Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
A WaveNet used as a vocoder can be conditioned on generated Mel Spectrograms from the Tacotron 2 LSTM neural network with attention to generate neat audio from text.
- from
- Education
- added
- 2026-10-10
- likes
- 0
similar
-
WaveNet: a Generative Model for Raw Audio arxiv.org
Epic raw voice/music generation with new architectures based on dilated causal convolutions to capture more audio length.
-
WaveNet: A Generative Model for Raw Audio deepmind.com
Realistic talking machines: perfect voice generation.
-
Wavenet github.com
This is a TensorFlow implementation of the WaveNet generative neural network architecture for audio generation.
-
-
textgenrnn github.com
Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code.
-
Text to speech github.com
Synthesizing speech from text.
Education › Papers > Attention Mechanisms: “A WaveNet used as a vocoder can be conditioned on generated Mel Spectrograms from the Tacotron 2 LSTM neural network with attention to generate neat audio from text.”