CN109088985A - Voice data generation method and relevant apparatus - Google Patents
Voice data generation method and relevant apparatus Download PDFInfo
- Publication number
- CN109088985A CN109088985A CN201810818290.9A CN201810818290A CN109088985A CN 109088985 A CN109088985 A CN 109088985A CN 201810818290 A CN201810818290 A CN 201810818290A CN 109088985 A CN109088985 A CN 109088985A
- Authority
- CN
- China
- Prior art keywords
- voice data
- data
- microphone
- ultrasonic signal
- electronic equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
- H04M1/7243—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality with interactive means for internal management of messages
- H04M1/72433—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality with interactive means for internal management of messages for voice messaging, e.g. dictaphones
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
- H04M1/72454—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions according to context-related or environment-related conditions
Abstract
This application discloses a kind of voice data generation method and relevant apparatus, applied to electronic equipment, the electronic equipment includes microphone and ultrasonic sensor, it include: that electronic equipment obtains ultrasonic signal, it is after generating ultrasonic sensor the first ultrasonic signal of transmission by voice data that voice data, which generates ultrasonic signal, the echo-signal received, ultrasonic signal, which is generated, according to voice data determines that voice data generates microphone and is blocked, when detecting the acquisition instruction of the first voice data, microphone, which is generated, by voice data obtains voice data the first voice data of generation, voice data is generated into the first voice data and inputs the first preset model generation voice data generation target speech data, voice data generates the first preset model and is used to predict the shortage of data segment that voice data generates the first voice data.The application is conducive to improve accuracy and intelligence that electronic equipment carries out voice data generation.
Description
Technical field
This application involves electronic technology field more particularly to a kind of voice data generation method and relevant apparatus.
Background technique
With the rapid development of intelligent terminal (such as smart phone) technology and more more and more universal, user is become
Indispensable electronic product in daily life.In more and more convenient communication, people do not carry out short message, phone singly,
It also will use other communication modes, such as the operation such as voice or progress video calling sent by wechat, when including voice, not
Exempt to will receive the influence of various factors and cause speech absence, so that communication is affected.
Summary of the invention
The embodiment of the present application provides a kind of voice data generation method and relevant apparatus, provides a kind of speech production method,
Be conducive to improve accuracy and intelligence that electronic equipment carries out voice data generation.
In a first aspect, the embodiment of the present application provides a kind of voice data generation method, it is applied to electronic equipment, the electronics
Equipment includes microphone and ultrasonic sensor, which comprises
Ultrasonic signal is obtained, the ultrasonic signal is to send the first ultrasonic signal by the ultrasonic sensor
Afterwards, the echo-signal received；
Determine that the microphone is blocked according to the ultrasonic signal；
When detecting the acquisition instruction of the first voice data, first voice data is obtained by the microphone；
First voice data is inputted into the first preset model and generates target speech data, first preset model is used
In the shortage of data segment for predicting first voice data.
Second aspect, the embodiment of the present application provide a kind of voice data generating means, are applied to electronic equipment, the electronics
Equipment includes microphone and ultrasonic sensor, and the voice data generating means include acquiring unit, determination unit and generation
Unit, wherein
The acquiring unit, for obtaining ultrasonic signal, the ultrasonic signal is sent out by the ultrasonic sensor
After sending the first ultrasonic signal, the echo-signal that receives；
The determination unit, for determining that the microphone is blocked according to the ultrasonic signal；
The acquiring unit is also used to obtain when detecting the acquisition instruction of the first voice data by the microphone
Take first voice data；
The generation unit generates target speech data for first voice data to be inputted the first preset model,
First preset model is used to predict the shortage of data segment of first voice data.
The third aspect, the embodiment of the present application provide a kind of electronic equipment, including processor, memory, communication interface and
One or more programs, wherein said one or multiple programs are stored in above-mentioned memory, and are configured by above-mentioned
It manages device to execute, above procedure is included the steps that for executing the instruction in the embodiment of the present application first aspect either method.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, wherein above-mentioned computer-readable
Storage medium storage is used for the computer program of electronic data interchange, wherein above-mentioned computer program executes computer such as
Step some or all of described in the embodiment of the present application first aspect either method.
As can be seen that in the embodiment of the present application, electronic equipment obtains ultrasonic signal first, and the ultrasonic signal is
After sending the first ultrasonic signal by the ultrasonic sensor, the echo-signal received, secondly, being believed according to the ultrasonic wave
It number determines that the microphone is blocked, then, when detecting the acquisition instruction of the first voice data, is obtained by the microphone
First voice data is taken, finally, first voice data, which is inputted the first preset model, generates target speech data, institute
The first preset model is stated for predicting the shortage of data segment of first voice data.Since electronic equipment can be according to ultrasound
Wave accurately judges the blocked state of microphone, can be according to preset model pair further after having included voice
It includes the part lacked in voice to be restored, avoids the feelings for causing user accidentally to handle because including the missing voice in voice
Condition generates, and is conducive to electronic equipment and is carrying out intelligence and accuracy in voice data generating process.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application or in background technique below will be implemented the application
Attached drawing needed in example or background technique is illustrated.
Fig. 1 is the structural schematic diagram of a kind of electronic equipment provided by the embodiments of the present application；
Fig. 2 is a kind of flow diagram of voice data generation method provided by the embodiments of the present application；
Fig. 3 is the flow diagram of another kind voice data generation method disclosed in the embodiment of the present application；
Fig. 4 is the flow diagram of another kind voice data generation method disclosed in the embodiment of the present application；
Fig. 5 is the structural schematic diagram of a kind of electronic equipment disclosed in the embodiment of the present application；
Fig. 6 is a kind of functional unit composition block diagram of voice data generating means disclosed in the embodiment of the present application.
Specific implementation
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only
The embodiment of the application a part, instead of all the embodiments.Based on the embodiment in the application, ordinary skill people
Member's every other embodiment obtained without making creative work, all should belong to the model of the application protection
It encloses.
It is described in detail separately below.
The description and claims of this application and term " first ", " second ", " third " and " in the attached drawing
Four " etc. are not use to describe a particular order for distinguishing different objects.In addition, term " includes " and " having " and it
Any deformation, it is intended that cover and non-exclusive include.Such as it contains the process, method of a series of steps or units, be
System, product or equipment are not limited to listed step or unit, but optionally further comprising the step of not listing or list
Member, or optionally further comprising other step or units intrinsic for these process, methods, product or equipment.
Referenced herein " embodiment " is it is meant that a particular feature, structure, or characteristic described can wrap in conjunction with the embodiments
It is contained at least one embodiment of the application.Each position in the description occur the phrase might not each mean it is identical
Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and
Implicitly understand, embodiment described herein can be combined with other embodiments.
Electronic equipment may include the various handheld devices with wireless communication function, mobile unit, wearable device (example
Such as smartwatch, Intelligent bracelet, pedometer), calculate equipment or be connected to other processing equipments of radio modem, with
And various forms of user equipmenies (User Equipment, UE), mobile station (Mobile Station, MS), terminal device
(terminal device) etc..For convenience of description, apparatus mentioned above is referred to as electronic equipment.
It describes in detail below to the embodiment of the present application.
Referring to Fig. 1, Fig. 1 is the structural schematic diagram of a kind of electronic equipment 100 provided by the embodiments of the present application, above-mentioned electronics
Equipment 100 includes: shell 110, the circuit board 120 being set in the shell 110, the display being set on the shell 110
Shield 130 and microphone 140, is provided with processor 121 on the circuit board 120, the processor 121 connects the display screen
130。
It describes in detail below to the embodiment of the present application.
Referring to Fig. 2, Fig. 2 is that the embodiment of the present application provides a kind of flow diagram of voice data generation method, answer
For electronic equipment, the electronic equipment includes microphone and ultrasonic sensor, this voice data generation method includes:
S201, electronic equipment obtain ultrasonic signal, and the ultrasonic signal is to send the by the ultrasonic sensor
After one ultrasonic signal, the echo-signal that receives.
Wherein, the mountable top or bottom in electronic equipment of ultrasonic sensor, does not do unique restriction herein.
S202, the electronic equipment determine that the microphone is blocked according to the ultrasonic signal.
Wherein, microphone plug-hole refers to that the through-hole for microphone acquisition sound of electronic equipment is in blocked state, such as
Blocked by the filter medium cloggings such as dust, water or finger etc., do not do unique restriction herein.
S203, the electronic equipment are obtained when detecting the acquisition instruction of the first voice data by the microphone
First voice data.
Wherein, the first voice data can include but is not limited to tone color, volume, audio etc., not do unique restriction herein.
First voice data is inputted the first preset model and generates target speech data by S204, the electronic equipment,
First preset model is used to predict the shortage of data segment of first voice data.
Wherein, preset model is model of mind, and model of mind includes many algorithms, can be predicted according to many algorithms described in
The shortage of data segment of first voice data.
As can be seen that electronic equipment obtains ultrasonic signal first in the embodiment of the present application, the ultrasonic signal be by
After the ultrasonic sensor sends the first ultrasonic signal, the echo-signal received, secondly, according to the ultrasonic signal
It determines that the microphone is blocked, then, when detecting the acquisition instruction of the first voice data, is obtained by the microphone
First voice data, finally, first voice data, which is inputted the first preset model, generates the target speech data,
First preset model is used to predict the shortage of data segment of first voice data.Since electronic equipment can be according to super
Sound wave accurately judges the blocked state of microphone, can be according to preset model further after having included voice
It is restored to the part lacked in voice is included, avoid causes user to miss processing because including the missing voice in voice
Situation generates, and is conducive to electronic equipment and is carrying out intelligence and accuracy in voice data generating process.
It is described to determine that the microphone is blocked according to the ultrasonic signal, comprising: electricity in a possible example
Sub- equipment detects at least one signal strength of the ultrasonic signal, at least one described signal strength in preset period of time
In each signal strength correspond to multiple periods in the preset period of time；If at least one signal in the preset period of time is strong
Degree is lower than preset signal strength, it is determined that the microphone is blocked.
Wherein, preset signal strength can include but is not limited to 20HZ, 50HZ, 100HZ etc., not do unique restriction herein.
For example, electronic equipment detects the ultrasonic signal strength within the 2S time, obtains detecting letter at 0.2 second
Number intensity is 20HZ, and the signal strength detected at 1 second is that 30HZ, 20HZ and 30HZ are below preset signal strength 100HZ,
Judge that current microphone is blocked.
As it can be seen that electronic equipment, to the detection of ultrasonic wave, can accurately judge wheat according within the period in this example
Whether gram wind is blocked, and avoids because of the case where detecting the signal strength outside more than the period, causing erroneous judgement, is conducive to mention
Intelligence and accuracy of the high electronic equipment when judging microphone blocking.
It is described to determine that the microphone is blocked according to the ultrasonic signal, comprising: electricity in a possible example
Sub- equipment detection gets the first time point of the ultrasonic signal and sends the second time of first ultrasonic signal
Point；The first time point and second time point are done into difference operation, obtain object time difference；If the object time
Difference is lower than preset time difference, it is determined that the microphone is blocked.
Wherein, preset time difference is, preset time difference poor according to normal time of the microphone in unplugged situation
It can include but is not limited to one second, two seconds, three seconds etc., do not do unique restriction herein.
For example, electronic equipment sends ultrasonic signal in 18 o'clock sharps of X X month X day, the 18: 0 of X X month X day
Points 2 seconds, echo-signal is received, 18 points of 2 seconds 0 minute and 18 o'clock sharps are done into difference operation, obtaining time difference is 2 seconds, lower than presetting
Time difference 6S is determined current microphone and is blocked.
As it can be seen that electronic equipment issues time and receiving time by detection in this example, the time difference is obtained, that is, when passing through
Between further judge whether microphone is blocked, if be blocked, the time difference can from far away be less than normal time it is poor, if not
Be blocked, time difference and normal time difference are essentially identical, improve electronic equipment when judge microphone blocking it is intelligent with
Accuracy.
It is described that first voice data is inputted into the first preset model generation target voice in a possible example
Data, comprising: electronic equipment determines at least one period of first voice data, institute by first preset model
Stating at least one period is at least one shortage of data segment corresponding period；It filters out at least one described period
Greater than the target time section of preset duration；It is crucial to extract at least one of reference time section corresponding with the target time section
Word, the reference time section are the part in the period in first voice data in addition at least one described period
Period；The second speech data of the shortage of data segment is determined according at least one described keyword；According to described second
Voice data and first voice data generate target speech data.
Wherein, reference time section is front and back five seconds, front and back three seconds, front and back four seconds etc., does not do unique restriction herein.
Wherein, preset duration can include but is not limited to three seconds, four seconds, five seconds, ten seconds etc., not do unique restriction herein.
As it can be seen that electronic equipment passes through the period of detection data deletion fragment, and further determine is more than pre- in this example
If the shortage of data segment of time, and according to the front and back of shortage of data segment sentence, data convert is carried out, is avoided in multiple numbers
When existing simultaneously according to deletion fragment, caused the case where accidentally restoring, improves electronic equipment progress voice data and generated
High efficiency and intelligence in journey.
In a possible example, described at least one keyword according to determines the of the shortage of data segment
Two voice data, comprising: electronic equipment obtains the first category of at least one keyword；It inquires belonging to the first category
Presetting database, the presetting database is stored with the associated voice data of the first category；When obtaining current target
Between parameter；In the presetting database, filter out and the matched target speech data of object time parameter, the target
Voice data is the second speech data of the shortage of data segment.
Wherein, classification is type or difference that is different by type and making different in keyword.
Wherein, the associated voice data of the first category of presetting database storage, has on every voice data pair
The time identifier answered in any time, can accurately find corresponding voice data according to the time identifier.
As it can be seen that electronic equipment obtains corresponding speech database, further according to the classification of keyword in this example
According to the current time, obtaining the voice data corresponding with the time in the database can accurately be determined by matching twice
Position goes out the scene of current missing voice, is conducive to accurate fixed and intelligence when electronic equipment is determined speech absence data.
In a possible example, described at least one keyword according to determines the of the shortage of data segment
After two voice data, the method also includes: obtain the voice in first voice data in addition to data deletion fragment
First tamber parameter；First tamber parameter is set by the tamber parameter of the second speech data.
Wherein, tone color, which refers in terms of the frequency of different sound shows waveform, always distinguished characteristic, tone color
It is to be determined by the harmonic spectrum and envelope of sound waveform.
As it can be seen that when electronic equipment restores data deletion fragment, adjusting the also raw content of deletion fragment in this example
Tone color, the voice data of the generation made is more natural, accurate, improves electronic equipment in carrying out voice data generating process
Intelligence.
It is consistent with the embodiment shown in Fig. 2, referring to Fig. 3, Fig. 3 is a kind of voice provided by the embodiments of the present application
The flow diagram of data creation method is applied to electronic equipment, and the electronic equipment includes microphone and ultrasonic sensor.
As shown, this voice data generation method includes:
S301, electronic equipment obtain ultrasonic signal, and the ultrasonic signal is to send the by the ultrasonic sensor
After one ultrasonic signal, the echo-signal that receives.
S302, electronic equipment detection, which gets the first time point of the ultrasonic signal and sends, described the first to surpass
Second time point of acoustic signals.
The first time point and second time point are done difference operation, obtain target by S303, the electronic equipment
Time difference.
S304, if the object time difference is lower than preset time difference, it is determined that the microphone is blocked.
S305, the electronic equipment are obtained when detecting the acquisition instruction of the first voice data by the microphone
First voice data.
First voice data is inputted the first preset model and generates target speech data by S306, the electronic equipment,
First preset model is used to predict the shortage of data segment of first voice data.
As can be seen that electronic equipment obtains ultrasonic signal first in the embodiment of the present application, the ultrasonic signal be by
After the ultrasonic sensor sends the first ultrasonic signal, the echo-signal received, secondly, according to the ultrasonic signal
It determines that the microphone is blocked, then, when detecting the acquisition instruction of the first voice data, is obtained by the microphone
First voice data, finally, first voice data, which is inputted the first preset model, generates target speech data, it is described
First preset model is used to predict the shortage of data segment of first voice data.Since electronic equipment can be according to ultrasonic wave
The blocked state of microphone is accurately judged, it, can be according to preset model to receipts further after having included voice
The part lacked in record voice is restored, and the case where causing user accidentally to handle because including the missing voice in voice is avoided
It generates, is conducive to electronic equipment and is carrying out intelligence and accuracy in voice data generating process.
In addition, electronic equipment issues time and receiving time by detection, obtain the time difference, i.e., it is further by the time
Judge whether microphone is blocked, if being blocked, the time difference can be poor less than normal time from far away, if not being blocked, when
Between difference it is essentially identical with normal time difference, improve electronic equipment judge microphone block when intelligence and accuracy.
It is consistent with the embodiment shown in Fig. 2, referring to Fig. 4, Fig. 4 is a kind of voice provided by the embodiments of the present application
The flow diagram of data creation method is applied to electronic equipment, and the electronic equipment includes microphone and ultrasonic sensor.
As shown, this voice data generation method includes:
S401, electronic equipment obtain ultrasonic signal, and the ultrasonic signal is to send the by the ultrasonic sensor
After one ultrasonic signal, the echo-signal that receives.
S402, the electronic equipment determine that the microphone is blocked according to the ultrasonic signal.
S403, the electronic equipment are obtained when detecting the acquisition instruction of the first voice data by the microphone
First voice data.
S404, when the electronic equipment determines at least one of first voice data by first preset model
Between section, at least one described period be at least one shortage of data segment corresponding period.
S405, the electronic equipment filter out the target time section for being greater than preset duration at least one described period.
S406, it is crucial that the electronic equipment extracts at least one of reference time section corresponding with the target time section
Word.
S407, the electronic equipment obtain the first category of at least one keyword.
S408, the electronic equipment inquire presetting database belonging to the first category.
S409, the electronic equipment obtain current object time parameter.
S410, the electronic equipment filter out and the matched mesh of object time parameter in the presetting database
Voice data is marked, the target speech data is the second speech data of the shortage of data segment.
S411, the electronic equipment generate the target language according to the second speech data and first voice data
Sound data.
It can be seen that the embodiment of the present application, electronic equipment obtains ultrasonic signal first, and the ultrasonic signal is by institute
After stating ultrasonic sensor the first ultrasonic signal of transmission, the echo-signal received, secondly, true according to the ultrasonic signal
The fixed microphone is blocked, and then, when detecting the acquisition instruction of the first voice data, obtains institute by the microphone
The first voice data is stated, finally, first voice data, which is inputted the first preset model, generates target speech data, described the
One preset model is used to predict the shortage of data segment of first voice data.Since electronic equipment can be according to ultrasonic wave pair
The blocked state of microphone is accurately judged, can be according to preset model to including further after having included voice
The part lacked in voice is restored, and the case where causing user accidentally to handle because including the missing voice in voice production is avoided
It is raw, be conducive to electronic equipment and carry out intelligence and accuracy in voice data generating process.
In addition, electronic equipment passes through the period of detection data deletion fragment, further determine is more than preset time
Shortage of data segment, and according to the front and back of shortage of data segment sentence, data convert is carried out, is avoided in multiple shortage of data pieces
When section exists simultaneously, caused the case where accidentally restoring, improves the height in electronic equipment progress voice data generating process
Effect property and intelligence.
It is further according to current in addition, classification of the electronic equipment according to keyword, obtains corresponding speech database
Time obtains the voice data corresponding with the time in the database, by matching twice, can accurately orient current lack
The scene of aphasia sound is conducive to accurate fixed and intelligence when electronic equipment is determined speech absence data.
It is consistent with described Fig. 2, Fig. 3, embodiment shown in Fig. 4, referring to Fig. 5, Fig. 5 is provided by the embodiments of the present application
The structural schematic diagram of a kind of electronic equipment 500, as shown, the electronic equipment 500 includes application processor 510, memory
520, communication interface 530 and one or more programs 521, wherein one or more of programs 521 are stored in above-mentioned deposit
In reservoir 520, and it is configured to be executed by above-mentioned application processor 510, one or more of programs 521 include for executing
The instruction of following steps；
Ultrasonic signal is obtained, the ultrasonic signal is to send the first ultrasonic signal by the ultrasonic sensor
Afterwards, the echo-signal received；
Determine that the microphone is blocked according to the ultrasonic signal；
When detecting the acquisition instruction of the first voice data, first voice data is obtained by the microphone；
First voice data is inputted into the first preset model and generates target speech data, first preset model is used
In the shortage of data segment for predicting first voice data.
As can be seen that electronic equipment obtains ultrasonic signal first in the embodiment of the present application, the ultrasonic signal be by
After the ultrasonic sensor sends the first ultrasonic signal, the echo-signal received, secondly, according to the ultrasonic signal
It determines that the microphone is blocked, then, when detecting the acquisition instruction of the first voice data, is obtained by the microphone
First voice data, finally, first voice data, which is inputted the first preset model, generates target speech data, it is described
First preset model is used to predict the shortage of data segment of first voice data.Since electronic equipment can be according to ultrasonic wave
The blocked state of microphone is accurately judged, it, can be according to preset model to receipts further after having included voice
The part lacked in record voice is restored, and the case where causing user accidentally to handle because including the missing voice in voice is avoided
It generates, is conducive to electronic equipment and is carrying out intelligence and accuracy in voice data generating process.
In a possible example, the blocked aspect of the microphone is determined according to the ultrasonic signal described,
Instruction in described program is specifically used for executing following operation: at least the one of the ultrasonic signal is detected in preset period of time
A signal strength, each signal strength corresponds to multiple periods in the preset period of time at least one described signal strength；If
At least one signal strength in the preset period of time is lower than preset signal strength, it is determined that the microphone is blocked.
In a possible example, the blocked aspect of the microphone is determined according to the ultrasonic signal described,
Instruction in described program is specifically used for executing following operation: detection gets the first time point and hair of the ultrasonic signal
Send the second time point of first ultrasonic signal；The first time point and second time point are done into difference operation,
Obtain object time difference；If the object time difference is lower than preset time difference, it is determined that the microphone is blocked.
In a possible example, first voice data is inputted into the first preset model generation target language described
In terms of sound data, the instruction in described program is specifically used for executing following operation: described in being determined by first preset model
At least one period of first voice data, when at least one described period is that at least one shortage of data segment is corresponding
Between section；Filter out the target time section for being greater than preset duration at least one described period；It extracts and the target time section
At least one keyword in corresponding reference time section, the reference time section be in first voice data except it is described extremely
The partial time period in period except a few period；The shortage of data is determined according at least one described keyword
The second speech data of segment；Target speech data is generated according to the second speech data and first voice data.
In a possible example, the shortage of data segment is determined in described at least one keyword according to
In terms of second speech data, the instruction in described program is specifically used for executing following operation: obtaining at least one described keyword
First category；Presetting database belonging to the first category is inquired, the presetting database is stored with the first category
Associated voice data；Obtain current object time parameter；In the presetting database, filter out and the object time
The matched target speech data of parameter, the target speech data are the second speech data of the shortage of data segment.
In a possible example, the shortage of data segment is determined in described at least one keyword according to
After second speech data, the instruction in described program is also used to execute following operation: obtaining and removes in first voice data
First tamber parameter of the voice outside shortage of data segment；Described first is set by the tamber parameter of the second speech data
Tamber parameter.
Above-described embodiment is mainly described the scheme of the embodiment of the present application from the angle of method side implementation procedure.It can
With understanding, in order to realize the above functions, it comprises execute the corresponding hardware configuration of each function and/or soft for electronic equipment
Part module.Those skilled in the art should be readily appreciated that, described in conjunction with the examples disclosed in the embodiments of the present disclosure
Unit and algorithm steps, the application can be realized with the combining form of hardware or hardware and computer software.Some function is studied carefully
Unexpectedly it is executed in a manner of hardware or computer software driving hardware, the specific application and design constraint depending on technical solution
Condition.Professional technician can specifically realize described function to each using distinct methods, but this
It realizes it is not considered that exceeding scope of the present application.
The embodiment of the present application can carry out the division of functional unit according to the method example to electronic equipment, for example, can
With each functional unit of each function division of correspondence, two or more functions can also be integrated in a processing unit
In.The integrated unit both can take the form of hardware realization, can also realize in the form of software functional units.It needs
It is noted that be schematical, only a kind of logical function partition to the division of unit in the embodiment of the present application, it is practical real
It is current that there may be another division manner.
The following is an embodiment of the apparatus of the present invention, and apparatus of the present invention embodiment is realized for executing embodiment of the present invention method
Method.Voice data generating means 600 as shown in FIG. 6, be applied to electronic equipment, the electronic equipment include microphone and
Ultrasonic sensor, the voice data generating means 600 include acquiring unit 601, determination unit 602 and generation unit 603,
Wherein,
The acquiring unit 601, for obtaining ultrasonic signal, the ultrasonic signal is by the ultrasonic sensor
After sending the first ultrasonic signal, the echo-signal that receives；
The determination unit 602, for determining that the microphone is blocked according to the ultrasonic signal；
The acquiring unit 601 is also used to pass through the microphone when detecting the acquisition instruction of the first voice data
Obtain first voice data；
The generation unit 603 generates target voice number for first voice data to be inputted the first preset model
According to first preset model is used to predict the shortage of data segment of first voice data.
As can be seen that electronic equipment obtains ultrasonic signal first in the embodiment of the present application, the ultrasonic signal be by
After the ultrasonic sensor sends the first ultrasonic signal, the echo-signal received, secondly, according to the ultrasonic signal
It determines that the microphone is blocked, then, when detecting the acquisition instruction of the first voice data, is obtained by the microphone
First voice data, finally, first voice data, which is inputted the first preset model, generates target speech data, it is described
First preset model is used to predict the shortage of data segment of first voice data.Since electronic equipment can be according to ultrasonic wave
The blocked state of microphone is accurately judged, it, can be according to preset model to receipts further after having included voice
The part lacked in record voice is restored, and the case where causing user accidentally to handle because including the missing voice in voice is avoided
It generates, is conducive to electronic equipment and is carrying out intelligence and accuracy in voice data generating process.
In a possible example, the blocked aspect of the microphone is determined according to the ultrasonic signal described,
The determination unit 602 is specifically used for: at least one signal strength of the ultrasonic signal, institute are detected in preset period of time
It states each signal strength at least one signal strength and corresponds to multiple periods in the preset period of time；If in the preset period of time
At least one interior signal strength is lower than preset signal strength, it is determined that the microphone is blocked.
In a possible example, the blocked aspect of the microphone is determined according to the ultrasonic signal described,
The determination unit 602 is specifically used for: detection, which gets the first time point of the ultrasonic signal and sends, described the first to surpass
Second time point of acoustic signals；The first time point and second time point are done into difference operation, obtain the object time
Difference；If the object time difference is lower than preset time difference, it is determined that the microphone is blocked.
In a possible example, first voice data is inputted into the first preset model generation target language described
In terms of sound data, the generation unit 603 is specifically used for: determining first voice data by first preset model
At least one period, at least one described period are at least one shortage of data segment corresponding period；Filter out institute
State the target time section for being greater than preset duration at least one period；Extract the reference time corresponding with the target time section
At least one keyword in section, reference time section be in first voice data except at least one described period it
Partial time period in the outer period；The second voice of the shortage of data segment is determined according at least one described keyword
Data；
Target speech data is generated according to the second speech data and first voice data.
In a possible example, the shortage of data segment is determined in described at least one keyword according to
In terms of second speech data, the generation unit 603 is specifically used for: obtaining the first category of at least one keyword；It looks into
Presetting database belonging to the first category is ask, the presetting database is stored with the associated voice number of the first category
According to；Obtain current object time parameter；In the presetting database, filter out and the matched mesh of object time parameter
Voice data is marked, the target speech data is the second speech data of the shortage of data segment.
In a possible example, the voice data generating means further include setting unit, described according to
After at least one keyword determines the second speech data of the shortage of data segment, the unit 604 is specifically used for:
Obtain the first tamber parameter of the voice in first voice data in addition to data deletion fragment；By the second speech data
Tamber parameter be set as first tamber parameter.
The embodiment of the present application also provides a kind of computer storage medium, wherein computer storage medium storage is for electricity
The computer program of subdata exchange, the computer program make computer execute any as recorded in above method embodiment
Some or all of method step, above-mentioned computer include electronic equipment.
The embodiment of the present application also provides a kind of computer program product, and above-mentioned computer program product includes storing calculating
The non-transient computer readable storage medium of machine program, above-mentioned computer program are operable to that computer is made to execute such as above-mentioned side
Some or all of either record method step in method embodiment.The computer program product can be a software installation
Packet, above-mentioned computer includes electronic equipment.
It should be noted that for the various method embodiments described above, for simple description, therefore, it is stated as a series of
Combination of actions, but those skilled in the art should understand that, the application is not limited by the described action sequence because
According to the application, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art should also know
It knows, the embodiments described in the specification are all preferred embodiments, related actions and modules not necessarily the application
It is necessary.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, reference can be made to the related descriptions of other embodiments.
In several embodiments provided herein, it should be understood that disclosed device, it can be by another way
It realizes.For example, the apparatus embodiments described above are merely exemplary, such as the division of said units, it is only a kind of
Logical function partition, there may be another division manner in actual implementation, such as multiple units or components can combine or can
To be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Coupling, direct-coupling or communication connection can be through some interfaces, the indirect coupling or communication connection of device or unit,
It can be electrical or other forms.
Above-mentioned unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If above-mentioned integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer-readable access to memory.Based on this understanding, the technical solution of the application substantially or
Person says that all or part of the part that contributes to existing technology or the technical solution can body in the form of software products
Reveal and, which is stored in a memory, including some instructions are used so that a computer equipment
(can be personal computer, server or network equipment etc.) executes all or part of each embodiment above method of the application
Step.And memory above-mentioned includes: USB flash disk, read-only memory (ROM, Read-Only Memory), random access memory
The various media that can store program code such as (RAM, Random Access Memory), mobile hard disk, magnetic or disk.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can store in a computer-readable memory, memory
May include: flash disk, read-only memory (English: Read-Only Memory, referred to as: ROM), random access device (English:
Random Access Memory, referred to as: RAM), disk or CD etc..
The embodiment of the present application is described in detail above, specific case used herein to the principle of the application and
Embodiment is expounded, the description of the example is only used to help understand the method for the present application and its core ideas；
At the same time, for those skilled in the art can in specific embodiments and applications according to the thought of the application
There is change place, in conclusion the contents of this specification should not be construed as limiting the present application.
Claims (10)
1. a kind of voice data generation method, which is characterized in that be applied to electronic equipment, the electronic equipment include microphone and
Ultrasonic sensor, which comprises
Ultrasonic signal is obtained, the ultrasonic signal is after sending the first ultrasonic signal by the ultrasonic sensor, to connect
The echo-signal received；
Determine that the microphone is blocked according to the ultrasonic signal；
When detecting the acquisition instruction of the first voice data, first voice data is obtained by the microphone；
First voice data is inputted into the first preset model and generates target speech data, first preset model is for pre-
Survey the shortage of data segment of first voice data.
2. the method according to claim 1, wherein described determine the microphone according to the ultrasonic signal
It is blocked, comprising:
At least one signal strength of the ultrasonic signal is detected in preset period of time, at least one described signal strength
Each signal strength corresponds to multiple periods in the preset period of time；
If at least one signal strength in the preset period of time is lower than preset signal strength, it is determined that the microphone is blocked
Plug.
3. the method according to claim 1, wherein described determine the microphone according to the ultrasonic signal
It is blocked, comprising:
Detection gets the first time point of the ultrasonic signal and sends the second time point of first ultrasonic signal；
The first time point and second time point are done into difference operation, obtain object time difference；
If the object time difference is lower than preset time difference, it is determined that the microphone is blocked.
4. method according to claim 1-3, which is characterized in that described by first voice data input the
One preset model generates target speech data, comprising:
At least one period of first voice data, at least one described time are determined by first preset model
Section is at least one shortage of data segment corresponding period；
Filter out the target time section for being greater than preset duration at least one described period；
At least one keyword in reference time section corresponding with the target time section is extracted, the reference time section is institute
State the partial time period in the period in the first voice data in addition at least one described period；
The second speech data of the shortage of data segment is determined according at least one described keyword；
Target speech data is generated according to the second speech data and first voice data.
5. according to the method described in claim 4, it is characterized in that, described at least one keyword according to determines the number
According to the second speech data of deletion fragment, comprising:
Obtain the first category of at least one keyword；
Presetting database belonging to the first category is inquired, the presetting database is stored with the associated language of the first category
Sound data；
Obtain current object time parameter；
In the presetting database, filter out and the matched target speech data of object time parameter, the target language
Sound data are the second speech data of the shortage of data segment.
6. according to the method described in claim 4, it is characterized in that, described at least one keyword according to determines the number
After the second speech data of deletion fragment, the method also includes:
Obtain the first tamber parameter of the voice in first voice data in addition to data deletion fragment；
First tamber parameter is set by the tamber parameter of the second speech data.
7. a kind of voice data generating means, which is characterized in that be applied to electronic equipment, the electronic equipment include microphone and
Ultrasonic sensor, the voice data generating means include acquiring unit, determination unit and generation unit, wherein
The acquiring unit, for obtaining ultrasonic signal, the ultrasonic signal is that the is sent by the ultrasonic sensor
After one ultrasonic signal, the echo-signal that receives；
The determination unit, for determining that the microphone is blocked according to the ultrasonic signal；
The acquiring unit is also used to when detecting the acquisition instruction of the first voice data, obtains institute by the microphone
State the first voice data；
The generation unit generates target speech data for first voice data to be inputted the first preset model, described
First preset model is used to predict the shortage of data segment of first voice data.
8. device according to claim 7, which is characterized in that determine the Mike according to the ultrasonic signal described
In terms of wind is blocked, the determination unit is specifically used for:
At least one signal strength of the ultrasonic signal is detected in preset period of time, at least one described signal strength
Each signal strength corresponds to multiple periods in the preset period of time；
If at least one signal strength in the preset period of time is lower than preset signal strength, it is determined that the microphone is blocked
Plug.
9. a kind of electronic equipment, which is characterized in that including processor, memory, communication interface, and one or more programs,
One or more of programs are stored in the memory, and are configured to be executed by the processor, described program packet
Include the instruction for executing the step in as the method according to claim 1 to 6.
10. a kind of computer readable storage medium, which is characterized in that storage is used for the computer program of electronic data interchange,
In, the computer program makes computer execute as the method according to claim 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810818290.9A CN109088985A (en) | 2018-07-24 | 2018-07-24 | Voice data generation method and relevant apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810818290.9A CN109088985A (en) | 2018-07-24 | 2018-07-24 | Voice data generation method and relevant apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109088985A true CN109088985A (en) | 2018-12-25 |
Family
ID=64838297
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810818290.9A Pending CN109088985A (en) | 2018-07-24 | 2018-07-24 | Voice data generation method and relevant apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109088985A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120077527A (en) * | 2010-12-30 | 2012-07-10 | 부산대학교 산학협력단 | Apparatus and method for feature compensation using weighted auto-regressive moving average filter and global cepstral mean and variance normalization |
| CN106790806A (en) * | 2016-12-21 | 2017-05-31 | 宇龙计算机通信科技(深圳)有限公司 | Loudspeaker assembly, mobile terminal and mobile terminal go out sound direction-controlling method |
| CN107393544A (en) * | 2017-06-19 | 2017-11-24 | 维沃移动通信有限公司 | A kind of voice signal restoration method and mobile terminal |
-
2018
- 2018-07-24 CN CN201810818290.9A patent/CN109088985A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120077527A (en) * | 2010-12-30 | 2012-07-10 | 부산대학교 산학협력단 | Apparatus and method for feature compensation using weighted auto-regressive moving average filter and global cepstral mean and variance normalization |
| CN106790806A (en) * | 2016-12-21 | 2017-05-31 | 宇龙计算机通信科技(深圳)有限公司 | Loudspeaker assembly, mobile terminal and mobile terminal go out sound direction-controlling method |
| CN107393544A (en) * | 2017-06-19 | 2017-11-24 | 维沃移动通信有限公司 | A kind of voice signal restoration method and mobile terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108958696A (en) | Principal and subordinate's earphone method for handover control and Related product | |
| CN108966067A (en) | Control method for playing back and Related product | |
| CN105654767A (en) | Station-arrival reminding processing method, device and terminal | |
| CN109660911A (en) | Recording sound effect treatment method, device, mobile terminal and storage medium | |
| JP5319062B2 (en) | Group formation analysis system | |
| CN108924417A (en) | Filming control method and Related product | |
| CN109151697A (en) | Microphone plug-hole detection method and Related product | |
| CN108595003A (en) | Function control method and relevant device | |
| CN107785027A (en) | A kind of audio-frequency processing method and electronic equipment | |
| CN109121046A (en) | Plug-hole processing method and Related product | |
| CN109121059A (en) | Loudspeaker plug-hole detection method and Related product | |
| CN110475020A (en) | Apparatus control method and Related product | |
| CN109089201A (en) | Microphone plug-hole detection method and Related product | |
| CN109065017A (en) | Voice data generation method and relevant apparatus | |
| CN109274812A (en) | The method and Related product of ultrasonic wave gesture control electronic device | |
| CN105632497A (en) | Voice output method, voice output system | |
| CN109121042A (en) | Voice data processing method and Related product | |
| CN108965562A (en) | Voice data generation method and relevant apparatus | |
| CN104898838B (en) | The incoming call response method and device of handheld device | |
| CN108337370B (en) | Fault detection method and Related product | |
| CN204117590U (en) | Voice collecting denoising device and voice quality assessment system | |
| CN108924705A (en) | 3D sound effect treatment method and Related product | |
| CN109391869A (en) | A kind of earphone and ear canal judge cut-in method | |
| CN108399325A (en) | Solve lock control method and Related product | |
| CN109088985A (en) | Voice data generation method and relevant apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181225 |
|
| RJ01 | Rejection of invention patent application after publication |