AutoKWS: Keyword Spotting with Differentiable Architecture Search
arXiv:2009.03658
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.
arXiv commentICASSP 2021
References in corpus (12)
- Adam: A Method for Stochastic Optimization
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
- DARTS: Differentiable Architecture Search
- Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
- Hello Edge: Keyword Spotting on Microcontrollers
- Streaming keyword spotting on mobile devices
- Neural Architecture Search For Keyword Spotting
- Temporal Convolution for Real-time Keyword Spotting on Mobile Devices
- Noisy Differentiable Architecture Search
- AutoSpeech: Neural Architecture Search for Speaker Recognition
- DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation