Remove unnecessary context concatenation of attention at pre-net

nii-yamagishilab / self-attention-tacotron

An implementation of "Investigation of enhanced Tacotron text-to-speech synthesis systems with self-attention for pitch accent language" https://arxiv.org/abs/1810.11960

BSD 3-Clause "New" or "Revised" License

114 stars 32 forks source link

Remove unnecessary context concatenation of attention at pre-net #19

Closed TanUkkii007 closed 5 years ago

TanUkkii007 commented 5 years ago

https://github.com/nii-yamagishilab/tacotron2/pull/12

Affects ExtendedTacotronV1Model and DualSourceSelfAttentionTacotronModel