Accent And Speaker Disentanglement In Many-to-many Voice Conversion
2020 · Zhichao Wang, Wenshuo Ge, Xiong Wang, et al.
Abstract
This paper proposes an interesting voice and accent joint conversion approach, which can convert an arbitrary source speaker's voice to a target speaker with non-native accent. This problem is challenging as each target speaker only has training data in native accent and we need to disentangle accent and speaker information in the conversion model training and re-combine them in the conversion stage. In our recognition-synthesis conversion framework, we manage to solve this problem by two proposed tricks. First, we use accent-dependent speech recognizers to obtain bottleneck features for different accented speakers. This aims to wipe out other factors beyond the linguistic information in the BN features for conversion model training. Second, we propose to use adversarial training to better disentangle the speaker and accent information in our encoder-decoder based conversion model. Specifically, we plug an auxiliary speaker classifier to the encoder, trained with an adversarial loss to
Authors
(none)
Tags
Stats
Related papers
- Accent Conversion Using Discrete Units With Parallel Data Synthesized From Controllable Accented TTS (2024)0.00
- Many-to-many Voice Conversion Based Feature Disentanglement Using Variational Autoencoder (2021)7.81
- Non-parallel Sequence-to-sequence Voice Conversion With Disentangled Linguistic And Speaker Representations (2019)14.02
- Multi-target Voice Conversion Without Parallel Data By Adversarially Learning Disentangled Audio Representations (2018)13.60
- Learning In Your Voice: Non-parallel Voice Conversion Based On Speaker Consistency Loss (2020)0.00
- Recognition-synthesis Based Non-parallel Voice Conversion With Adversarial Learning (2020)0.00
- Improving Accent Conversion With Reference Encoder And End-to-end Text-to-speech (2020)0.00
- Transfer The Linguistic Representations From TTS To Accent Conversion With Non-parallel Data (2024)6.77