Semi-supervised voice conversion with amortized variational inference
This addresses the challenge of limited parallel data in voice conversion for practical applications, offering an incremental improvement over existing systems.
The paper tackles the voice conversion problem by introducing a semi-supervised approach that uses both parallel and non-parallel utterances during training, showing improved performance over fully supervised methods when parallel data is limited, with gains increasing as more non-parallel data is added.
In this work we introduce a semi-supervised approach to the voice conversion problem, in which speech from a source speaker is converted into speech of a target speaker. The proposed method makes use of both parallel and non-parallel utterances from the source and target simultaneously during training. This approach can be used to extend existing parallel data voice conversion systems such that they can be trained with semi-supervision. We show that incorporating semi-supervision improves the voice conversion performance compared to fully supervised training when the number of parallel utterances is limited as in many practical applications. Additionally, we find that increasing the number non-parallel utterances used in training continues to improve performance when the amount of parallel training data is held constant.