# A Fast Network Exploration Strategy to Profile Low Energy Consumption for Keyword Spotting

arXiv: https://arxiv.org/abs/2202.02361 · HTML: https://mlsanity.com/paper/2202.02361/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 4 Feb 2022.

## Builds on (most cited first, 8 of 8)

- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [Hello Edge: Keyword Spotting on Microcontrollers](https://mlsanity.com/paper/1711.07128/) (2017)
- [Streaming keyword spotting on mobile devices](https://mlsanity.com/paper/2005.06720/) (2020)
- [Ternary Neural Networks for Resource-Efficient AI Applications](https://mlsanity.com/paper/1609.00222/) (2016)
- [Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting](https://mlsanity.com/paper/1703.05390/) (2017)
- [Small-Footprint Keyword Spotting on Raw Audio Data with Sinc-Convolutions](https://mlsanity.com/paper/1911.02086/) (2019)
- [Neural Architecture Search For Keyword Spotting](https://mlsanity.com/paper/2009.00165/) (2020)
- [Tiny-CRNN: Streaming Wakeword Detection In A Low Footprint Setting](https://mlsanity.com/paper/2109.14725/) (2021)

## Built on by (most cited first, 1 of 1)

- [Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations](https://mlsanity.com/paper/2605.15216/) (2026)

## Abstract (arXiv)

Keyword Spotting nowadays is an integral part of speech-oriented user interaction targeted for smart devices. To this extent, neural networks are extensively used for their flexibility and high accuracy. However, coming up with a suitable configuration for both accuracy requirements and hardware deployment is a challenge. We propose a regression-based network exploration technique that considers the scaling of the network filters (s) and quantization (q) of the network layers, leading to a friendly and energy-efficient configuration for FPGA hardware implementation. We experiment with different combinations of NNscriptstylelangle q,,srangle displaystyle on the FPGA to profile the energy consumption of the deployed network so that the user can choose the most energy-efficient network configuration promptly. Our accelerator design is deployed on the Xilinx AC 701 platform and has at least 2.1× and 4× improvements on energy and energy efficiency results, respectively, compared to recent hardware implementations for keyword spotting.