Novel DTD and VAD assisted voice detection algorithm for VoIP systems

Meng, Ming; Wang, Ke; Ji, Hong

doi:10.1016/s1005-8885(16)60040-7

Cited by 1 publication

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Prior to processing, the data are segmented into components, with each component corresponding to the sounds from a single inhale-exhale cycle. The respiratory cycle endpoint is detected based on the maximum of the autocorrelation function 22 . The autocorrelation is the correlation of the sound signal with a delayed copy of itself.…”

Section: Methodsmentioning

confidence: 99%

A Novel Method for Automatic Identification of Breathing State

Niu

Cai

Shi

et al. 2019

Sci Rep

View full text Add to dashboard Cite

Sputum deposition blocks the airways of patients and leads to blood oxygen desaturation. Medical staff must periodically check the breathing state of intubated patients. This process increases staff workload. In this paper, we describe a system designed to acquire respiratory sounds from intubated subjects, extract the audio features, and classify these sounds to detect the presence of sputum. Our method uses 13 features extracted from the time-frequency spectrum of the respiratory sounds. To test our system, 220 respiratory sound samples were collected. Half of the samples were collected from patients with sputum present, and the remainder were collected from patients with no sputum present. Testing was performed based on ten-fold cross-validation. In the ten-fold cross-validation experiment, the logistic classifier identified breath sounds with sputum present with a sensitivity of 93.36% and a specificity of 93.36%. The feature extraction and classification methods are useful and reliable for sputum detection. This approach differs from waveform research and can provide a better visualization of sputum conditions. The proposed system can be used in the ICU to inform medical staff when sputum is present in a patient’s trachea.

show abstract

Section: Methodsmentioning

confidence: 99%