EfficientWord-Net: An Open Source Hotword Detection Engine based on One-shot Learning

TL;DR

This paper introduces EfficientWord-Net, a lightweight hotword detection engine utilizing one-shot learning, enabling real-time hotword recognition with minimal training data, improving efficiency over traditional methods.

Contribution

The paper presents a novel hotword detection engine based on one-shot learning that reduces training data requirements and retraining needs for new hotwords.

Findings

Achieved 94.51% accuracy in hotword detection

Reduces training data and retraining costs

Operates efficiently in real-time environments

Abstract

Voice assistants like Siri, Google Assistant, Alexa etc. are used widely across the globe for home automation, these require the use of special phrases also known as hotwords to wake it up and perform an action like "Hey Alexa!", "Ok Google!" and "Hey Siri!" etc. These hotwords are detected with lightweight real-time engines whose purpose is to detect the hotwords uttered by the user. This paper presents the design and implementation of a hotword detection engine based on one-shot learning which detects the hotword uttered by the user in real-time with just one or few training samples of the hotword. This approach is efficient when compared to existing implementations because the process of adding a new hotword in the existing systems requires enormous amounts of positive and negative training samples and the model needs to retrain for every hotword. This makes the existing implementations inefficient in terms of computation and cost. The architecture proposed in this paper has achieved an accuracy of 94.51%.