CN107368840A - A kind of underwater manoeuvre Small object recognition methods based on MFCC and SVMs - Google Patents
A kind of underwater manoeuvre Small object recognition methods based on MFCC and SVMs Download PDFInfo
- Publication number
- CN107368840A CN107368840A CN201610308104.8A CN201610308104A CN107368840A CN 107368840 A CN107368840 A CN 107368840A CN 201610308104 A CN201610308104 A CN 201610308104A CN 107368840 A CN107368840 A CN 107368840A
- Authority
- CN
- China
- Prior art keywords
- mrow
- mfcc
- characteristic quantities
- svms
- domain signal
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
Abstract
The invention provides a kind of underwater manoeuvre Small object recognition methods based on MFCC and SVMs, methods described includes：The original sound signal s (n) of target to be identified is pre-processed, obtains the time-domain signal x (n) of each speech frame；Extract time-domain signal x (n) MFCC characteristic quantities, difference MFCC characteristic quantities are obtained using MFCC characteristic quantities, the crest frequency of MFCC characteristic quantities, difference MFCC characteristic quantities and time-domain signal x (n) is combined, form MFCC composite character amounts, the MFCC composite characters vector is input to the support vector machine classifier trained to be identified, exports the type of identification.The apish auditory properties of MFCC composite characters of the method extraction of the present invention, the outstanding sound signal processing ability of human ear is effectively applied to the classification of underwater manoeuvre Small object；The interframe feature of signal is make use of simultaneously, reduces error caused by ambient noise；When carrying out target classification to MFCC composite characters using SVMs, the problems such as can largely overcoming " dimension disaster " and " cross study ".
Description
Technical field
The present invention relates to the identification field of underwater Small object, and in particular to a kind of underwater based on MFCC and SVMs
Small maneuvering target recognition methods.
Background technology
Cold War period, various countries are in the war state of alert, and sea detection and the object defendd are mainly the warship of hostile nations
The large-scale target such as ship and submarine.After the end of cold war, particularly the Soviet Union's dissolution, Underwater Battery equipment minimizes rapid
Development, the technical equipment such as frogman, underwater research vehicle and underwater robot it is increasingly mature, this kind of target has good concealment, breaks
Bad power waits by force the attack pattern of obvious " asymmetric " advantage, it has also become terrorist carries out the important way of terrorist activity.
In recent years, wait the detection to the underwater Small object such as frogman and identification to carry out correlative study both at home and abroad, but be directed to water
The Classification and Identification of lower small maneuvering target is less.The torpedo homing system of many foreign navies, has also had been provided with identification ship now
The ability of oceangoing ship critical position.Document [1] (Wu state, Li Jing, Li Xunhao, Chen Yaoming, Yuan Yi ship noises identification (III)-dual
The feature extraction of spectrum and average power spectra and Prototype drawing acoustic journals, 1999,24 (2):191-196 pages；Wu Guoqing, Li Jing, Lee
Instruction method, Chen Yaoming, Yuan Yi ship noises identification (IV)-fuzzy neural network acoustic journals, 1999,24 (3):275-280
Page) substantial amounts of research has been carried out to the radiated noise on naval vessel, it is extracted numerous features of ship-radiated noise, and using counting mould
Ship noise is identified the mode that formula is identified and fuzzy neural network is combined.Document [2] (LI Qihu, WANG
Jinlin,WEI Wei.An application of expert system in recognition of radiated
noise of under-water target.Beijing:Institute of Acoustics,Chinese Academy of
Sciences, 1989.404-408) Acoustic Object expert's identifying system is have developed, in most cases, when signal to noise ratio is not less than
During 3dB, the discrimination of signal has exceeded 75%.
In field of underwater acoustic signal processing, currently used method is that time-domain signal is transformed into time-frequency combination domain, when passing through
The non-stationary and frequency that frequency Joint Distribution discloses signal changes with time feature.This patent is used for reference largely to be made in speech recognition
Mel cepstrum coefficients (MFCC) extracting method, MFCC feature extracting methods are applied in Underwater Targets Recognition.Document [3]
(application [J] the acoustic techniques of stone supermale based on the MFCC of lifting wavelet transform in target identification, 2014,33 (4):372-
375.) method for proposing the MFCC using lifting wavelet transform, to underwater passive sonar target classification and identification.It emulates real
Test and show, lifting wavelet transform method extraction MFCC has the advantages of discrimination is higher, preferable to noise robustness.Document [4]
(Zhu Leqing, insect sound automatic identification [J] the insect journals of true based on MFCC and GMM, 2012,55 (4):466-471.)
MFCC and gauss hybrid models (GMM) are applied to the identification of insect in forest, in the Sample Storehouse comprising 58 kinds of insect sound
Assessed, achieve higher correct recognition rata and comparatively ideal time performance.These researchs show the side based on MFCC
The voice signal property extraction identification that method can be used under complex situations.It is general to be currently based on recognition methods of the MFCC to submarine target
It is low all over noise immunity, more situations higher applied to signal to noise ratio, therefore for current signal to noise ratio is relatively low, plurality of target coexists complexity
The Small object discrimination of underwater environment is relatively low.
SVMs is that one kind that the V.Vapnik in AT＆T Bell laboratories et al. proposes according to Statistical Learning Theory is new
Machine learning method, obtained preferable effect in pattern-recognition, regression analysis and feature selecting etc..Due to it
Establish on empirical risk minimization, rather than empiric risk is reached minimum, so that supporting vector point
Appliances have preferable Generalization Ability.Grader uses SVMs, takes full advantage of the generalization ability of SVMs, keeps away
Exempted from some defects of neutral net, as network structure determine there is no clear and definite rule, can not ensure to converge to globe optimum.
The content of the invention
It is underwater it is an object of the invention to overcome current MFCC methods to be used for the complexity that signal to noise ratio is relatively low, plurality of target coexists
A kind of the problem of discrimination existing for the Small object identification of environment is relatively low, it is proposed that underwater machine based on MFCC and SVMs
Dynamic Small object recognition methods, this method extract the mixing MFCC characteristic quantities of target audio signal, including：Difference MFCC features and
MFCC features；Then the mixing MFCC characteristic quantities of extraction are identified using SVMs, experimental data shows the present invention
The recognition methods of proposition has higher object recognition rate.
To achieve these goals, the present invention proposes a kind of underwater manoeuvre Small object based on MFCC and SVMs
Recognition methods, methods described include：The original sound signal s (n) of target to be identified is pre-processed, obtains each speech frame
Time-domain signal x (n)；Time-domain signal x (n) MFCC characteristic quantities are extracted, difference MFCC characteristic quantities are obtained using MFCC characteristic quantities,
The crest frequency of MFCC characteristic quantities, difference MFCC characteristic quantities and time-domain signal x (n) is combined, forms MFCC composite characters
Amount, the MFCC composite characters vector is input to the support vector machine classifier trained and is identified, export the class of identification
Type.
In above-mentioned technical proposal, methods described specifically includes：
Step 1) pre-processes to the original sound signal s (n) of target to be identified, obtains the time domain letter of each speech frame
Number x (n)；
Step 2) calculates time-domain signal x (n) 2K MFCC coefficient, and the MFCC coefficients of even number position are formed into MFCC spies
Sign amount；
Step 3) carries out Further Feature Extraction to 2K MFCC coefficient, calculates 2K difference MFCC coefficient, and by even bit
The MFCC coefficients put form difference MFCC characteristic quantities；
Step 4) calculates time-domain signal x (n) crest frequency f；
MFCC characteristic quantities, difference MFCC characteristic quantities and crest frequency f are combined by step 5), form MFCC composite characters
Amount；
The MFCC composite characters vector is input to the support vector machine classifier trained and is identified by step 6), directly
To identifying the type that successfully, exports identification.
In above-mentioned technical proposal, the step 2) specifically includes：
Time-domain signal x (n) is obtained linear spectral X (k) by step 201) after discrete Fourier transform：
Wherein, N is the points for representing Fourier transformation；
Step 202) calculates linear spectral X (k) energy spectrum, and band logical filter is carried out to energy spectrum by 2K bandpass filter
Ripple；
Step 203) calculates the logarithmic energy that each bandpass filter group exports：
Step 204) carries out discrete cosine transform to the logarithmic energy S (m) of output and obtains MFCC coefficients：
Step 205) time-domain signal x (n) MFCC characteristic quantities are：[C(2),C(4),...,C(2K)].
In above-mentioned technical proposal, the specific implementation process of the step 3) is：
The computational methods of difference MFCC coefficients are：
Wherein, k is constant, k=2；
Difference MFCC characteristic quantities are：[d(2),d(4),...d(2K)].
In above-mentioned technical proposal, the MFCC composite character amounts in the step 5) are：
[C(2),C(4),...,C(2K),d(2),d(4),...,d(2K),f]
Its dimension is 2K+1.
In above-mentioned technical proposal, also include before the step 6)：Training Support Vector Machines grader；Specifically include:
Step S1) training sample is classified；
Step S2) pretreatment is carried out to training sample form time-domain signal；
Step S3) using each training sample time-domain signal as x (t), according to step 1), step 2), step 3), step 4)
The MFCC composite characters vector of the time-domain signal of each training sample is built with step 5)；
Step S4) using the MFCC composite characters vector of all training samples as the input of SVMs, train branch
Hold vector machine classifier.
In above-mentioned technical proposal, the support vector machine classifier is the SVMs based on decision-making directed acyclic graph；
When the number of types of identification is m, the support vector machine classifier needs to construct m (m-1)/2 one-against-one device.
The advantage of the invention is that：
1st, the apish auditory properties of MFCC composite characters of method of the invention extraction, by the outstanding voice signal of human ear
Disposal ability is effectively applied to the classification of underwater manoeuvre Small object；The interframe feature of signal is make use of simultaneously, is reduced environment and is made an uproar
Error caused by sound；When carrying out target classification to MFCC composite characters using SVMs, supporting vector can be made full use of
The advantages that machine outstanding learning ability and fault-tolerant ability, and be largely overcoming " dimension disaster " and " cross and learn " etc. and asked
Topic；
2nd, recognition methods proposed by the present invention designs specially for the underwater environment that a variety of small maneuvering targets coexist, due to underwater ring
The complexity in border, but every kind of target has its distinctive frequency distribution, therefore frequency domain character is also a kind of important spy of target
Sign, frequency domain character addition MFCC characteristic vectors can be taken full advantage of into signal frequency domain feature.
Brief description of the drawings
Fig. 1 is the flow chart of the underwater Small object recognition methods based on MFCC and SVMs of the present invention；；
Fig. 2 is the DAGSVM structure charts of four class problems.
Embodiment
The present invention will be further described in detail with specific embodiment below in conjunction with the accompanying drawings.
In order to describe acoustically to differentiate the impression of volume up-down so as to introduce the concept of tone in phonetics.It is low to frequency
Sound, people, which sound, feels that its tone is low, the sound high to frequency, and people, which sound, feels that its tone is high.But
The frequency of tone and tone color is not directly proportional relation.That is, frequency progress of the ear of people to sound is non-linear
Processing, i.e., have different perceptions to the voice of different frequency.In order to preferably describe tone, people make use of Mel frequencies
Rate scale is, it is specified that the unit of tone is Mel.Critical bandwidth is the important evidence of division Mel frequency scales.And critical broadband is drawn
Enter is to describe masking effect of the narrow-band noise to pure tone.When increasing the bandwidth of noise, this narrow-band noise is to pure tone
Masking amount is initially increase, but would not be increased when after a certain bandwidth, and this bandwidth is thus referred to as critical bandwidth.
Experiment shows：When centre frequency is in below 1kHz, the substantially linear distribution of critical bandwidth, about 100Hz；When centre frequency surpasses
When crossing 1kHz, with the increase of centre frequency, critical bandwidth is in logarithm increase.Therefore the frequency scale of the auditory system of people is met
Division should have higher frequency resolution in low frequency part, and have relatively low frequency resolution in HFS.Therefore
The present invention proposes a kind of composite character recognition methods based on MFCC.
A kind of as shown in figure 1, underwater manoeuvre Small object identification side based on MFCC composite characters and SVMs (SVM)
Method, methods described specifically include：
Step 1) gathers the original sound signal s (n) of target to be identified；Original sound signal s (n) passes through preemphasis, divided
The processing such as frame and adding window, obtains the time-domain signal x (n) of each speech frame；
Step 2) calculates time-domain signal x (n) 2K MFCC coefficient, and the MFCC coefficients of even number position are formed into MFCC spies
Sign amount；Specifically include：
Time-domain signal x (n) is obtained linear spectral X (k) by step 201) after discrete Fourier transform (DFT)：
Wherein, N is the points for representing Fourier transformation.
Step 202) calculates linear spectral X (k) energy spectrum, and band logical is carried out to energy spectrum by several bandpass filters
Filtering；
Square of linear spectral X (k) amplitude of calculating, i.e. energy spectrum；By the triangular filter group of one group of Mel yardstick,
Frequency domain carries out bandpass filtering to energy spectrum；Wherein Mel frequency filters group be set in the spectral range of voice several
Bandpass filter Hm(k), its centre frequency is that f (m), m=1,2 ... M, M are the number of bandpass filter, and M is even number；At this
In embodiment, M=24；Each bandpass filter has triangle filtering characteristic, and its transmission function is：
Wherein
Step 203) calculates the logarithmic energy that each bandpass filter group exports：
Step 204) carries out discrete cosine transform (DCT) to the logarithmic energy S (m) of output and obtains MFCC coefficients：
Step 205) time-domain signal x (n) MFCC characteristic quantities are：[C(2),C(4),...,C(M)]；
In step 202), the number of bandpass filter is M, can obtain M MFCC coefficient, wherein selection even number digit
MFCC coefficients form MFCC characteristic quantities；The MFCC coefficients of odd number digit are used to construct follow-up MFCC characteristic quantities；
Step 3) carries out Further Feature Extraction to 2K MFCC coefficient, calculates 2K difference MFCC coefficient, and by even bit
The MFCC coefficients put form difference MFCC characteristic quantities；
Further Feature Extraction is that original sequence of feature vectors is analyzed again, by characteristic vector with weighting, it is poor
The methods of dividing, screening, further separate the target signature for being hidden in voice signal behind.Can to the first-order difference of characteristic vector
To obtain the pace of change of characteristic vector, the change of characteristic vector embodies the change of target sound signal.
The computational methods of difference MFCC coefficients are：
Wherein, k is constant, it is preferred that k=2；Obtained difference Mel cepstrum coefficient d (n) are front cross frame and rear two frame
Linear combination.
Difference MFCC characteristic quantities are：[d(2),d(4),...,d(M)].
Step 4) calculates crest frequency f；
MFCC characteristic quantities, MFCC Differential Characteristics amount and crest frequency are combined by step 5), form MFCC composite characters
Amount；
The radiated noise signals of underwater manoeuvre Small object have the characteristics of similar to voice signal, therefore use MFCC and (poor
The method for dividing MFCC to be combined, the behavioral characteristics (transition feature) of radiated noise are also taken in, and such echo signal is moved
State feature and static nature information form complementation, can effectively improve the performance of system.
Because underwater Small object radiated noise signals have the characteristics of different from pure voice signal, every kind of target radiated noise again
Signal has each independent frequency distribution again, therefore adds characteristic vector using the crest frequency of echo signal as one of feature.
Composite character amount is:[C (2), C (4) ..., C (M), d (2), d (4) ..., d (M), f], dimension 25, wherein envelope 12 are tieed up
MFCC characteristic quantities, 12 dimension difference MFCC amounts and crest frequency.
Composite character vector is inputted support vector machine classifier by step 6), is input to from root node based on the oriented nothing of decision-making
In the SVMs (DDAGSVM) of ring figure, according to the output valve of two graders of each node, next layer of classification section is determined
Point, most Zhongdao layer 5 obtain output valve of classifying, and classification results are worth to according to output.
Also include before the step 6)：Training Support Vector Machines grader；Specifically include:
Step S1) training sample is classified；
Step S2) pretreatment is carried out to training sample form time-domain signal；
Step S3) using each training sample time-domain signal as x (t), according to step 1), step 2), step 3), step 4)
The MFCC composite characters vector of the time-domain signal of each training sample is built with step 5)；
Step S4) using the MFCC composite characters vector of all training samples as the input of SVMs, train branch
Hold vector machine classifier.
SVMs (Support Vector Machine) grader is carried on the basis of two classification problems are studied
Out, but in actual applications, we are often required to carry out more sort researches.In order to solve this problem, the present invention uses
One kind is adapted to the polytypic branch based on decision-making directed acyclic graph (Decision Directed Acyclic Graph, DDAG)
Hold vector machine multivalue sorting algorithm and carry out structural classification device.This method is substantially still 1-vs-1 sorting algorithms, simply in decision-making
The algorithm of directed acyclic graph is introduced in journey.The classification problem of k classification is needed to construct k (k-1)/2 OVO (one-
Versus-one, one-to-one) grader.
One OVO grader of each node on behalf, top layer only have a node, and i-th layer includes i node, i-th layer of jth
Individual node points to+1 node of i+1 layer jth and jth, the k classification of k node on behalf final classification of bottom.
Example：The underwater manoeuvre Small object radiated noise data of outfield experiments are extracted, extract underwater frogman first, sounding is fed
The mixing MFCC characteristic vectors of the targets such as newborn animal, underwater robot, water surface speedboat, then Training Support Vector Machines grader.
It shown below is the contrast of traditional MFCC characteristic recognition methods and mixing MFCC characteristic recognition methods proposed by the present invention, table 1
It is the contrast of four classification target correct recognition ratas,
Table 1
| Underwater frogman | Underwater robot | Water surface speedboat | Sounding mammal | |
| Training data | 100% | 98% | 99% | 100% |
| Test data | 92% | 91% | 90% | 93% |
The discrimination of the method for the present invention is higher it can be seen from the data processed result of table 1, equal to the discrimination of target
Reach more than 90%.Say that the hybrid feature extraction method based on MFCC is effective, illustrated that SVMs can be made
For the grader of underwater manoeuvre target.The method that the present invention goes out can apply to the Classification and Identification of underwater manoeuvre Small object.
Claims (7)
1. a kind of underwater manoeuvre Small object recognition methods based on MFCC and SVMs, methods described include：To be identified
The original sound signal s (n) of target is pre-processed, and obtains the time-domain signal x (n) of each speech frame；Extract time-domain signal x
(n) MFCC characteristic quantities, difference MFCC characteristic quantities are obtained using MFCC characteristic quantities, by MFCC characteristic quantities, difference MFCC characteristic quantities
It is combined with time-domain signal x (n) crest frequency, forms MFCC composite character amounts, the MFCC composite characters vector is defeated
Enter to the support vector machine classifier trained and be identified, export the type of identification.
2. the underwater manoeuvre Small object recognition methods according to claim 1 based on MFCC and SVMs, its feature
It is, methods described specifically includes：
Step 1) pre-processes to the original sound signal s (n) of target to be identified, obtains the time-domain signal x of each speech frame
(n)；
Step 2) calculates time-domain signal x (n) 2K MFCC coefficient, and the MFCC coefficients of even number position are formed into MFCC features
Amount；
Step 3) carries out Further Feature Extraction to 2K MFCC coefficient, calculates 2K difference MFCC coefficient, and by even number position
MFCC coefficients form difference MFCC characteristic quantities；
Step 4) calculates time-domain signal x (n) crest frequency f；
MFCC characteristic quantities, difference MFCC characteristic quantities and crest frequency f are combined by step 5), form MFCC composite character amounts；
The MFCC composite characters vector is input to the support vector machine classifier trained and is identified by step 6), until knowing
Not Cheng Gong, export the type of identification.
3. the underwater manoeuvre Small object recognition methods according to claim 2 based on MFCC and SVMs, its feature
It is, the step 2) specifically includes：
Time-domain signal x (n) is obtained linear spectral X (k) by step 201) after discrete Fourier transform：
<mrow>
<mi>X</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>n</mi>
<mo>=</mo>
<mn>0</mn>
</mrow>
<mrow>
<mi>N</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</munderover>
<mi>x</mi>
<mrow>
<mo>(</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
<msup>
<mi>e</mi>
<mrow>
<mo>-</mo>
<mi>j</mi>
<mn>2</mn>
<mi>&pi;</mi>
<mi>n</mi>
<mi>k</mi>
<mo>/</mo>
<mi>N</mi>
</mrow>
</msup>
<mo>,</mo>
<mn>0</mn>
<mo>&le;</mo>
<mi>k</mi>
<mo>&le;</mo>
<mi>N</mi>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein, N is the points for representing Fourier transformation；
Step 202) calculates linear spectral X (k) energy spectrum, and bandpass filtering is carried out to energy spectrum by 2K bandpass filter；
Step 203) calculates the logarithmic energy that each bandpass filter group exports：
<mrow>
<mi>S</mi>
<mrow>
<mo>(</mo>
<mi>m</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>l</mi>
<mi>n</mi>
<mrow>
<mo>(</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>k</mi>
<mo>=</mo>
<mn>0</mn>
</mrow>
<mrow>
<mi>N</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</munderover>
<msup>
<mrow>
<mo>|</mo>
<mrow>
<msub>
<mi>X</mi>
<mi>a</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
</mrow>
<mo>|</mo>
</mrow>
<mn>2</mn>
</msup>
<msub>
<mi>H</mi>
<mi>m</mi>
</msub>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mo>,</mo>
<mn>0</mn>
<mo>&le;</mo>
<mi>m</mi>
<mo>&le;</mo>
<mn>2</mn>
<mi>K</mi>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</mrow>
Step 204) carries out discrete cosine transform to the logarithmic energy S (m) of output and obtains MFCC coefficients：
<mrow>
<mi>C</mi>
<mrow>
<mo>(</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>m</mi>
<mo>=</mo>
<mn>0</mn>
</mrow>
<mrow>
<mi>N</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</munderover>
<mi>S</mi>
<mrow>
<mo>(</mo>
<mi>m</mi>
<mo>)</mo>
</mrow>
<mi>c</mi>
<mi>o</mi>
<mi>s</mi>
<mrow>
<mo>(</mo>
<mi>&pi;</mi>
<mi>n</mi>
<mo>(</mo>
<mrow>
<mi>m</mi>
<mo>-</mo>
<mn>0.5</mn>
</mrow>
<mo>)</mo>
<mo>/</mo>
<mi>M</mi>
<mo>)</mo>
</mrow>
<mo>,</mo>
<mn>0</mn>
<mo>&le;</mo>
<mi>n</mi>
<mo><</mo>
<mn>2</mn>
<mi>K</mi>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>3</mn>
<mo>)</mo>
</mrow>
</mrow>
Step 205) time-domain signal x (n) MFCC characteristic quantities are：[C(2),C(4),...,C(2K)].
4. the underwater manoeuvre Small object recognition methods according to claim 3 based on MFCC and SVMs, its feature
It is, the specific implementation process of the step 3) is：
The computational methods of difference MFCC coefficients are：
<mrow>
<mi>d</mi>
<mrow>
<mo>(</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<msqrt>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mo>-</mo>
<mi>k</mi>
</mrow>
<mi>k</mi>
</munderover>
<msup>
<mi>i</mi>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
</mfrac>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mo>-</mo>
<mi>k</mi>
</mrow>
<mi>k</mi>
</munderover>
<mi>C</mi>
<mrow>
<mo>(</mo>
<mi>n</mi>
<mo>+</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>4</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein, k is constant, k=2；
Difference MFCC characteristic quantities are：[d(2),d(4),...d(2K)].
5. the underwater manoeuvre Small object recognition methods according to claim 4 based on MFCC and SVMs, its feature
It is, the MFCC composite character amounts in the step 5) are：
[C(2),C(4),...,C(2K),d(2),d(4),...,d(2K),f]
Its dimension is 2K+1.
6. the underwater manoeuvre Small object recognition methods according to claim 2 based on MFCC and SVMs, its feature
It is, also includes before the step 6)：Training Support Vector Machines grader；Specifically include:
Step S1) training sample is classified；
Step S2) pretreatment is carried out to training sample form time-domain signal；
Step S3) using each training sample time-domain signal as x (t), according to step 1), step 2), step 3), step 4) and step
The MFCC composite characters vector of the rapid time-domain signal for 5) building each training sample；
Step S4) the MFCC composite characters of all training samples vector is used as to the input of SVMs, train support to
Amount machine grader.
7. the underwater manoeuvre Small object recognition methods according to claim 6 based on MFCC and SVMs, its feature
It is, the support vector machine classifier is the SVMs based on decision-making directed acyclic graph；When the number of types of identification is m
When, the support vector machine classifier needs to construct m (m-1)/2 one-against-one device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610308104.8A CN107368840A (en) | 2016-05-11 | 2016-05-11 | A kind of underwater manoeuvre Small object recognition methods based on MFCC and SVMs |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610308104.8A CN107368840A (en) | 2016-05-11 | 2016-05-11 | A kind of underwater manoeuvre Small object recognition methods based on MFCC and SVMs |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107368840A true CN107368840A (en) | 2017-11-21 |
Family
ID=60303495
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610308104.8A Pending CN107368840A (en) | 2016-05-11 | 2016-05-11 | A kind of underwater manoeuvre Small object recognition methods based on MFCC and SVMs |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107368840A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110390949A (en) * | 2019-07-22 | 2019-10-29 | 苏州大学 | Acoustic Object intelligent identification Method based on big data |
| CN111709299A (en) * | 2020-05-19 | 2020-09-25 | 哈尔滨工程大学 | Underwater sound target identification method based on weighting support vector machine |
| CN112052880A (en) * | 2020-08-13 | 2020-12-08 | 哈尔滨工程大学 | Underwater sound target identification method based on weight updating support vector machine |
| CN113345443A (en) * | 2021-04-22 | 2021-09-03 | 西北工业大学 | Marine mammal vocalization detection and identification method based on mel-frequency cepstrum coefficient |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102831895A (en) * | 2012-08-29 | 2012-12-19 | 山东大学 | Method for achieving MFCC (Mel Frequency Cepstrum Coefficient) parameter extraction by field-programmable gate array |
| US9313359B1 (en) * | 2011-04-26 | 2016-04-12 | Gracenote, Inc. | Media content identification on mobile devices |
-
2016
- 2016-05-11 CN CN201610308104.8A patent/CN107368840A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9313359B1 (en) * | 2011-04-26 | 2016-04-12 | Gracenote, Inc. | Media content identification on mobile devices |
| CN102831895A (en) * | 2012-08-29 | 2012-12-19 | 山东大学 | Method for achieving MFCC (Mel Frequency Cepstrum Coefficient) parameter extraction by field-programmable gate array |
Non-Patent Citations (3)
| Title |
|---|
| HONGJIAN SONG 等: "《An Automatic Identification Algorithm of Yangtze Finless Porpoise》", 《ICSPCC2015》 * |
| WEN TAO 等: "《An Identification Method Based on Multi-aspect Target Scattering Characteristics》", 《COA2016》 * |
| 王巍巍: "《鱼类声信号的分析及特征提取研究》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110390949A (en) * | 2019-07-22 | 2019-10-29 | 苏州大学 | Acoustic Object intelligent identification Method based on big data |
| CN110390949B (en) * | 2019-07-22 | 2021-06-15 | 苏州大学 | Underwater sound target intelligent identification method based on big data |
| CN111709299A (en) * | 2020-05-19 | 2020-09-25 | 哈尔滨工程大学 | Underwater sound target identification method based on weighting support vector machine |
| CN111709299B (en) * | 2020-05-19 | 2022-04-22 | 哈尔滨工程大学 | Underwater sound target identification method based on weighting support vector machine |
| CN112052880A (en) * | 2020-08-13 | 2020-12-08 | 哈尔滨工程大学 | Underwater sound target identification method based on weight updating support vector machine |
| CN113345443A (en) * | 2021-04-22 | 2021-09-03 | 西北工业大学 | Marine mammal vocalization detection and identification method based on mel-frequency cepstrum coefficient |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112364779B (en) | Underwater sound target identification method based on signal processing and deep-shallow network multi-model fusion | |
| CN105488466B (en) | A kind of deep-neural-network and Acoustic Object vocal print feature extracting method | |
| CN109800700A (en) | A kind of underwater sound signal target classification identification method based on deep learning | |
| CN104732978B (en) | The relevant method for distinguishing speek person of text based on combined depth study | |
| CN108847238B (en) | Service robot voice recognition method | |
| CN106847309A (en) | A kind of speech-emotion recognition method | |
| CN106529428A (en) | Underwater target recognition method based on deep learning | |
| CN106952649A (en) | Method for distinguishing speek person based on convolutional neural networks and spectrogram | |
| CN107609488A (en) | A kind of ship noise method for identifying and classifying based on depth convolutional network | |
| CN107368840A (en) | A kind of underwater manoeuvre Small object recognition methods based on MFCC and SVMs | |
| CN111723701B (en) | Underwater target identification method | |
| Wang et al. | ia-PNCC: Noise Processing Method for Underwater Target Recognition Convolutional Neural Network. | |
| CN110456332A (en) | A kind of underwater sound signal Enhancement Method based on autocoder | |
| CN102664010B (en) | Robust speaker distinguishing method based on multifactor frequency displacement invariant feature | |
| CN105957537A (en) | Voice denoising method and system based on L1/2 sparse constraint convolution non-negative matrix decomposition | |
| CN112017682B (en) | Single-channel voice simultaneous noise reduction and reverberation removal system | |
| CN111261189B (en) | Vehicle sound signal feature extraction method | |
| CN103854660B (en) | A kind of four Mike's sound enhancement methods based on independent component analysis | |
| CN108091345B (en) | Double-ear voice separation method based on support vector machine | |
| Sun et al. | Underwater single-channel acoustic signal multitarget recognition using convolutional neural networks | |
| Wei et al. | A method of underwater acoustic signal classification based on deep neural network | |
| Shen et al. | Improved auditory inspired convolutional neural networks for ship type classification | |
| Dong et al. | Bidirectional denoising autoencoders-based robust representation learning for underwater acoustic target signal denoising | |
| CN112183582A (en) | Multi-feature fusion underwater target identification method | |
| CN107369444A (en) | A kind of underwater manoeuvre Small object recognition methods based on MFCC and artificial neural network |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171121 |