AI engineering glossary · Generative media multimodal
What is neural vocoder?
Neural vocoder: A neural network that converts an intermediate acoustic representation, usually a mel spectrogram, into a raw audio waveform. Its quality determines how natural and free of buzzing the final synthesised voice sounds.
Neural vocoder: an example
A TTS pipeline predicts a mel spectrogram from text, and a vocoder turns that into a 22,050 Hz waveform.
Related terms
More Generative media multimodal terms
- Noise schedule
- Normalizing flow
- Object hallucination
- Omni model
- Outpainting
- Perceiver resampler
- Phoneme
- Pix2Pix
Where you learn it
Neural vocoder is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.