In this work, we propose ParaNet, a non-autoregressive seq2seq model that
converts text to spectrogram. It is fully convolutional and brings 46.7 times
speed-up over the lightweight Deep Voice 3 at synthesis, while obtaining
reasonably good speech quality. ParaNet also produces stable alignment between
text and speech on the challenging test sentences by iteratively improving the
attention in a layer-by-layer manner. Furthermore, we build the parallel
text-to-speech system and test various parallel neural vocoders, which can
synthesize speech from text through a single feed-forward pass. We also explore
a novel VAE-based approach to train the inverse autoregressive flow (IAF) based
parallel vocoder from scratch, which avoids the need for distillation from a
separately trained WaveNet as previous work.

本文提出 ParaNet，一种非自回归 seq2seq 模型，用于将文本转换为频谱图，并通过各种平行神经音色器进行了测试，其中包括一种基于 VAE 的方法，用于从头开始训练反自回归流（IAF）平行音色器。

非自回归神经文本转语音

Non-Autoregressive Neural Text-to-Speech

In this paper, we propose a new volume-preserving flow and show that it
performs similarly to the linear general normalizing flow. The idea is to
enrich a linear Inverse Autoregressive Flow by introducing multiple
lower-triangular matrices with ones on the diagonal and combining them using a
convex combination. In the experimental studies on MNIST and Histopathology
data we show that the proposed approach outperforms other volume-preserving
flows and is competitive with current state-of-the-art linear normalizing flow.

本文提出了一种新的体积保持流，并表明它的表现与线性普通归一化流类似。在实验研究中，我们表明所提出的方法比其他体积保持流表现更好，并且与当前最先进的线性归一化流具有竞争力。

利用凸组合线性反自回归流改进变分自编码器

Improving Variational Auto-Encoders using convex combination linear  Inverse Autoregressive Flow

The framework of normalizing flows provides a general strategy for flexible
variational inference of posteriors over latent variables. We propose a new
type of normalizing flow, inverse autoregressive flow (IAF), that, in contrast
to earlier published flows, scales well to high-dimensional latent spaces. The
proposed flow consists of a chain of invertible transformations, where each
transformation is based on an autoregressive neural network. In experiments, we
show that IAF significantly improves upon diagonal Gaussian approximate
posteriors. In addition, we demonstrate that a novel type of variational
autoencoder, coupled with IAF, is competitive with neural autoregressive models
in terms of attained log-likelihood on natural images, while allowing
significantly faster synthesis.

本文提出了一种新型正则化流架构 —— 逆自回归流，它是一种基于自回归神经网络的可逆转换链。实验结果表明，逆自回归流显著改善了高维空间中对角高斯近似后验的变分推断，同时也证明了，结合逆自回归流的新型变分自编码器，在自然图像的对数似然度方面，与神经自回归模型相当，同时合成速度显著更快。