Lung sound signal endpoint detection method and system and storage medium
An endpoint detection and lung sound technology, applied in speech analysis, instruments, etc., can solve the problems of mixing valid speech frame signals and invalid interference frame signals, and unable to ensure that the initial lung sound signal can be directly used by researchers, so as to achieve reliable extraction. , the effect of eliminating noise interference and improving accuracy
Pending Publication Date: 2021-08-03
GUANGDONG POLYTECHNIC NORMAL UNIV
View PDF9 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
For the collection process of lung sound signals, the use of commonly used lung sound recording equipment cannot guarantee that the collected initial lung sound signals can be directly used by researchers. The initial lung sound signals will actually be disturbed by the noise of the current environment, among which mixed effective speech frame signal and invalid interference frame signal
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0042] See figure 1 , figure 1 A flow diagram showing the pulmonary sound signal end point detection method in the embodiment of the present invention is shown.
[0043] like figure 1 As shown, a pulmonary signal endpoint detection method includes the following steps:
[0044] S101, performs a windowing frame of the collected initial lung sound signal to obtain a number of frames to be tested;
[0045] The implementation of the present invention includes: first calculating the total number of samples of the acquired initial lung sound signals to be s 0 , Defining the sampling points of each frame of initial lung sound signal (frame length) of each frame (frame length) 0 And the number of points (frame shift) of each frame of the initial pulmonary signal of each frame (frame shift) is m 0 At this time, the initial lung sound signal can be divided into F 0 Frame, where F 0 (S) 0 NN 0 ) / M 0 +1; Secondly by means of the Han Ming window to process f 0 The frame initial lung sound sig...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a lung sound signal endpoint detection method and system and a storage medium, and the method comprises the steps: carrying out the windowing and framing of a collected initial lung sound signal, and obtaining a plurality of frames of to-be-detected lung sound signals; performing noise reduction processing on the plurality of frames of to-be-detected lung sound signals by using a spectral subtraction method to obtain a power spectrum of each frame of noise-reduced lung sound signal; calculating a power spectrum change characteristic value and a dynamic threshold value corresponding to each frame of noise reduction lung sound signal in combination with the power spectrum of each frame of noise reduction lung sound signal; and comparing and screening the power spectrum change characteristic value corresponding to each frame of noise-reduced lung sound signal with a dynamic threshold thereof until continuous effective lung sound signals are extracted from the initial lung sound signals. In the embodiment of the invention, reliable extraction of effective lung sound signals can be realized through signal frequency domain feature analysis, and the accuracy of a detection result is improved.
Description
Technical field [0001] The present invention relates to the field of pulmonary sound detection, and more particularly to a pulmonary sound signal end point detection method, a system, and a storage medium. Background technique [0002] The lung sound signal is a physiological sound signal generated by the human respiratory system and the outside in the ventilation process, and its correlation with pathophysiology can extend to the field of clinical respiratory disease diagnosis. For the collection process of the pulmonary signal, the collected initial lung sound signal is not guaranteed by the commonly used lung sound admission equipment is the researchers can be directly utilized, and the initial lung sound signal is actually the noise interference of the current environment, where is mixed Effective speech frame signal and invalid interference frame signal. Therefore, how to screen these two types of frame signals to extract an effective lung sound signal, it is a problem that ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G10L21/0208G10L21/0232G10L25/45G10L25/87
CPCG10L21/0208G10L21/0232G10L25/87G10L25/45
Inventor 詹瑾唐四云赵慧民
Owner GUANGDONG POLYTECHNIC NORMAL UNIV