SpectroStream：一种通用的神经音频编解码器
SpectroStream: A Versatile Neural Codec for General Audio
AI总结：
本文提出SpectroStream，一种全频带多通道神经音频编解码器，通过时频域表示和延迟融合策略，在4-16 kbps比特率下实现48 kHz立体声音乐的高质量重建。
摘要：
我们提出了SpectroStream，一种全频带多通道神经音频编解码器。作为成熟的SoundStream的继任者，SpectroStream将其能力扩展到24 kHz单声道音频之外，并能在4--16 kbps的比特率下实现48 kHz立体声音乐的高质量重建。这是通过一种新的神经架构实现的，该架构利用时频域中的音频表示，从而带来更好的音频质量，尤其是在更高的采样率下。该模型还采用延迟融合策略来处理多通道音频，这对于平衡每通道声学质量和跨通道相位一致性至关重要。
英文摘要：
We propose SpectroStream, a full-band multi-channel neural audio codec. Successor to the well-established SoundStream, SpectroStream extends its capability beyond 24 kHz monophonic audio and enables high-quality reconstruction of 48 kHz stereo music at bit rates of 4--16 kbps. This is accomplished with a new neural architecture that leverages audio representation in the time-frequency domain, which leads to better audio quality especially at higher sample rate. The model also uses a delayed-fusion strategy to handle multi-channel audio, which is crucial in balancing per-channel acoustic quality and cross-channel phase consistency.
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。
