# Neural Architecture Search For Keyword Spotting

arXiv: https://arxiv.org/abs/2009.00165 · HTML: https://mlsanity.com/paper/2009.00165/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2020.

## Built on by (most cited first, 11 of 11)

- [Deep Spoken Keyword Spotting: An Overview](https://mlsanity.com/paper/2111.10592/) (2021)
- [AdvRush: Searching for Adversarially Robust Neural Architectures](https://mlsanity.com/paper/2108.01289/) (2021)
- [Partially-Connected Differentiable Architecture Search for Deepfake and Spoofing Detection](https://mlsanity.com/paper/2104.03123/) (2021)
- [Ultra-Low Power Keyword Spotting at the Edge](https://mlsanity.com/paper/2111.04988/) (2021)
- [Efficient Automation of Neural Network Design: A Survey on Differentiable Neural Architecture Search](https://mlsanity.com/paper/2304.05405/) (2023)
- [Text Anchor Based Metric Learning for Small-footprint Keyword Spotting](https://mlsanity.com/paper/2108.05516/) (2021)
- [End-to-end Keyword Spotting using Neural Architecture Search and Quantization](https://mlsanity.com/paper/2104.06666/) (2021)
- [Encoder-Decoder Neural Architecture Optimization for Keyword Spotting](https://mlsanity.com/paper/2106.02738/) (2021)
- [To Wake-up or Not to Wake-up: Reducing Keyword False Alarm by Successive Refinement](https://mlsanity.com/paper/2304.03416/) (2023)
- [A Fast Network Exploration Strategy to Profile Low Energy Consumption for Keyword Spotting](https://mlsanity.com/paper/2202.02361/) (2022)
- [ERSAM: Neural Architecture Search For Energy-Efficient and Real-Time Social Ambiance Measurement](https://mlsanity.com/paper/2303.10727/) (2023)

## Abstract (arXiv)

Deep neural networks have recently become a popular solution to keyword spotting systems, which enable the control of smart devices via voice. In this paper, we apply neural architecture search to search for convolutional neural network models that can help boost the performance of keyword spotting based on features extracted from acoustic signals while maintaining an acceptable memory footprint. Specifically, we use differentiable architecture search techniques to search for operators and their connections in a predefined cell search space. The found cells are then scaled up in both depth and width to achieve competitive performance. We evaluated the proposed method on Google's Speech Commands Dataset and achieved a state-of-the-art accuracy of over 97% on the setting of 12-class utterance classification commonly reported in the literature.