CN107452402B - The system and method for content is tapped using voice signal detection keyboard - Google Patents
The system and method for content is tapped using voice signal detection keyboard Download PDFInfo
- Publication number
- CN107452402B CN107452402B CN201710535127.7A CN201710535127A CN107452402B CN 107452402 B CN107452402 B CN 107452402B CN 201710535127 A CN201710535127 A CN 201710535127A CN 107452402 B CN107452402 B CN 107452402B
- Authority
- CN
- China
- Prior art keywords
- keystroke
- voice signal
- signal
- energy
- characteristic parameter
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000001514 detection method Methods 0.000 title claims description 38
- 238000009527 percussion Methods 0.000 claims abstract description 20
- 230000005236 sound signal Effects 0.000 claims abstract description 17
- 230000008569 process Effects 0.000 claims abstract description 10
- 230000009471 action Effects 0.000 claims description 16
- 238000010079 rubber tapping Methods 0.000 claims description 13
- 230000004044 response Effects 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 5
- 240000007651 Rubus glaucus Species 0.000 claims description 4
- 235000011034 Rubus glaucus Nutrition 0.000 claims description 4
- 235000009122 Rubus idaeus Nutrition 0.000 claims description 4
- 238000012790 confirmation Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 6
- 230000010365 information processing Effects 0.000 abstract 1
- 230000006872 improvement Effects 0.000 description 9
- 238000011160 research Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000030808 detection of mechanical stimulus involved in sensory perception of sound Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000001027 hydrothermal synthesis Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/18—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using ultrasonic, sonic, or infrasonic waves
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
- G06F3/041—Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means
- G06F3/043—Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means using propagating acoustic waves
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Auxiliary Devices For Music (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The present invention relates to the information processing technologies, and it discloses a kind of method and system that content is tapped based on voice signal identification keyboard.This method pre-processes voice signal by collecting the voice signal that keystroke generates using sound signal collecting device, to reach the identifying purpose for carrying out singly-bound and Macintosh.The key step that the method includes, which is specifically included that, collects the voice signal of percussion keyboard in desktop to be specifically laid out using sound collector, denoises by using the methods of Butterworth to the voice signal received；It calculates the short-time energy value of each keystroke and does normalized, using numerical value as a feature；Calculate the time difference that two microphones are taken to receive is merged as another feature and with a upper feature；Feature is classified using sorting algorithm, so as to identify singly-bound percussion or the percussion of Macintosh.
Description
Technical field
The present invention relates to based on voice signal identification field more particularly to it is a kind of using voice signal detection keyboard tap in
The method and system of appearance.
Background technique
Nowadays, with the development of various signal detection systems, keyboard key stroke identification is become more and more important.By different
Signal detection, we can reappear the content for tapping keyboard out.As the development and people of information security technology are to information privacy
Requirement it is higher and higher, carried out while being able to detect signal reverse-examination survey, exactly to be considered instantly.Carrying out detection keystroke
While behavior, preferably mode is designed to protect the privacy of people.In existing indoor environment, sound caused by keystroke,
Research in terms of influence and keystroke power of the gesture to indoor WiFi signal can be by the technology as eavesdropping, from technical principle
Upper research keyboard identification technology, is ravesdropping to be better protected from keystroke behavior.
Existing keyboard identification system can be mainly divided into two aspects, first, obtaining personal tap according to keystroke dynamics
The feature of keyboard carries out the certification of personal identification；Second, WiFi, the signals such as light carry out the knowledge that keyboard taps content using sound
Not.Following a few classes can be divided into terms of second of research again.(1) it is based on WiFi signal, keyboard percussion is carried out using CSI technology
The identification of content.Such as Wikey, (2) tap based on voice signal etc. the identification .Context-free of keyboard content, pass through
Capture the reconstruct that voice signal carries out keyboard layout.
It above method or needs to require using dedicated Signal Collection Technology and to the condition of environment relatively high,
The detection device quantity needed is relatively high and calculates higher cost, does not have universality.
Summary of the invention
In order to overcome the shortcoming in the prior art of above-mentioned meaning, the present invention provides a kind of utilization voice signal detection
Keyboard taps the method and system of content, by the voice signal to be come using analysis acquisition, to realize in specific layout
Identification to keystroke content, and method of the time and computing resource of whole process consuming with respect to before is less.
The present invention is achieved by the following technical solutions:
A kind of system based on voice signal detection keyboard hammer action comprising:
S1, sound collector, which are collected, taps the voice signal that keyboard generates, and pre-processes to voice signal；
S2, using energy detection algorithm and extract each hammer action keystroke peak signal segment；
S3, the short-time energy normalized value for calculating each hammer action and binding time difference are classified as feature
S4, feedback are directed to the response message of recognition result, adjust the parameter of sorting algorithm, further promote accuracy.
As a further improvement of the present invention: the signal receiving end includes at least two Mikes that different location is arranged in
Wind；It includes between the signal exported according to different microphones that the parameter for carrying out training before according to feature, which carries out classification and matching,
Difference, obtain the characteristic parameter of the voice signal, and it is arranged or the characteristic parameter of training matches with prior；Institute
Stating feedback module includes that the result for detecting judgment module and existing characteristic parameter are compared, if the feature of the two is joined
Existing deviation is counted, then it is corrected.
As a further improvement of the present invention: the signal receiving end include two be arranged in it is on a smart phone,
Microphone being linked together by raspberry pie mode, with fixed range.
As a further improvement of the present invention: the judgment module each microphone is connect respectively the audio signal of output into
Row processing obtains the maximum wave crest section of energy of each microphone output, obtained wave crest section is normalized respectively；
Energy difference and the time difference between two wave crest sections are obtained respectively, and the energy difference and time difference are formed into a vector, are obtained
To characteristic parameter.
As a further improvement of the present invention: the feedback module is used to feed back the response letter for the result of Classification and Identification
The characteristic parameter of this keystroke is corresponded to the obtained keystroke position, and is added in existing characteristic parameter by breath.
In addition, including the following steps: the present invention also provides a kind of method for carrying out keyboard identification based on voice signal
S1, signal receiving end, which are collected, taps the voice signal that keyboard generates, and pre-processes to voice signal；Including logical
It crosses at least two setting positions and collects the voice signal for tapping keyboard and generating at a distance of the microphone of set distance, and respectively to each
The voice signal of microphone output is pre-processed；
S2, using energy detection algorithm and extract each hammer action keystroke peak signal segment；Including the use of
Energy detection algorithm is respectively and the signal on audio signal peak that extract the output of each microphone, that a keystroke movement generates
Segment；
S3, the short-time energy normalized value for calculating each hammer action and binding time difference are classified as feature；
Including calculating separately the short-time energy normalized value of the signal segment on each obtained audio signal peak, and two in short-term can
Amount normalized value subtracts each other to obtain energy difference；Calculate the time difference of the signal segment on two audio signal peaks；The time that will be obtained
Difference and energy difference form a vector, obtain characteristic parameter；It is carried out in existing characteristic parameter using obtained characteristic parameter
Matching, obtains keystroke content；
S4, feedback module feedback are directed to the response message of recognition result, adjust the parameter of sorting algorithm.
As a further improvement of the present invention: the pretreatment that voice signal is carried out in the step S1, specifically:
S11, the signal that each microphone is acquired and exported carry out Butterworth filtering method respectively and are filtered；
S12, environmental background signal is subtracted by the signal that filtering obtains by above-mentioned, obtains current demand signal；Wherein, the ring
Border background signal is the voice signal in one section of environment acquired when acting and occur without keystroke.
As a further improvement of the present invention: in the step S2, being detected and extracted each using energy detection algorithm
The sound clip of hammer action includes:
S21, detect that a keystroke acts to be analyzed in the audio signal generated, energy using energy detection algorithm
It is worth maximum percussion wave crest；
S22, to the percussion wave crest identified after, pass through the threshold value ratio for setting the energy value of the wave crest waveform and one
Compared with obtaining the starting point and ending point of the percussion wave crest.
As a further improvement of the present invention: the step S3 further comprises:
S31, the energy value for the percussion wave crest for having each microphone output is normalized respectively, obtains it in short-term
Energy value；S32, two short-time energy values are subtracted each other, the short-time energy for obtaining this keystroke is poor；
S33, the initial time that two tap wave crest is subtracted each other, obtains the time difference of this keystroke；
S34, by obtained short-time energy difference and time difference being subsequently placed at together according to setting, obtain a vector,
That is the characteristic parameter of this keystroke；
S35, the parameter of this obtained keystroke is matched in existing characteristic parameter, confirmation and this keystroke
The immediate existing characteristic parameter of characteristic parameter, and then selecting the corresponding keystroke position of the existing characteristic parameter is this keystroke
Position.
As a further improvement of the present invention: the step S4 further comprises: confirming the judging result of this keystroke just
After really, the characteristic parameter of this keystroke is corresponded into the obtained keystroke position, and be added in existing characteristic parameter.
The beneficial effects of the present invention are: the present invention utilizes the advantages of sound detection, have devised a kind of based on sound detection
Keyboard tap system, and more acurrate sound can be identified using modified hydrothermal process and correction module；Sound of the invention
The treatment process of the keyboard key stroke detection of sound signal, pre-processes according to by the signal of receiving end, and binding time is poor first
In addition this feature judges keystroke content using the sorting algorithm of machine learning, then passes through artificial and algorithm continuous school
Just, reach more accurate identification；The present invention, which can satisfy, carries out Classification and Identification to the content of institute's keystroke, and identification stability is good.
Detailed description of the invention
Attached drawing 1 is a kind of system configuration schematic diagram that content is tapped based on sound detection keyboard of embodiment of the invention；
Attached drawing 2 is the data processing real time process flow schematic diagram of the method for the invention that content is tapped based on sound detection keyboard；
Attached drawing 3 is that a kind of system for tapping content based on sound detection keyboard of the invention realizes control flow chart；
Specific embodiment
For the ease of the understanding of those skilled in the art, present invention work is further retouched with example with reference to the accompanying drawing
It states.
A method of content being tapped based on voice signal detection keyboard, step includes:
S1, sound collector, which are collected, taps the voice signal that keyboard generates, and pre-processes to voice signal；
S2, using energy detection algorithm and extract each hammer action keystroke peak signal segment；
S3, the short-time energy normalized value for calculating each hammer action and binding time difference are classified as feature
S4, feedback are directed to the response message of recognition result, adjust the parameter of sorting algorithm, further promote accuracy.
Specifically, in step sl, the sound collector can be existing smart phone, and device is in raspberry pie
Microphone etc., the relative position that must carry two microphones and two microphones remains unchanged, and keyboard and sound are searched
Acquisition means are placed in same level and keeping parallelism, between the two distance away, and in step sl, every time
The position for collecting signal keyboard and mobile phone keeps relatively fixed.
Referring to Fig. 1, it illustrates the position passes in situation a kind of in the present embodiment between above-mentioned keyboard and detection device
System；In the present embodiment, the sound for tapping keyboard and generating is collected at a distance of the microphone of set distance by least two setting positions
Sound signal, and the voice signal of each microphone output is pre-processed respectively；Then simultaneously using energy detection algorithm difference
The signal segment on audio signal peak that extract each microphone output, that a keystroke movement generates；Realize above-mentioned steps
Afterwards, the short-time energy normalized value of the signal segment on each obtained audio signal peak is calculated separately, and two in short-term can
Amount normalized value subtracts each other to obtain energy difference；Calculate the time difference of the signal segment on two audio signal peaks；The time that will be obtained
Difference and energy difference form a vector, obtain characteristic parameter；It is carried out in existing characteristic parameter using obtained characteristic parameter
Matching, obtains keystroke content；Finally, the response message of the recognition result according to this identification, to above-mentioned existing characteristic parameter
It is adjusted.
In the present embodiment, pretreatment voice signal carried out, specifically: the letter that each microphone is acquired and exported
Number, Butterworth filtering method is carried out respectively to be filtered；Then environmental background is subtracted by the signal that filtering obtains by above-mentioned
Signal obtains current demand signal；Wherein, the environmental background signal is the sound in one section of environment acquired when acting and occur without keystroke
Sound signal.
And the sound clip that each hammer action is detected and extracted using energy detection algorithm includes: using energy measuring
Algorithm detects that a keystroke acts to be analyzed in the audio signal generated, the maximum percussion wave crest of energy value；Later, right
After the percussion wave crest identified, by obtaining the knock wave for the energy value of the wave crest waveform and a threshold value comparison set
The starting point and ending point at peak.
In the present embodiment, the short-time energy normalized value of each hammer action and binding time difference are calculated as feature
Classify specifically: the energy value for the percussion wave crest for having each microphone output is normalized respectively, obtains it
Short-time energy value；Then, two short-time energy values are subtracted each other, the short-time energy for obtaining this keystroke is poor；Again by two knock waves
The initial time at peak is subtracted each other, and the time difference of this keystroke is obtained；Later, by obtained short-time energy difference and time difference according to setting
Be subsequently placed at together, obtain a vector, the i.e. characteristic parameter of this keystroke；Finally by the parameter of this obtained keystroke
It is matched in existing characteristic parameter, the immediate existing characteristic parameter of characteristic parameter of confirmation and this keystroke, in turn
Selecting the corresponding keystroke position of the existing characteristic parameter is this keystroke position.
It in the present embodiment, include: to confirm that the judging result of this keystroke is correct for the adjustment of existing characteristic parameter
Afterwards, the characteristic parameter of this keystroke is corresponded into the obtained keystroke position, and be added in existing characteristic parameter.
In the present embodiment, for an angle, the step S2 is to judge knock wave using energy detection method
Peak and the signal segment for extracting complete entire hammer action:
S21, a hammer action detect the knock wave to be analyzed according to energy detection algorithm there are three wave crests
Peak；
S22, to the percussion wave crest identified after, judged by a threshold value tap starting point and ending point as this
The further improvement of invention: the step S3 includes:
S31, in order to enable the recognition accuracy that taps of entire keyboard is higher, introduce the time difference as tapping every time in addition
One feature simultaneously merges two features；
S32, in order to classification and matching algorithm is more accurate, introducing performance, more preferably neural network algorithm carries out classification
Match, identifies each percussion；
Method based on voice signal detection keyboard of the invention further include: feedback is directed to the response message of recognition result,
Adjust the model of matching algorithm.
Specifically, as shown in Fig. 2, the present invention provides a kind of being detected based on voice signal for embodiment to tap keyboard
Implementation process, asks the step to include:
S301, both hands tap key on keyboard normally to tap speed；
S302, in signal acquisition stage, carry out the collection of signal and be filtered using Butterworth method and white noise
The mode of removal removes noise；
S303, using common segmentation algorithm, be split to signal is got, to intercept the signal patch of hammer action
Section；
S304, the short-time energy value for calculating the same key that two microphones obtain, and the short-time energy for finding out the two is poor
Value
S305, multiple groups experiment is carried out, to find out multiple groups energy differences and do normalized, and using this numerical value as one
Feature；
Two S306, calculating microphones obtain the time difference of same signal segment, and will be used as a feature and energy
Value is merged；
S307, using two above feature as one group of vector value, classified using neural network algorithm；
S308, to identifying single key and Macintosh.
In one embodiment, a kind of system that keyboard identification is carried out based on voice signal, comprising:
Signal receiving end, for receiving the voice signal of percussion keyboard generation and being pre-processed；
Judgment module, the information for being received according to receiving end, the parameter of training is divided before being carried out according to feature
Class matching, identifies tapped key；
Result that judgment module detects and known classification are compared feedback module, if there is deviation, carry out
Correction, to be that distinguished number is more accurate；
Display module, using the display screen of mobile phone terminal or other display modules, for showing the result identified.
The signal receiving end for receive tap keyboard caused by voice signal, including but not limited to smart phone and
The microphone system of raspberry pie link.
In the judgment module, information is received according to receiving end, will after energy normalized value and time difference as feature,
After adjusting parameter, preferably matched using sorting algorithm.
The feedback module is used to feed back the response message of the result for Classification and Identification, adjusts sorting algorithm model.
The judgment module carries out the identification of key using following steps:
321, using Statistical Learning Theory, pre-establish to set in space and be led since the characteristic of keyboard percussion is obstructed
Cause model of the mode of voice signal variation as training sample；
322, energy differences and time difference, which are received, as characteristic value for two microphones is input to training sample
In model, to obtain the classification of object key.The knowledge of above-mentioned keyboard can be realized using single mobile terminal (such as mobile phone)
Not.
The above content is specific preferred embodiment is combined, further detailed description of the invention, should not assert this hair
Bright specific implementation is confined to described above.For those skilled in the art, present inventive concept is not being departed from
Under the premise of, several simple deduction or replace can also be made, are regarded as being determined by the claim submitted of the present invention
Within protection scope.
Claims (7)
1. a kind of system for tapping content using voice signal detection keyboard characterized by comprising
Signal receiving end, for receiving the voice signal of percussion keyboard generation and being pre-processed；
Judgment module, the information for being received according to receiving end, the parameter of training carries out classification before being carried out according to feature
Match, identifies tapped key；
Result that judgment module detects and known classification are compared, if there is deviation, carry out school by feedback module
Just, to be that distinguished number is more accurate；
Display module, for showing the result identified；
Wherein, the signal receiving end includes at least two microphones that different location is arranged in；It is described that it is carried out according to feature
It includes the difference between the signal exported according to different microphones that the parameter of preceding training, which carries out classification and matching, obtains the sound letter
Number characteristic parameter, and it is arranged or the characteristic parameter of training matches with prior；The feedback module includes that will judge
The result and existing characteristic parameter that module detects are compared, if there is deviation in the characteristic parameter of the two, to its into
Row correction；
The signal receiving end include two be arranged in it is on a smart phone, being linked together by raspberry pie mode,
Microphone with fixed range；
The judgment module is respectively handled the audio signal that each microphone connects output, obtains each microphone output
The maximum wave crest section of energy, is respectively normalized obtained wave crest section；The energy between two wave crest sections is obtained respectively
Amount difference and time difference, and the energy difference and time difference are formed into a vector, obtain characteristic parameter.
2. the system for tapping content using voice signal detection keyboard as described in claim 1, which is characterized in that the feedback
Module is used to feed back the response message of the result for Classification and Identification, and the characteristic parameter of this keystroke is corresponded to obtained keystroke
Position, and be added in existing characteristic parameter.
3. a kind of method for tapping content using voice signal detection keyboard, which comprises the steps of:
S1, signal receiving end, which are collected, taps the voice signal that keyboard generates, and pre-processes to voice signal；Including by extremely
The voice signal for tapping keyboard and generating is collected at a distance of the microphone of set distance in few two setting positions, and respectively to each Mike
The voice signal of wind output is pre-processed；
S2, using energy detection algorithm and extract each hammer action keystroke peak signal segment；Including the use of energy
Detection algorithm is respectively and the signal patch on audio signal peak that extract the output of each microphone, that a keystroke movement generates
Section；
S3, the short-time energy normalized value for calculating each hammer action and binding time difference are classified as feature；Including
The short-time energy normalized value of the signal segment on each obtained audio signal peak is calculated separately, and two short-time energies are returned
One change value subtracts each other to obtain energy difference；Calculate the time difference of the signal segment on two audio signal peaks；By the obtained time difference and
Energy difference forms a vector, obtains characteristic parameter；It is matched in existing characteristic parameter using obtained characteristic parameter,
Obtain keystroke content；
S4, feedback module feedback are directed to the response message of recognition result, adjust the parameter of sorting algorithm.
4. the method according to claim 3 for tapping content using voice signal detection keyboard, it is characterised in that: the step
The pretreatment that voice signal is carried out in rapid S1, specifically:
S11, the signal that each microphone is acquired and exported carry out Butterworth filtering method respectively and are filtered；
S12, the signal obtained by filtering is subtracted into environmental background signal, obtains current demand signal；Wherein, the environmental background letter
It number is the voice signal in one section of environment acquired when acting and occur without keystroke.
5. the method according to claim 4 for tapping content using voice signal detection keyboard, it is characterised in that: the step
In rapid S2, is detected using energy detection algorithm and the sound clip for extracting each hammer action includes:
S21, detect that a keystroke acts to be analyzed in the audio signal generated, energy value most using energy detection algorithm
Big percussion wave crest；
S22, to the percussion wave crest identified after, by the threshold value comparison for setting the energy value of the wave crest waveform and one, obtain
To the starting point and ending point of the percussion wave crest.
6. the method according to claim 5 for tapping content using voice signal detection keyboard, it is characterised in that: the step
Rapid S3 further comprises:
S31, the energy value for the percussion wave crest for having each microphone output is normalized respectively, obtains its short-time energy
Value；
S32, two short-time energy values are subtracted each other, the short-time energy for obtaining this keystroke is poor；
S33, the initial time that two tap wave crest is subtracted each other, obtains the time difference of this keystroke；
S34, by obtained short-time energy difference and time difference being subsequently placed at together according to setting, obtain a vector, i.e., this
The characteristic parameter of secondary keystroke；
S35, the parameter of this obtained keystroke is matched in existing characteristic parameter, the feature of confirmation and this keystroke
The immediate existing characteristic parameter of parameter, and then selecting the corresponding keystroke position of the existing characteristic parameter is this keystroke position
It sets.
7. the method according to claim 6 for tapping content using voice signal detection keyboard, it is characterised in that: the step
Rapid S4 further comprises: after confirming that the judging result of this keystroke is correct, the characteristic parameter of this keystroke being corresponded to and is obtained
Keystroke position, and be added in existing characteristic parameter.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610521466.5A CN106128452A (en) | 2016-07-05 | 2016-07-05 | Acoustical signal detection keyboard is utilized to tap the system and method for content |
| CN2016105214665 | 2016-07-05 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107452402A CN107452402A (en) | 2017-12-08 |
| CN107452402B true CN107452402B (en) | 2019-02-12 |
Family
ID=57468544
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610521466.5A Pending CN106128452A (en) | 2016-07-05 | 2016-07-05 | Acoustical signal detection keyboard is utilized to tap the system and method for content |
| CN201710535127.7A Active CN107452402B (en) | 2016-07-05 | 2017-06-30 | The system and method for content is tapped using voice signal detection keyboard |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610521466.5A Pending CN106128452A (en) | 2016-07-05 | 2016-07-05 | Acoustical signal detection keyboard is utilized to tap the system and method for content |
Country Status (2)
| Country | Link |
|---|---|
| CN (2) | CN106128452A (en) |
| WO (1) | WO2018006797A1 (en) |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106128452A (en) * | 2016-07-05 | 2016-11-16 | 深圳大学 | Acoustical signal detection keyboard is utilized to tap the system and method for content |
| CN107133135B (en) * | 2017-05-02 | 2021-02-09 | 电子科技大学 | Keyboard key detection method based on statistics and sound positioning |
| CN107300971B (en) * | 2017-06-09 | 2019-04-02 | 深圳大学 | The intelligent input method and system propagated based on osteoacusis vibration signal |
| CN107608534A (en) * | 2017-08-31 | 2018-01-19 | 深圳大学 | A kind of acoustic keyboard realizes system, implementation method and application method |
| CN108182418B (en) * | 2017-12-30 | 2022-02-01 | 儒安科技有限公司 | Keystroke identification method based on multi-dimensional sound wave characteristics |
| SG10201801032UA (en) * | 2018-02-06 | 2019-09-27 | Singapore Management Univ | Systems and methods for two-factor authentication |
| CN108732571B (en) * | 2018-03-28 | 2021-06-15 | 南京航空航天大学 | Keyboard monitoring method based on combination of ultrasonic positioning and keystroke sound |
| CN108648763B (en) * | 2018-04-04 | 2019-11-29 | 深圳大学 | Personal computer usage behavior monitoring method and system based on acoustic channels |
| CN110058689A (en) * | 2019-04-08 | 2019-07-26 | 深圳大学 | A kind of smart machine input method based on face's vibration |
| CN110111812B (en) * | 2019-04-15 | 2020-11-03 | 深圳大学 | Self-adaptive identification method and system for keyboard keystroke content |
| CN110688048B (en) * | 2019-05-23 | 2023-09-01 | 南京理工大学 | Method for analyzing key information of smart phone |
| CN110245477B (en) * | 2019-05-31 | 2021-06-15 | 联想(北京)有限公司 | Information verification method, device, equipment and storage medium |
| CN111090337B (en) * | 2019-11-21 | 2023-04-07 | 辽宁工程技术大学 | CFCC spatial gradient-based keyboard single-key keystroke content identification method |
| CN112272019A (en) * | 2020-10-22 | 2021-01-26 | 广东美的制冷设备有限公司 | Control method and device for sound-control knocking switch, household appliance and storage medium |
| CN113867561B (en) * | 2021-08-17 | 2024-02-27 | 支付宝(杭州)信息技术有限公司 | Touch screen fault detection system and method and touch screen equipment |
| CN116415166A (en) * | 2021-12-28 | 2023-07-11 | 深圳大学 | Multi-keyboard mixed key sound identification method, device, equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102187301A (en) * | 2008-09-04 | 2011-09-14 | 甲骨文美国公司 | System and method for using sound to differentiate keypresses |
| CN103576126A (en) * | 2012-07-27 | 2014-02-12 | 姜楠 | Four-channel array sound source positioning system based on neural network |
| CN104536585A (en) * | 2014-12-31 | 2015-04-22 | 无锡清华信息科学与技术国家实验室物联网技术中心 | Keyboard input detecting method based on dynamic conditional random field |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060232558A1 (en) * | 2005-04-15 | 2006-10-19 | Huan-Wen Chien | Virtual keyboard |
| CN103901401B (en) * | 2014-04-10 | 2016-08-17 | 北京大学深圳研究生院 | A kind of binaural sound source of sound localization method based on ears matched filtering device |
| US10591580B2 (en) * | 2014-09-23 | 2020-03-17 | Hewlett-Packard Development Company, L.P. | Determining location using time difference of arrival |
| CN106128452A (en) * | 2016-07-05 | 2016-11-16 | 深圳大学 | Acoustical signal detection keyboard is utilized to tap the system and method for content |
-
2016
- 2016-07-05 CN CN201610521466.5A patent/CN106128452A/en active Pending
-
2017
- 2017-06-30 CN CN201710535127.7A patent/CN107452402B/en active Active
- 2017-07-04 WO PCT/CN2017/091669 patent/WO2018006797A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102187301A (en) * | 2008-09-04 | 2011-09-14 | 甲骨文美国公司 | System and method for using sound to differentiate keypresses |
| CN103576126A (en) * | 2012-07-27 | 2014-02-12 | 姜楠 | Four-channel array sound source positioning system based on neural network |
| CN104536585A (en) * | 2014-12-31 | 2015-04-22 | 无锡清华信息科学与技术国家实验室物联网技术中心 | Keyboard input detecting method based on dynamic conditional random field |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107452402A (en) | 2017-12-08 |
| CN106128452A (en) | 2016-11-16 |
| WO2018006797A1 (en) | 2018-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107452402B (en) | The system and method for content is tapped using voice signal detection keyboard | |
| CN105353881B (en) | Gesture identification method and system based on RFID | |
| CN102270451B (en) | Method and system for identifying speaker | |
| CN105844216B (en) | Detection and matching mechanism for recognizing handwritten letters by WiFi signals | |
| CN101364408A (en) | Sound image combined monitoring method and system | |
| WO2020164264A1 (en) | Facial image recognition method and apparatus, and computer device | |
| CN110299142B (en) | Voiceprint recognition method and device based on network convergence | |
| KR20130110565A (en) | Apparatus and method for recognizing user activity | |
| WO2015085811A1 (en) | Method and device for banknote identification based on thickness signal identification | |
| CN105678273A (en) | Initial point detection algorithm of transient signal in radio frequency fingerprint identification technology | |
| CN102682760A (en) | Overlapped voice detection method and system | |
| CN105160359B (en) | A kind of labyrinth damage collaboration recognition methods based on supersonic guide-wave | |
| CN105873212A (en) | Indoor-environment-person detection method based on channel state information | |
| CN101996308A (en) | Human face identification method and system and human face model training method and system | |
| CN103065122A (en) | Facial expression recognition method based on facial motion unit combination features | |
| CN102982321A (en) | Acquisition method and device for face database | |
| Hou et al. | Research on audio-visual detection method for conveyor belt longitudinal tear | |
| CN104268134A (en) | Subjective and objective classifier building method and system | |
| CN106446877A (en) | Signal amplitude sequence based radio frequency fingerprint feature extraction and identification method | |
| CN103915096A (en) | Police service voiceprint recognition method | |
| CN107798351B (en) | Deep learning neural network-based identity recognition method and system | |
| CN108182418A (en) | A kind of thump recognition methods based on multidimensional acoustic characteristic | |
| CN204791050U (en) | Authentication equipment | |
| CN102592142A (en) | Computer-system-based handwritten signature stability evaluation method | |
| CN102721963A (en) | Target feature extraction method for one-dimensional imaging of target by using broadband radar |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |