SqueezeWave: Extremely Lightweight Vocoders for On-device Speech Synthesis
Abstract
Automatic speech synthesis is a challenging task that is becoming increasingly important as edge devices begin to interact with users through speech. Typical text-to-speech pipelines include a vocoder, which translates intermediate audio representations into an audio waveform. Most existing vocoders are difficult to parallelize since each generated sample is conditioned on previous samples. WaveGlow is a flow-based feed-forward alternative to these auto-regressive models (Prenger et al., 2019). However, while WaveGlow can be easily parallelized, the model is too expensive for real-time speech synthesis on the edge. This paper presents SqueezeWave, a family of lightweight vocoders based on WaveGlow that can generate audio of similar quality to WaveGlow with 61x - 214x fewer MACs. Code, trained models, and generated audio are publicly available at https://github.com/tianrengao/SqueezeWave.
Cite
@article{arxiv.2001.05685,
title = {SqueezeWave: Extremely Lightweight Vocoders for On-device Speech Synthesis},
author = {Bohan Zhai and Tianren Gao and Flora Xue and Daniel Rothchild and Bichen Wu and Joseph E. Gonzalez and Kurt Keutzer},
journal= {arXiv preprint arXiv:2001.05685},
year = {2020}
}