On-the-fly deterministic binary filters for memory efficient keyword spotting applications on embedded devices

Lightweight keyword spotting (KWS) applications are often used to trigger the execution of more complex speech recognition algorithms that are computationally demanding and therefore cannot be constantly running on the device. Often KWS applications are executed in small microcontrollers with very constrained memory (e.g. 128kB) and compute capabilities (e.g. CPU at 80MHz) limiting the complexity of deployable KWS systems. We present a compact binary architecture with 60% fewer parameters and 50% fewer operations (OP) during inference compared to the current state of the art for KWS applications at the cost of 3.4% accuracy drop. It makes use of binary orthogonal codes to analyse speech features from a voice command resulting in a model with minimal memory footprint and computationally cheap, making possible its deployment in very resource-constrained microcontrollers with less than 30kB of on-chip memory. Our technique offers a different perspective to how filters in neural networks could be constructed at inference time instead of directly loading them from disk.