CN113049080A - GDWC auditory feature extraction method for ship radiation noise - Google Patents
GDWC auditory feature extraction method for ship radiation noise Download PDFInfo
- Publication number
- CN113049080A CN113049080A CN202110252073.XA CN202110252073A CN113049080A CN 113049080 A CN113049080 A CN 113049080A CN 202110252073 A CN202110252073 A CN 202110252073A CN 113049080 A CN113049080 A CN 113049080A
- Authority
- CN
- China
- Prior art keywords
- auditory
- radiation noise
- ship target
- gamma
- gdwc
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000005855 radiation Effects 0.000 title claims abstract description 70
- 238000000605 extraction Methods 0.000 title claims abstract description 12
- 230000005236 sound signal Effects 0.000 claims abstract description 12
- 210000003477 cochlea Anatomy 0.000 claims abstract description 8
- 210000000721 basilar membrane Anatomy 0.000 claims abstract description 7
- 210000005069 ears Anatomy 0.000 claims abstract description 7
- 238000001228 spectrum Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 11
- 239000013598 vector Substances 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000005316 response function Methods 0.000 claims description 7
- 238000007906 compression Methods 0.000 claims description 6
- 230000006835 compression Effects 0.000 claims description 6
- 238000009432 framing Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 230000035807 sensation Effects 0.000 claims description 2
- 238000000034 method Methods 0.000 abstract description 16
- 230000000694 effects Effects 0.000 abstract description 8
- 230000008569 process Effects 0.000 abstract description 5
- 238000012545 processing Methods 0.000 abstract description 5
- 230000009466 transformation Effects 0.000 abstract description 5
- 238000001914 filtration Methods 0.000 abstract description 3
- 238000004088 simulation Methods 0.000 abstract description 3
- 210000002469 basement membrane Anatomy 0.000 abstract 1
- 238000004458 analytical method Methods 0.000 description 12
- 230000003595 spectral effect Effects 0.000 description 8
- 230000008447 perception Effects 0.000 description 7
- 238000011160 research Methods 0.000 description 4
- 230000033764 rhythmic process Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 241000251729 Elasmobranchii Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000013332 literature search Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 210000004379 membrane Anatomy 0.000 description 1
- 239000012528 membrane Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000013535 sea water Substances 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H3/00—Measuring characteristics of vibrations by using a detector in a fluid
- G01H3/10—Amplitude; Power
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Soundproofing, Sound Blocking, And Sound Damping (AREA)
Abstract
The invention relates to a GDWC auditory feature extraction method for ship target radiation noise, which simulates the frequency selection characteristic of a human ear cochlea basement membrane to sound signals by analyzing the processing process of simulating human ears to sound and selecting a Gamma atone auditory filter bank, and reserves local detail features by combining discrete wavelet transformation, thereby providing a ship target radiation noise identification method based on the GDWC auditory feature. Compared with the Mel auditory filter bank used for MFCC auditory features, the Gamma auditory filter bank used for GDWC auditory features has better simulation effect on the nonlinear frequency filtering characteristic of the basilar membrane of the cochlea of the human ear. The GDWC auditory characteristics have very good recognition effects on different ship targets and excellent noise interference resistance, and can exert very important application values in practical situations.
Description
Technical Field
The invention belongs to the field of ship noise feature extraction, and particularly relates to a GDWC auditory feature extraction method for ship target radiation noise.
Background
Due to the continuous improvement of demands of offshore defense and anti-submarine battles, the technology for quickly and effectively identifying different ship targets in the ocean by extracting effective characteristics of ship target radiation noise becomes a key technology in the underwater sound field, is greatly related to the survival and the formulation of technical and tactics of naval ships of our country, and is also a key way for realizing the intelligent and modern development of underwater weapon systems.
When the ship target navigates in the ocean, noise will inevitably radiate to the surroundings uninterruptedly due to the motion of the ship target and the operation of mechanical devices, and random noise will be generated by the interaction between the ship target and the seawater. The types, navigational speeds and tonnages of ship targets in the ocean are different, the complexity of respective mechanical structures is different to a greater or lesser extent, and the differences cause differences of radiation noise in time domain, frequency domain and the like to a certain extent.
The sound signal is used as a mechanical longitudinal wave, the signal attenuation of underwater transmission is much smaller than that of electromagnetic waves, the transmission distance is far longer, the propagation distance can reach hundreds of meters or even dozens of kilometers, and the method for identifying different targets by using ship radiation noise can identify ship targets on the water surface and can also identify targets such as underwater submarines, torpedoes and the like. The key to ship target identification is to extract effective characteristics capable of accurately distinguishing radiation noise of different ship targets.
The radiation noise of the underwater ship target is complex and changeable, and the acoustic characteristics of the underwater ship target are also various. Therefore, in order to obtain stable and effective characteristics of the radiation noise of the ship target in an actual marine combat environment for a long time, a sonar soldier is often required to further identify different ship targets according to the acoustic characteristics of the radiation noise of the ship target, such as rhythm, fluctuation, tone and the like.
The auditory system of the human ear has a phenomenon of "cocktail party", that is, the auditory system of the human ear still can not be interfered by other noise sources in a very loud environment, so that the auditory system can effectively track and concentrate on a certain interested sound. This is a unique ability of the human ear during long-term evolution. In many cases, the auditory system of the human ear has such an excellent voice recognition effect that the existing machine recognition method cannot achieve. In the process of modeling the auditory perception mechanism of the underwater sound target, the research on the filter bank of the nonlinear human ear-like cochlea basal membrane is an important key technology, and the research provides great help for the identification of the underwater sound target, particularly the identification of the radiation noise of the ship target.
In the existing literature and research, the commonly used methods for extracting the radiation noise characteristics of the ship target are LOFAR spectral characteristic analysis, DEMON spectral characteristic analysis and an isochronous frequency analysis method. In part of methods for extracting the radiation noise characteristics of the ship target by using an auditory model, MFCC auditory characteristics of the radiation noise of the ship target are adopted, and a Mel auditory filter bank is used for simulating the auditory perception characteristics of human ears.
The currently common methods include LOFAR spectral feature analysis, DEMON spectral feature analysis, MFCC feature analysis and the like. Qi shao Ling, Congregate Yuyu, and the like of Shanghai university of transportation published a paper Lofar spectrogram characteristic principal component analysis research of underwater target signals in journal of data acquisition and processing, and provides a characteristic processing method of ship target radiation noise signals by combining LOFAR spectrogram characteristics and principal component analysis. The Bin and Luo Xin of the university of southeast have proposed a broadband demodulation method based on modulation frequency band compensation in the acoustic society of acoustics in China of 2019, thereby improving the quality of DEMON spectra and improving the performance of DEMON spectral analysis.
However, the identification rate of the conventional time-frequency analysis methods such as common LOFAR spectral feature analysis and DEMON spectral feature analysis is low, and a sonar soldier is still required to further identify different ship targets according to the acoustic features such as rhythm, fluctuation and tone of the radiation noise of the ship targets.
Specifically, the prior art has the following defects:
1. the conventional time-frequency analysis methods such as common LOFAR spectral feature analysis, DEMON spectral feature analysis and the like have low recognition rate, and often require a sonar soldier to further recognize different ship targets according to the acoustic features such as rhythm, fluctuation, tone and the like of the radiation noise of the ship targets.
The Mel auditory filter bank used for MFCC auditory features is composed of a series of triangular band-pass filters distributed at equal intervals on Mel scale, and has a general simulation effect on frequency selective characteristics of cochlear basilar membrane in human auditory system to sound signals.
MFCC auditory characteristics can only reflect the static characteristics of the ship target radiated noise, and lack the description of the dynamically changing characteristics of the ship target radiated noise.
Gammatone auditory filter bank: the Gamma atom auditory filter bank is a simpler human ear auditory system filter model, can well simulate the frequency selection characteristic of a human ear cochlea basilar membrane and accords with the perception characteristic of the human ear auditory system to sound signals.
GDWC auditory features: the Gamma atom Discrete Wavelet Coefficient (GDWC) combines the Gamma atom auditory filter bank with the Discrete Wavelet Transform (DWT), which not only can effectively simulate the perception process of the human auditory system to sound signals, but also can keep the local transformation detail characteristics of the original ship target radiation noise.
Disclosure of Invention
The technical problem solved by the invention is as follows: in order to solve the problem that the existing technology ignores acoustic features of ship radiation noise and dynamic local transformation details, which results in low recognition rate of different ship targets in practical application, the invention provides a GDWC acoustic feature extraction method of ship target radiation noise.
The technical scheme of the invention is as follows: a GDWC auditory feature extraction method for ship target radiation noise comprises the following steps:
step 1: extracting radiation noise on a ship target, and converting the radiation noise through an analog-to-digital converter to obtain a radiation noise sequence x (n);
step 2: preprocessing the radiation noise sequence x (n) obtained in the step 1 to obtain an output sequence y (n) of a preprocessed ship target radiation noise signal;
and step 3: performing short-time Fourier transform on the output sequence y (n) obtained in the step 2 to obtain a ship target radiation noise power spectrum p (f) | Y (k) & gt2Wherein:
wherein: k represents 0. ltoreq. k. ltoreq.N-1; y (k) represents a spectrum of the ship target radiated noise;
and 4, step 4: simulating the frequency selection characteristic of the basilar membrane of the cochlea of the human ear to the sound signal by the power spectrum of the ship target radiation noise obtained in the step 3 through a Gamma tone auditory filter bank to obtain the energy output by the Gamma tone auditory filter;
E(m)＝∑p(f)·GTm(f)
wherein M represents the ordinal number of the Gamma auditory filter, M is 0, 1, 2, …, M-1; e (m) represents the energy output by the mth Gamma auditory filter; GT systemm(f) The frequency response transfer function of the mth Gamma filter is represented and obtained by carrying out Fourier transform on the impulse response function of the Gamma auditory filter bank;
and 5: and (4) carrying out logarithmic compression on the energy output by the Gamma auditory filter obtained in the step (4), and fitting a nonlinear relation between the sound intensity and the auditory sensation of the human ears:
S(m)＝ln(E(m))
wherein S (m) represents a Gamma atom energy spectrum of the ship target radiation noise after logarithmic compression;
step 6: performing discrete wavelet transform on the nonlinear relation obtained in the step 5 to finally obtain a GDWC auditory characteristic vector of the ship target radiation noise:
G(n)＝DWT(S(m))。
the further technical scheme of the invention is as follows: the preprocessing in the step 2 comprises the following substeps:
step 2.1: framing and pre-emphasizing a ship target radiation noise sequence x (n), and reserving 40-50% of an overlapped part between two adjacent frames;
step 2.2: and windowing each frame of radiation noise sequence.
The further technical scheme of the invention is as follows: the window function used in step 2.2 is a hamming window, and the mathematical expression is:
y(n)＝x(n)×w(n)
in the formula: n is more than or equal to 0 and less than or equal to N-1, and N is the length of the Hamming window; w (n) denotes a Hamming window coefficient; x (n) represents an input ship target radiated noise sequence; and y (n) represents an output sequence of the ship target radiation noise signal after preprocessing.
The further technical scheme of the invention is as follows: GT in the step 4m(f) The expression is as follows:
GTm(f)＝FFT(gm(t))，
wherein g ism(t) is the impulse response function of the mth Gamma auditory filter bank, expressed as:
gm(t)＝Bm ntn-1exp(-2πBt)·cos(2πfcmt+φm)·u(t)
in the formula: f. ofcmExpressed as the center frequency of the mth gamma hearing filter; phi is amExpressed as the initial phase of the mth gamma hearing filter; u (t) is expressed as a step function when t<When 0, u (t) is 0, and when t>At 0 time，u(t)＝1；BmRepresenting the bandwidth of the mth Gammatone auditory filter.
The further technical scheme of the invention is as follows: b ismThe following equation is used to obtain:
effects of the invention
The invention has the technical effects that: the method combines a Gamma atone auditory filter bank and discrete wavelet transform to simulate the auditory perception process of human ears, extracts the GDWC auditory characteristics of the ship target radiation noise by simulating the auditory perception process of human ears, has excellent anti-noise recognition capability on the GDWC auditory characteristics provided by the patent to the ship target radiation noise, and has the following specific beneficial effects compared with the prior art:
the Gammatone auditory filterbank better simulates the nonlinear filtering characteristics of the basilar membrane of the cochlea of the human ear than the triangular bandpass filters of the mel auditory filterbank.
The GDWC auditory characteristics are combined with discrete wavelet transformation, and the acoustic characteristics of the ship target radiation noise are represented while the acoustic characteristics are enabled to have excellent localization characteristics.
3. Compared with MFCC hearing characteristics, GDWC hearing characteristics have better capability of resisting noise interference, and the simulation effect of the cocktail party effect on the human auditory system is very excellent.
And 4, the physical realization of the Gamma atom auditory filter bank is simple, so that the calculated amount for extracting the GDWC auditory characteristics of the ship target radiation noise is small, and the Gamma atom auditory filter bank has important practical application value.
Drawings
FIG. 1 is a flow chart of the method
FIG. 2 is the GDWC eigenvector of the radiated noise of cargo ship No. 1
Figure 3 is the GDWC eigenvector of No. 2 tanker radiated noise
Detailed Description
Referring to fig. 1-3, the method includes the steps of:
(1) pre-processing operations such as pre-emphasis, framing, and windowing. The sound signal has the time-varying characteristic and is relatively stable within 10-30 ms. Therefore, the method divides the radiation noise of the ship target into frames, and reserves 40-50% of overlapping part between two adjacent frames so as to reserve dynamic change information of the radiation noise signal of the ship target as much as possible. In addition, the windowing processing is carried out on each frame of radiation noise signal, so that the continuity between the left end and the right end of each frame of signal can be guaranteed, the window function used in the patent is a Hamming (Hamming) window, and the mathematical expression of the window function is as follows:
y(n)＝x(n)×w(n) (2)
in the formula:
n is more than or equal to N and less than or equal to N-1, and N is the length of the Hamming window;
w (n) -Hamming window coefficients;
x (n) -input vessel target radiated noise sequence;
y (n) -the output signal of the ship target radiation noise signal after pretreatment.
(2) And obtaining a ship target radiation noise power spectrum through Short-Time Fourier Transform (STFT).
p(f)＝|Y(k)|2 (4)
In the formula:
k——0≤k≤N-1；
y (k) -the frequency spectrum of the ship target radiated noise;
p (f) -power spectrum of ship target radiation noise.
(3) The frequency selective characteristic of the basilar membrane of the cochlea of the human ear to the sound signal is simulated through a Gamma atom auditory filter bank.
E(m)＝∑p(f)·GTm(f) (5)
In the formula:
m-the ordinal number of the Gammatone auditory filter, M ═ 0, 1, 2, …, M-1;
e (m) -the energy output by the mth Gamma auditory filter;
GTm(f) the frequency response transfer function of the mth gamma filter can be obtained by fourier transforming the impulse response function of the gamma auditory filter bank.
GTm(f)＝FFT(gm(t)) (6)
Wherein, gm(t) is the impulse response function of the mth Gamma auditory filter bank, which can be described by the causal impulse response function in equation (7), and can be considered as being synthesized by the Gamma function and the single-frequency sound signal:
gm(t)＝Bm ntn-1 exp(-2πBt)·cos(2πfcmt+φm)·u(t) (7)
in the formula:
fcm-center frequency of mth Gammatone auditory filter;
φm-initial phase of mth gamma hearing filter;
u (t) -step function, when t <0, u (t) is 0, and when t >0, u (t) is 1;
Bm-the bandwidth of the mth gamma hearing filter, which can be obtained by equation (8):
(4) the output energy of the Gamma auditory filter bank is logarithmically compressed through nonlinear transformation so as to fit the nonlinear relation between the sound intensity and the auditory perception of human ears on the objective physiology of sound.
S(m)＝ln(E(m)) (9)
In the formula:
s (m) -Gamma energy spectrum of the ship target radiation noise after logarithmic compression.
(5) The interference of background noise to the extracted auditory sense is reduced by discrete wavelet transform and local details in the original sound signal can be preserved.
G(n)＝DWT(S(m)) (10)
In the formula:
g (n) -GDWC auditory feature vector of ship target radiation noise.
The technical content of the present invention is further explained below with reference to a specific embodiment.
2 groups of ship target radiation noise data actually collected in the ocean test are selected, and specific relevant information of the 2 groups of data is shown in table 1.
TABLE 1 relevant information of actually measured ship target radiation noise
According to the flow of extracting the GDWC auditory feature vector of the ship target radiation noise, a Hamming window is added to each group of input ship target radiation noise, the Hamming window is divided into sound segments with the length of 0.2s, the power spectrum of each frame of sound signal is obtained through short-time Fourier transform, then after filtering processing of a Gamma tone auditory filter bank, logarithmic compression and discrete wavelet transform processing are carried out on the output energy of a filter, and therefore the GDWC auditory feature vectors of the 2 groups of ship target radiation noise can be respectively extracted, as shown in fig. 1 and fig. 2. In this example, the gamma-atom auditory filter bank used should consist of 23 individual 4-order gamma-atom filters, depending on the sampling frequency at which the ship target radiated noise is acquired.
As can be seen from fig. 1 and fig. 2, the GDWC acoustic feature vectors of the samples of the same group of ship target radiation noise have the same variation trend along with the increase of the dimension, and the distances of the GDWC acoustic feature vectors of the samples in the group are close, so that the similarity is high; however, the distances of the GDWC auditory characteristics of the two groups of ship target radiation noises are far away, and the similarity is low. This demonstrates that the GDWC acoustic feature vectors of the ship target radiated noise have the ability to identify different ship targets.
Claims (5)
1. A GDWC auditory feature extraction method of ship target radiation noise is characterized by comprising the following steps:
step 1: extracting radiation noise on a ship target, and converting the radiation noise through an analog-to-digital converter to obtain a radiation noise sequence x (n);
step 2: preprocessing the radiation noise sequence x (n) obtained in the step 1 to obtain an output sequence y (n) of a preprocessed ship target radiation noise signal;
and step 3: performing short-time Fourier transform on the output sequence y (n) obtained in the step 2 to obtain a ship target radiation noise power spectrum p (f) | Y (k) & gt2Wherein:
wherein: k represents 0. ltoreq. k. ltoreq.N-1; y (k) represents a spectrum of the ship target radiated noise;
and 4, step 4: simulating the frequency selection characteristic of the basilar membrane of the cochlea of the human ear to the sound signal by the power spectrum of the ship target radiation noise obtained in the step 3 through a Gamma tone auditory filter bank to obtain the energy output by the Gamma tone auditory filter;
E(m)＝∑p(f)·GTm(f)
wherein M represents the ordinal number of the Gamma auditory filter, M is 0, 1, 2, …, M-1; e (m) represents the energy output by the mth Gamma auditory filter; GT systemm(f) The frequency response transfer function of the mth Gamma filter is represented and obtained by carrying out Fourier transform on the impulse response function of the Gamma auditory filter bank;
and 5: and (4) carrying out logarithmic compression on the energy output by the Gamma auditory filter obtained in the step (4), and fitting a nonlinear relation between the sound intensity and the auditory sensation of the human ears:
S(m)＝ln(E(m))
wherein S (m) represents a Gamma atom energy spectrum of the ship target radiation noise after logarithmic compression;
step 6: performing discrete wavelet transform on the nonlinear relation obtained in the step 5 to finally obtain a GDWC auditory characteristic vector of the ship target radiation noise:
G(n)＝DWT(S(m))。
2. the GDWC auditory feature extraction method for the ship target radiation noise as claimed in claim 1, wherein the preprocessing in step 2 includes the following sub-steps:
step 2.1: framing and pre-emphasizing a ship target radiation noise sequence x (n), and reserving 40-50% of an overlapped part between two adjacent frames;
step 2.2: and windowing each frame of radiation noise sequence.
3. The GDWC auditory feature extraction method for ship target radiated noise according to claim 2, wherein the window function used in step 2.2 is a hamming window, and the mathematical expression is:
y(n)＝x(n)×w(n)
in the formula: n is more than or equal to 0 and less than or equal to N-1, and N is the length of the Hamming window; w (n) denotes a Hamming window coefficient; x (n) represents an input ship target radiated noise sequence; and y (n) represents an output sequence of the ship target radiation noise signal after preprocessing.
4. The GDWC auditory feature extraction method for ship target radiation noise as claimed in claim 1, wherein GT in step 4 ism(f) The expression is as follows:
GTm(f)＝FFT(gm(t))，
wherein g ism(t) impact of mth Gamma auditory filter bankA response function, expressed as:
gm(t)＝Bm ntn-1exp(-2πBt)·cos(2πfcmt+φm)·u(t)
in the formula: f. ofcmExpressed as the center frequency of the mth gamma hearing filter; phi is amExpressed as the initial phase of the mth gamma hearing filter; u (t) is expressed as a step function when t<When 0, u (t) is 0, and when t>At 0, u (t) is 1; b ismRepresenting the bandwidth of the mth Gammatone auditory filter.
5. The GDWC auditory feature extraction method for ship target radiation noise of claim 4, wherein B ismThe following equation is used to obtain:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110252073.XA CN113049080A (en) | 2021-03-08 | 2021-03-08 | GDWC auditory feature extraction method for ship radiation noise |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110252073.XA CN113049080A (en) | 2021-03-08 | 2021-03-08 | GDWC auditory feature extraction method for ship radiation noise |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113049080A true CN113049080A (en) | 2021-06-29 |
Family
ID=76510332
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110252073.XA Pending CN113049080A (en) | 2021-03-08 | 2021-03-08 | GDWC auditory feature extraction method for ship radiation noise |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113049080A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114036650A (en) * | 2022-01-07 | 2022-02-11 | 中国空气动力研究与发展中心计算空气动力研究所 | Reverse design method of non-axisymmetrical natural laminar flow nacelle and natural laminar flow nacelle |
| CN115451877A (en) * | 2022-09-29 | 2022-12-09 | 天津大学 | Supersonic separator droplet deposition amount and deposition position acoustic prediction method |
| CN115950517A (en) * | 2023-03-02 | 2023-04-11 | 南京大学 | Configurable underwater acoustic signal feature extraction method and device |
| CN116973901A (en) * | 2023-09-14 | 2023-10-31 | 海底鹰深海科技股份有限公司 | Algorithm application of time-frequency analysis in sonar signal processing |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102645265A (en) * | 2012-03-21 | 2012-08-22 | 西北工业大学 | Ship radiated noise level measuring method based on virtual time reversal mirror |
| CN103559893A (en) * | 2013-10-17 | 2014-02-05 | 西北工业大学 | Gammachirp cepstrum coefficient auditory feature extraction method of underwater targets |
| CN103557925A (en) * | 2013-10-17 | 2014-02-05 | 西北工业大学 | Underwater target gammatone discrete wavelet coefficient auditory feature extraction method |
| BR102015017870A2 (en) * | 2015-07-27 | 2017-11-07 | Universidade Federal De Pernambuco - Ufpe | METHOD FOR COMPUTING THE DCT SPECTRUM FOR ACCUMULATED AND / OR MEDIUM NULL SIGNS |
| CN111462766A (en) * | 2020-04-09 | 2020-07-28 | 浙江大学 | Auditory pulse coding method and system based on sparse coding |
-
2021
- 2021-03-08 CN CN202110252073.XA patent/CN113049080A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102645265A (en) * | 2012-03-21 | 2012-08-22 | 西北工业大学 | Ship radiated noise level measuring method based on virtual time reversal mirror |
| CN103559893A (en) * | 2013-10-17 | 2014-02-05 | 西北工业大学 | Gammachirp cepstrum coefficient auditory feature extraction method of underwater targets |
| CN103557925A (en) * | 2013-10-17 | 2014-02-05 | 西北工业大学 | Underwater target gammatone discrete wavelet coefficient auditory feature extraction method |
| BR102015017870A2 (en) * | 2015-07-27 | 2017-11-07 | Universidade Federal De Pernambuco - Ufpe | METHOD FOR COMPUTING THE DCT SPECTRUM FOR ACCUMULATED AND / OR MEDIUM NULL SIGNS |
| CN111462766A (en) * | 2020-04-09 | 2020-07-28 | 浙江大学 | Auditory pulse coding method and system based on sparse coding |
Non-Patent Citations (6)
| Title |
|---|
| WEIXIN SON 等: "Feature extraction and classification of ship targets based on gammatone filter bank", 《2021 ICSPCC》, pages 4 * |
| 吴姚振: "水下目标辐射噪声生理感知特征的提取方法研究", 《中国博士学位论文全文数据库信息科技辑》, no. 7, pages 1136 - 17 * |
| 吴姚振: "水下目标辐射噪声生理感知特征的提取方法研究", 中国博士学位论文全文数据库信息科技辑》, no. 7, pages 1136 - 17 * |
| 张小蓟 等: "基于经验模态分解的目标特征提取与选择", 《西北工业大学学报》, no. 4, pages 453 - 456 * |
| 李聪 等: "非线性幂变换Gammachirp 滤波器的鲁棒语音特征提取", 《计算机科学与探索》, vol. 13, no. 8, pages 1351 - 1359 * |
| 杨峰: "现代多目标跟踪与多传感器融合关键技术研究", 《中国博士学位论文全文数据库信息科技辑》, no. 4, pages 1136 - 37 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114036650A (en) * | 2022-01-07 | 2022-02-11 | 中国空气动力研究与发展中心计算空气动力研究所 | Reverse design method of non-axisymmetrical natural laminar flow nacelle and natural laminar flow nacelle |
| CN115451877A (en) * | 2022-09-29 | 2022-12-09 | 天津大学 | Supersonic separator droplet deposition amount and deposition position acoustic prediction method |
| CN115950517A (en) * | 2023-03-02 | 2023-04-11 | 南京大学 | Configurable underwater acoustic signal feature extraction method and device |
| CN116973901A (en) * | 2023-09-14 | 2023-10-31 | 海底鹰深海科技股份有限公司 | Algorithm application of time-frequency analysis in sonar signal processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113049080A (en) | GDWC auditory feature extraction method for ship radiation noise | |
| Vaseghi | Multimedia signal processing: theory and applications in speech, music and communications | |
| CN109815942B (en) | Method for extracting normal wave features based on marine environment noise signals | |
| Wang et al. | Feature extraction of underwater target in auditory sensation area based on MFCC | |
| Branstetter et al. | Auditory masking patterns in bottlenose dolphins (Tursiops truncatus) with natural, anthropogenic, and synthesized noise | |
| Wang et al. | ia-PNCC: Noise Processing Method for Underwater Target Recognition Convolutional Neural Network. | |
| Wang et al. | Deep learning assisted time-frequency processing for speech enhancement on drones | |
| CN113077813B (en) | Ship noise identification method based on holographic spectrum and deep learning | |
| CN103557925B (en) | Underwater target gammatone discrete wavelet coefficient auditory feature extraction method | |
| CN103559893B (en) | One is target gammachirp cepstrum coefficient aural signature extracting method under water | |
| Lian et al. | Underwater acoustic target recognition based on gammatone filterbank and instantaneous frequency | |
| CN109215635B (en) | Broadband voice frequency spectrum gradient characteristic parameter reconstruction method for voice definition enhancement | |
| Guo et al. | Underwater target detection and localization with feature map and CNN-based classification | |
| Feroze et al. | Classification of underwater acoustic signals using multi-classifiers | |
| CN116417011A (en) | Underwater sound target identification method based on feature fusion and residual CNN | |
| Lian et al. | Feature extraction of underwater acoustic target signals using gammatone filterbank and subband instantaneous frequency | |
| Sonz et al. | Feature extraction and classification of ship targets based on gammatone filter bank | |
| Korany | Application of wavelet transform for classification of underwater acoustic signals | |
| Wu et al. | Robust target feature extraction based on modified cochlear filter analysis model | |
| Mansour et al. | Blind separation of underwater acoustic signals | |
| Padmapriya et al. | Voice extraction from background noise using filter bank analysis for voice communication applications | |
| Wang et al. | Underwater acoustic target recognition combining multi-scale features and attention mechanism | |
| Petrick et al. | Robust front end processing for speech recognition in reverberant environments: Utilization of speech characteristics | |
| CN118191805A (en) | Pulse signal reconstruction method in broadband continuous interference | |
| Du et al. | Classification Method for Ship-Radiated Noise Based on Joint Feature Extraction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210629 |