no code implementations • 18 Mar 2022 • Haitong Zhang, Yue Lin
Recently, few-shot voice cloning has achieved a significant improvement.
no code implementations • 14 Oct 2021 • Haitong Zhang, Yue Lin
More importantly, we find that our method can achieve a comparable result to the state-of-the-art (SOTA) performance in cross-lingual voice cloning.
no code implementations • 14 Oct 2021 • Haoyue Zhan, Xinyuan Yu, Haitong Zhang, Yang Zhang, Yue Lin
In this paper, we study the disentanglement of speaker and language representations in non-autoregressive cross-lingual TTS models from various aspects.
no code implementations • 14 Oct 2021 • Haitong Zhang, Haoyue Zhan, Yang Zhang, Xinyuan Yu, Yue Lin
Experiments show that the way to process the IPA and suprasegmental sequence has a negligible impact on the CL VC performance.
no code implementations • 15 Oct 2020 • Haitong Zhang
In practice, our system can be developed with VCC 2020 dataset for both Task 1 (intra-lingual) and Task 2 (cross-lingual).
Sound Audio and Speech Processing
no code implementations • 12 Dec 2019 • Haitong Zhang, Yongping Du, Jiaxin Sun, Qingxiao Li
Definition modeling provides a more intuitive way to evaluate embeddings by utilizing them to generate natural language definitions of corresponding words.