Audio-Based Activities of Daily Living (ADL) Recognition with Large-Scale Acoustic Embeddings from Online Videos
This work addresses activity recognition for healthcare and monitoring applications by reducing annotation effort, though it is incremental as it builds on existing deep learning and embedding methods.
The paper tackled audio-based recognition of Activities of Daily Living (ADL) by using large-scale acoustic embeddings from online videos to train classifiers without manual audio annotation, achieving 64.2% top-1 and 83.6% top-3 accuracy in a home-based study with 15 activities and 14 participants.
Over the years, activity sensing and recognition has been shown to play a key enabling role in a wide range of applications, from sustainability and human-computer interaction to health care. While many recognition tasks have traditionally employed inertial sensors, acoustic-based methods offer the benefit of capturing rich contextual information, which can be useful when discriminating complex activities. Given the emergence of deep learning techniques and leveraging new, large-scaled multi-media datasets, this paper revisits the opportunity of training audio-based classifiers without the onerous and time-consuming task of annotating audio data. We propose a framework for audio-based activity recognition that makes use of millions of embedding features from public online video sound clips. Based on the combination of oversampling and deep learning approaches, our framework does not require further feature processing or outliers filtering as in prior work. We evaluated our approach in the context of Activities of Daily Living (ADL) by recognizing 15 everyday activities with 14 participants in their own homes, achieving 64.2% and 83.6% averaged within-subject accuracy in terms of top-1 and top-3 classification respectively. Individual class performance was also examined in the paper to further study the co-occurrence characteristics of the activities and the robustness of the framework.