CN103345921B - Based on the nighttime sleep acoustic signal analysis method of multiple features - Google Patents

Abstract

The invention discloses a kind of nighttime sleep acoustic signal analysis method based on multiple features.First the method reads the person's nighttime sleep acoustical signal data to be measured by microphone records, carries out end-point detection by short-time energy gate method to nighttime sleep acoustical signal; Then multiple acoustic features of a series of signal Processing Algorithm to nighttime sleep acoustical signal are utilized to extract; The database that can supply subsequent analysis and research is set up finally by every nighttime sleep acoustical signal feature of basic statistical method to person to be measured.The present invention realizes easily, and method is simple, and after being developed to product, hardware cost is little, has a extensive future.

Description

Based on the nighttime sleep acoustic signal analysis method of multiple features

Technical field

The invention belongs to and realize During Night Time sleep acoustical signal Database technology, particularly a kind of nighttime sleep acoustic signal analysis method based on multiple features by Underwater Acoustic channels means.

Background technology

The analysis of the nighttime sleep acoustical signal of human body is very important for the health monitoring system in exploitation wisdom family.The nighttime sleep acoustical signal be often concerned generally includes the improper Speech acoustics signals such as the sound of snoring, cough, groan.These nighttime sleep acoustical signals are for early monitoring and the snoring that notes abnormalities, judge that health states, monitoring dream sleep-walking are significant.

For utilizing acoustic signal analysis means to person's nighttime sleep acoustic signal extraction feature to be measured, it is follow-up basis of carrying out large-scale data analysis, mathematical modeling and pattern-recognition.Taiwan has method (the 1.Liao Wenhung that scholar proposes the data analysis of SAN acoustical signal, Su Yisyuan.Classification of audio signalsin all-night sleep studies [C] .Proc.18th Int.Conf.on Pattern Recognition, HongKong, China, August2006,302-305), but they do not relate to and carry out Database to the nighttime sleep acoustical signal of person to be measured, and selected feature is single, physical significance also and indefinite.Thus can not reflect the sound-source signal discrimination characteristically of some specific physical significance, thus not be suitable for follow-up analysis and modeling.

As from the foregoing, prior art exist method not comprehensively, function singleness, be not suitable for the defects such as follow-up study.

Summary of the invention

The object of the present invention is to provide a kind of nighttime sleep acoustic signal analysis method based on multiple features.

The technical solution realizing the object of the invention is: a kind of nighttime sleep acoustic signal analysis method based on multiple features, and step is as follows:

Step 1, carry out end-point detection to nighttime sleep acoustical signal, namely the nighttime sleep acoustical signal data of first reading microphone records, then become sample by Data Segmentation, and carry out end-point detection to nighttime sleep acoustical signal, by the filtering of " unvoiced segments " data; Carry out end-point detection to nighttime sleep acoustical signal specifically to comprise the following steps:

Step 1-1, carry out sub-frame processing in short-term to nighttime sleep acoustical signal data, " frame length " is 64ms, and " frame moves " is 32ms, and " frame " data are considered as a sample;

Step 1-2, starting point is set to " frame " sequence number n=k of current reading, and pointer j resets;

Step 1-3, utilize formula determine the short-time energy of current reading " frame ";

In formula, k is current reading " frame " sequence number, and the digital signal samples that N comprises for sample is counted, E _kfor the short-time energy of sample, S _kfor digital signal samples amplitude;

Step 1-4, judge E _kwhether be greater than threshold value E _th, if so, perform step 1-5, otherwise current reading " frame " sequence number k is from increasing 1, pointer j from increasing 1 and performing step 1-3; Described threshold value E _thfor microphone noise substrate E _btwice;

Step 1-5, judge whether pointer j is greater than interval d, if so, perform step 1-6, otherwise perform step 1-2; Described interval d is 3 ~ 4.

Step 1-6, to determine " abort frame " and " start frame ", wherein " abort frame " sequence number n _stop=n-1, " start frame " sequence number n _initial=n – j – 1.

Step 2, multi-feature extraction is carried out to the nighttime sleep acoustical signal by end-point detection; Be specially:

Step 2-1, each frame of the nighttime sleep acoustical signal fragment by end-point detection is all multiplied by Hamming window function, wherein Hamming window function is:

$w\left(m\right)=0.54-0.46\cos \left(2\mathrm{\π}\frac{m}{M}\right),0\≤m\≤M;$

In formula, M is the sampling number of one " frame " sample;

Step 2-2, all extract " frequecy characteristic " each frame of the nighttime sleep acoustical signal fragment after step 2-1 process, formula used is:

$\underset{f_i=0}{\overset{f_{\mathrm{center}}}{\mathrm{\Σ}}}{X}_{f_i}=\underset{f_i=f_{\mathrm{center}}}{\overset{f_c}{\mathrm{\Σ}}}{X}_{f_i};$

$X_{f_{\mathrm{peak}}}=\max \{X_{f_i},f_i=0,...,f_c\};$

$f_{\mathrm{mean}}=\frac{\underset{f_i=0}{\overset{f_c}{\mathrm{\Σ}}}{f}_i*X_{f_i}}{\underset{f_i=0}{\overset{f_c}{\mathrm{\Σ}}}{X}_{f_i}};$

$f_{\mathrm{mean}}\left(j\right)=\frac{\underset{f_i=1000*(j-1)}{\overset{1000*j}{\mathrm{\Σ}}}{f}_i*X_{f_i}}{\underset{f_i=1000*(j-1)}{\overset{1000*j}{\mathrm{\Σ}}}{X}_{f_i}}j=\mathrm{1,2},...,[f_s/1000];$

In formula, the frequency f of nighttime sleep acoustical signal after Fast Fourier Transform (FFT) _ithe absolute value of the power spectrum density at place, X _fpeakbe nighttime sleep acoustical signal after Fast Fourier Transform (FFT) in crest frequency frequency f _peakthe absolute value of the power spectrum density at place, f _cbeing cutoff frequency, is sample frequency f _s1/2, [] is bracket function, f _centercentre frequency, f _peakcrest frequency, f _meanbarycenter of frequency spectrum, f _mean(j) (j=1,2 ..., [f _s/ 1000]) be the barycenter of frequency spectrum of each 1000Hz sub-band;

Step 2-3, all extract " energy feature " each frame in the nighttime sleep acoustical signal fragment after step 2-1 process, formula used is:

${\mathrm{BER}}_{\left(j\right)}=\frac{\underset{f_i=1000*(j-1)}{\overset{1000*j}{\mathrm{\Σ}}}{X}_{f_i}^2}{\underset{f_i=0}{\overset{f_c}{\mathrm{\Σ}}}{X}_{f_i}^2}j=\mathrm{1,2},...,[f_s/1000];$

In formula, the frequency f of nighttime sleep acoustical signal after Fast Fourier Transform (FFT) _ithe absolute value of the power spectrum density at place, f _cbeing cutoff frequency, is sample frequency f _s1/2, BER (j) (j=1,2 ..., [f _s/ 1000]) be the energy Ratios of each 1000Hz sub-band;

Step 2-4, all extract " empirical mode decomposition feature " each frame in the nighttime sleep acoustical signal fragment after step 2-1 process, formula used is:

$E_i={\∫}_{-\∞}^{+\∞}{\left|c_i\left(t\right)\right|}^2\mathrm{dti}=\mathrm{1,2},...,l;$

$T=[E_1/E,E_2/E,...,E_l/E],E=\underset{i=1}{\overset{l}{\mathrm{\Σ}}}{E}_i;$

$H_E=-\underset{i=1}{\overset{l}{\mathrm{\Σ}}}{p}_i{\log }_2{p}_i,p_i=E_i/E;$

In formula, c _i(t) (i=1,2 ..., l) be the l layer intrinsic mode function that nighttime sleep acoustical signal obtains after empirical mode decomposition, E _ibe the energy of i-th layer of intrinsic mode function, T is intrinsic mode function energy Ratios eigenvector, and E is the gross energy of each layer intrinsic mode function, H _eit is intrinsic mode function Energy-Entropy.

Step 3, multiple feature building databases that step 2 is extracted, and the distribution of feature is added up.Carry out statistics to the distribution of feature to comprise: obtain the maximal value of each feature of overall sample, minimum value, average, variance and dynamic range.

Compared with prior art, its remarkable advantage is in the present invention: 1) method of the present invention is concentrated and is extracted comparatively comprehensive multiple nighttime sleep acoustical signal feature; 2) the present invention carries out feature extraction to person's nighttime sleep acoustical signal data to be measured, and the statistical property finally drawn can reflect the dynamic changing process of relevant physiological or behavior state in person's SAN to be measured; 3) method of the present invention realizes simple, and after being developed to hardware product, cost is less, is easy to promote the use of.

Below in conjunction with accompanying drawing, the present invention is described in further detail.

Accompanying drawing explanation

Fig. 1 is the process flow diagram of the nighttime sleep acoustic signal analysis method that the present invention is based on multiple features.

Fig. 2 is that the present invention carries out the process flow diagram of end-point detection to nighttime sleep acoustical signal.

Fig. 3 is that the present invention is to the histogram of certain feature of nighttime sleep acoustical signal data extracted in example and the Kernel function curve diagram of matching.

Embodiment

Composition graphs 1, a kind of nighttime sleep acoustic signal analysis method based on multiple features of the present invention, step is as follows:

Step 1, carry out end-point detection to nighttime sleep acoustical signal, namely the nighttime sleep acoustical signal data of first reading microphone records, then become sample by Data Segmentation, and carry out end-point detection to nighttime sleep acoustical signal, by the filtering of " unvoiced segments " data; Carry out end-point detection to nighttime sleep acoustical signal specifically to comprise the following steps:

Step 1-1, carry out sub-frame processing in short-term to nighttime sleep acoustical signal data, " frame length " is 64ms, and " frame moves " is 32ms, and " frame " data are considered as a sample;

Step 1-2, starting point is set to " frame " sequence number n=k of current reading, and pointer j resets;

Step 1-3, utilize formula determine the short-time energy of current reading " frame ";

In formula, k is current reading " frame " sequence number, and the digital signal samples that N comprises for sample is counted, E _kfor the short-time energy of sample, S _kfor digital signal samples amplitude;

Step 1-4, judge E _kwhether be greater than threshold value E _th, if so, perform step 1-5, otherwise current reading " frame " sequence number k is from increasing 1, pointer j from increasing 1 and performing step 1-3; Described threshold value E _thfor microphone noise substrate E _btwice;

Step 1-5, judge whether pointer j is greater than interval d, if so, perform step 1-6, otherwise perform step 1-2; Described middle interval d is 3 ~ 4.

Step 1-6, to determine " abort frame " and " start frame ", wherein " abort frame " sequence number n _stop=n-1, " start frame " sequence number n _initial=n – j – 1.

Step 2, multi-feature extraction is carried out to the nighttime sleep acoustical signal by end-point detection; Carry out multi-feature extraction to the nighttime sleep acoustical signal by end-point detection to be specially:

Step 2-1, each frame of the nighttime sleep acoustical signal fragment by end-point detection is all multiplied by Hamming window function, wherein Hamming window function is:

$w\left(m\right)=0.54-0.46\cos \left(2\mathrm{\π}\frac{m}{M}\right),0\≤m\≤M;$

In formula, M is the sampling number of one " frame " sample;

Step 2-2, all extract " frequecy characteristic " each frame of the nighttime sleep acoustical signal fragment after step 2-1 process, formula used is:

$\underset{f_i=0}{\overset{f_{\mathrm{center}}}{\mathrm{\Σ}}}{X}_{f_i}=\underset{f_i=f_{\mathrm{center}}}{\overset{f_c}{\mathrm{\Σ}}}{X}_{f_i};$

$X_{f_{\mathrm{peak}}}=\max \{X_{f_i},f_i=0,...,f_c\};$

$f_{\mathrm{mean}}=\frac{\underset{f_i=0}{\overset{f_c}{\mathrm{\Σ}}}{f}_i*X_{f_i}}{\underset{f_i=0}{\overset{f_c}{\mathrm{\Σ}}}{X}_{f_i}};$

$f_{\mathrm{mean}}\left(j\right)=\frac{\underset{f_i=1000*(j-1)}{\overset{1000*j}{\mathrm{\Σ}}}{f}_i*X_{f_i}}{\underset{f_i=1000*(j-1)}{\overset{1000*j}{\mathrm{\Σ}}}{X}_{f_i}}j=\mathrm{1,2},...,[f_s/1000];$

In formula, the frequency f of nighttime sleep acoustical signal after Fast Fourier Transform (FFT) _ithe absolute value of the power spectrum density at place, X _fpeakbe nighttime sleep acoustical signal after Fast Fourier Transform (FFT) in crest frequency frequency f _peakthe absolute value of the power spectrum density at place, f _cbeing cutoff frequency, is sample frequency f _s1/2, [] is bracket function, f _centercentre frequency, f _peakcrest frequency, f _meanbarycenter of frequency spectrum, f _mean(j) (j=1,2 ..., [f _s/ 1000]) be the barycenter of frequency spectrum of each 1000Hz sub-band;

Step 2-3, all extract " energy feature " each frame in the nighttime sleep acoustical signal fragment after step 2-1 process, formula used is:

${\mathrm{BER}}_{\left(j\right)}=\frac{\underset{f_i=1000*(j-1)}{\overset{1000*j}{\mathrm{\Σ}}}{X}_{f_i}^2}{\underset{f_i=0}{\overset{f_c}{\mathrm{\Σ}}}{X}_{f_i}^2}j=\mathrm{1,2},...,[f_s/1000];$

In formula, the frequency f of nighttime sleep acoustical signal after Fast Fourier Transform (FFT) _ithe absolute value of the power spectrum density at place, f _cbeing cutoff frequency, is sample frequency f _s1/2, BER (j) (j=1,2 ..., [f _s/ 1000]) be the energy Ratios of each 1000Hz sub-band;

Step 2-4, all extract " empirical mode decomposition feature " each frame in the nighttime sleep acoustical signal fragment after step 2-1 process, formula used is:

$E_i={\∫}_{-\∞}^{+\∞}{\left|c_i\left(t\right)\right|}^2\mathrm{dti}=\mathrm{1,2},...,l;$

$T=[E_1/E,E_2/E,...,E_l/E],E=\underset{i=1}{\overset{l}{\mathrm{\Σ}}}{E}_i;$

$H_E=-\underset{i=1}{\overset{l}{\mathrm{\Σ}}}{p}_i{\log }_2{p}_i,p_i=E_i/E;$

In formula, c _i(t) (i=1,2 ..., l) be the l layer intrinsic mode function that nighttime sleep acoustical signal obtains after empirical mode decomposition, E _ibe the energy of i-th layer of intrinsic mode function, T is intrinsic mode function energy Ratios eigenvector, and E is the gross energy of each layer intrinsic mode function, H _eit is intrinsic mode function Energy-Entropy.

Step 3, multiple feature building databases that step 2 is extracted, and the distribution of feature is added up.Carry out statistics to the distribution of feature to comprise: obtain the maximal value of each feature of overall sample, minimum value, average, variance and dynamic range.

Below in conjunction with example, further detailed description is done to the present invention:

Composition graphs 1, the present invention is based on the nighttime sleep acoustic signal analysis method of multiple features, step is as follows:

The first step, carries out " in short-term framing " process to person's nighttime sleep acoustical signal data to be measured of microphone records, calculates the short-time energy value of every " frame " (i.e. sample) respectively, then carries out end-point detection by shown in Fig. 2 to nighttime sleep acoustical signal.

(1) to reading by the nighttime sleep sound data of microphone records and using " in short-term framing " to process, 50% overlap " framing " is carried out to raw data, " frame length " is got for 64ms in example, " frame moves " is 32ms, and " frame " nighttime sleep sound data visualization is a sample.

(2) starting point is that current reading " frame " sequence number n=k, pointer j reset.

(3) according to formula the short-time energy of (k represents a kth sample, and the digital signal samples that N comprises for each sample is counted) calculating " present frame " sample.

(4) E is judged _kwhether be greater than threshold value E _th, if so, perform (5), otherwise current reading " frame " sequence number k is from increasing 1, pointer j from increasing 1 and performing (3), E in example _thbe 0.015.

(5) judge whether pointer j is greater than interval d, getting d in example is 3, if so, performs (6), otherwise performs (2);

(6) " abort frame " sequence number n _stop=n-1, " start frame " sequence number n _initial=n – j – 1.

Second step, multi-feature extraction: as shown in Figure 1, carries out multi-feature extraction to the nighttime sleep acoustical signal data by end-point detection.

(1) to being carried out " windowing process " (namely each frame of former nighttime sleep acoustical signal fragment is all multiplied by a window function) by the nighttime sleep acoustical signal data after end-point detection, generally choose Hamming window, window function formula used is:

$w\left(m\right)=0.54-0.46\cos \left(2\mathrm{\π}\frac{m}{M}\right),0\≤m\≤M$

Wherein, M is the sampling number of one " frame " sample, is 1024 in example.

(2) " frequecy characteristic " is extracted:

$\underset{f_i=0}{\overset{f_{\mathrm{center}}}{\mathrm{\Σ}}}{X}_{f_i}=\underset{f_i=f_{\mathrm{center}}}{\overset{f_c}{\mathrm{\Σ}}}{X}_{f_i};$

$X_{f_{\mathrm{peak}}}=\max \{X_{f_i},f_i=0,...,f_c\};$

$f_{\mathrm{mean}}=\frac{\underset{f_i=0}{\overset{f_c}{\mathrm{\Σ}}}{f}_i*X_{f_i}}{\underset{f_i=0}{\overset{f_c}{\mathrm{\Σ}}}{X}_{f_i}};$

$f_{\mathrm{mean}}\left(j\right)=\frac{\underset{f_i=1000*(j-1)}{\overset{1000*j}{\mathrm{\Σ}}}{f}_i*X_{f_i}}{\underset{f_i=1000*(j-1)}{\overset{1000*j}{\mathrm{\Σ}}}{X}_{f_i}}j=\mathrm{1,2},...,[f_s/1000];$

In formula, the frequency f of nighttime sleep acoustical signal after Fast Fourier Transform (FFT) _ithe absolute value of the power spectrum density at place, X _fpeakbe nighttime sleep acoustical signal after Fast Fourier Transform (FFT) in crest frequency frequency f _peakthe absolute value of the power spectrum density at place, f _cbeing cutoff frequency, is sample frequency f _s1/2, [] is bracket function, f _centercentre frequency, f _peakcrest frequency, f _meanbarycenter of frequency spectrum, f _mean(j) (j=1,2 ..., [f _s/ 1000]) be the barycenter of frequency spectrum of each 1000Hz sub-band.

(3) " energy feature " is extracted:

${\mathrm{BER}}_{\left(j\right)}=\frac{\underset{f_i=1000*(j-1)}{\overset{1000*j}{\mathrm{\Σ}}}{X}_{f_i}^2}{\underset{f_i=0}{\overset{f_c}{\mathrm{\Σ}}}{X}_{f_i}^2}j=\mathrm{1,2},...,[f_s/1000];$

In formula, the frequency f of nighttime sleep acoustical signal after Fast Fourier Transform (FFT) _ithe absolute value of the power spectrum density at place, f _cbeing cutoff frequency, is sample frequency f _s1/2, BER (j) (j=1,2 ..., [f _s/ 1000]) be the energy Ratios of each 1000Hz sub-band.

(4) " empirical mode decomposition feature " is extracted:

$E_i={\∫}_{-\∞}^{+\∞}{\left|c_i\left(t\right)\right|}^2\mathrm{dti}=\mathrm{1,2},...,n;$

$T=[E_1/E,E_2/E,...,E_l/E],E=\underset{i=1}{\overset{l}{\mathrm{\Σ}}}{E}_i;$

$H_E=-\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{p}_i{\log }_2{p}_i,p_i=E_i/E;$

In formula, c _i(t), i=1,2, n is the l layer intrinsic mode function that nighttime sleep acoustical signal obtains after empirical mode decomposition, in example, l is taken as 10, (2.Huang N.E. can be tried to achieve by empirical mode decomposition method, Shen Zheng, Long R.S., et al.The empiricalmode decomposition and the Hilbert spectrum for nonlinear andnon-stationary time series analysis [J] .Proc.R.Soc.Lond.A, 1998,454 (1971): 903-995.), E _ibe the energy of i-th layer of intrinsic mode function, T is intrinsic mode function energy Ratios eigenvector, and E is the gross energy of each layer intrinsic mode function, H _eit is intrinsic mode function Energy-Entropy.

3rd step, multiple features building database to extracting: obtain the maximal value of overall each feature of sample, minimum value, average, variance and dynamic range (difference of maxima and minima), the statistic histogram of certain feature is depicted in example, simulate the Kernel function curve of this feature distribution, Kernel function is as follows:

${\hat{f}}_h\left(x\right)=\frac{1}{\mathrm{Ns}}\underset{i=1}{\overset{\mathrm{Ns}}{\mathrm{\Σ}}}{K}_h(x-x_i);$

In formula, K () is Kernel function, selects normal distyribution function in example, and h is Kernel function " bandwidth ", is taken as 1.06 σ Ns in example ^-0.2(σ is the positive square root value of this feature variance), x _i(i=1,2,3 ..., Ns) and by all numerical value of certain feature of nighttime sleep acoustical signal of matching, Ns is the number of nighttime sleep acoustical signal sample.Fig. 3 gives certain feature histogram of nighttime sleep acoustical signal data and the Kernel function curve of matching.

As from the foregoing, method of the present invention can extract the comparatively comprehensive multinomial acoustic feature of nighttime sleep acoustical signal, and makes analysis by the feature distribution situation of analytical approach to nighttime sleep acoustical signal of Corpus--based Method.The person's nighttime sleep acoustical signal multiple features database to be measured risen by method establishment of the present invention can carry out analyzing and research provides basis for follow-up.

Claims (3)

1., based on a nighttime sleep acoustic signal analysis method for multiple features, it is characterized in that, step is as follows:

Step 1, carry out end-point detection to nighttime sleep acoustical signal, namely the nighttime sleep acoustical signal data of first reading microphone records, then become sample by Data Segmentation, and carry out end-point detection to nighttime sleep acoustical signal, by the filtering of " unvoiced segments " data; Carry out end-point detection to nighttime sleep acoustical signal specifically to comprise the following steps:

Step 1-1, carry out sub-frame processing in short-term to nighttime sleep acoustical signal data, " frame length " is 64ms, and " frame moves " is 32ms, and " frame " data are considered as a sample;

Step 1-2, starting point is set to " frame " sequence number n=k of current reading, and pointer j resets;

Step 1-3, utilize formula determine the short-time energy of current reading " frame ";

In formula, k is current reading " frame " sequence number, and the digital signal samples that N comprises for sample is counted, E _kfor the short-time energy of sample, S _kfor digital signal samples amplitude;

Step 1-4, judge E _kwhether be greater than threshold value E _th, if so, perform step 1-5, otherwise current reading " frame " sequence number k is from increasing 1, pointer j from increasing 1 and performing step 1-3;

Step 1-5, judge whether pointer j is greater than interval d, if so, perform step 1-6, otherwise perform step 1-2;

Step 1-6, to determine " abort frame " and " start frame ", wherein " abort frame " sequence number n _stop=n-1, " start frame " sequence number n _initial=n – j – 1;

Step 2, multi-feature extraction is carried out to the nighttime sleep acoustical signal by end-point detection; Be specially:

Step 2-1, each frame of the nighttime sleep acoustical signal fragment by end-point detection is all multiplied by Hamming window function, wherein Hamming window function is:

$w\left(m\right)=0.54-0.46\cos \left(2\mathrm{\π}\frac{m}{M}\right),0\≤m\≤M;$

In formula, M is the sampling number of one " frame " sample;

Step 2-2, all extract " frequecy characteristic " each frame of the nighttime sleep acoustical signal fragment after step 2-1 process, formula used is:

$\underset{f_i=0}{\overset{f_{\mathrm{center}}}{\mathrm{\Σ}}}{X}_{f_i}=\underset{f_i=f_{\mathrm{center}}}{\overset{f_c}{\mathrm{\Σ}}}{X}_{f_i};$

$X_{f_{\mathrm{peak}}}=\max \{X_{f_i},f_i=0,...,f_c\};$

$f_{\mathrm{mean}}=\frac{\underset{f_i=0}{\overset{f_c}{\mathrm{\Σ}}}{f}_i*X_{f_i}}{\underset{f_i=0}{\overset{f_c}{\mathrm{\Σ}}}{X}_{f_i}};$

$f_{\mathrm{mean}}\left(j\right)=\frac{\underset{f_i=1000*(j-1)}{\overset{1000*j}{\mathrm{\Σ}}}{f}_i*X_{f_i}}{\underset{f_i=1000*(j-1)}{\overset{1000*j}{\mathrm{\Σ}}}{X}_{f_i}},j=\mathrm{1,2},...,[f_s/1000];$

In formula, X _fithe frequency f of nighttime sleep acoustical signal after Fast Fourier Transform (FFT) _ithe absolute value of the power spectrum density at place, X _fpeakbe nighttime sleep acoustical signal after Fast Fourier Transform (FFT) in crest frequency frequency f _peakthe absolute value of the power spectrum density at place, f _cbeing cutoff frequency, is sample frequency f _s1/2, [] is bracket function, f _centercentre frequency, f _peakcrest frequency, f _meanbarycenter of frequency spectrum, f _mean(j) (j=1,2 ..., [f _s/ 1000]) be the barycenter of frequency spectrum of each 1000Hz sub-band;

Step 2-3, all extract " energy feature " each frame in the nighttime sleep acoustical signal fragment after step 2-1 process, formula used is:

${\mathrm{BER}}_{\left(j\right)}=\frac{\underset{f_i=1000*(j-1)}{\overset{1000*j}{\mathrm{\Σ}}}{X}_{f_i}^2}{\underset{f_i=0}{\mathrm{\Σ}}{X}_{f_i}^2},j=\mathrm{1,2},...,[f_s/1000];$

In formula, X _fithe frequency f of nighttime sleep acoustical signal after Fast Fourier Transform (FFT) _ithe absolute value of the power spectrum density at place, f _cbeing cutoff frequency, is sample frequency f _s1/2, BER (j) (j=1,2 ..., [f _s/ 1000]) be the energy Ratios of each 1000Hz sub-band;

Step 2-4, all extract " empirical mode decomposition feature " each frame in the nighttime sleep acoustical signal fragment after step 2-1 process, formula used is:

$E_i={\∫}_{-\∞}^{+\∞}{\left|c_i\left(t\right)\right|}^2\mathrm{dt},i=\mathrm{1,2},...,l;$

$T=[E_1/E_2,E_2/E,...,E_l/E],E=\underset{i=1}{\overset{l}{\mathrm{\Σ}}}{E}_i;$

$H_E=-\underset{i=1}{\overset{l}{\mathrm{\Σ}}}{p}_i{\log }_2{p}_i,p_i=E_i/E;$

In formula, c _i(t) (i=1,2 ..., l) be the l layer intrinsic mode function that nighttime sleep acoustical signal obtains after empirical mode decomposition, E _ibe the energy of i-th layer of intrinsic mode function, T is intrinsic mode function energy Ratios eigenvector, and E is the gross energy of each layer intrinsic mode function, H _eit is intrinsic mode function Energy-Entropy;

Step 3, multiple feature building databases that step 2 is extracted, and the distribution of feature is added up.

2. the nighttime sleep acoustic signal analysis method based on multiple features according to claim 1, is characterized in that, the distribution of step 3 pair feature is carried out statistics and comprised: obtain the maximal value of each feature of overall sample, minimum value, average, variance and dynamic range.

3. the nighttime sleep acoustic signal analysis method based on multiple features according to claim 1, is characterized in that, the threshold value E described in step 1-4 _thfor microphone noise substrate E _btwice, in step 1-5, interval d is 3 ~ 4.