Phuong Thi Le — accepted AI-conference papers

2023

CNEG-VC: Contrastive Learning Using Hard Negative Example In Non-Parallel Voice Conversion

Bima Prihasto, Yi-Xing Lin, Phuong Thi Le, Chien-Lin Huang, Jia-Ching Wang

ICASSP 2023accepted

Contrastive learning has advantages for non-parallel voice conversion, but the previous conversion results could be better and more preserved. In previous techniques, negative samples were randomly selected in the features vector from different locations. A positive example could not be effectively…

Cited by 0 Source ↗Scholar ↗

2023

Code-Switching Speech Synthesis Based on Self-Supervised Learning and Domain Adaptive Speaker Encoder

Yi-Xing Lin, Cheng-Hsun Pai, Phuong Thi Le, Bima Prihasto, Chien-Ling Huang, Jia-Ching Wang

ICASSP 2023accepted

Recently, end-to-end speech synthesis models based on deep learning have made great progress in speech quality, and gradually replaced traditional speech synthesis methods into the mainstream. However, these methods are still challenging to synthesize highly natural speech. In order to solve the abo…

Cited by 0 Source ↗Scholar ↗