Any-to-many voice conversion with location-relative sequence-to-sequence modeling

S Liu, Y Cao, D Wang, X Wu, X Liu… - IEEE/ACM Transactions …, 2021 - ieeexplore.ieee.org
This paper proposes an any-to-many location-relative, sequence-to-sequence (seq2seq),
non-parallel voice conversion approach, which utilizes text supervision during training. In …
被引用次数：77 相关文章
[PDF] academia.edu

[PDF][PDF] Any-to-Many Voice Conversion with Location-Relative Sequence-to-Sequence Modeling

S Liu, Y Cao, D Wang, X Wu, X Liu… - … ACM TRANSACTIONS ON …, 2021 - academia.edu
This paper proposes an any-to-many locationrelative, sequence-to-sequence (seq2seq),
non-parallel voice conversion approach, which utilizes text supervision during training. In …

Any-to-Many Voice Conversion with Location-Relative Sequence-to-Sequence Modeling

S Liu, Y Cao, D Wang, X Wu, X Liu, H Meng - arXiv preprint arXiv …, 2020 - arxiv.org
This paper proposes an any-to-many location-relative, sequence-to-sequence (seq2seq),
non-parallel voice conversion approach, which utilizes text supervision during training. In …

Any-to-Many Voice Conversion With Location-Relative Sequence-to-Sequence Modeling

S Liu, Y Cao, D Wang, X Wu, X Liu… - IEEE/ACM Transactions on …, 2021 - dl.acm.org
This paper proposes an any-to-many location-relative, sequence-to-sequence (seq2seq),
non-parallel voice conversion approach, which utilizes text supervision during training. In …
[PDF] cuhk.edu.hk

[PDF][PDF] Any-to-Many Voice Conversion With Location-Relative Sequence-to-Sequence Modeling

S Liu, Y Cao, D Wang, X Wu, X Liu… - … ON AUDIO, SPEECH …, 1717 - se.cuhk.edu.hk
This paper proposes an any-to-many location-relative, sequence-to-sequence (seq2seq),
non-parallel voice conversion approach, which utilizes text supervision during training. In …

Any-to-Many Voice Conversion With Location-Relative Sequence-to-Sequence Modeling

S Liu, Y Cao, D Wang, X Wu, X Liu… - … ON AUDIO, SPEECH …, 1717 - openreview.net
This paper proposes an any-to-many location-relative, sequence-to-sequence (seq2seq),
non-parallel voice conversion approach, which utilizes text supervision during training. In …

Any-to-Many Voice Conversion with Location-Relative Sequence-to-Sequence Modeling

S Liu, Y Cao, D Wang, X Wu, X Liu, H Meng - arXiv e-prints, 2020 - ui.adsabs.harvard.edu
This paper proposes an any-to-many location-relative, sequence-to-sequence (seq2seq),
non-parallel voice conversion approach, which utilizes text supervision during training. In …
[PDF] cuhk.edu.hk

[PDF][PDF] Any-to-Many Voice Conversion With Location-Relative Sequence-to-Sequence Modeling

S Liu, Y Cao, D Wang, X Wu, X Liu… - … ON AUDIO, SPEECH …, 1717 - se.cuhk.edu.hk
This paper proposes an any-to-many location-relative, sequence-to-sequence (seq2seq),
non-parallel voice conversion approach, which utilizes text supervision during training. In …