论文标题
使用STFT和微调RESNET18网络对肺部声音中的呼吸异常进行分类
Classify Respiratory Abnormality in Lung Sounds Using STFT and a Fine-Tuned ResNet18 Network
论文作者
论文摘要
识别肺部声音中的模式对于检测和监测呼吸道疾病至关重要。当前用于分析呼吸道声音需求领域专家的技术，并受到解释。因此，需要精确，自动的呼吸声音分类系统。在这项工作中，我们采用了一种数据驱动的方法来对异常的肺部声音进行分类。我们使用三种不同的特征提取技术比较了性能，即短期傅立叶变换（STFT），MEL SPECTROGRAM和WAV2VEC以及三种不同的分类器，包括预训练的RESNET18，LightCNN和音频谱图变压器。我们的主要贡献包括不同音频功能提取器和基于神经网络的分类器的台式标记，以及使用STFT和微调RESNET18网络的完整管道实现。所提出的方法在IEEE BioCAS 2022在呼吸道声音分类中的测试集上，在任务1-1、1-2、2-1和2-2方面的谐波得分分别为1-1、1-2、2-1和2-2，分别为0.89、0.80、0.71、0.36。
Recognizing patterns in lung sounds is crucial to detecting and monitoring respiratory diseases. Current techniques for analyzing respiratory sounds demand domain experts and are subject to interpretation. Hence an accurate and automatic respiratory sound classification system is desired. In this work, we took a data-driven approach to classify abnormal lung sounds. We compared the performance using three different feature extraction techniques, which are short-time Fourier transformation (STFT), Mel spectrograms, and Wav2vec, as well as three different classifiers, including pre-trained ResNet18, LightCNN, and Audio Spectrogram Transformer. Our key contributions include the bench-marking of different audio feature extractors and neural network based classifiers, and the implementation of a complete pipeline using STFT and a fine-tuned ResNet18 network. The proposed method achieved Harmonic Scores of 0.89, 0.80, 0.71, 0.36 for tasks 1-1, 1-2, 2-1 and 2-2, respectively on the testing sets in the IEEE BioCAS 2022 Grand Challenge on Respiratory Sound Classification.
