SDDSLGNov 29, 2016

Fast Wavenet Generation Algorithm

arXiv:1611.09482v185 citations
Originality Synthesis-oriented
AI Analysis

This incremental improvement addresses efficiency issues for researchers and practitioners using autoregressive models with dilated convolutions.

The paper tackled the high computational complexity of Wavenet generation, reducing it from O(2^L) to O(L) by caching previous calculations, with timing experiments showing significant speed improvements.

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.

Code Implementations6 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes