Autokws: Keyword Spotting With Differentiable Architecture Search

Abstract

Smart audio devices are gated by an always-on lightweight keyword spotting program to reduce power consumption. It is however challenging to design models that have both high accuracy and low latency for accurate and fast responsiveness. Many efforts have been made to develop end-to-end neural networks, in which depthwise separable convolutions, temporal convolutions, and LSTMs are adopted as building units. Nonetheless, these networks designed with human expertise may not achieve an optimal trade-off in an expansive search space. In this paper, we propose to leverage recent advances in differentiable neural architecture search to discover more efficient networks. Our searched model attains 97.2% top-1 accuracy on Google Speech Command Dataset v1 with only nearly 100K parameters.

Stats

• citations20
• S2 citations—
• github stars0
• HF likes0
• heat score9.92
• arxiv keyzhang2020autokws

Related papers

• Neural Architecture Search For Keyword Spotting (2020)10.61
• End-to-end Keyword Spotting Using Neural Architecture Search And Quantization (2021)8.60
• Convmixer: Feature Interactive Convolution With Curriculum Learning For Small Footprint And Noisy Far-field Keyword Spotting (2022)12.61
• Predicting Detection Filters For Small Footprint Open-vocabulary Keyword Spotting (2019)9.92
• A Separable Temporal Convolution Neural Network With Attention For Small-footprint Keyword Spotting (2021)0.00
• Small-footprint Keyword Spotting With Graph Convolutional Network (2019)10.48
• Efficient Keyword Spotting Using Time Delay Neural Networks (2018)10.21
• An End-to-end Architecture For Keyword Spotting And Voice Activity Detection (2016)0.00