WaveFFJORD: FFJORD-Based Vocoder for Statistical Parametric Speech Synthesis

By Ning Wu, Zhenhua Ling. 2020

9 citations recorded by the source corpus.

Free-form Jacobian of Reversible Dynamics(FFJORD) is a flowbased invertible generative model defined by ordinary differential equations (ODE). Inspired by WaveGlow, in this paper, we propose WaveFFJORD, a neural vocoder that can synthesize speech waveforms from acoustic features, by combining FFJORD and WaveNet. WaveFFJORD can generate speech waveforms directly by the blackbox ODE solvers, without the need for autoregressive structures. Our experimental results show that WaveFFJORD can achieve a smaller model size, lower memory cost, and better speech quality than WaveGlow. Besides, the ODE framework allows users to control the generation speed and quality by setting the error tolerance of the ODE solvers.

Subfields: Artificial Intelligence, Generative Models, Speech & Audio, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Generative Models

In Speech & Audio

In Signal Processing

Citations in the corpus

WaveGrad: Estimating Gradients for Waveform Generation (2020, background): “…al., 2018; Ping et al., 2019), generative ﬂow (Glow) (Prenger et al., 2019; Kim et al., 2019), and continuous normalizing ﬂow (CNF) (Kim et al., 2020; Wu & Ling, 2020), implicit generative models like generative adversarial network (GAN) (Donahue et al., 2018; Engel et al., 2019; Kumar et al.,…”
Quasi-Periodic Parallel WaveGAN Vocoder: A Non-autoregressive Pitch-dependent Dilated Convolution Model for Parametric Speech Generation (2020, methodology): “Unlike flow-based models [15–19] adopting an invertible network to transform the distribution of the input noise to the real data distribution, PWG adopts a GAN structure to make the generator learn the transformation via the feedback from the discriminator.”