autoregressive-free vocoder
C24491
concept
An autoregressive-free vocoder is a neural audio synthesis model that generates high-quality speech or sound waveforms in parallel, without relying on step-by-step autoregressive prediction.
All labels observed (4)
| Label | Occurrences |
|---|---|
| autoregressive-free vocoder canonical | 1 |
| neural vocoder architecture | 1 |
| parallel WaveNet-style model | 1 |
| speech 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-free vocoder
Generated description
An autoregressive-free vocoder is a neural audio synthesis model that generates high-quality speech or sound waveforms in parallel, without relying on step-by-step autoregressive prediction.
Instances (3)
| Instance | Via concept surface |
|---|---|
| WaveGlow | — |
| Parallel WaveNet | neural vocoder architecture |
| ClariNet | parallel WaveNet-style model |