Daniel Tompkins

Benjamin Elizalde, Daniel Tompkins

COVID-19 has resulted in over 100 million infections and caused worldwide lock downs due to its high transmission rate and limited testing options. Current diagnostic tests can be expensive, limited in availability, time-intensive and require risky in-person appointments. It has been established that symptomatic COVID-19 seriously impairs normal functioning of the respiratory system, thus affecting the coughing acoustics. The 2021 DiCOVA Challenge @ INTERSPEECH was designed to find scientific and engineering insights to the question by enabling participants to analyze an acoustic dataset gathered from COVID-19 positive and non-COVID-19 individuals. In this report we describe our participation in the Challenge (Track 1). We achieved 82.37% AUC ROC on the blind test outperforming the Challenge's baseline of 69.85%.

Jianyu Fan, Eric Nichols, Daniel Tompkins et al.

Realistic recordings of soundscapes often have multiple sound events co-occurring, such as car horns, engine and human voices. Sound event retrieval is a type of content-based search aiming at finding audio samples, similar to an audio query based on their acoustic or semantic content. State of the art sound event retrieval models have focused on single-label audio recordings, with only one sound event occurring, rather than on multi-label audio recordings (i.e., multiple sound events occur in one recording). To address this latter problem, we propose different Deep Learning architectures with a Siamese-structure and a Pairwise Presence Matrix. The networks are trained and evaluated using the SONYC-UST dataset containing both single- and multi-label soundscape recordings. The performance results show the effectiveness of our proposed model.