PaperSwipe

WaveNODE: A Continuous Normalizing Flow for Speech Synthesis

Published 5 years agoVersion 4arXiv:2006.04598

Authors

Hyeongju Kim, Hyeonseung Lee, Woo Hyun Kang, Sung Jun Cheon, Byoung Jin Choi, Nam Soo Kim

Categories

cs.SDcs.CLcs.LGeess.AS

Abstract

In recent years, various flow-based generative models have been proposed to generate high-fidelity waveforms in real-time. However, these models require either a well-trained teacher network or a number of flow steps making them memory-inefficient. In this paper, we propose a novel generative model called WaveNODE which exploits a continuous normalizing flow for speech synthesis. Unlike the conventional models, WaveNODE places no constraint on the function used for flow operation, thus allowing the usage of more flexible and complex functions. Moreover, WaveNODE can be optimized to maximize the likelihood without requiring any teacher network or auxiliary loss terms. We experimentally show that WaveNODE achieves comparable performance with fewer parameters compared to the conventional flow-based vocoders.

WaveNODE: A Continuous Normalizing Flow for Speech Synthesis

5 years ago
v4
6 authors

Categories

cs.SDcs.CLcs.LGeess.AS

Abstract

In recent years, various flow-based generative models have been proposed to generate high-fidelity waveforms in real-time. However, these models require either a well-trained teacher network or a number of flow steps making them memory-inefficient. In this paper, we propose a novel generative model called WaveNODE which exploits a continuous normalizing flow for speech synthesis. Unlike the conventional models, WaveNODE places no constraint on the function used for flow operation, thus allowing the usage of more flexible and complex functions. Moreover, WaveNODE can be optimized to maximize the likelihood without requiring any teacher network or auxiliary loss terms. We experimentally show that WaveNODE achieves comparable performance with fewer parameters compared to the conventional flow-based vocoders.

Authors

Hyeongju Kim, Hyeonseung Lee, Woo Hyun Kang et al. (+3 more)

arXiv ID: 2006.04598
Published Jun 8, 2020

Click to preview the PDF directly in your browser