Learning a Neural Diff for Speech Models
This work addresses data budget constraints for deploying speech models on edge devices, representing an incremental improvement in model update efficiency.
The paper tackled the problem of transferring updated speech models to edge devices under data budget constraints by proposing neural update methods that learn compact representations, and demonstrated that these budgeted updates outperform model compression baselines by significant margins on automatic speech recognition and spoken language understanding tasks.
As more speech processing applications execute locally on edge devices, a set of resource constraints must be considered. In this work we address one of these constraints, namely over-the-network data budgets for transferring models from server to device. We present neural update approaches for release of subsequent speech model generations abiding by a data budget. We detail two architecture-agnostic methods which learn compact representations for transmission to devices. We experimentally validate our techniques with results on two tasks (automatic speech recognition and spoken language understanding) on open source data sets by demonstrating when applied in succession, our budgeted updates outperform comparable model compression baselines by significant margins.