SNAC：多尺度神经音频编解码器
SNAC: Multi-Scale Neural Audio Codec
AI总结：
本文提出多尺度神经音频编解码器SNAC，通过在不同时间分辨率上扩展残差矢量量化，实现更高效的音频压缩，并开源代码与模型权重。
摘要：
神经音频编解码器近来受到广泛关注，因为它们能够在极低比特率下高保真地表示音频信号，从而使基于语言建模的音频生成与理解方法变得可行。残差矢量量化（RVQ）已成为利用级联VQ码本进行神经音频压缩的标准技术。本文提出了多尺度神经音频编解码器，这是对RVQ的一种简单扩展，其中量化器可以在不同的时间分辨率下工作。通过在可变帧率上应用分层量化器，该编解码器能够适应多个时间尺度上的音频结构。大量客观和主观评估表明，这带来了更高效的压缩效果。代码和模型权重已在 https://github.com/hubertsiuzdak/snac 开源。
英文摘要：
Neural audio codecs have recently gained popularity because they can represent audio signals with high fidelity at very low bitrates, making it feasible to use language modeling approaches for audio generation and understanding. Residual Vector Quantization (RVQ) has become the standard technique for neural audio compression using a cascade of VQ codebooks. This paper proposes the Multi-Scale Neural Audio Codec, a simple extension of RVQ where the quantizers can operate at different temporal resolutions. By applying a hierarchy of quantizers at variable frame rates, the codec adapts to the audio structure across multiple timescales. This leads to more efficient compression, as demonstrated by extensive objective and subjective evaluations. The code and model weights are open-sourced at https://github.com/hubertsiuzdak/snac.
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。
