no code implementations • 1 Apr 2019 • Hieu-Thi Luong, Xin Wang, Junichi Yamagishi, Nobuyuki Nishizawa
When the available data of a target speaker is insufficient to train a high quality speaker-dependent neural text-to-speech (TTS) system, we can combine data from multiple speakers and train a multi-speaker TTS model instead.
no code implementations • 2 Aug 2018 • Hieu-Thi Luong, Xin Wang, Junichi Yamagishi, Nobuyuki Nishizawa
We investigated the impact of noisy linguistic features on the performance of a Japanese speech synthesis system based on neural network that uses WaveNet vocoder.