well for several language pairs. We also discuss important future directions including the need for better evaluation metrics.