A Real-Time Keyword Spotting System Based on an End-To-End Binary Convolutional Neural Network in FPGA

Yoon, Jinsung; Lee, Donghyun; Kim, Neungyun; Lee, Su Jung; Kwak, Gil-Ho; Kim, Tae‐Hwan

doi:10.1109/coolchips57690.2023.10121981

Search citation statements

Order By: Relevance

Paper Sections

Select...

Introduction1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

Publication Types

Select...

Article1

Relationship

Self Cite1

Independent0

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This work proposes a resource-efficient KWS system based on a 1D binary convolutional neural network (1D-BCNN) and validates the proposed system with the implementation results. This is the extension of our preliminary work presented in [16]. The contributions can be summarized as follows:…”

Section: Introductionmentioning

confidence: 75%

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

Yoon,

Kim,

Lee

et al. 2023

Electronics

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 75%