论文标题
神经声码器是您所需的语音超级分辨率所需的
Neural Vocoder is All You Need for Speech Super-resolution
论文作者
论文摘要
语音超分辨率（SR）是通过产生高频组件来提高语音采样率的任务。现有的语音SR方法在受限的实验设置中进行培训，例如固定的上采样率。这些强大的限制可能会导致不匹配的现实情况中的泛化能力差。在本文中，我们提出了一种基于神经声码器的语音超分辨率方法（NVSR），该方法可以处理各种输入分辨率和提升比率。 NVSR由Mel-Bandwidth扩展模块，神经声音编码模块和后处理模块组成。我们提出的系统在VCTK多扬声器基准测试中实现了最先进的结果。在44.1 kHz的目标分辨率上，NVSR在对数光谱距离上的表现分别优于WSRGLOW和NU-WAVE，分别高出8％和37％，并实现了更高的感知质量。我们还证明，通过使用简单的复制方法进行MEL-BANDWIDTH扩展，预训练的Vocoder中的先验知识对于语音SR至关重要。可以在https://haoheliu.github.io/nvsr中找到样品。
Speech super-resolution (SR) is a task to increase speech sampling rate by generating high-frequency components. Existing speech SR methods are trained in constrained experimental settings, such as a fixed upsampling ratio. These strong constraints can potentially lead to poor generalization ability in mismatched real-world cases. In this paper, we propose a neural vocoder based speech super-resolution method (NVSR) that can handle a variety of input resolution and upsampling ratios. NVSR consists of a mel-bandwidth extension module, a neural vocoder module, and a post-processing module. Our proposed system achieves state-of-the-art results on the VCTK multi-speaker benchmark. On 44.1 kHz target resolution, NVSR outperforms WSRGlow and Nu-wave by 8% and 37% respectively on log spectral distance and achieves a significantly better perceptual quality. We also demonstrate that prior knowledge in the pre-trained vocoder is crucial for speech SR by performing mel-bandwidth extension with a simple replication-padding method. Samples can be found in https://haoheliu.github.io/nvsr.
