# Fast Wavenet Generation Algorithm

arXiv: https://arxiv.org/abs/1611.09482 · HTML: https://mlsanity.com/paper/1611.09482/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2016.

## Built on by (most cited first, 14 of 14)

- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [NWT: Towards natural audio-to-video generation with representation learning](https://mlsanity.com/paper/2106.04283/) (2021)
- [Semantic Hearing: Programming Acoustic Scenes with Binaural Hearables](https://mlsanity.com/paper/2311.00320/) (2023)
- [Approximation Theory of Convolutional Architectures for Time Series Modelling](https://mlsanity.com/paper/2107.09355/) (2021)
- [Iterative autoregression: a novel trick to improve your low-latency speech enhancement model](https://mlsanity.com/paper/2211.01751/) (2022)
- [AdaCat: Adaptive Categorical Discretization for Autoregressive Models](https://mlsanity.com/paper/2208.02246/) (2022)
- [Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and Beyond](https://mlsanity.com/paper/2410.12982/) (2024)
- [Revealing and Mitigating the Local Pattern Shortcuts of Mamba](https://mlsanity.com/paper/2410.15678/) (2024)
- [Non-Autoregressive vs Autoregressive Neural Networks for System Identification](https://mlsanity.com/paper/2105.02027/) (2021)
- [TinyD'ej`aVu: Smaller RAM and Faster Inference with Neural Networks on MCUs for Sensor Data Streams](https://mlsanity.com/paper/2512.09786/) (2025)
- [Implicit Feature Decoupling with Depthwise Quantization](https://mlsanity.com/paper/2203.08080/) (2022)
- [Deep Fake Detection, Deterrence and Response: Challenges and Opportunities](https://mlsanity.com/paper/2211.14667/) (2022)
- [Speech Synthesis By Unrolling Diffusion Process using Neural Network Layers](https://mlsanity.com/paper/2309.09652/) (2023)
- [Generative Adversarial Training for Text-to-Speech Synthesis Based on Raw Phonetic Input and Explicit Prosody Modelling](https://mlsanity.com/paper/2310.09636/) (2023)

## Abstract (arXiv)

This paper presents an efficient implementation of the Wavenet generation process called Fast Wavenet. Compared to a naive implementation that has complexity O(2^L) (L denotes the number of layers in the network), our proposed approach removes redundant convolution operations by caching previous calculations, thereby reducing the complexity to O(L) time. Timing experiments show significant advantages of our fast implementation over a naive one. While this method is presented for Wavenet, the same scheme can be applied anytime one wants to perform autoregressive generation or online prediction using a model with dilated convolution layers. The code for our method is publicly available.