AutoKWS: Keyword Spotting with Differentiable Architecture Search

2020/09/08 by Bo Zhang, Wenfeng Li, Zhang, Bo +9 · 2 citations
Computer Science · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Music and Audio Processing #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2009.03658

openalex publication_date 2020/09/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Adam: A Method for Stochastic Optimization
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Hello Edge: Keyword Spotting on Microcontrollers
• Google Speech Commands-Musan test set
• DARTS: Differentiable Architecture Search
• Temporal Convolution for Real-time Keyword Spotting on Mobile Devices
• AutoSpeech: Neural Architecture Search for Speaker Recognition
• DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation

Cited by

• Keyword Mamba: Spoken Keyword Spotting with State Space Models
• Advances in Small-Footprint Keyword Spotting: A Comprehensive Review of Efficient Models and Algorithms

Related

• End-to-end Keyword Spotting using Neural Architecture Search and Quantization
• Encoder-Decoder Neural Architecture Optimization for Keyword Spotting
• Resource-efficient DNNs for Keyword Spotting using Neural Architecture Search and Quantization
• Stochastic Adaptive Neural Architecture Search for Keyword Spotting
• Hello Edge: Keyword Spotting on Microcontrollers