AI engineering glossary · Generative media multimodal
What is waveNet?
WaveNet: A deep generative model from DeepMind that produces audio one sample at a time using stacked dilated causal convolutions. It set a new bar for natural synthetic speech, though sample-by-sample generation is slow.
WaveNet: an example
To generate one second at 16 kHz, WaveNet makes 16,000 sequential predictions.
Related terms
- Neural vocoder
- HiFi-GAN
- Text-to-speech
More Generative media multimodal terms
- Whisper
- Zero-shot TTS
- 3D Gaussian splatting
- Acoustic model
- Audio language model
- Beta-VAE
- BLIP
- Classifier-free guidance
Where you learn it
WaveNet is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.