A Resource-Efficient Keyword Spotting System Based on a One-Dimensional Binary Convolutional Neural Network

This paper proposes a resource-efficient keyword spotting (KWS) system based on a convolutional neural network (CNN). The end-to-end KWS process is performed based solely on 1D-CNN inference, where features are first extracted from a few convolutional blocks, and then the keywords are classified using a few fully connected blocks. The 1D-CNN model is binarized to reduce resource usage, and its inference is executed by employing a dedicated engine. This engine is designed to skip redundant operations, enabling high inference speed despite its low complexity. The proposed system is implemented using 6895 ALUTs in an Intel Cyclone V FPGA by integrating the essential components for performing the KWS process. In the system, the latency required to process a frame is 22 ms, and the spotting accuracy is 91.80% in an environment where the signal-to-noise ratio is 10 dB for Google speech commands dataset version 2.

Automated summary

This paper proposes a resource-efficient keyword spotting system based on a convolutional neural network. The system utilizes a one-dimensional CNN for end-to-end keyword recognition, achieving high accuracy and fast processing speed. By binarizing the model and employing a dedicated engine, the system reduces resource usage without sacrificing performance. Experimental results show that the system achieves a processing latency of 22 ms and a spotting accuracy of 91.80% in a specific environment.