[3Xin2] Poster session 1

[3Xin2-115] Exploring Pre-trained General-purpose Audio Representations for Heart Murmur Detection

〇Daisuke Niizumi¹, Daiki Takeuchi¹, Yasunori Ohishi¹, Noboru Harada¹, Kunio Kashino¹ (1.NTT Communication Science Laboratories)

Keywords:General-purpose audio representation, Pre-training, Transfer learning, Heart murmur detection

To reduce the need for skilled clinicians in heart sound interpretation, recent studies on automating cardiac auscultation have explored deep learning approaches. However, despite the demands for large data for deep learning, the size of the heart sound datasets is limited, and no pre-trained model is available. On the contrary, many pre-trained models for general audio tasks are available as general-purpose audio representations. This study explores the potential of general-purpose audio representations pre-trained on large-scale datasets for transfer learning in heart murmur detection. Experiments on the CirCor DigiScope heart sound dataset show that the recent self-supervised learning Masked Modeling Duo (M2D) outperforms previous methods with the results of a weighted accuracy of 0.832 and an unweighted average recall of 0.713. These results demonstrate the effectiveness of general-purpose audio representation in processing heart sounds and open the way for further applications.