Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces RIPPLE, a novel approach for generating inter-channel phase information in multi-channel waveforms rather than relying on traditional recovery methods. By treating phase as a prior and refining it through a rectified flow process, RIPPLE preserves the critical inter-channel relationships that are often lost in conventional pipelines. The results demonstrate significant improvements in coherence metrics, particularly in seismic applications, where learned phase generation drastically reduces polarization error compared to per-channel recovery methods.
Generating inter-channel phase directly leads to a dramatic reduction in seismic polarization error, outperforming traditional recovery methods by a significant margin.
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 $33.8^\circ$.