CN108157219A - A kind of pet based on convolutional neural networks stops apparatus and method of barking - Google Patents
A kind of pet based on convolutional neural networks stops apparatus and method of barking Download PDFInfo
- Publication number
- CN108157219A CN108157219A CN201711407047.XA CN201711407047A CN108157219A CN 108157219 A CN108157219 A CN 108157219A CN 201711407047 A CN201711407047 A CN 201711407047A CN 108157219 A CN108157219 A CN 108157219A
- Authority
- CN
- China
- Prior art keywords
- pet
- convolutional neural
- neural networks
- sound
- barks
- 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
- 238000013527 convolutional neural network Methods 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000006870 function Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 238000009432 framing Methods 0.000 claims description 3
- 238000013178 mathematical model Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000001537 neural effect Effects 0.000 claims 1
- 238000005457 optimization Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000003475 lamination Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K15/00—Devices for taming animals, e.g. nose-rings or hobbles; Devices for overturning animals in general; Training or exercising equipment; Covering boxes
- A01K15/02—Training or exercising equipment, e.g. mazes or labyrinths for animals ; Electric shock devices ; Toys specially adapted for animals
- A01K15/021—Electronic training devices specially adapted for dogs or cats
- A01K15/022—Anti-barking devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Environmental Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- Animal Husbandry (AREA)
- Zoology (AREA)
- Artificial Intelligence (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Biodiversity & Conservation Biology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Physical Education & Sports Medicine (AREA)
- Toys (AREA)
Abstract
The present invention provides a kind of pets based on convolutional neural networks to stop method of barking, and includes the following steps：S1, prepare training sample, several sections of pets is selected to yelp training data of the sound as model；S2, pretreatment, the sound that yelps to original pet pre-process；S3, sound spectrograph is calculated；S4, sound spectrograph is inputted into convolutional neural networks；S5, training pattern；S6, pet identification；S7, sounds trigger of only barking, play and stop bark sound.The present invention also provides a kind of pets based on convolutional neural networks to stop device of barking.The beneficial effects of the invention are as follows：Convolutional neural networks are applied to pet to stop in method of barking, improve the flexibility only barked and anti-interference, and pet will not be damaged, in addition it can carry out identification to pet.
Description
Technical field
It only barks apparatus and method the present invention relates to only bark method more particularly to a kind of pet based on convolutional neural networks.
Background technology
Tradition only barks method other than cutting sound band of performing an operation to pet (such as dog), wearing pet mask, also makes
With skeleton symbol electronics barking stop device, such as oscillating mode, ultrasonic wave or electric shock type.
Conventional method shortcoming is as follows：
(1) it is dumb, easily pet is damaged.
(2) can not yelp to triggering the pet identification of sound.
Invention content
In order to solve the problems in the prior art, the present invention provides a kind of pets based on convolutional neural networks to stop dress of barking
It puts and method.
Only bark device the present invention provides a kind of pet based on convolutional neural networks, including microphone, operational amplifier,
Embeded processor, memory, power amplifier and loudspeaker, wherein, the output terminal of the microphone and the operational amplifier
Input terminal connection, the output terminal of the operational amplifier is connect with the input terminal of the embeded processor, described embedded
Processor is connect with the memory, and the output terminal of the embeded processor is connect with the input terminal of the power amplifier,
The output terminal of the power amplifier is connect with the input terminal of the loudspeaker.
The present invention also provides a kind of pets based on convolutional neural networks to stop method of barking, and includes the following steps：
S1, prepare training sample, several sections of pets is selected to yelp training data of the sound as model；
S2, pretreatment, the sound that yelps to original pet pre-process；
S3, sound spectrograph is calculated；
S4, sound spectrograph is inputted into convolutional neural networks；
S5, training pattern；
S6, pet identification；
S7, sounds trigger of only barking, play and stop bark sound.
As a further improvement on the present invention, the pretreatment in step S2 include preemphasis, framing adding window, yelp sound end
Point detection.
As a further improvement on the present invention, the convolutional neural networks in step S4 include convolutional layer, down-sampled layer and complete
Articulamentum；First layer of the convolutional layer as convolutional neural networks directly carries out convolution operation to two-dimentional sound spectrograph signal；Convolution kernel
Wave filter size selects 5X5 templates, and the result acted on by different convolution kernel wave filters constitutes characteristic pattern；Each volume
Product core wave filter shares identical parameter, and including identical weight matrix and bias term, the convolutional layer mathematical model of use is as follows：
Y=f (x*k+b)
Wherein, x is input signal, and k is convolution kernel, and * is convolution operation, and b is bias term, and f is sigmoid functions, and y is defeated
Go out characteristic pattern；
Down-sampled layer is deployed in after convolutional layer, and desampling fir filter selection 2X2 templates, sampling policy takes 4 pixels pair
The maximum value answered, full articulamentum give score value to grader.
As a further improvement on the present invention, in step s 5, model training is completed on computer PC, by it is preceding to
It propagates and back-propagating, adjusting parameter is optimal training pattern.For the model of the training on PC, also can preferably dispose
At the relatively deficient embedded mobile end of computing resource, need to weights be quantified with reduced model, the APK moulds that generation Android is supported
Type file.
As a further improvement on the present invention, in step s 6, the apk model files after training are deployed in claim 1
The pet Embedded A ndroid based on convolutional neural networks is only barked in device, which stops Mike's elegance in device of barking
Collection pet yelps voice signal, extracts sound sound spectrograph, as the input of convolutional neural networks model, obtains scoring probability
Value, the scoring probability value relatively differentiate that, more than threshold value, pet identity to be detected is confirmed with given threshold, otherwise not really
Recognize.
As a further improvement on the present invention, in the step s 7, it is determined that after pet identity, then detect pet and yelp sound width
Whether value is more than the threshold value set, if being more than, will be stored in the only bark sound of memory, and be played back by loudspeaker.
The beneficial effects of the invention are as follows：Convolutional neural networks are applied to pet to stop in method of barking, improve the spirit only barked
Activity and anti-interference, and pet will not be damaged, in addition it can carry out identification to pet.
Description of the drawings
Fig. 1 is the schematic diagram that a kind of pet based on convolutional neural networks of the present invention stops device of barking.
Fig. 2 is the flow diagram that a kind of pet based on convolutional neural networks of the present invention stops method of barking.
Specific embodiment
The invention will be further described for explanation and specific embodiment below in conjunction with the accompanying drawings.
The device as shown in Figure 1, a kind of pet based on convolutional neural networks only barks, including microphone 101, operational amplifier
102nd, embeded processor 103, memory 104, power amplifier 105 and loudspeaker 106, wherein, the output of the microphone 101
End is connect with the input terminal of the operational amplifier 102, output terminal and the embeded processor of the operational amplifier 102
103 input terminal connection, the embeded processor 103 are connect with the memory 104, the embeded processor 103
Output terminal is connect with the input terminal of the power amplifier 105, the output terminal of the power amplifier 105 and the loudspeaker 106
Input terminal connection, should the device of only barking of the pet based on convolutional neural networks only bark device for Embedded A ndroid mobile terminals.
The device as shown in Figure 1, a kind of pet based on convolutional neural networks provided by the invention only barks, the microphone
101 acquisition pets yelp sound and after system pre-processes, and are output to operational amplifier 102, and the pet sound that yelps is put by operation
After the 102 signal amplification of big device, it is input in the identification model of embeded processor 103, after the correct pet identity of Model Identification,
The only bark sound for the pet owner that memory 104 is recorded in advance, by doting at 106 broadcasting of power amplifier 105 and loudspeaker
Object hears that owner stops yelping after stopping bark sound, so as to achieve the purpose that only to bark.
Convolutional neural networks are most studies in current deep learning system, using a model the most successful, wide
The numerous areas such as general application and image, voice, video, huge contribution is made that in artificial intelligence field.The present invention, which is broken through, to be passed
The technological means of system barks convolutional neural networks in voice recognition with only.This method is divided according to function, mainly including pet
Yelp the training of acoustic model, only pet identification, bark sound (referring generally to the prevention bark sound that pet owner is recorded in advance) triggering.
Wherein model training and Model Identification stop in computer and Embedded A ndroid mobile terminals being completed on device of barking respectively.
A kind of method as shown in Fig. 2, pet based on convolutional neural networks only barks, includes the following steps：
1st, pet yelps the training of acoustic model
(1) prepare training sample
20 sections of pets (such as pet dog) is selected to yelp sound as model training data, the general 30 seconds left sides of every section of sound length
It is right.
(2) it pre-processes
In order to extract the useful acoustical signal that yelps, Environmental Noise Influence is reduced, needs to pre-process it.This programme is adopted
Preprocess method is including preemphasis, framing adding window, yelp sound end-point detection etc..
(3) sound spectrograph is calculated
It yelps acoustic information in view of pet, here using input of the sound spectrograph as convolutional neural networks.Sound spectrograph packet
Information largely related with the characteristic for the sound that yelps is contained, the advantages of it combines spectrogram and time domain waveform.
(4) convolutional neural networks
Here using typical convolutional neural networks structure, structure includes convolutional layer, down-sampled layer and full articulamentum.Volume
First layer of the lamination as convolutional neural networks directly carries out convolution operation to two-dimentional sound spectrograph signal.Convolution and wave filter are big
Small selection 5X5 templates.The result acted on by different convolution kernels constitutes characteristic pattern.Each convolution kernel wave filter is shared
Identical parameter, including identical weight matrix and bias term.Here the convolutional layer mathematical model used is as follows：
Y=f (x*k+b)
Wherein, x is input signal, and k is convolution kernel, and * is convolution operation, and b is bias term, and f is sigmoid functions, and y is defeated
Go out characteristic pattern.
In order to increase the robustness of system, reduce computation complexity, down-sampled to inputting, down-sampled layer is deployed in convolution
After layer.Desampling fir filter selects 2X2 templates, and sampling policy takes the corresponding maximum value of 4 pixels.Full articulamentum is by score value
Give grader (such as softmax graders).
(5) training pattern
What model training was completed on computer PC, by propagated forward and back-propagating, adjusting parameter makes training pattern
It is optimal.For the model of the training on PC, the relatively deficient embedded mobile end of computing resource also can be preferably deployed in,
Weights need to be quantified with reduced model, the APK model files that generation Android is supported.
2nd, pet identification
APK models after training, which are deployed in Embedded A ndroid mobile terminals, to be stopped in device of barking.Embedded A ndroid is moved
End microphone 101 in device of only barking collects pet and yelps voice signal, extraction sound spectrograph semaphore, using sound spectrograph as convolution
The input of neural network model obtains scoring probability value, which is more than the threshold value of setting, and pet to be detected is confirmed, otherwise
It is unconfirmed.
3rd, stop sounds trigger of barking
After pet identity is determined, then detects pet and whether yelp magnitude of sound more than the threshold value set, it, will if being more than
The only bark sound of memory 104 is stored in, is played back by loudspeaker 106.
A kind of pet based on convolutional neural networks provided by the invention stops apparatus and method of barking, Promethean by convolution god
In only barking through network application to pet, the flexibility only barked and anti-interference are improved, and pet will not be damaged, in addition
The present invention can also carry out identification to pet.
A kind of pet based on convolutional neural networks provided by the invention stops apparatus and method of barking, and has the characteristics that：
1st, human speech identity recognizing technology, which is applied, yelps in pet in identification.
2nd, model of the convolutional neural networks as training and identification.
3rd, extraction pet yelps input of the sound spectrograph feature as convolutional neural networks of sound.
The above content is a further detailed description of the present invention in conjunction with specific preferred embodiments, it is impossible to assert
The specific implementation of the present invention is confined to these explanations.For those of ordinary skill in the art to which the present invention belongs, exist
Under the premise of not departing from present inventive concept, several simple deduction or replace can also be made, should all be considered as belonging to the present invention's
Protection domain.
Claims (7)
- The device 1. a kind of pet based on convolutional neural networks only barks, it is characterised in that：Including microphone, operational amplifier, embedding Enter formula processor, memory, power amplifier and loudspeaker, wherein, the output terminal of the microphone and the operational amplifier Input terminal connects, and the output terminal of the operational amplifier is connect with the input terminal of the embeded processor, the embedded place Reason device is connect with the memory, and the output terminal of the embeded processor is connect with the input terminal of the power amplifier, institute The output terminal for stating power amplifier is connect with the input terminal of the loudspeaker.
- A kind of method 2. pet based on convolutional neural networks only barks, which is characterized in that include the following steps：S1, prepare training sample, several sections of pets is selected to yelp training data of the sound as model；S2, pretreatment, the sound that yelps to original pet pre-process；S3, sound spectrograph is calculated；S4, sound spectrograph is inputted into convolutional neural networks；S5, training pattern；S6, pet identification；S7, sounds trigger of only barking, play and stop bark sound.
- The method 3. pet according to claim 2 based on convolutional neural networks only barks, it is characterised in that：In step S2 Pretreatment includes that preemphasis, framing adding window, yelp sound end-point detection.
- The method 4. pet according to claim 2 based on convolutional neural networks only barks, it is characterised in that：In step S4 Convolutional neural networks include convolutional layer, down-sampled layer and full articulamentum；First layer of the convolutional layer as convolutional neural networks, directly Convolution operation is carried out to two-dimentional sound spectrograph signal；Convolution kernel wave filter size selects 5X5 templates, is filtered by different convolution kernels The result that device acts on constitutes characteristic pattern；Each convolution kernel wave filter shares identical parameter, including identical weight square Battle array and bias term, the convolutional layer mathematical model of use are as follows：Y=f (x*k+b)Wherein, x is input signal, and k is convolution kernel, and * is convolution operation, and b is bias term, and f is sigmoid functions, and y is that output is special Sign figure；Down-sampled layer is deployed in after convolutional layer, and desampling fir filter selection 2X2 templates, sampling policy takes 4 pixels corresponding Maximum value, full articulamentum give score value to grader.
- The method 5. pet according to claim 2 based on convolutional neural networks only barks, it is characterised in that：In step S5 In, after model training and optimization, the APK model files of generation Android supports.
- The method 6. pet according to claim 5 based on convolutional neural networks only barks, it is characterised in that：In step S6 In, the APK model files after training are disposed the pet described in claim 1 based on convolutional neural networks and are stopped in device of barking, The pet microphone acquisition pet in device that only barks yelps signal, sound spectrograph semaphore is extracted, using sound spectrograph as convolutional Neural The input of network model obtains scoring probability value, which is more than threshold value, and pet identity to be detected is confirmed, is not otherwise obtained Confirm.
- The method 7. pet according to claim 6 based on convolutional neural networks only barks, it is characterised in that：In step S7 In, it is determined that it after pet identity, then detects pet and whether yelps amplitude more than the threshold value set, if being more than, deposited being stored in The only bark sound of reservoir, is played back by loudspeaker.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711407047.XA CN108157219A (en) | 2017-12-22 | 2017-12-22 | A kind of pet based on convolutional neural networks stops apparatus and method of barking |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711407047.XA CN108157219A (en) | 2017-12-22 | 2017-12-22 | A kind of pet based on convolutional neural networks stops apparatus and method of barking |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108157219A true CN108157219A (en) | 2018-06-15 |
Family
ID=62523500
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711407047.XA Pending CN108157219A (en) | 2017-12-22 | 2017-12-22 | A kind of pet based on convolutional neural networks stops apparatus and method of barking |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108157219A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110322894A (en) * | 2019-06-27 | 2019-10-11 | 电子科技大学 | A kind of waveform diagram generation and giant panda detection method based on sound |
| CN111866192A (en) * | 2020-09-24 | 2020-10-30 | 汉桑（南京）科技有限公司 | Pet interaction method, system and device based on pet ball and storage medium |
| CN115104548A (en) * | 2022-07-11 | 2022-09-27 | 深圳市前海远为科技有限公司 | Pet behavior adjustment and human-pet interaction method and device based on multimedia information technology |
| CN118435880A (en) * | 2024-05-06 | 2024-08-06 | 深圳市安牛智能创新有限公司 | Dynamic adaptation virtual reality dog training method and system and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5927233A (en) * | 1998-03-10 | 1999-07-27 | Radio Systems Corporation | Bark control system for pet dogs |
| CN102231117A (en) * | 2011-07-08 | 2011-11-02 | 盛乐信息技术（上海）有限公司 | Software installment method and system for embedded platform |
| CN102499106A (en) * | 2011-09-29 | 2012-06-20 | 鲁东大学 | Bark stop device with voice recognition function |
| CN104794527A (en) * | 2014-01-20 | 2015-07-22 | 富士通株式会社 | Method and equipment for constructing classification model based on convolutional neural network |
| CN106454634A (en) * | 2016-11-18 | 2017-02-22 | 深圳市航天华拓科技有限公司 | Environment sound detection-based barking stopping apparatus and barking stopping method |
| CN106782504A (en) * | 2016-12-29 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Audio recognition method and device |
| CN106782501A (en) * | 2016-12-28 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Speech Feature Extraction and device based on artificial intelligence |
| CN106821337A (en) * | 2017-04-13 | 2017-06-13 | 南京理工大学 | A kind of sound of snoring source title method for having a supervision |
-
2017
- 2017-12-22 CN CN201711407047.XA patent/CN108157219A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5927233A (en) * | 1998-03-10 | 1999-07-27 | Radio Systems Corporation | Bark control system for pet dogs |
| CN102231117A (en) * | 2011-07-08 | 2011-11-02 | 盛乐信息技术（上海）有限公司 | Software installment method and system for embedded platform |
| CN102499106A (en) * | 2011-09-29 | 2012-06-20 | 鲁东大学 | Bark stop device with voice recognition function |
| CN104794527A (en) * | 2014-01-20 | 2015-07-22 | 富士通株式会社 | Method and equipment for constructing classification model based on convolutional neural network |
| CN106454634A (en) * | 2016-11-18 | 2017-02-22 | 深圳市航天华拓科技有限公司 | Environment sound detection-based barking stopping apparatus and barking stopping method |
| CN106782501A (en) * | 2016-12-28 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Speech Feature Extraction and device based on artificial intelligence |
| CN106782504A (en) * | 2016-12-29 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Audio recognition method and device |
| CN106821337A (en) * | 2017-04-13 | 2017-06-13 | 南京理工大学 | A kind of sound of snoring source title method for having a supervision |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110322894A (en) * | 2019-06-27 | 2019-10-11 | 电子科技大学 | A kind of waveform diagram generation and giant panda detection method based on sound |
| CN110322894B (en) * | 2019-06-27 | 2022-02-11 | 电子科技大学 | Sound-based oscillogram generation and panda detection method |
| CN111866192A (en) * | 2020-09-24 | 2020-10-30 | 汉桑（南京）科技有限公司 | Pet interaction method, system and device based on pet ball and storage medium |
| CN115104548A (en) * | 2022-07-11 | 2022-09-27 | 深圳市前海远为科技有限公司 | Pet behavior adjustment and human-pet interaction method and device based on multimedia information technology |
| CN115104548B (en) * | 2022-07-11 | 2022-12-27 | 深圳市前海远为科技有限公司 | Pet behavior adjustment and human-pet interaction method and device based on multimedia information technology |
| CN118435880A (en) * | 2024-05-06 | 2024-08-06 | 深圳市安牛智能创新有限公司 | Dynamic adaptation virtual reality dog training method and system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108157219A (en) | A kind of pet based on convolutional neural networks stops apparatus and method of barking | |
| Cai et al. | Sensor network for the monitoring of ecosystem: Bird species recognition | |
| CN106504768B (en) | Phone testing audio frequency classification method and device based on artificial intelligence | |
| CN109473120A (en) | A kind of abnormal sound signal recognition method based on convolutional neural networks | |
| CN104732978B (en) | The relevant method for distinguishing speek person of text based on combined depth study | |
| Mielke et al. | A method for automated individual, species and call type recognition in free-ranging animals | |
| CN110047510A (en) | Audio identification methods, device, computer equipment and storage medium | |
| CN106775198A (en) | A kind of method and device for realizing accompanying based on mixed reality technology | |
| CN108875592A (en) | A kind of convolutional neural networks optimization method based on attention | |
| CN104036776A (en) | Speech emotion identification method applied to mobile terminal | |
| CN108711436A (en) | Speaker verification's system Replay Attack detection method based on high frequency and bottleneck characteristic | |
| CN107103903A (en) | Acoustic training model method, device and storage medium based on artificial intelligence | |
| CN109924194A (en) | A kind of scarer and bird repellent method | |
| Charrier et al. | Vocal recognition of mothers by Australian sea lion pups: individual signature and environmental constraints | |
| CN107818366A (en) | A kind of lungs sound sorting technique, system and purposes based on convolutional neural networks | |
| CN109255296A (en) | A kind of daily Human bodys' response method based on depth convolutional neural networks | |
| ES2849124B2 (en) | ENVIRONMENTAL SOUND DETECTION METHOD AND SYSTEM FOR A COCHLEAR IMPLANT | |
| CN113947376B (en) | C/S (computer/subscriber line) card punching method and device based on multiple biological characteristics | |
| CN112820275A (en) | Automatic monitoring method for analyzing abnormality of suckling piglets based on sound signals | |
| CN110047502A (en) | The recognition methods of hierarchical voice de-noising and system under noise circumstance | |
| CN109584904A (en) | The sightsinging audio roll call for singing education applied to root LeEco identifies modeling method | |
| CN109447199A (en) | A kind of multi-modal criminal's recognition methods and system based on step information | |
| CN112738338A (en) | Telephone recognition method, device, equipment and medium based on deep learning | |
| Kastelein et al. | Temporary hearing threshold shift in harbor seals (Phoca vitulina) due to a one-sixth-octave noise band centered at 32 kHz | |
| CN115810365A (en) | Pig health early warning method and system based on pig sound |
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: 20180615 |