The recent advancement of end-to-end neural audio codecs enables compressing audio at very low bitrates while reconstructing the output audio with high fidelity. Nonetheless, such improvements often come at the cost of increased model complexity. In this paper, we identify and address the problems of existing neural audio codecs. We show that the performance of Wave-U-Net does not increase consistently as the network depth increases. We analyze the root cause of such a phenomenon and suggest a variance-constrained design. Also, we reveal various distortions in previous waveform domain discriminators and propose a novel distortion-free discriminator. The resulting model, \textit{HILCodec}, is a real-time streaming audio codec that demonstrates state-of-the-art quality across various bitrates and audio types.

翻译：近年来，端到端神经音频编解码器的进步使得在极低比特率下压缩音频的同时，能够高保真地重建输出音频。然而，这种提升往往以模型复杂度增加为代价。本文识别并解决了现有神经音频编解码器存在的问题。我们证明了Wave-U-Net的性能并非随网络深度增加而持续提升，分析了该现象的根源，并提出了方差约束设计。此外，我们揭示了以往波形域判别器中的各类失真问题，并提出了一种新型无失真判别器。由此得到的模型\textit{HILCodec}是一种实时流式音频编解码器，在多种比特率和音频类型下均展现出最优质量。