PHALAR: Phasors for Learned Musical Audio Representations 事件

PHALAR: Phasors for Learned Musical Audio Representations arXiv:2605.03929v4 Announce Type: replace-cross Abstract: Stem retrieval, the task of matching missing stems to a given audio submix, is a key challenge currently limited by models that discard temporal information. We introduce PHALAR, a contrastive framework achieving a relative accuracy increase of up to $\approx 70\%$ over the state-of-the-art while requiring $<50\%$ of the parameters and a 7$\times$ training speedup. By utilizing a