autoregressive neural vocoder

C24489
concept

An autoregressive neural vocoder is a generative model that synthesizes high-quality audio waveforms sample-by-sample by predicting each new sample conditioned on previously generated samples and acoustic features.

All labels observed (3)

Label Occurrences
autoregressive neural network 1
autoregressive neural vocoder canonical 1
neural audio synthesis model 1

Description generation (CDg)

The one-sentence description above was generated by prompting gpt-5.1 with the class name and this instruction.

Instruction
generate a one-sentence description for a given conceptual class.
# Response Format
Return only the sentence: "Description: [one-sentence description of the conceptional class]"
Input
Class: autoregressive neural vocoder
Generated description
An autoregressive neural vocoder is a generative model that synthesizes high-quality audio waveforms sample-by-sample by predicting each new sample conditioned on previously generated samples and acoustic features.

Instances (3)

Instance Via concept surface
WaveRNN
Aaron van den Oord
surface form: WaveNet
autoregressive neural network
ClariNet neural audio synthesis model