Paper Info
Title
Efficient Neural Audio Synthesis.
Abstract
Sequential models achieve state-of-the-art results in audio, visual and textual domains with respect to both estimating the data distribution and generating high-quality samples. Efficient sampling for this class of models has however remained an elusive problem. With a focus on text-to-speech synthesis, we describe a set of general techniques for reducing sampling time while maintaining high output quality. We first describe a single-layer recurrent neural network, the WaveRNN, with a dual softmax layer that matches the quality of the state-of-the-art WaveNet model. The compact form of the network makes it possible to generate 24kHz 16-bit audio 4x faster than real time on a GPU. Second, we apply a weight pruning technique to reduce the number of weights in the WaveRNN. We find that, for a constant number of parameters, large sparse networks perform better than small dense networks and this relationship holds for sparsity levels beyond 96%. The small number of weights in a Sparse WaveRNN makes it possible to sample high-fidelity audio on a mobile CPU in real time. Finally, we propose a new generation scheme based on subscaling that folds a long sequence into a batch of shorter sequences and allows one to generate multiple samples at once. The Subscale WaveRNN produces 16 samples per step without loss of quality and offers an orthogonal method for increasing sampling efficiency.
Year
Venue
DocType
2018
ICML
Conference
Volume
Citations 
PageRank 
abs/1802.08435
14
0.62
References 
Authors
11
10
Name
Order
Citations
PageRank
Nal Kalchbrenner13662149.32
Erich Elsen255129.33
Karen Simonyan312058446.84
Seb Noury4541.93
Norman Casagrande5674.50
Edward Lockhart6775.44
Florian Stimberg7542.61
Aäron Van Den Oord8158564.43
Sander Dieleman92607102.93
Koray Kavukcuoglu1010189504.11