Enhancing Wearable Tap Water Audio Detection through Subclass Annotation in the HD-Epic Dataset

TL;DR

This paper introduces a new tap water label in the HD-Epic dataset, enabling improved wearable water flow detection through subclass annotation, with lightweight classifiers demonstrating effective learning of this new class.

Contribution

The paper adds a tap water subclass to the HD-Epic dataset and evaluates lightweight classifiers, enhancing water detection in wearable activity recognition.

Findings

The tap water class can be learned more easily than the general water class.

Lightweight classifiers effectively recognize the new tap water label.

Subclass annotation improves contextual water detection in wearable data.

Abstract

Wearable human activity recognition has been shown to benefit from the inclusion of acoustic data, as the sounds around a person often contain valuable context. However, due to privacy concerns, it is usually not ethically feasible to record and save microphone data from the device, since the audio could, for instance, also contain private conversations. Rather, the data should be processed locally, which in turn requires processing power and consumes energy on the wearable device. One special use case of contextual information that can be utilized to augment special tasks in human activity recognition is water flow detection, which can, e.g., be used to aid wearable hand washing detection. We created a new label called tap water for the recently released HD-Epic data set, creating 717 hand-labeled annotations of tap water flow, based on existing annotations of the water class. We analyzed the relation of tap water and water in the dataset and additionally trained and evaluated two lightweight classifiers to evaluate the newly added label class, showing that the new class can be learned more easily.