Tuning In: Analysis of Audio Classifier Performance in Clinical Settings with Limited Data

arXiv:2402.10100v1 Announce Type: cross
Abstract: This study assesses deep learning models for audio classification in a clinical setting with the constraint of small datasets reflecting real-world prospective data collection. We analyze CNNs, including DenseNet and ConvNeXt, alongside transformer models like ViT, SWIN, and AST, and compare them against pre-trained audio models such as YAMNet and VGGish. Our method highlights the benefits of pre-training on large datasets before fine-tuning on specific clinical data. We prospectively collected two first-of-their-kind patient audio datasets …

abstract analysis analyze arxiv audio classification classifier clinical cnns collection cs.ai cs.lg cs.sd data data collection datasets deep learning eess.as performance small study swin them transformer transformer models type vit world