Audio-Based Onset Detection applied to Chewing Cycle Segmentation

In this paper we compare three onset detection algorithms for acoustic chewing cycle detection, which is a basic step in eating detection and automated dietary monitoring. We introduce a spectral flux algorithm that uses the spectrogram of a chewing sequence to compute a novelty function. Furthermore, beat tracking, in particular the notion of a predominant local pulse is introduced. We compare the two algorithms to a baseline energy-based segmentation in a chewing dataset with seven participants consuming pieces of six different foods, including in total 9818 annotated chewing cycles. Best performance was achieved for the beat tracking algorithm with 83% F-measure after leave-one-participant-out cross validation.

Automated summary

This paper compares three onset detection algorithms for acoustic chewing cycle detection, finding that the beat tracking algorithm performs the best in dietary monitoring. After leave-one-participant-out cross validation, the algorithm achieved 83% F-measure performance.