Neural vocoders based on the generative adversarial neural network (GAN) have been widely used due to their fast inference speed and lightweight networks while generating high-quality speech waveforms. Since the perceptually important speech components are primarily concentrated in the low-frequency band, most of the GAN-based neural vocoders perform multi-scale analysis that evaluates downsampled speech waveforms. This multi-scale analysis helps the generator improve speech intelligibility. However, in preliminary experiments, we observed that the multi-scale analysis which focuses on the low-frequency band causes unintended artifacts, e.g., aliasing and imaging artifacts, and these artifacts degrade the synthesized speech waveform quality. Therefore, in this paper, we investigate the relationship between these artifacts and GAN-based neural vocoders and propose a GAN-based neural vocoder, called Avocodo, that allows the synthesis of high-fidelity speech with reduced artifacts. We introduce two kinds of discriminators to evaluate waveforms in various perspectives: a collaborative multi-band discriminator and a sub-band discriminator. We also utilize a pseudo quadrature mirror filter bank to obtain downsampled multi-band waveforms while avoiding aliasing. The experimental results show that Avocodo outperforms conventional GAN-based neural vocoders in both speech and singing voice synthesis tasks and can synthesize artifact-free speech. Especially, Avocodo is even capable to reproduce high-quality waveforms of unseen speakers.
翻译:基于基因对抗神经神经网络(GAN)的神经立体变声器已被广泛使用,原因是其快速发酵速度和轻量网络,同时产生了高质量的语音波形。由于感知性重要的语音组件主要集中于低频波段,大多数基于GAN的神经立体元件进行多尺度分析,对降压语音波形进行评价。这一多尺度分析有助于发电机改进语音智能。然而,在初步实验中,我们观察到,侧重于低频频波段的多尺度分析造成意想不到的手工艺品,例如化名和成像制品,而这些手工艺品会降低合成语音波形质量。因此,在本文中,我们调查这些手工艺与基于GAN的神经变声波形器之间的关系,并提议一种基于GAN的神经变音波形器,称为Avocodocaldo,这样可以将高知性语音变音式语音带与减少的手工艺品类合成。我们引入两种类型的歧视器来评估各种语音变形,例如变形的语音变音器和成型变形的变形品,同时使用高频变形机的Grod-rographal-roal-rodal-rod-rodal-rod-lad-rod-lad-lad-lad-lad-lad-lad-rod-lad-lad-lad-rod-lad-lad-mod-lad-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mods-mods-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mods-mods-mods-mods-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-