Preserving background sound in noise-robust voice conversion via
multi-task learningIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022 |
AccentSpeech: Learning Accent from Crowd-sourced Data for Target Speaker
TTS with AccentsInternational Symposium on Chinese Spoken Language Processing (ISCSLP), 2022 |
Noise-robust voice conversion with domain adversarial trainingNeural Networks (NN), 2022 |
Text-Free Image-to-Speech Synthesis Using Learned Segmental UnitsAnnual Meeting of the Association for Computational Linguistics (ACL), 2020 |
Accent and Speaker Disentanglement in Many-to-many Voice ConversionInternational Symposium on Chinese Spoken Language Processing (ISCSLP), 2020 |
Data Efficient Voice Cloning from Noisy Samples with Domain Adversarial
TrainingInterspeech (Interspeech), 2020 |