Merge pull request #5 from Vproject/patch-1

fix references in readme, change format todo list
This commit is contained in:
Eren Golge 2018-03-19 18:42:26 +01:00 committed by GitHub
commit 2fe69db10b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 10 additions and 9 deletions

View File

@ -71,19 +71,20 @@ Best way to test your pretrained network is to use the Notebook under ```noteboo
Any kind of contribution is highly welcome as we are propelled by the open-source spirit. If you like to add or edit things in code, please also consider to write tests to verify your segment so that we can be sure things are on the track as this repo gets bigger. Any kind of contribution is highly welcome as we are propelled by the open-source spirit. If you like to add or edit things in code, please also consider to write tests to verify your segment so that we can be sure things are on the track as this repo gets bigger.
## TODO ## TODO
- [DONE] Make the default Tacotron architecture functional with reasonable fidelity. - [x] Make the default Tacotron architecture functional with reasonable fidelity.
- Update the architecture with the latest improvements at the field. (e.g. Monotonic Attention, World Vocoder) - [ ] Update the architecture with the latest improvements at the field. (e.g. Monotonic Attention, World Vocoder)
- Using harmonized teacher forcing proposed by - Using harmonized teacher forcing proposed by
- Update the attention module with a monotonic alternative. (e.g GMM attention, Window based attention) - Update the attention module with a monotonic alternative. (e.g GMM attention, Window based attention)
- References: - References:
- [Efficient Neural Audio Synthesis](https://arxiv.org/pdf/1506.07503.pdf) - [Efficient Neural Audio Synthesis](https://arxiv.org/pdf/1802.08435.pdf)
- [Attention-Based models for speech recognition](https://arxiv.org/pdf/1308.0850.pdf) - [Attention-Based models for speech recognition](https://arxiv.org/pdf/1506.07503.pdf)
- [Char2Wav](https://openreview.net/pdf?id=B1VWyySKx) - [Generating Sequences With Recurrent Neural Networks](https://arxiv.org/pdf/1308.0850.pdf)
- [VoiceLoop](https://arxiv.org/pdf/1707.06588.pdf) - [Char2Wav: End-to-End Speech Synthesis](https://openreview.net/pdf?id=B1VWyySKx)
- Simplify the architecture and push the limits of performance vs efficiency. - [VoiceLoop: Voice Fitting and Synthesis via a Phonological Loop](https://arxiv.org/pdf/1707.06588.pdf)
- Improve vocoder part of the network. - [ ] Simplify the architecture and push the limits of performance vs efficiency.
- [ ] Improve vocoder part of the network.
- Possible Solutions: - Possible Solutions:
- WORLD vocoder - WORLD vocoder
- [WaveRNN](https://128.84.21.199/pdf/1802.08435.pdf) - [WaveRNN](https://arxiv.org/pdf/1802.08435.pdf)
- [Faster WaveNet](https://arxiv.org/abs/1611.09482) - [Faster WaveNet](https://arxiv.org/abs/1611.09482)
- [Parallel WaveNet](https://arxiv.org/abs/1711.10433) - [Parallel WaveNet](https://arxiv.org/abs/1711.10433)