Neural Speech Synthesis on a Shoestring: Improving the Efficiency of Lpcnet
Jean-Marc Valin, Umut Isik, Paris Smaragdis, Arvindh Krishnaswamy
Abstract
Neural speech synthesis models can synthesize high quality speech but typically require a high computational complexity to do so. In previous work, we introduced LPCNet, which uses linear prediction to significantly reduce the complexity of neural synthesis. In this work, we further improve the efficiency of LPCNet – targeting both algorithmic and computational improvements – to make it usable on a wide variety of devices. We demonstrate an improvement in synthesis quality while operating 2.5x faster. The resulting open-source <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> LPCNet algorithm can perform real-time neural synthesis on most existing phones and is even usable in some embedded devices.
BibTeX
@inproceedings{icassp2022_neuralspeechsynt,
title = {Neural Speech Synthesis on a Shoestring: Improving the Efficiency of Lpcnet},
author = {Jean-Marc Valin and Umut Isik and Paris Smaragdis and Arvindh Krishnaswamy},
booktitle = {ICASSP 2022},
year = {2022}
}