Understanding WaveNet architecture | by Satyam Kumar | Medium

WaveNet is deep autoregressive, generative model, which produces human-like voice, where raw audio is feeded as input to the model, taking…

WaveNet is deep autoregressive, generative model, which produces human-like voice, where raw audio is feeded as input to the model, taking speech synthesis to another level. 5 min read May 20, 2019 -- WaveNet is combination of two different ideas wavelet and Neural networks. Raw audio is generally represented as a sequence of 16 bits. 16 bits samples produces ²¹⁶ (65536) quantization values, which are processed through softmax, making it computationally expensive. Hence the sequences of samples is reduced to 8 bits, using μ-law transformation, F(x) = sign(x) ln(1+μ|x|)/ln(1+μ), -1 ≤ x ≤…

related reading

• WaveNetdeepmind.com
• WaveGrad: Estimating Gradients for Waveform Generationarxiv.org
• An Open Base Model for Conversational Speech | blogsi.inc
• Generating music in the waveform domain – Sander Dielemansander.ai
• The Annotated Transformernlp.seas.harvard.edu
• Generative modelling in latent space – Sander Dielemansander.ai
• What are Diffusion Models? | Lil'Loglilianweng.github.io
• Convolutional Neural Networks, Explained | Towards Data Sciencetowardsdatascience.com
• H-Nets - the Past | Goomba Labgoombalab.github.io
• DeltaNet Explained (Part I) | Songlin Yangsustcsonglin.github.io
• Wavelet transform - Wikipediaen.wikipedia.org
• Sequence Modeling with CTCdistill.pub