SOURCE-LINKED INTELLIGENCE

Parallel Time-Band Mixing with Learned Observation-Adding for Robust ASR Front-Ends

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Speech enhancement is often used as a front-end for robust ASR, yet recurrent temporal and cross-band modules introduce sequential dependencies that reduce parallel efficiency. In this paper, we present a sequence-parallel band-split enhancement front-end built on a Parallel Time-Band Mixer (PTBM) block that eliminates within-block recurrent unrolling. PTBM integrates intra-band temporal mixing and per-frame cross-band attention within a unified parallel architecture, enabling efficient contextual modeling across both time and frequency dimensions. The system retains the mask-plus-residual rec

Read original source ↗ Open in workspace

recordType

paper

region

Global