RIPPLE：生成多通道相位，而非恢复相位
RIPPLE: Generating Multi-Channel Phase, Not Recovering It
浏览论文内容
中文总结 AI 辅助
该研究针对多通道波形相位恢复的缺陷，提出RIPPLE方法，将Griffin-Lim作为相位先验，结合校正流细化相位，在Ambisonics和地震任务中优于传统恢复方法，降低了S波极化误差。
中文摘要 AI 辅助
生成模型能合成高保真的幅度谱，而相位则交由恢复模块（如Griffin-Lim、声码器或潜在解码器）独立处理每个通道。对于多通道波形而言，这种处理方式成本高昂：空间音频和三分量地震记录的物理内容存在于通道间的相位关系中，而通道独立的恢复模块无法生成这种关系。这种成本也难以察觉，因为这两个领域常用的基于幅度的指标，在通道间相位相干性崩溃时几乎没有变化——因此，一个流程可能在丢弃输出中的物理信息的同时，仍能获得高分。我们认为应当生成相位，而非恢复相位，并提出了RIPPLE（基于先验学习的校正通道间相位，Rectified Inter-channel Phase with Prior-based LEarning），该方法将Griffin-Lim重新解释为相位**先验**而非最终估计器：该先验从源相位初始化，携带需保留的通道间结构，校正流则在显式的通道间相位损失下将其细化至目标。在一阶 Ambisonics 环境迁移和地震跨台站转换这两个物理无关的领域测试中，RIPPLE在下游分析所用的相干性指标上优于基于恢复的流程。地震案例的结果具有决定性：在架构不同的生成器中，每通道恢复使S波极化误差接近57.3°的随机预期值，而学习到的相位将其降至33.8°。
英文摘要
Generative models synthesize magnitude spectra with high fidelity, while phase is delegated to a recovery module---Griffin--Lim, a vocoder, or a latent decoder---applied independently to each channel. For multi-channel waveforms this delegation is costly: the physical content of spatial audio and three-component seismograms lives in the phase relationships between channels, precisely what channel-independent recovery cannot produce. The cost is also invisible, since the magnitude-based metrics common to both fields barely move when inter-channel phase coherence collapses---so a pipeline can discard the physical information in its output while still scoring well. We argue that phase should be generated, not recovered, and present RIPPLE (Rectified Inter-channel Phase with Prior-based LEarning), which reinterprets Griffin--Lim as a phase **prior** rather than a final estimator: initialized from the source phase, this prior carries the inter-channel structure to be preserved, and a rectified flow refines it toward the target under an explicit inter-channel phase loss. Tested on first-order ambisonics environment transfer and seismic cross-station translation---two physically unrelated domains---RIPPLE outperforms recovery-based pipelines on the coherence metrics that downstream analyses consume. The seismic case is decisive: across architecturally distinct generators, per-channel recovery leaves S-wave polarization error near the $57.3^\circ$ random expectation, whereas learned phase reduces it to $33.8^\circ$.
