-
Is it possible to use PWG vocoder(https://github.com/kan-bayashi/ParallelWaveGAN) instead of Wavenet on the output of the decoder? Specifically, do I need to change the frame length and frame hop to m…
-
Hi,
I am following the LJspeech TTS recipe (https://github.com/espnet/espnet/blob/master/egs2/TEMPLATE/tts1/README.md#how-to-run), and by default griffin-lim is used for decoding in stage 7. Is th…
-
- AI News
- [페이스북, 뉴욕대 연구 계정 차단…데이터 연구활용 놓고 갈등](https://n.news.naver.com/mnews/article/001/0012579462?sid=105)
- [DEVIEW 2021 연사 모집](https://deview.kr/2021/cfs)
- 8월 25일까지
- 이번에도 온라인으로…
-
I have trained both tacotron2 (200 epochs) and fastspeech 2 (1000 epochs) models on my dataset (fs=22050) with PWG vocoder. The tacotron2 synthesised speech sounds very good but the fastspeech2 sounds…
-
I am trying to use WaveFlow vocoder with deepvoice3. In order to implement the same i have made minor tweaks in the codebase,:
Firstly i have modified the examples/deepvoice3/utils.py to output onl…
-
-
I just want to clarify if we need to train the vocoder first if we want to train this synthesizer with a different dataset? For instance, you recommend downloading the pre-trained VocGAN but that is o…
-
Good job on neural vocoder. I'm working on implementing your paper "Neural Homomorphic Vocoder". In part2.1 impulse train generator, I got some trouble on these part, can you share the impulse train g…
-
Hello,
I noticed that the audio samples you provided sound robotic. What is the reason for this?
Thanks.
ghost updated
3 years ago
-
Hi,
First of all, thank you for this nice implementation.
I trained the network with default settings and data (~500k iteration), but the results are really unnaturalistic (eg.: [link](https://…