# Sub-mW Keyword Spotting on an MCU: Analog Binary Feature Extraction and Binary Neural Networks

arXiv: https://arxiv.org/abs/2201.03386 · HTML: https://mlsanity.com/paper/2201.03386/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 52 references that are in the map.
- First posted on arXiv 10 Jan 2022.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients](https://mlsanity.com/paper/1606.06160/) (2016)
- [Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights](https://mlsanity.com/paper/1702.03044/) (2017)
- [Fixed Point Quantization of Deep Convolutional Networks](https://mlsanity.com/paper/1511.06393/) (2015)
- [Hello Edge: Keyword Spotting on Microcontrollers](https://mlsanity.com/paper/1711.07128/) (2017)
- [Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1](https://mlsanity.com/paper/1602.02830/) (2016)
- [A multi-device dataset for urban acoustic scene classification](https://mlsanity.com/paper/1807.09840/) (2018)
- [Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM](https://mlsanity.com/paper/1707.09870/) (2017)
- [Deep Learning for IoT Big Data and Streaming Analytics: A Survey](https://mlsanity.com/paper/1712.04301/) (2017)
- [A Cascade Architecture for Keyword Spotting on Mobile Devices](https://mlsanity.com/paper/1712.03603/) (2017)
- [CUTIE: Beyond PetaOp/s/W Ternary DNN Inference Acceleration with Better-than-Binary Energy Efficiency](https://mlsanity.com/paper/2011.01713/) (2020)
- [Sound Event Detection with Binary Neural Networks on Tightly Power-Constrained IoT Devices](https://mlsanity.com/paper/2101.04446/) (2021)
- [Compact recurrent neural networks for acoustic event detection on low-energy low-complexity platforms](https://mlsanity.com/paper/2001.10876/) (2020)
- [Online Keyword Spotting with a Character-Level Recurrent Neural Network](https://mlsanity.com/paper/1512.08903/) (2015)
- [Efficient Convolutional Neural Network For Audio Event Detection](https://mlsanity.com/paper/1709.09888/) (2017)
- [Additive Noise Annealing and Approximation Properties of Quantized Neural Networks](https://mlsanity.com/paper/1905.10452/) (2019)
- [An End-to-End Architecture for Keyword Spotting and Voice Activity Detection](https://mlsanity.com/paper/1611.09405/) (2016)
- [An Optimized Recurrent Unit for Ultra-Low-Power Keyword Spotting](https://mlsanity.com/paper/1902.05026/) (2019)
- [Binary Weighted Memristive Analog Deep Neural Network for Near-Sensor Edge Processing](https://mlsanity.com/paper/1808.00737/) (2018)
- [Mist Computing: Principles, Trends and Future Direction](https://mlsanity.com/paper/1709.06927/) (2017)

## Built on by (most cited first, 5 of 5)

- [xTern: Energy-Efficient Ternary Neural Network Inference on RISC-V-Based Edge Systems](https://mlsanity.com/paper/2405.19065/) (2024)
- [Efficient Continual Learning in Keyword Spotting using Binary Neural Networks](https://mlsanity.com/paper/2505.02469/) (2025)
- [Adaptive Noise Resilient Keyword Spotting Using One-Shot Learning](https://mlsanity.com/paper/2505.09304/) (2025)
- [Implementing Keyword Spotting on the MCUX947 Microcontroller with Integrated NPU](https://mlsanity.com/paper/2506.08911/) (2025)
- [LearnAFE: Circuit-Algorithm Co-design Framework for Learnable Audio Analog Front-End](https://mlsanity.com/paper/2507.00755/) (2025)

## Abstract (arXiv)

Keyword spotting (KWS) is a crucial function enabling the interaction with the many ubiquitous smart devices in our surroundings, either activating them through wake-word or directly as a human-computer interface. For many applications, KWS is the entry point for our interactions with the device and, thus, an always-on workload. Many smart devices are mobile and their battery lifetime is heavily impacted by continuously running services. KWS and similar always-on services are thus the focus when optimizing the overall power consumption. This work addresses KWS energy-efficiency on low-cost microcontroller units (MCUs). We combine analog binary feature extraction with binary neural networks. By replacing the digital preprocessing with the proposed analog front-end, we show that the energy required for data acquisition and preprocessing can be reduced by 29x, cutting its share from a dominating 85% to a mere 16% of the overall energy consumption for our reference KWS application. Experimental evaluations on the Speech Commands Dataset show that the proposed system outperforms state-of-the-art accuracy and energy efficiency, respectively, by 1% and 4.3x on a 10-class dataset while providing a compelling accuracy-energy trade-off including a 2% accuracy drop for a 71x energy reduction.