Transferring Source Style in Non-Parallel Voice Conversion

Songxiang Liu, Yuewen Cao, Shiyin Kang, Na Hu, Xunying Liu, Dan Su, Dong Yu, Helen Meng

Voice conversion (VC) techniques aim to modify speaker identity of an utterance while preserving the underlying linguistic information. Most VC approaches ignore modeling of the speaking style (e.g. emotion and emphasis), which may contain the factors intentionally added by the speaker and should be retained during conversion. This study proposes a sequence-to-sequence based non-parallel VC approach, which has the capability of transferring the speaking style from the source speech to the converted speech by explicitly modeling. Objective evaluation and subjective listening tests show superiority of the proposed VC approach in terms of speech naturalness and speaker similarity of the converted speech. Experiments are also conducted to show the source-style transferability of the proposed approach.

 DOI: 10.21437/Interspeech.2020-2412

Cite as: Liu, S., Cao, Y., Kang, S., Hu, N., Liu, X., Su, D., Yu, D., Meng, H. (2020) Transferring Source Style in Non-Parallel Voice Conversion. Proc. Interspeech 2020, 4721-4725, DOI: 10.21437/Interspeech.2020-2412.

  author={Songxiang Liu and Yuewen Cao and Shiyin Kang and Na Hu and Xunying Liu and Dan Su and Dong Yu and Helen Meng},
  title={{Transferring Source Style in Non-Parallel Voice Conversion}},
  booktitle={Proc. Interspeech 2020},