@inproceedings{oai:nitech.repo.nii.ac.jp:00003415, author = {Oura, Keiichiro and 大浦, 圭一郎 and Tokuda, Keiichi and Yamagishi, Junichi and King, Simon and Wester, Mirjam}, book = {ICASSP 2010. IEEE International Conference on Acoustics, Speech and Signal Processing, 2010.}, month = {}, note = {application/pdf, In the EMIME project, we are developing a mobile device that performs personalized speech-to-speech translation such that a user's spoken input in one language is used to produce spoken output in another language, while continuing to sound like the user's voice. We integrate two techniques, unsupervised adaptation for HMM-based TTS using a word-based large-vocabulary continuous speech recognizer and cross-lingual speaker adaptation for HMM-based TTS, into a single architecture. Thus, an unsupervised cross-lingual speaker adaptation system can be developed. Listening tests show very promising results, demonstrating that adapted voices sound similar to the target speaker and that differences between supervised and unsupervised cross-lingual speaker adaptation are small., 14-19 March 2010Dallas, TX, USA}, pages = {4594--4597}, publisher = {Institute of Electrical and Electronics Engineers}, title = {Unsupervised Cross-Lingual Speaker Adaptation for HMM-Based Speech Synthes}, year = {2010}, yomi = {オオウラ, ケイイチロウ} }