SPRSound: Open-Source SJTU Paediatric Respiratory Sound Database

Zhang, Qing; Zhang, Jing; Yuan, Jiang; Huang, Huajie; Zhang, Yuhang; Zhang, Baoqin; Lv, Gaomei; Lin, Shuzhu; Wang, Na; Liu, Xin; Tang, Mingyu; Wang, Yahua; Ma, Hui; Liu, Lu; Yuan, Shuo; Zhou, Hongyuan; Zhao, Jian; Li, Yongfu; Yin, Yong; Zhao, Liebin; Wang, Guoxing; Lian, Yong

doi:10.1109/tbcas.2022.3204910

Cited by 29 publications

(4 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, M2D-X shows more significant performance gains, indicating that it can effectively achieve further pre-training in a small-data scenario with the help of the background noise and additional tasks. 4) Dataset Ablation using SPRSound: We further verified the applicability of M2D-X to another dataset using SPRSound [78], a dataset similar to ICBHI2017. SPRSound is a respiratory sound dataset comprising 2683 recordings (8.2 h) from 292 subjects and is as small as ICBHI2017 (920 recordings/5.5 h/128 subjects).…”

Section: ) Performance Transition In Training Progressmentioning

confidence: 78%

Masked Modeling Duo: Towards a Universal Audio Pre-Training Framework

Niizumi,

Takeuchi,

Ohishi

et al. 2024

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Self-supervised learning (SSL) using masked prediction has made great strides in general-purpose audio representation. This study proposes Masked Modeling Duo (M2D), an improved masked prediction SSL, which learns by predicting representations of masked input signals that serve as training signals. Unlike conventional methods, M2D obtains a training signal by encoding only the masked part, encouraging the two networks in M2D to model the input. While M2D improves general-purpose audio representations, a specialized representation is essential for real-world applications, such as in industrial and medical domains. The often confidential and proprietary data in such domains is typically limited in size and has a different distribution from that in pre-training datasets. Therefore, we propose M2D for X (M2D-X), which extends M2D to enable the pre-training of specialized representations for an application X. M2D-X learns from M2D and an additional task and inputs background noise. We make the additional task configurable to serve diverse applications, while the background noise helps learn on small data and forms a denoising task that makes representation robust. With these design choices, M2D-X should learn a representation specialized to serve various application needs. Our experiments confirmed that the representations for general-purpose audio, specialized for the highly competitive AudioSet and speech domain, and a small-data medical task achieve top-level performance, demonstrating the potential of using our models as a universal audio pre-training framework. Our code is available online for future studies.

show abstract

Section: ) Performance Transition In Training Progressmentioning

confidence: 78%

Masked Modeling Duo: Towards a Universal Audio Pre-Training Framework

Niizumi,

Takeuchi,

Ohishi

et al. 2024

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…Meanwhile, for the binary-class problems, the overall results for normal vs. abnormal were 85.61%, 83.44%, 83.44%, and 84.21% for accuracy, sensitivity, specificity, and F1-score, respectively, and for crackles and wheezes, they were 84.21%, 93.57%, 93.53%, and 93.15%, respectively. To further validate the robustness of our framework, we also conducted experiments using another public dataset, the SJTU Paediatric dataset [ 53 ], for various respiratory diseases, including healthy samples and seven distinct lung diseases: coarse crackle (C), fine crackle (F), rhonchi (R), stridor (S), wheeze (W), and both wheeze and crackle (B). The results, presented in Table 11 , demonstrate that our findings are not only applicable to a single dataset but also generalize well across different datasets.…”

Section: Resultsmentioning

confidence: 99%

Auscultation-Based Pulmonary Disease Detection through Parallel Transformation and Deep Learning

Khan,

Saeed

et al. 2024

Bioengineering

View full text Add to dashboard Cite

Respiratory diseases are among the leading causes of death, with many individuals in a population frequently affected by various types of pulmonary disorders. Early diagnosis and patient monitoring (traditionally involving lung auscultation) are essential for the effective management of respiratory diseases. However, the interpretation of lung sounds is a subjective and labor-intensive process that demands considerable medical expertise, and there is a good chance of misclassification. To address this problem, we propose a hybrid deep learning technique that incorporates signal processing techniques. Parallel transformation is applied to adventitious respiratory sounds, transforming lung sound signals into two distinct time-frequency scalograms: the continuous wavelet transform and the mel spectrogram. Furthermore, parallel convolutional autoencoders are employed to extract features from scalograms, and the resulting latent space features are fused into a hybrid feature pool. Finally, leveraging a long short-term memory model, a feature from the latent space is used as input for classifying various types of respiratory diseases. Our work is evaluated using the ICBHI-2017 lung sound dataset. The experimental findings indicate that our proposed method achieves promising predictive performance, with average values for accuracy, sensitivity, specificity, and F1-score of 94.16%, 89.56%, 99.10%, and 89.56%, respectively, for eight-class respiratory diseases; 79.61%, 78.55%, 92.49%, and 78.67%, respectively, for four-class diseases; and 85.61%, 83.44%, 83.44%, and 84.21%, respectively, for binary-class (normal vs. abnormal) lung sounds.

show abstract

“…Notably, each respiratory cycle within the recordings is also annotated based on the existence of crackles, wheezes, both crackles and wheezes, or the absence of these adventitious sounds, making it ideal for disease or lower respiratory disease symptom sound classification tasks. Another dataset for respiratory sound classification is the SPRSound dataset [ 95 ], which was created within the context of IEEE BioCAS 2022 Respiratory challenge [ 99 ]. It consists of 2683 records and 9089 respiratory sound events from 292 participants.…”

Section: Publicly Available Datasetsmentioning

confidence: 99%

Respiratory Diseases Diagnosis Using Audio Analysis and Artificial Intelligence: A Systematic Review

Kapetanidis,

Kalioras,

Tsakonas

et al. 2024

Sensors

View full text Add to dashboard Cite

Respiratory diseases represent a significant global burden, necessitating efficient diagnostic methods for timely intervention. Digital biomarkers based on audio, acoustics, and sound from the upper and lower respiratory system, as well as the voice, have emerged as valuable indicators of respiratory functionality. Recent advancements in machine learning (ML) algorithms offer promising avenues for the identification and diagnosis of respiratory diseases through the analysis and processing of such audio-based biomarkers. An ever-increasing number of studies employ ML techniques to extract meaningful information from audio biomarkers. Beyond disease identification, these studies explore diverse aspects such as the recognition of cough sounds amidst environmental noise, the analysis of respiratory sounds to detect respiratory symptoms like wheezes and crackles, as well as the analysis of the voice/speech for the evaluation of human voice abnormalities. To provide a more in-depth analysis, this review examines 75 relevant audio analysis studies across three distinct areas of concern based on respiratory diseases’ symptoms: (a) cough detection, (b) lower respiratory symptoms identification, and (c) diagnostics from the voice and speech. Furthermore, publicly available datasets commonly utilized in this domain are presented. It is observed that research trends are influenced by the pandemic, with a surge in studies on COVID-19 diagnosis, mobile data acquisition, and remote diagnosis systems.

show abstract

SPRSound: Open-Source SJTU Paediatric Respiratory Sound Database

Cited by 29 publications

References 76 publications

Masked Modeling Duo: Towards a Universal Audio Pre-Training Framework

Masked Modeling Duo: Towards a Universal Audio Pre-Training Framework

Auscultation-Based Pulmonary Disease Detection through Parallel Transformation and Deep Learning

Respiratory Diseases Diagnosis Using Audio Analysis and Artificial Intelligence: A Systematic Review

Contact Info

Product

Resources

About