CN206726760U - Microphone, data processor and monitoring system - Google Patents
Microphone, data processor and monitoring system Download PDFInfo
- Publication number
- CN206726760U CN206726760U CN201720498105.3U CN201720498105U CN206726760U CN 206726760 U CN206726760 U CN 206726760U CN 201720498105 U CN201720498105 U CN 201720498105U CN 206726760 U CN206726760 U CN 206726760U
- Authority
- CN
- China
- Prior art keywords
- signal
- microphone
- sound
- module
- data processor
- 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
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The utility model provides a kind of microphone, including sound collection portion, and for gathering the actual sound signal of user, the microphone also includes：Signal transmitting and receiving module, it is connected with the sound collection portion, actual sound signal for the sound collection portion to be gathered is sent, and receive and signal is judged according to the sound status of the actual sound signal generation, the level of sound quality that the sound status judges signal and includes being generated according to the level of sound quality of user judges signal and/or the health status type decision signal generated according to the health status type of user；Prompting module, for judging signal generation alerting signal according to the sound status.Correspondingly, the utility model also provides a kind of data processor, monitoring system.The utility model can be easy to vocal music worker to understand the health status such as itself level of sound quality and vocal cords at any time.
Description
Technical field
It the utility model is related to smart machine field, and in particular to a kind of microphone, data processor and monitoring system.
Background technology
With the development of big data computing technique, various intelligent electronic devices and cloud server are applied to wisdom and shown
Show, the product such as smart home, intelligent terminal.Wherein, still it is only limitted in the product of current sound collection equipment such as microphone
Simple function, for example, carrying out support, the displaying of music score and sound based on limited waveform analysis and frequency analysis technique
Record and fraction of practising singing test and appraisal, the physiological health situation such as the level of sound quality of vocal music worker or vocal cords can not be examined
Survey.
Utility model content
The utility model is intended at least solve one of technical problem present in prior art, it is proposed that a kind of microphone, number
According to processor and monitoring system, in order to which vocal music worker understands the level of sound quality and health status type of itself at any time.
One of in order to solve the above-mentioned technical problem, the utility model provides a kind of microphone, including sound collection portion, for adopting
Collect the actual sound signal of user, the microphone also includes：
Signal transmitting and receiving module, it is connected with the sound collection portion, for the actual sound for gathering the sound collection portion
Signal is sent, and is received and judged signal, the sound status according to the sound status of the actual sound signal generation
The level of sound quality that judging signal includes being generated according to the level of sound quality of user judges signal and/or the healthy shape according to user
The health status type decision signal of state type generation；
Prompting module, for judging signal generation alerting signal according to the sound status.
Preferably, the sound status judges that signal includes the level of sound quality and judges signal and the health status type
Judge signal；
The microphone also includes sign information acquisition module, for gathering the sign information of user；
The signal transmitting and receiving module is also connected with the sign information acquisition module, for the sign information to be gathered into mould
The sign information that block collects is sent, and is received and given birth to according to the combination of the actual sound signal and the sign information
Into the health status type decision signal.
Preferably, the sign information includes at least one of body temperature, pulse wave, blood oxygen amount, heart rate and blood pressure.
Preferably, the prompting module includes indicator lamp, and the alerting signal includes optical signal；And/or
The prompting module includes display panel, and the alerting signal includes picture signal.
Preferably, the microphone includes housing, if the housing includes hand grip portion and is arranged on the hand grip portion top
Cylinder head, the sound collection portion is arranged in the microphone head；The sign information acquisition module is arranged on the holding
On the outer wall in portion；
When the prompting module includes indicator lamp, the indicator lamp is arranged in microphone head, microphone head energy
Enough printing opacities；
When the prompting module includes display panel, the display panel is arranged on the housing exterior walls.
Preferably, the microphone also includes identity information acquisition module, for gathering the identity information of user；The letter
Number transceiver module is also connected with the identity information acquisition module, and can send the identity information.
Preferably, the identity information acquisition module is arranged on the outer wall of the hand grip portion, and the identity information includes
Finger print information.
Correspondingly, the utility model also provides a kind of data processor, including：
Signal receiving module, for receiving the actual sound signal transmitted by the signal transmitting and receiving module of above-mentioned microphone；
Processing module, it is connected with the signal receiving module, described in being received according to the signal receiving module
Actual sound signal generation sound status judges signal, wherein, the sound status judges that signal includes the sound according to user
The level of sound quality of the horizontal generation of matter judges that signal and/or the health status type generated according to the health status type of user are sentenced
Determine signal；
Signal transmitting module, it is connected with the processing module, for sound status judgement signal to be sent to described
Microphone.
Preferably, the processing module includes the first analytic unit and/or the second analytic unit：
First analytic unit is used to calculate the actual sound signal and standard sound using default similarity calculation
The similarity of sound signal, the level of sound quality is used as using the similarity；
Second analytic unit is used for the health status type that the user is judged using default sorter model.
Preferably, the similarity calculation includes the first convolution neural network model, and the sorter model includes
Second convolution neural network model.
Preferably, the processing module includes first analytic unit and second analytic unit；
When the microphone also includes sign information acquisition module,
The signal receiving module is additionally operable to receive the sign information that the signal transmitting and receiving module of the microphone is sent；Described
Two analytic units can judge the health of the user according to the combination of the actual sound signal and the sign information
Status Type.
Preferably, the processing module also includes pretreatment unit, for the actual speech gathered to the microphone
Signal and the sign information are pre-processed, and by pretreated actual sound signal output to first analytic unit
With second analytic unit, pretreated sign information is exported to second analytic unit.
Preferably, the data processor also includes：
Training module, for according to default multiple first voice signal samples and each self-corresponding similarity sample training
Obtain the similarity calculation；And multiple it is made up of according to default second sound signal sample and sign sample
Health status type sample training obtains the sorter model corresponding to sample group and each sample group.
Preferably, the data processor also includes：
Update module, be connected with the training module and the processing module, for according to the actual speech signal with
And the similarity calculation is updated by the similarity that the actual speech signal is calculated, and according to the reality
Voice signal and sign information and by the health status type that the combination of the two is judged to the sorter model carry out
Renewal.
Preferably, when microphone also includes identity information acquisition module, the data processor also includes memory module, uses
In the identity information of storage user and the level of sound quality and/or health status type of the user.
Preferably, the sound status judges that signal includes the level of sound quality and judges signal and the health status type
Judge signal,
When the prompting module of the microphone includes display panel, the data processor also includes instructing module, and this refers to
Guide module is connected with the processing module, for judging that signal is instructed in signal generation vocal music according to the level of sound quality, and according to
The health status type decision signal generation health guidance signal；
The signal transmitting module also instructs module to be connected with described, for the vocal music to be instructed into signal and health guidance
Signal is sent to the microphone, so that the display panel of the microphone instructs signal to show that letter is instructed in vocal music according to the vocal music
Breath, and health guidance information is shown according to the health guidance signal.
Correspondingly, the utility model also provides a kind of monitoring system, including above-mentioned microphone provided by the utility model and upper
State data processor.
Preferably, the microphone and the data processor become one structure；
Or the microphone and the data processor are the structure of two separation, and communicating wireless signals can be carried out.
In the utility model, the actual sound signal that data processor gathers according to microphone judges the tonequality water of user
Flat, generation level of sound quality judges signal, and the health status type of user, generation can also be judged according to actual sound signal
Health condition judging signal；The prompting module of microphone generates the alerting signal corresponding with level of sound quality, can also generate and be good for
The corresponding alerting signal of health Status Type, to remind user.Listened compared to traditional dependence people (vocal music tutor)
Pronunciation is taken to be compared with the normal diagnostic of throat doctor, the monitoring system in the utility model is by way of data analysis to using
The level of sound quality and health status of person is monitored at any time so that user understands the level of sound quality of itself and is good at any time
Health state, so that user understands self-condition more early, and judged result is more objective.Also, microphone can also be adopted
Collect the sign information of user, so that the voice signal and sign information of data processor combined use person judge user
Health status type, improve the accuracy rate of judgement.In addition, microphone can also gather the identity information of user, data processing
Device is stored the level of sound quality and health status type of the identity information of user and user, consequently facilitating user
Solve the sound status of own recent.
Brief description of the drawings
Accompanying drawing is to be further understood for providing to of the present utility model, and a part for constitution instruction, and following
Embodiment be used to explain the utility model together, but do not form to limitation of the present utility model.In the accompanying drawings：
Fig. 1 is the structured flowchart for the microphone for carrying out signal transmission in embodiment of the present utility model with data processor；
Fig. 2 is the surface structure schematic diagram of the microphone provided in the utility model embodiment；
Fig. 3 is the structured flowchart of the data processor provided in the utility model embodiment；
Fig. 4 is the monitoring method flow chart provided in the utility model embodiment；
Fig. 5 is the particular flow sheet of the monitoring method provided in the utility model embodiment.
Wherein, reference is：
100th, microphone；110th, sound collection portion；120th, signal transmitting and receiving module；130th, prompting module；131st, display panel；
140th, sign information acquisition module；150th, identity information acquisition module；160th, housing；161st, microphone head；162nd, hand grip portion；
200th, data processor；210th, signal receiving module；220th, processing module；221st, the first analytic unit；222nd, the second analysis is single
Member；223rd, pretreatment unit；230th, signal transmitting module；240th, training module；250th, update module；260th, memory module；
270th, module is instructed.
Embodiment
Specific embodiment of the present utility model is described in detail below in conjunction with accompanying drawing.It should be appreciated that herein
Described embodiment is merely to illustrate and explained the utility model, is not limited to the utility model.
As one side of the present utility model, there is provided a kind of microphone 100, as shown in figure 1, the microphone 100 is adopted including sound
Collection portion 110, signal transmitting and receiving module 120 and prompting module 130.Wherein, sound collection portion 110 is used for the actual sound for gathering user
Sound signal.Signal transmitting and receiving module 120 is connected with sound collection portion 110, for the voice signal hair for gathering sound collection portion 110
See off, and receive the sound status generated according to the voice signal and judge signal, wherein, the sound status judges letter
Number level of sound quality for including being generated according to the level of sound quality of user judges signal and/or the health status type according to user
The health status type decision signal of generation.Prompting module 130 is used to judge that signal generation reminds letter according to the sound status
Number.It should be appreciated that sound collection portion 110 can gather the sound of user, and the sound collected is converted into telecommunications
Number；In addition, signal transmission can be carried out between sound collection portion 110 and signal transmitting and receiving module 120 by the way of wireless connection,
Signal transmission can also be carried out by the way of wired connection.The sound status judges that signal can be by data processor 200
Generation, specifically will hereinafter be described, and not repeat first here.
The microphone 100 can be used in the vocal music exercise of the vocal music worker such as singer, announcer.Wherein, the tonequality
Level refers to user when carrying out vocal music exercise, sends being consistent for volume, tone color, tone of sound etc. and standard voice
Degree.The health status refers to the vocal cords of user, throat health status, for example, can include vocal cords whether fatigue, vocal cords
Whether whether load, throat there is lesion etc..The alerting signal of prompting module 130 can be optical signal, voice signal, vibrations letter
Number or be indirectly displayed as text information etc., as long as user can be caused to understand the sound shape of itself according to different alerting signals
State.
In the utility model, microphone 100 sends the voice signal of collection to can interpolate that level of sound quality and/or health
The data processor 200 of Status Type, so that data processor 200, which generates level of sound quality, judges signal, and/or healthy shape
State judges signal, at this moment, the prompting module 130 of microphone 100 according to level of sound quality judge signal generation alerting signal and/or according to
Health status type decision signal generation alerting signal, to remind user, so that user is in the same of sounding
When just can soon understand the level of sound quality and health status of itself, listen to pronunciation compared to traditional dependence people (vocal music tutor)
Compared with the normal diagnostic of throat doctor, the utility model can supervise at any time to the level of sound quality and health status of user
Survey so that user understands the level of sound quality and health status of itself at any time, so that user is more early
Self-condition is solved, and judged result is more objective.
Wherein, prompting module 130 can include indicator lamp, and the alerting signal includes the different face that the indicator lamp is sent
Color or the optical signal of different brightness；And/or prompting module 130 includes display panel, the alerting signal includes the display surface
The picture signal that plate is shown.For example, prompting module 130 includes different the first indicator lamps and the second indicator lamp of glow color, when
After signal transmitting and receiving module 120 receives level of sound quality judgement signal, prompting module 130 generates corresponding first alerting signal, the
One indicator lamp lights, and during level of sound quality judgement signal difference, the brightness of the first indicator lamp is different；When signal transmitting and receiving module
After 120 receive health status type decision signal, prompting module 130 generates corresponding second alerting signal, the second indicator lamp
It is luminous, and during the health status type decision signal difference, the brightness of the second indicator lamp is different.Certainly, prompting module 130
Audio can be included and play part, alerting signal is used as to send different sound；Or be vibrations part, to produce different frequency
Vibrations are used as alerting signal；Or be display panel, to directly display image information as alerting signal.
Preferably, the sound status judges that signal includes the level of sound quality and judges signal and the health status type
Judge signal, i.e. data processor 200 can either judge the level of sound quality of user, also can interpolate that the healthy shape of user
State type.
To enable data processor 200 more accurately to judge the health status type of user, further, such as scheme
Shown in 1, microphone 100 also includes sign information acquisition module 140, for gathering the sign information of user.Signal transmitting and receiving module
120 are also connected with sign information acquisition module 140, and the sign information for sign information acquisition module 140 to be collected is sent
Go out, so that the healthy shape can be generated with reference to the actual sound signal and the sign information by obtaining data processor 200
State type decision signal.Wherein, the sign information includes at least one in body temperature, pulse wave, blood oxygen amount, heart rate and blood pressure
Person, correspondingly, sign information acquisition module 140 can include being used for clinical thermometer, the pulse wave for measurement for measuring body temperature
Appointing in electronic sphygmograph, the porjection type infrared sensor for detecting blood oxygen amount and heart rate, the blood pressure device for measuring blood pressure
Meaning one.
Fig. 2 is the surface structure schematic diagram of microphone, as shown in Fig. 2 microphone 100 includes housing 160, housing 160 includes hand
Hold portion 162 and be arranged on the microphone head 161 on the top of hand grip portion 162, sound collection portion 110 is arranged in microphone head 161.For
100 integrally-built integrated level of raising microphone, reduce volume, sign information acquisition module 140 can be arranged on hand grip portion
On 162 outer walls.As indicated above, prompting module 130 can include indicator lamp, and at this moment, the indicator lamp can be arranged on microphone
In head 161, microphone head 161 being capable of printing opacity；Specifically, microphone head 161 can be a netted cover body, sound collection portion
110 can also be arranged in net blanket body.When prompting module 130 includes display panel 131, display panel 131 is arranged on shell
It on the outer wall of body 160, can specifically set on the outer wall of microphone head 161 (as shown in Figure 2), or be arranged on the outer wall of hand grip portion 162
On.
Further, as depicted in figs. 1 and 2, microphone 100 also includes identity information acquisition module 150, is used for gathering
The identity information of person；Signal transmitting and receiving module 120 is connected for 150 pieces also with identity information acquisition mould, and can be by the identity of user
Information is gone out, such as is sent to data processor 200., can be in order to the basis of data processor 200 by the collection of identity information
User's identity information and its actual sound signal, level of sound quality and health status type establish the individual for belonging to user itself
Database, consequently facilitating user checks the change of itself level of sound quality and the change of health status.
Wherein, identity information acquisition module 150 is arranged on the outer wall of hand grip portion 162, and the identity information includes fingerprint
Information.Identity information acquisition module 150 can specifically include touch-screen, in order to while user's hand microphone 100 just
The fingerprint of user can be collected.
As another aspect of the present utility model, there is provided a kind of data processor 200, as shown in figure 3, data processor
200 include signal receiving module 210, processing module 220 and signal transmitting module 230.Signal receiving module 210 is used to receive
State the actual sound signal transmitted by the signal transmitting and receiving module 120 of microphone 100；Processing module 220 and the phase of signal receiving module 210
Even, the actual sound signal generation sound status for being received according to signal receiving module 210 judges signal, wherein,
The level of sound quality that the sound status judges signal and includes being generated according to the level of sound quality of user judges signal and/or according to making
The health status type decision signal of the health status type generation of user.Signal transmitting module 230 and the phase of processing module 220
Even, for sound status judgement signal to be sent to microphone 100.
Preferably, the sound status judges that signal had both included the level of sound quality and judged signal, also including the health
Status Type judges signal.That is, after microphone 100 collects the actual sound of microphone user, the processing of data processor 200
Module 220 can judge the level of sound quality of user according to the actual sound signal of user, so as to generate corresponding tonequality water
Ordinary mail number；The health status type of user can also be judged according to the actual sound signal of user, it is corresponding so as to generate
Health status type decision signal.Afterwards, level of sound quality is judged into signal and/or health status class by signal transmitting module 230
Type judges that signal is sent to microphone 100, so that the prompting module 130 of microphone 100 generates above-mentioned alerting signal, to cause
User knows the level of sound quality and health status type of itself according to the alerting signal.
Wherein, data processor 200 can be to become one structure with microphone 100, or with the phase point of microphone 100
From structure, for example, be single cloud server, as long as signal transmission can be carried out with microphone 100, and data can be carried out
Processing, to judge the health status type of the level of sound quality of user and/or user according to the actual sound signal of user
.
Specifically, as shown in figure 3, processing module 220 can include being used for the first analytic unit 221 for judging level of sound quality
And/or for judging the second analytic unit 222 of health status type.Preferably, processing unit 220 is simultaneously including the first analysis
The analytic unit 222 of unit 221 and second, to carry out the judgement of level of sound quality and health status type simultaneously.
First analytic unit 221 is used to calculate the actual sound signal and standard using default similarity calculation
The similarity of voice signal, using the similarity as the level of sound quality, similarity is higher, i.e., level of sound quality is higher.As above
Described, above-mentioned microphone can be used in the vocal music training of vocal music practitioner, and now, standard voice signal can be collection in advance
, the voice signal of pronunciation standard, for example, one or more snippets voice signal for being used to carry out vocal music training can be gathered in advance,
The voice signal can cover certain range and comprising multiple different tones；When user carries out vocal music instruction using microphone 100
When practicing, sounding can be carried out according to standard voice signal, afterwards, microphone 100 sends the actual sound signal of user to number
According to processor 200, so that the first analytic unit 221 is believed according to frequency, volume, tone color of user's actual sound signal etc.
Cease to judge the similarity of actual sound signal and standard voice signal.
In order to improve the efficiency of Similarity Measure and accuracy rate, similarity calculation can specifically include the first convolution god
Through network model, the first convolution neural network model can use deep neural network model.First convolutional neural networks mould
Type can include input layer, multiple convolutional layers, multiple excitation layers and full articulamentum.Wherein, the first analytic unit 221 can be first right
Actual sound signal carries out feature extraction, obtain needed for fixed length characteristic vector, and by this feature vector standard voice signal
Characteristic vector input the input layer of the first convolution neural network model；After Similarity Measure, full articulamentum output
The similarity of the actual sound signal and the standard voice signal.Wherein, the extraction of sound characteristic can use what is commonly used
The extracting mode of mel cepstrum coefficients (Mel-scale Frequency Cepstral Coefficients, abbreviation MFCC).
Second analytic unit 222 is used to judge user's health status type using default sorter model.For
Raising classification effectiveness and accuracy rate, the sorter model can include the second convolution neural network model；Second convolution
Neural network model also uses deep neural network model.The structure of the nervus opticus network model and first nerves network model
It is similar, including input layer, multiple convolutional layers, multiple excitation layers and full articulamentum.With the first analytic unit 221 similarly, second
Analytic unit 222 can also carry out feature extraction to actual sound signal, and the characteristic vector after extraction is inputted into nervus opticus net
The input layer of network model, so that full articulamentum output coefficient corresponding with multiple default health status types, coefficient is most
Big health status type is the health status type corresponding to actual sound signal.
As described above, microphone 100 can also include sign information acquisition module 140, at this moment, 210 signal receiving modules
It is additionally operable to receive the sign information that the signal transmitting and receiving module 120 of microphone 100 is sent, the second analytic unit 222 can also utilize institute
State sorter model and the health status type is judged according to the combination of the actual sound signal and the sign information.
That is, the characteristic vector of the characteristic vector of the actual sound signal and the sign information is inputted into the second convolution nerve net jointly
The input layer of network, it is jointly corresponding with the actual sound signal and the sign information so as to be judged according to the output of full articulamentum
Health status type.
It should be noted that the first analytic unit 221 and the second analytic unit 222 are carrying out feature to actual sound signal
During extraction, only according to the shape information of the voice signals such as the frequency, volume, tone color of actual sound signal, and sound need not be analyzed
The linguistic information (for example, specific word, sentence etc.) of sound signal.
It can introduce noise in view of voice signal gatherer process and transmitting procedure and cause distorted signals, therefore,
Processing module 220 can also include pretreatment unit 223, and the pretreatment unit 223 is used for the actual sound that microphone 100 gathers
Signal is pre-processed, and by pretreated actual sound signal output to the first analytic unit 221 and the second analytic unit
222, pretreated sign information is exported to the second analytic unit 222.It is described pretreatment specifically can include filtering and noise reduction,
Normalization etc..
In order to obtain the similarity calculation and the sorter model, further, as shown in figure 3, at data
Reason device 200 also includes training module 240, and the training module 240 is for according to default multiple first voice signal samples and respectively
Self-corresponding similarity sample training obtains the similarity calculation；And according to default multiple by second sound signal sample
Health status type sample training corresponding to this sample group formed with sign information sample and each sample group obtains described point
Class device model.
Training of the training i.e. to the first convolution neural network model to similarity calculation, so as to obtain the first convolution
Mapping relations between each node layer of neural network model.During training, first sample storehouse is first established, first sample storehouse Zhong Bao
The a large amount of first voice signal samples gathered in advance are included, similarity corresponding to each first voice signal sample is, it is known that referred to as phase
Like degree sample；Afterwards, voice signal sample and standard voice signal are inputted into the defeated of the first initial convolution neural network model
Enter layer, corresponding similarity sample is inputted into full articulamentum, the specific knot of the first convolutional neural networks is obtained by repeatedly training
Structure.
Similarly, training of the training to sorter model i.e. to the second convolution neural network model, to obtain volume Two
Mapping relations between each node layer of product neural network model.During training, the second Sample Storehouse is first established, in second Sample Storehouse
Including multiple different health status types (for example, health, the tired out, Vocal cord lesion of vocal cords etc., referred to as health status class pattern
This), and a large amount of the second sound signal samples and sign information sample gathered in advance under each health status type；Afterwards,
Second sound signal sample and corresponding sign information sample are inputted to the input layer of the second convolutional neural networks；By full articulamentum
In node corresponding to health status type sample corresponding with the two be arranged to 1, other nodes are arranged to 0.By multigroup sample
Training, obtain the structure of the second convolution neural network model.First convolution neural network model and the second convolutional neural networks
The specific training method of model can use existing stochastic gradient descent method (the Moment based based on momentum
Stochastic Gradient Descent), I will not elaborate.
It should be appreciated that the input of neural network model input layer is corresponding during training process and use
, as described above, after the first analytic unit 221 and the second analytic unit 222 carry out feature extraction to actual sound signal
The input layer of the first convolution neural network model and nervus opticus network model is inputted again, correspondingly, to the first convolutional Neural
When network and the second convolution neural network model are trained, the first voice signal sample and second sound signal sample are also special
Sample after sign extraction.Certainly, the first voice signal sample and second sound signal sample can also be without feature extraction
Sample, in this case, when carrying out Similarity Measure and health status type judges, the voice signal of input layer input is also
Signal without feature extraction, so as to complete feature extraction and Similarity Measure (or health status inside neural network model
Type judges).In addition, the second analytic unit 222 only can also judge corresponding health status class according to actual sound signal
Type, in this case, in the training process of nervus opticus network model, input layer no longer inputs sign information sample.
Further, as shown in figure 3, data processor 200 can also include update module 250, the update module 250 with
Training module 240 is connected with processing module 220, believes for the actual sound signal according to user and by the actual speech
Number similarity calculated (level of sound quality judged according to the actual speech signal) is carried out to the similarity calculation
Renewal, and according to the actual sound signal and sign information and the health status type pair judged by the combination of the two
The sorter model is updated.As described above, in the training process of similarity calculation and classifier calculated model,
Initially set up first sample storehouse and the second Sample Storehouse, update module 250 is to similarity calculation and classifier calculated model
Renewal i.e., by actual sound signal and its corresponding similarity also serves as sample and added in first sample storehouse, in terms of to similarity
Calculate model and carry out further training renewal, so as to improve the accuracy of Similarity Measure；Actual sound signal and sign are believed
Health status type corresponding to breath is common also serves as sample and added in the second Sample Storehouse, to be carried out further to sorter model
Training renewal, so as to improve the accuracy that healthy type judges.
As described above, microphone 100 also includes identity information acquisition module 150, at this moment, data processor 200 can also wrap
Memory module 260 is included, for storing the actual sound signal of user's identity information and processing module 220 according to the user
The level of sound quality and/or health status type of the user judged, consequently facilitating user understands the sound of own recent
Matter level and health status.
Further, when the prompting module 130 of microphone 100 includes display panel, data processor 200 also includes instructing
Module 270, this instructs module 270 to be connected with processing module 220, for judging that signal generation vocal music refers to according to the level of sound quality
Signal is led, and according to the health status type decision signal generation health guidance signal.Signal transmitting module 230 also with guidance
Module 270 is connected, for instructing signal and health guidance signal to send to microphone 100 vocal music, so that the basis of microphone 100
The vocal music instructs signal to show vocal music tutorial message and shows health guidance information according to the health guidance signal.
Specifically, the health guidance information can be pre-set, for example, for level of sound quality, will can be represented
The similarity of level of sound quality is divided into multiple scopes, and pre-setting a kind of vocal music for each scope instructs signal；Work as processing
First analytic unit 221 of module 220 calculates the actual sound signal and after the similarity of standard voice signal, signal is sent out
Module 230 is sent to instruct signal to send to microphone 100, the display panel of microphone 100 vocal music corresponding to the similarity location
Vocal music according to receiving instructs signal to show corresponding vocal music tutorial message, in order to which user adjusts the exercise side of itself
Formula, improve itself level of sound quality.For health status, every kind of health status type can also be corresponded to one kind and pre-set
Health guidance signal；When the second analytic unit 222 of processing module 220 calculates the actual sound signal and sign information
After corresponding health status type, signal transmitting module 230 by health guidance signal corresponding to the health status type send to
Microphone 100, to cause the display panel of microphone 100 to show corresponding health guidance information, refer to so as to provide health for user
Lead and suggest.For example, when according to the actual sound signal and sign information, to judge health status type be " vocal cords are tired out ",
The health guidance information that display panel is shown is the printed words of " taking a good rest ".
As 3rd of the present utility model aspect, there is provided a kind of monitoring system, including it is provided by the utility model above-mentioned
Microphone 100 and data processor 200.With reference to shown in Fig. 1 and Fig. 3, the signal transmitting and receiving module 120 and data processor of microphone 100
200 signal receiving module 210 can carry out signal connection, the prompting module 130 of microphone 100 and the letter of data processor 200
Number sending module 230 can carry out signal connection, so as to gather user in microphone 100 actual sound signal after, at data
Manage device 200 and produce sound status judgement signal, and then the prompting module 130 of microphone 100 is generated alerting signal and reminded.Such as
Described above, microphone 100 and data processor 200 can become one structure, for example, data processor 200 is integrated in
In the housing of microphone 100；Or cylinder 100 and data processor 200 can be the structure of two separation, and can carry out wireless
Signal communication, for example, data processor 200 is the cloud server separated with microphone.
Monitoring system in the utility model is acquired and utilized to actual sound signal and other information using microphone
Data processor carries out data processing, and level of sound quality and health status by way of data analysis to user are carried out at any time
Monitoring so that user understands the level of sound quality and health status of itself at any time, so that user is more early
Understand self-condition, and judged result is more objective.
As 4th of the present utility model aspect, there is provided a kind of monitoring method using above-mentioned monitoring system, with reference to figure
1st, shown in Fig. 3 and Fig. 4, the monitoring method includes：
S10, microphone 100 gather the actual sound signal of user.
S20, data processor 200 judge signal according to the actual sound signal generation sound status, and by the sound
State judges that signal is sent to microphone 100；Wherein, the sound status judges that signal includes giving birth to according to the level of sound quality of user
Into level of sound quality judge signal and/or according to the health status type of user generate health status type decision signal.
S30, the prompting module 130 of microphone 100 judge signal generation alerting signal according to the sound status.
The process of the monitoring method is specifically introduced with reference to Fig. 1, Fig. 3 to Fig. 5.As shown in figure 1, microphone
100 include sound collection portion 110, signal dispatcher module 120, prompting module 130, sign information acquisition module 140；Prompting module
130 include display panel.As shown in figure 3, data processor 200 includes signal receiving module 210, processing module 220, signal hair
Module 230, training module 240, update module 250 are sent, processing module 220 includes pretreatment unit 223, first processing units
221 and second processing unit 222.As shown in figure 5, the monitoring method specifically includes：
S01, data processor 200 training module 240 according to default multiple first voice signal samples and each it is right
The similarity sample training answered obtains similarity calculation, and the similarity calculation includes the first convolutional neural networks mould
Type.
S02, training module 240 are according to default multiple samples being made up of second sound signal sample and sign sample
Health status type sample training corresponding to this group and each sample group obtains sorter model, and the sorter model includes the
Two convolutional neural networks models.The training process and principle of similarity calculation and sorter model are situated between above
Continue, repeat no more here.Step S01 and S02 can be carried out simultaneously, can also successively be carried out, two steps can S10 it
Before, carried out between the step S10 and S20 that can also refer to below.
S10, the sound collection portion 110 of microphone 100 gather the actual sound signal of user, and signal transmitting and receiving module 120 will
Actual sound signal is sent to data processor 200.
S11, the sign information acquisition module 140 of microphone 100 gather the sign information of user, signal transmitting and receiving module 120
The sign information of user is sent to data processor 200.
Above-mentioned steps S10 and S11 are carried out simultaneously, can also successively be carried out.
S20, data processor 200 judge signal according to the actual sound signal generation sound status, and by the sound
State judges that signal is sent to microphone 100.The step specifically includes following steps S20a and S20b.
S20a, actual speech signal and sign information to microphone collection pre-process.
S20b, the first analytic unit 221 of data processor 200 calculate the reality using default similarity calculation
The similarity of border voice signal and standard voice signal, using the similarity as the level of sound quality, so as to further generate sound
Matter is horizontal to judge signal；Second analytic unit 222 is using the sorter model and according to the actual sound signal and described
The combination of sign information judges the health status type of the user, so as to further generate health status type decision letter
Number.It should be appreciated that the similarity calculated using the similarity calculation is according to pretreated actual speech signal
Obtain, i.e. what the first analytic unit 221 calculated is the similarity between pretreated actual speech signal and standard signal；
The health status type that second analytic unit 222 is judged using default sorter model is according to pretreated actual language
What sound signal and pretreated sign information obtained.
S21, the update module 250 of data processor 200 are believed according to the actual speech signal and by the actual speech
Number similarity calculated is updated to the similarity calculation.
S22, update module 250 are judged according to the actual sound signal and sign information and by the combination of the two
Health status type the sorter model is updated.The more new principle of update module 250 is being described above, here
Repeat no more.
S30, microphone 100 prompting module 130 according to the sound status judge signal (level of sound quality judge signal and/
Or health status type decision signal) generation alerting signal.
In addition, as described above, microphone 100 can also include identity information acquisition module 150, data processor 200 wraps
Memory module 260 is included, in this case, microphone 100 while actual sound signal and sign information is gathered, adopt by identity information
Collection module 150 can also be acquired to the identity information of user, and step S20 also includes after terminating：Data processor 200 is deposited
Store up the identity information of user and the level of sound quality and/or health status type of the user.
In addition, also include instructing module 270 when the prompting module of microphone 100 includes display panel, data processor 200
When, step S20 also includes afterwards：
Data processor 200 instructs module 270 to judge that signal is instructed in signal generation vocal music according to the level of sound quality, and
According to the health status type decision signal generation health guidance signal；The display panel of microphone 100 refers to according to the vocal music
Signal is led to show vocal music tutorial message and show health guidance information according to the health guidance signal.Vocal music is instructed signal and is good for
Health instructs the generating principle of the generation of signal, vocal music tutorial message and health guidance information being described above, no longer superfluous here
State.
It is above description to microphone provided by the utility model, data processor, monitoring system and monitoring method, can be with
To find out, the actual sound signal that data processor of the present utility model gathers according to microphone judges the level of sound quality of user,
And generate level of sound quality and judge signal, the health status type of user can also be judged according to actual sound signal, and it is raw
Into health condition judging signal；The prompting module of microphone generates alerting signal according to level of sound quality, can also be according to healthy shape
State type generates alerting signal, to remind user.Compared to traditional dependence people (vocal music tutor) listen to pronunciation and
The normal diagnostic of throat doctor is compared, and the monitoring system in the utility model is by way of data analysis to the tonequality of user
Horizontal and health status is monitored at any time so that and user understands the level of sound quality and health status of itself at any time,
So that user understands self-condition more early, and judged result is more objective.Also, microphone can also gather user
Sign information so that the voice signal and sign information of data processor combined use person judge the healthy shape of user
State type, improve the accuracy rate of judgement.In addition, microphone can also gather the identity information of user, data processor will use
The identity information of person and the level of sound quality of user and health status type are stored, consequently facilitating to understand itself near by user
The sound status of phase.
It is understood that embodiment of above is merely to illustrate that principle of the present utility model and used exemplary
Embodiment, but the utility model is not limited thereto.For those skilled in the art, this is not being departed from
In the case of the spirit and essence of utility model, various changes and modifications can be made therein, and these variations and modifications are also considered as this reality
With new protection domain.
Claims (18)
1. a kind of microphone, including sound collection portion, for gathering the actual sound signal of user, it is characterised in that the words
Cylinder also includes：
Signal transmitting and receiving module, it is connected with the sound collection portion, for the actual sound signal for gathering the sound collection portion
Send, and receive and signal is judged according to the sound status of the actual sound signal generation, the sound status judges
The level of sound quality that signal includes being generated according to the level of sound quality of user judges signal and/or the health status class according to user
The health status type decision signal of type generation；
Prompting module, for judging signal generation alerting signal according to the sound status.
2. microphone according to claim 1, it is characterised in that the sound status judges that signal includes the level of sound quality
Judge signal and the health status type decision signal；
The microphone also includes sign information acquisition module, for gathering the sign information of user；
The signal transmitting and receiving module is also connected with the sign information acquisition module, for the sign information acquisition module to be adopted
The sign information collected is sent, and is received and generated institute according to the combination of the actual sound signal and the sign information
State health status type decision signal.
3. microphone according to claim 2, it is characterised in that the sign information include body temperature, pulse wave, blood oxygen amount,
At least one of heart rate and blood pressure.
4. microphone according to claim 2, it is characterised in that the prompting module includes indicator lamp, the alerting signal
Including optical signal；And/or
The prompting module includes display panel, and the alerting signal includes picture signal.
5. microphone according to claim 4, it is characterised in that the microphone includes housing, and the housing includes hand grip portion
With the microphone head for being arranged on the hand grip portion top, the sound collection portion is arranged in the microphone head；The sign
Information acquisition module is arranged on the outer wall of the hand grip portion；
When the prompting module includes indicator lamp, the indicator lamp is arranged in microphone head, and the microphone head can be saturating
Light；
When the prompting module includes display panel, the display panel is arranged on the housing exterior walls.
6. microphone according to claim 5, it is characterised in that the microphone also includes identity information acquisition module, is used for
Gather the identity information of user；The signal transmitting and receiving module is also connected with the identity information acquisition module, and can be by institute
Identity information is stated to send.
7. microphone according to claim 6, it is characterised in that the identity information acquisition module is arranged on the hand grip portion
Outer wall on, the identity information includes finger print information.
A kind of 8. data processor, it is characterised in that including：
Signal receiving module, for receiving transmitted by the signal transmitting and receiving module of the microphone in claim 1 to 7 described in any one
Actual sound signal；
Processing module, it is connected with the signal receiving module, for the reality received according to the signal receiving module
Voice signal generation sound status judges signal, wherein, the sound status judges that signal includes the tonequality water according to user
All one's life into level of sound quality judge signal and/or according to the health status type of user generate health status type decision believe
Number；
Signal transmitting module, it is connected with the processing module, for sound status judgement signal to be sent to the microphone.
9. data processor according to claim 8, it is characterised in that the processing module includes the first analytic unit
And/or second analytic unit：
First analytic unit is used to calculate the actual sound signal and standard voice letter using default similarity calculation
Number similarity, the level of sound quality is used as using the similarity；
Second analytic unit is used for the health status type that the user is judged using default sorter model.
10. data processor according to claim 9, it is characterised in that the similarity calculation includes the first volume
Product neural network model, the sorter model include the second convolution neural network model.
11. data processor according to claim 9, it is characterised in that the processing module includes the described first analysis
Unit and second analytic unit；
When the microphone also includes sign information acquisition module,
The signal receiving module is additionally operable to receive the sign information that the signal transmitting and receiving module of the microphone is sent；Described second point
Analysis unit can judge the health status of the user according to the combination of the actual sound signal and the sign information
Type.
12. data processor according to claim 11, it is characterised in that it is single that the processing module also includes pretreatment
Member, the actual speech signal and the sign information for being gathered to the microphone pre-process, and by after pretreatment
Actual sound signal output to first analytic unit and second analytic unit, pretreated sign information is defeated
Go out to second analytic unit.
13. data processor according to claim 11, it is characterised in that the data processor also includes：
Training module, for being obtained according to default multiple first voice signal samples and each self-corresponding similarity sample training
The similarity calculation；And according to default multiple samples being made up of second sound signal sample and sign sample
Health status type sample training obtains the sorter model corresponding to group and each sample group.
14. data processor according to claim 13, it is characterised in that the data processor also includes：
Update module, it is connected with the training module and the processing module, for according to the actual speech signal and logical
The similarity that the actual speech signal is calculated is crossed to be updated the similarity calculation, and according to the actual sound
Signal and sign information and the health status type judged by the combination of the two are updated to the sorter model.
15. data processor according to claim 8, it is characterised in that when microphone also includes identity information acquisition module
When, the data processor also includes memory module, for storing the identity information of user and the tonequality water of the user
Flat and/or health status type.
16. data processor according to claim 8, it is characterised in that it is described that the sound status judges that signal includes
Level of sound quality judges signal and the health status type decision signal,
When the prompting module of the microphone includes display panel, the data processor also includes instructing module, and this instructs mould
Block is connected with the processing module, for judging that signal is instructed in signal generation vocal music according to the level of sound quality, and according to described
Health status type decision signal generation health guidance signal；
The signal transmitting module also instructs module to be connected with described, for the vocal music to be instructed into signal and health guidance signal
Send to the microphone, so that the display panel of the microphone instructs signal to show vocal music tutorial message according to the vocal music, and
Health guidance information is shown according to the health guidance signal.
17. a kind of monitoring system, it is characterised in that including the microphone and claim described in any one in claim 1 to 7
Data processor in 8 to 16 described in any one.
18. monitoring system according to claim 17, it is characterised in that the microphone and the data processor are integrated into
Integrative-structure；
Or the microphone and the data processor are the structure of two separation, and communicating wireless signals can be carried out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201720498105.3U CN206726760U (en) | 2017-05-05 | 2017-05-05 | Microphone, data processor and monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201720498105.3U CN206726760U (en) | 2017-05-05 | 2017-05-05 | Microphone, data processor and monitoring system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN206726760U true CN206726760U (en) | 2017-12-08 |
Family
ID=60510277
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201720498105.3U Active CN206726760U (en) | 2017-05-05 | 2017-05-05 | Microphone, data processor and monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN206726760U (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108269590A (en) * | 2018-01-17 | 2018-07-10 | 广州势必可赢网络科技有限公司 | Vocal cord recovery scoring method and device |
| WO2018201688A1 (en) * | 2017-05-05 | 2018-11-08 | Boe Technology Group Co., Ltd. | Microphone, vocal training apparatus comprising microphone and vocal analyzer, vocal training method, and non-transitory tangible computer-readable storage medium |
| CN112102849A (en) * | 2019-06-18 | 2020-12-18 | 成都医学院 | Sound analysis method and device |
-
2017
- 2017-05-05 CN CN201720498105.3U patent/CN206726760U/en active Active
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018201688A1 (en) * | 2017-05-05 | 2018-11-08 | Boe Technology Group Co., Ltd. | Microphone, vocal training apparatus comprising microphone and vocal analyzer, vocal training method, and non-transitory tangible computer-readable storage medium |
| CN108806720A (en) * | 2017-05-05 | 2018-11-13 | 京东方科技集团股份有限公司 | Microphone, data processor, monitoring system and monitoring method |
| US10499149B2 (en) | 2017-05-05 | 2019-12-03 | Boe Technology Group Co., Ltd. | Microphone, vocal training apparatus comprising microphone and vocal analyzer, vocal training method, and non-transitory tangible computer-readable storage medium |
| CN108806720B (en) * | 2017-05-05 | 2019-12-06 | 京东方科技集团股份有限公司 | Microphone, data processor, monitoring system and monitoring method |
| CN108269590A (en) * | 2018-01-17 | 2018-07-10 | 广州势必可赢网络科技有限公司 | Vocal cord recovery scoring method and device |
| CN112102849A (en) * | 2019-06-18 | 2020-12-18 | 成都医学院 | Sound analysis method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108806720A (en) | Microphone, data processor, monitoring system and monitoring method | |
| JP7238794B2 (en) | Information processing device, information processing method and program | |
| CN102247128B (en) | Human body pulse information collecting device and human body health status monitoring device | |
| CN206726760U (en) | Microphone, data processor and monitoring system | |
| US20190046067A1 (en) | Exercise guidance method and exercise guidance device | |
| CN107622797A (en) | A kind of health based on sound determines system and method | |
| EP3881910A1 (en) | Information processing device, information processing method, and program | |
| CN103530727A (en) | Management platform system for field operation mental protection shelter | |
| CN106097828A (en) | Technical ability detecting system is sung in a kind of musicology teaching | |
| CN110584601B (en) | Old man cognitive function monitoring and evaluation system | |
| CN107591196A (en) | A kind of auditory sense cognition dysfunction evaluation and test and device for healing and training | |
| CN101125078A (en) | Integrated human body function index comprehensive test device and its working method | |
| CN102525412A (en) | Method and equipment for promoting emotion balance, evaluating emotion state and evaluating emotion regulating effect | |
| JP7367690B2 (en) | information processing equipment | |
| CN108597621A (en) | Health status monitoring device, system and method based on theory of traditional Chinese medical science | |
| CN109859570A (en) | A kind of brain training method and system | |
| CN207024470U (en) | A kind of rope skipping system | |
| KR102324431B1 (en) | Respiration Meditation Inducement device with Headphones for Sensing Brain Wave and Respiration Meditation Inducement System for Displaying and Storing it By Using the Same | |
| CN109949935A (en) | A kind of personalized terminal service campus health platform based on artificial intelligence | |
| CN101785665A (en) | Pulse diagnosis analyzer based on MEMS sensor | |
| CN106618502A (en) | Intelligent robot-based health monitoring apparatus | |
| CN106097829A (en) | A kind of vocal music exercising auxiliary device | |
| CN113521723A (en) | Cognitive function evaluation system and method based on virtual reality | |
| CN208422436U (en) | Health status monitoring device and system based on theory of traditional Chinese medical science | |
| JP4009202B2 (en) | Personal information distribution system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |