WaveNODE: A Continuous Normalizing Flow for Speech Synthesis
arXiv:2006.04598
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.
8 pages, 4 figures, Second workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models (ICML 2020)
References in corpus (9)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Density estimation using Real NVP
- FastSpeech: Fast, Robust and Controllable Text to Speech
- Neural Ordinary Differential Equations
- FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
- MelNet: A Generative Model for Audio in the Frequency Domain
- Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning
- ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech
- FloWaveNet : A Generative Flow for Raw Audio