arXiv cs.LG
· Papers
Cumsum-Composable Phase Transport for Low-Cost Streaming Keyword Spotting
arXiv:2607.20086v1 Announce Type: cross Abstract: State-space sequence models are attractive for streaming speech because they maintain compact recurrent state, but scan-style training kernels can have unfavorable constants for short audio tasks. We study cumsum-composable phase transport, a streaming-native temporal l