The NUS & NWPU system for Voice Conversion Challenge 2020
Xiaohai Tian, Zhichao Wang, Yang Shan, Xinyong Zhou, Hongqiang Du, Yi Xin Zhou, Mingyang Zhang, Kun Zhou, Berrak Şişman, Lei Xie, Haizhou Li · 2020
This paper presents the NUS & NWPU voice conversion system for Voice Conversion Challenge 2020.Our submission is a Phonetic PosteriorGram (PPG) based voice conversion system, which consists of three modules, including PPG extractor, feature conversion and converted speech signal generation modules.Firstly, a PPG extractor is adopted to extract the speaker independent content features from a speech signal.Then, an encoder-decoder based feature conversion model is used to predict the converted features with the PPG inputs.Finally, a multiband WaveRNN is utilized to generate the time-domain speech signal from the converted features.The same implementation is used for both intra-lingual and cross-lingual voice conversion tasks.Evaluation results demonstrated the effectiveness of our proposed system.