Sub-Model Short-Term Memory Convolutions for Keyword Spotting Systems on Device

Abstract:Keyword Spotting (KWS) is becoming increasingly important as voice-controlled devices grow more widespread. While voice interaction with smartphones and smart TVs is already common, deploying KWS on heavily resource-constrained edge devices such as wearables remains challenging. These systems must meet high accuracy requirements while operating under strict constraints on computational power, memory footprint, and real-time latency. In this work, we present an application of the STMC (Short-Term Memory Convolutions) framework to adapt a modular CNN model for online, LSTM-like inference. Our approach reduces power consumption and redundant computations while maintaining the stability and simplicity of training CNNs. We achieve up to 82% and 46% MCPS reduction compared to equivalently frequent standard CNN execution and vanilla STMC, respectively. The best configuration achieves 93.8% accuracy on the 11-class Google Speech Commands task and 97.1% on the same task with zero-padded data.

Sound (cs.SD); Machine Learning (cs.LG)

arXiv:2609.35005 [cs.SD]

(or arXiv:2609.35005v1 [cs.SD] for this version)

https://doi.org/10.48550/arXiv.2609.35005 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

Proc. Interspeech 2026, 4077-4081

https://doi.org/10.21437/Interspeech.2026-1343 Focus to learn more DOI(s) linking to related resources

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.