Small-footprint Keyword Spotting with Graph Convolutional Network
This work addresses the problem of efficient keyword spotting for resource-constrained devices, representing an incremental improvement over prior methods.
The authors tackled the challenge of achieving high precision keyword spotting on resource-constrained devices by proposing a novel context-aware and compact architecture, which achieved state-of-the-art performance on the Google Speech Command Dataset with lower computational cost.
Despite the recent successes of deep neural networks, it remains challenging to achieve high precision keyword spotting task (KWS) on resource-constrained devices. In this study, we propose a novel context-aware and compact architecture for keyword spotting task. Based on residual connection and bottleneck structure, we design a compact and efficient network for KWS task. To leverage the long range dependencies and global context of the convolutional feature maps, the graph convolutional network is introduced to encode the non-local relations. By evaluated on the Google Speech Command Dataset, the proposed method achieves state-of-the-art performance and outperforms the prior works by a large margin with lower computational cost.