AERO：音频超分辨率的频谱域
AERO: Audio Super Resolution in the Spectral Domain
摘要：
我们提出了AERO，这是一种音频超分辨率模型，可以在谱域中处理语音和音乐信号。AERO是基于一个编码器-解码器架构与U-Net一样跳过连接。我们使用时域和频域损失函数来优化模型。具体来说，我们考虑一组重建损失连同感知的形式对抗和功能的损失损失函数。为了更好地处理相位信息，所提出的方法使用两个单独的通道对复值频谱图进行操作。与主要考虑低频和高频级联的音频超分辨率的现有工作不同，所提出的方法直接预测全频率范围。我们在考虑语音和音乐的广泛采样率范围内表现出高性能。考虑到对数光谱距离、ViSQOL和主观MUSHRA测试，AERO优于评估的基线。音频示例和代码可在https://pages.cs.huji.ac.il/adiyoss-lab/aero上获得
英文摘要：
We present AERO, a audio super-resolution model that processes speech and music signals in the spectral domain. AERO is based on an encoder-decoder architecture with U-Net like skip connections. We optimize the model using both time and frequency domain loss functions. Specifically, we consider a set of reconstruction losses together with perceptual ones in the form of adversarial and feature discriminator loss functions. To better handle phase information the proposed method operates over the complex-valued spectrogram using two separate channels. Unlike prior work which mainly considers low and high frequency concatenation for audio super-resolution, the proposed method directly predicts the full frequency range. We demonstrate high performance across a wide range of sample rates considering both speech and music. AERO outperforms the evaluated baselines considering Log-Spectral Distance, ViSQOL, and the subjective MUSHRA test. Audio samples and code are available at https://pages.cs.huji.ac.il/adiyoss-lab/aero
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
