Understanding WaveNet architecture | by Satyam Kumar | Medium
medium.com · 888 words · saved by 1 readers
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
- Generating music in the waveform domain – Sander Dielemansander.ai
- WaveGrad: Estimating Gradients for Waveform Generationarxiv.org
- Aman's AI Journal • Primers • Ilya Sutskever's Top 30aman.ai
- Generative modelling in latent space – Sander Dielemansander.ai
- The Unreasonable Effectiveness of Recurrent Neural Networkskarpathy.github.io
- Ilya 30u30arc.net
- GANSynth: Making music with GANsmagenta.tensorflow.org
- The Little Book of Deep Learningfleuret.org
- Feature-wise transformationsdistill.pub
- CS231n Deep Learning for Computer Visioncs231n.github.io
- Generative AI: A New Generation of AI - by Josh Houjoshhou.substack.com