CN105741841B - Sound control method and electronic equipment - Google Patents
Sound control method and electronic equipment Download PDFInfo
- Publication number
- CN105741841B CN105741841B CN201410768009.7A CN201410768009A CN105741841B CN 105741841 B CN105741841 B CN 105741841B CN 201410768009 A CN201410768009 A CN 201410768009A CN 105741841 B CN105741841 B CN 105741841B
- Authority
- CN
- China
- Prior art keywords
- voice data
- digital audio
- voice
- frequency
- audio frequency
- 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
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a kind of sound control method, the sound control method the following steps are included: A, voice control key triggering when, acquire voice data, and obtain collected voice data digital audio frequency；B, judge whether the voice data is voice data according to the digital audio frequency；If C, voice data, then acquired according to the digital audio set of frequency and extend the time, and when the voice control key is closed, extends time extension sound collection according to the acquisition.The invention also discloses a kind of electronic equipment.The present invention can be improved the integrality of the voice messaging of acquisition.
Description
Technical field
The present invention relates to voice control field more particularly to a kind of sound control methods and electronic equipment.
Background technique
With the development of communication technology, various electronic equipments are tending to be digitized while also tending to be intelligent.At present may be used
It is generally used to record etc. to carry out the electronic equipment of sound collection, does not have other intelligentized functions.For example, user
In the electronic device preset acquisition time, but to the time of voice collecting hold inaccuracy, in the acquisition time cannot with
The voice messaging acquisition at family is complete, for example, adopting when that is, electronic equipment has enrolled audio data not yet if user speaks relatively slowly
Collection just finishes, and the voice messaging at this moment acquired is imperfect.
Summary of the invention
The skill that it is a primary object of the present invention to solve that the incomplete situation of electronic equipment acquisition voice messaging is avoided to occur
Art problem.
To achieve the above object, a kind of sound control method provided by the invention, comprising:
A, voice control key trigger when, acquire voice data, and obtain collected voice data digital audio
Frequency；
B, judge whether the voice data is voice data according to the digital audio frequency；
If C, voice data, is then acquired according to the digital audio set of frequency and extend the time, and in the voice control
When key processed is closed, extend time extension sound collection according to the acquisition.
Preferably, after the step B further include:
If D, non-speech data, when reaching the preset sound collection time, stop the acquisition of the voice data.
Preferably, the step B includes:
The digital audio frequency for acquiring the voice data, by digital audio frequency collected and preset sound frequency range
It is compared；
If digital audio frequency collected in the preset sound band limits, judges that the voice data is
Voice data.
Preferably, the sound control method further includes step E, F:
E, voice data collected is subjected to speech recognition, obtains recognition result；
F, recognition result is sent to smart machine, using as the smart machine input instruction to the smart machine into
Row operation.
Preferably, the step E includes:
The voice data is matched with the word of local dictionary；
If successful match, using the word of successful match as the recognition result；
If it fails to match, by the audio data transmitting to cloud, and the recognition result of cloud return is obtained.
To achieve the goals above, the present invention also provides a kind of electronic equipment, the electronic equipment includes:
Module is obtained, for acquiring voice data in the triggering of voice control key, and obtains the collected voice data of institute
Digital audio frequency；
Judgment module, for judging whether the voice data is voice data according to the digital audio frequency；
Setup module then acquires according to the digital audio set of frequency if being used for voice data and extends the time, and
When the voice control key is closed, extend time extension sound collection according to the acquisition.
Preferably, the electronic equipment further include:
Stopping modular, if stopping the sound number when reaching the preset sound collection time for non-speech data
According to acquisition.
Preferably, the judgment module includes:
Comparing unit, for acquiring the digital audio frequency of the voice data, by digital audio frequency collected with
Preset sound frequency range is compared；
Judging unit, if judging in the preset sound band limits for digital audio frequency collected
The voice data is voice data.
Preferably, the electronic equipment further include:
Identification module obtains recognition result for voice data collected to be carried out speech recognition；
Sending module, for recognition result to be sent to smart machine, to instruct as smart machine input to institute
Smart machine is stated to be operated.
Preferably, the identification module includes:
Matching unit, for matching the voice data with the word of local dictionary；
First recognition unit, if successful match is used for, using the word of successful match as the recognition result；
Second recognition unit, if by the audio data transmitting to cloud, and obtaining cloud return for it fails to match
Recognition result.
Of the invention a kind of sound control method and electronic equipment, electronic equipment acquires voice data, according to voice data
Digital audio frequency confirm its whether be voice input voice data, if it is voice data, then according to digital audio frequency
Rate setting acquisition extends the time, i.e., extends the time according to user's speed degree setting acquisition of speaking, avoid user speak it is relatively slow,
Speech controling switch closes in advance and the incomplete situation of the voice data of admission is caused to occur, and improves the voice data of admission
Integrality.
Detailed description of the invention
Fig. 1 is the flow diagram of sound control method first embodiment of the present invention；
Fig. 2 is the flow diagram of sound control method second embodiment of the present invention；
Fig. 3 is the refinement flow diagram of the step B in Fig. 1；
Fig. 4 is the flow diagram of sound control method 3rd embodiment of the present invention；
Fig. 5 is the functional block diagram of electronic equipment first embodiment of the present invention；
Fig. 6 is the functional block diagram of electronic equipment second embodiment of the present invention；
Fig. 7 is the functional block diagram of judgment module in Fig. 5；
Fig. 8 is the functional block diagram of electronic equipment 3rd embodiment of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The present invention provides a kind of sound control method, and referring to Fig.1, in one embodiment, which includes:
Step A, voice control key triggering when, acquire voice data, and obtain collected voice data number
Audio frequency；
In the present embodiment, preset phonetic controller in electronic equipment starts to acquire sound when pressing voice control key
Data.
Preferably, the present embodiment is more suitable for carrying out the admission of the voice data of short time, such as the sound number in admission 5 seconds
According to.
In the present embodiment, electronic equipment is converted into digital signal while acquiring voice data.Wherein, it is acquiring
The digital audio frequency that voice data is just obtained when sub-fraction voice data can know sound according to the digital audio frequency
The speed of the word speed of data, and then according to the operation of the speed of the word speed of voice data progress next step.
For example, the electronic equipment in the present embodiment, which can be remote controler or other, can acquire the electronics of voice data
Equipment (such as mobile phone, recording pen), when user presses the voice control key in remote controler, speech controling switch is connected, so
The voice data in ambient enviroment is acquired afterwards, remote controler can be used for example, the voice collecting of user gets off, it is defeated as voice
Enter to control television set.In the present embodiment, while acquiring voice data, obtain collected voice data number
Audio frequency.
Step B judges whether the voice data is voice data according to the digital audio frequency；
Wherein, its affiliated frequency range can be known by the digital audio frequency in collected voice data, in the present embodiment
In, defining f (x) is digital audio frequency, and unit is hertz:
(246.9 < f (x) < 987.8): frequency range when soprano speaks；
(164.8 < f (x) < 659.2): frequency range when alto is spoken；
(110 < f (x) < 440): frequency range when tenor is spoken；
(73.4 < f (x) < 293.7): frequency range when bass is spoken；
(100 < f (x) < 300): frequency range when ordinary people speaks.
Wherein, the characteristics of digital audio frequency of voice data when the present embodiment is spoken according to people and frequency defined above
Rate range is sampled using certain algorithm, such as to sound frequency, the several word tones of 10 of continuous acquisition above sound data
Frequent rate, if there is 5 several word audio frequencies are in some above-mentioned frequency range, such as in 246.9 < f (x) < 987.8,
Then it is judged as that corresponding soprano speaks.Its affiliated frequency range or frequency model are obtained according to the digital audio frequency in voice data
It encloses, it can be deduced that be the voice data that soprano, alto, tenor, bass or ordinary people speak.
In general, the sample frequency of voice is 40KHz at present, i.e., the number per second to original signal samples is 40000
It is secondary.
Preferably, if having obtained frequency range belonging to the digital audio frequency of current collected voice data, may be used also
Voice data is calculated again using other algorithms, with reaffirm its whether be voice voice data.Implement one
In example, if frequency range belonging to confirmation is soprano 246.9-987.8Hz, the n group frequency in voice data is taken, if there is n/2 group frequency
When the number that rate occurs is in the range of (40000/246.9)-(40000/987.8), then it is confirmed as the voice data of voice, it is no
It is not then the voice data of voice, the processing without next step.
Step C is then acquired according to the digital audio set of frequency if voice data and is extended the time, and in institute's predicate
When sound control key is closed, extend time extension sound collection according to the acquisition；
In the present embodiment, after being determined as voice data, the speed of the word speed of voice is judged by digital audio frequency, if
Digital audio frequency is higher, that is, shows that user speaks comparatively fast, on the contrary then relatively slow, and user, which speaks, comparatively fast can be set shorter acquisition
Extend the time, and speaks and the longer acquisition extension time relatively then can be set slowly.
It in the present embodiment, is acquired according to digital audio set of frequency and extends the time, for example, if user speaks relatively slowly, then may be used
Extend the time so that the voice collecting of electronic equipment is arranged, extends the acquisition time of electronic equipment with this, voice such as can be set
The acquisition extension time is 300m seconds or 500m seconds etc..When user cannot hold the voice collecting time, i.e., words electronics is finished not yet
The speech controling switch of equipment is just disconnected in advance, and the present embodiment still can be recorded due to extending the voice collecting time
Voice data is taken, avoids user from disconnecting speech controling switch in advance when speaking slower and causes the voice data of admission incomplete
It happens.
In the present embodiment, if it is confirmed that be acquisition being voice data, no matter user speaks speed, all in accordance with digital audio
Set of frequency acquisition extend the time, prevent it is no acquire voice data when, speech controling switch disconnect and cause enroll
Voice data is imperfect.
Compared with prior art, the electronic equipment of the present embodiment acquires voice data, according to the digital audio of voice data
Frequency confirms whether it is that the voice data that voice inputs then is acquired according to digital audio set of frequency if it is voice data
Extend the time, i.e., the time is extended according to user's speed degree setting acquisition of speaking, avoids user's relatively slow, voice control of speaking and open
It closes and closes in advance and the incomplete situation of the voice data of admission is caused to occur, improve the integrality of the voice data of admission.
In a preferred embodiment, as shown in Fig. 2, the present embodiment is above-mentioned on the basis of the embodiment of above-mentioned Fig. 1
After step C further include:
Step D, if not voice data stops the voice data then when reaching the preset sound collection time
Acquisition.
In the present embodiment, can a preset timer in the electronic device, when really admit a fault voice data when, timer
Timing starts, and when reaching the preset sound collection time, speech controling switch is automatically closed by the triggering of timer, stops
The acquisition of voice data.
Preferably, in the present embodiment, if detect voice data within the preset sound collection time, timing
The timing time of device is reset, and is then acquired according to the digital audio set of frequency of voice data and is extended the time.
In the present embodiment, if voice data is not detected, electronic equipment continues the acquisition of voice data, default when reaching
The sound collection time when, stop the acquisition of the voice data.
In a preferred embodiment, as shown in figure 3, on the basis of the embodiment of above-mentioned Fig. 1, above-mentioned steps B is also wrapped
It includes:
Step B1 acquires the digital audio frequency of the voice data, by digital audio frequency collected with it is preset
Sound frequency range is compared；
Step B2, if digital audio frequency collected judges the sound in the preset sound band limits
Sound data are voice data.
In the present embodiment, preset sound frequency range include above-mentioned soprano, alto, tenor, bass or
The sound frequency range of the pronunciation of ordinary people.
Wherein, the characteristics of digital audio frequency of voice data when the present embodiment is spoken according to people and frequency defined above
Rate range is sampled using certain algorithm, such as to sound frequency, the several word tones of 10 of continuous acquisition above sound data
Frequent rate, if there is 5 several word audio frequencies are in some above-mentioned frequency range, such as in 246.9 < f (x) < 987.8,
Then it is judged as that corresponding soprano speaks.Its affiliated frequency range or frequency model are obtained according to the digital audio frequency in voice data
It encloses, it can be deduced that be the voice data that soprano, alto, tenor, bass or ordinary people speak.
In the present embodiment, the sound frequency range belonging to it is gone out as the digital audio Rate derivation in voice data are as follows:
Table 1
Table 2
Shown in table 1 and table 2 as above, table 1 and table 2 are the priori value tested repeatedly.Input low band frequency or input
The digital audio frequency of high band frequency quite in this present embodiment, Zstar low-limit frequency and Zend highest frequency are formed in the number
The frequency range of the corresponding sound type of word audio frequency, thus, it is possible to obtain: multiple proportion P (x)=(Zend-Zstar)/F
(x)=2.5, and so on.
Therefore, if having acquired the digital audio frequency in the present embodiment, the number sound can be obtained by calculation
Sound frequency range belonging to frequent rate, as shown in table 3 below:
Table 3
As shown in table 3, the multiple proportion P (x) of table 3 is being averaged for the sum of the two of above-mentioned table 1 and the multiple proportion in table 2
Number, i.e. multiple proportion P (x)=(2.5+1.25)/2=1.875.
In addition, in the present embodiment, frequency F (x) is inputted if it is greater than or equal to 500Hz, then can take the Zstar low-limit frequency to be
The half of F (x), if input frequency F (x) is less than 500Hz, can take Zstar low-limit frequency is the one third of F (x), then
Calculate Zend highest frequency=F (x) * P (x)+Zstar=500*1.875+250=1187.5Hz.
So far, show that the sound frequency range belonging to it is 250-1187.5 as the digital audio frequency in voice data.
In addition, judging the number of appearance digital audio frequency each second whether in the corresponding number model of preset sound frequency range
In enclosing:
For example, for soprano: if low-limit frequency=260 Zstar, the number that frequency each second occurs is
40000/260=153, and so on.
If taking 10 groups of Zstar low-limit frequencies, the number for calculating separately to obtain appearance frequency each second is 153,4000,153,
153,150,150,150,150,150 and 150, occurring corresponding number preset sound frequency range each second is (40000/
1187.5) in the range of (40000/250), i.e., in the range of 33.68 to 160.It is found that 4000 in addition to second group take second place
Outside, therefore other numbers, have 9 groups of data to meet condition in the range of 33.68 to 160, and two greater than 10 groups/
One, therefore, it can reaffirm that enrolled voice data is voice data.
In a preferred embodiment, as shown in figure 4, on the basis of the embodiment of above-mentioned Fig. 1, the sound control method
Further include:
Step E, voice data collected is subjected to speech recognition, obtains recognition result；
Step F, recognition result is sent to smart machine, to set as smart machine input instruction to the intelligence
It is standby to be operated.
In the present embodiment, after acquisition, the voice data enrolled can be carried out speech recognition by electronic equipment, so
After be sent to smart machine, recognition result is exported and is displayed on the screen by smart machine.
In the present embodiment, electronic equipment can be remote controler, is acquired by remote controler or enrolls voice data, by sound number
It according to being identified, is sent to smart television and shows, then TV can also be manipulated using recognition result as input information.
Preferably, above-mentioned steps E includes: to match the voice data with the word of local dictionary；If matching at
Function, using the word of successful match as the recognition result；If it fails to match, by the audio data transmitting to cloud, and
Obtain the recognition result that cloud returns.
Wherein, electronic equipment can be identified first locally, i.e., by voice data and local word in local dictionary
The word in library is matched；If being not matched to locally, audio data transmitting to cloud can also be identified.
The present invention provides a kind of electronic equipment, and referring to Fig. 5, in one embodiment, electronic equipment includes:
Module 101 is obtained, for acquiring voice data in the triggering of voice control key, and obtains the collected sound of institute
The digital audio frequency of data；
In the present embodiment, preset phonetic controller in electronic equipment starts to acquire sound when pressing voice control key
Data.
Preferably, the present embodiment is more suitable for carrying out the admission of the voice data of short time, such as the sound number in admission 5 seconds
According to.
In the present embodiment, electronic equipment is converted into digital signal while acquiring voice data.Wherein, it is acquiring
The digital audio frequency that voice data is just obtained when sub-fraction voice data can know sound according to the digital audio frequency
The speed of the word speed of data, and then according to the operation of the speed of the word speed of voice data progress next step.
For example, the electronic equipment in the present embodiment, which can be remote controler or other, can acquire the electronics of voice data
Equipment (such as mobile phone, recording pen), when user presses the voice control key in remote controler, speech controling switch is connected, so
The voice data in ambient enviroment is acquired afterwards, remote controler can be used for example, the voice collecting of user gets off, it is defeated as voice
Enter to control television set.In the present embodiment, while acquiring voice data, obtain collected voice data number
Audio frequency.
Judgment module 102, for judging whether the voice data is voice data according to the digital audio frequency；
Wherein, its affiliated frequency range can be known by the digital audio frequency in collected voice data, in the present embodiment
In, defining f (x) is digital audio frequency, and unit is hertz:
(246.9 < f (x) < 987.8): frequency range when soprano speaks；
(164.8 < f (x) < 659.2): frequency range when alto is spoken；
(110 < f (x) < 440): frequency range when tenor is spoken；
(73.4 < f (x) < 293.7): frequency range when bass is spoken；
(100 < f (x) < 300): frequency range when ordinary people speaks.
Wherein, the characteristics of digital audio frequency of voice data when the present embodiment is spoken according to people and frequency defined above
Rate range is sampled using certain algorithm, such as to sound frequency, the several word tones of 10 of continuous acquisition above sound data
Frequent rate, if there is 5 several word audio frequencies are in some above-mentioned frequency range, such as in 246.9 < f (x) < 987.8,
Then it is judged as that corresponding soprano speaks.Its affiliated frequency range or frequency model are obtained according to the digital audio frequency in voice data
It encloses, it can be deduced that be the voice data that soprano, alto, tenor, bass or ordinary people speak.
In general, the sample frequency of voice is 40KHz at present, i.e., the number per second to original signal samples is 40000
It is secondary.
Preferably, if having obtained frequency range belonging to the digital audio frequency of current collected voice data, may be used also
Voice data is calculated again using other algorithms, with reaffirm its whether be voice voice data.Implement one
In example, if frequency range belonging to confirmation is soprano 246.9-987.8Hz, the n group frequency in voice data is taken, if there is n/2 group frequency
When the number that rate occurs is in the range of (40000/246.9)-(40000/987.8), then it is confirmed as the voice data of voice, it is no
It is not then the voice data of voice, the processing without next step.
Setup module 103 then acquires according to the digital audio set of frequency if being used for voice data and extends the time,
And when the voice control key is closed, extend time extension sound collection according to the acquisition.
In the present embodiment, after being determined as voice data, the speed of the word speed of voice is judged by digital audio frequency, if
Digital audio frequency is higher, that is, shows that user speaks comparatively fast, on the contrary then relatively slow, and user, which speaks, comparatively fast can be set shorter acquisition
Extend the time, and speaks and the longer acquisition extension time relatively then can be set slowly.
It in the present embodiment, is acquired according to digital audio set of frequency and extends the time, for example, if user speaks relatively slowly, then may be used
Extend the time so that the voice collecting of electronic equipment is arranged, extends the acquisition time of electronic equipment with this, voice such as can be set
The acquisition extension time is 300m seconds or 500m seconds etc..When user cannot hold the voice collecting time, i.e., words electronics is finished not yet
The speech controling switch of equipment is just disconnected in advance, and the present embodiment still can be recorded due to extending the voice collecting time
Voice data is taken, avoids user from disconnecting speech controling switch in advance when speaking slower and causes the voice data of admission incomplete
It happens.
In the present embodiment, if it is confirmed that be acquisition being voice data, no matter user speaks speed, all in accordance with digital audio
Set of frequency acquisition extend the time, prevent it is no acquire voice data when, speech controling switch disconnect and cause enroll
Voice data is imperfect.
In a preferred embodiment, as shown in fig. 6, on the basis of the embodiment of above-mentioned Fig. 5, the electronic equipment is also
Include:
Stopping modular 104, if stopping the sound when reaching the preset sound collection time for non-speech data
The acquisition of sound data.
In the present embodiment, can a preset timer in the electronic device, when really admit a fault voice data when, timer
Timing starts, and when reaching the preset sound collection time, speech controling switch is automatically closed by the triggering of timer, stops
The acquisition of voice data.
Preferably, in the present embodiment, if detect voice data within the preset sound collection time, timing
The timing time of device is reset, and is then acquired according to the digital audio set of frequency of voice data and is extended the time.
In the present embodiment, if voice data is not detected, electronic equipment continues the acquisition of voice data, default when reaching
The sound collection time when, stop the acquisition of the voice data.
In a preferred embodiment, as shown in fig. 7, on the basis of the embodiment of above-mentioned Fig. 5, the judgment module
102 include:
Comparing unit 1021, for acquiring the digital audio frequency of the voice data, by digital audio frequency collected
Rate is compared with preset sound frequency range；
Judging unit 1022, if for digital audio frequency collected in the preset sound band limits,
Judge the voice data for voice data.
In the present embodiment, preset sound frequency range include above-mentioned soprano, alto, tenor, bass or
The sound frequency range of the pronunciation of ordinary people.
Wherein, the characteristics of digital audio frequency of voice data when the present embodiment is spoken according to people and frequency defined above
Rate range is sampled using certain algorithm, such as to sound frequency, the several word tones of 10 of continuous acquisition above sound data
Frequent rate, if there is 5 several word audio frequencies are in some above-mentioned frequency range, such as in 246.9 < f (x) < 987.8,
Then it is judged as that corresponding soprano speaks.Its affiliated frequency range or frequency model are obtained according to the digital audio frequency in voice data
It encloses, it can be deduced that be the voice data that soprano, alto, tenor, bass or ordinary people speak.
In the present embodiment, going out the sound frequency range belonging to it as the digital audio Rate derivation in voice data can be refering to upper
Table 1, table 2, the data in table 3 and the relevant derivation process stated, details are not described herein again.
In addition, judging the number of appearance digital audio frequency each second whether in the corresponding number model of preset sound frequency range
In enclosing:
For example, for soprano: if low-limit frequency=260 Zstar, the number that frequency each second occurs is
40000/260=153, and so on.
If taking 10 groups of Zstar low-limit frequencies, the number for calculating separately to obtain appearance frequency each second is 153,4000,153,
153,150,150,150,150,150 and 150, occurring corresponding number preset sound frequency range each second is (40000/
1187.5) in the range of (40000/250), i.e., in the range of 33.68 to 160.It is found that 4000 in addition to second group take second place
Outside, therefore other numbers, have 9 groups of data to meet condition in the range of 33.68 to 160, and two greater than 10 groups/
One, therefore, it can reaffirm that enrolled voice data is voice data.
In a preferred embodiment, as shown in figure 8, on the basis of the embodiment of above-mentioned Fig. 5, the electronic equipment is also
Include:
Identification module 105 obtains recognition result for voice data collected to be carried out speech recognition；
Sending module 106, for recognition result to be sent to smart machine, to input instruction pair as the smart machine
The smart machine is operated.
In the present embodiment, after acquisition, the voice data enrolled can be carried out speech recognition by electronic equipment, so
After be sent to smart machine, recognition result is exported and is displayed on the screen by smart machine.
In the present embodiment, electronic equipment can be remote controler, is acquired by remote controler or enrolls voice data, by sound number
It according to being identified, is sent to smart television and shows, then TV is manipulated using recognition result as input information.
Preferably, the identification module 105 includes: matching unit, for by the word of the voice data and local dictionary
Language is matched；First recognition unit, if successful match is used for, using the word of successful match as the recognition result；Second
Recognition unit, if by the audio data transmitting to cloud, and obtaining the recognition result of cloud return for it fails to match.
Wherein, electronic equipment can be identified first locally, i.e., by voice data and local word in local dictionary
The word in library is matched；If being not matched to locally, audio data transmitting to cloud can also be identified.
It should be noted that all modules in the embodiment of above-mentioned remote controler can handle mould by the CPU of remote controler
Block completes corresponding function to control.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (8)
1. a kind of sound control method, which comprises the following steps:
A, voice control key trigger when, acquire voice data, and obtain collected voice data digital audio frequency；
B, judge whether the voice data is voice data according to the digital audio frequency；
If C, detecting voice data within the preset sound collection time, prolonged according to digital audio set of frequency acquisition
For a long time, and when the voice control key is closed, extend time extension sound collection according to the acquisition；
Wherein, the step B includes:
The digital audio frequency for acquiring the voice data carries out digital audio frequency collected and preset sound frequency range
It compares；
If digital audio frequency collected is in the preset sound band limits, and the digital audio each second occurs
Number in the corresponding numbers range of preset sound frequency range, then judge the voice data for voice data.
2. sound control method as described in claim 1, which is characterized in that after the step B further include:
If voice data D, is not detected, when reaching the preset sound collection time, stop the acquisition of the voice data.
3. sound control method as described in claim 1, which is characterized in that the sound control method further includes step E, F:
E, voice data collected is subjected to speech recognition, obtains recognition result；
F, recognition result is sent to smart machine, to grasp as smart machine input instruction to the smart machine
Make.
4. sound control method as claimed in claim 3, which is characterized in that the step E includes:
The voice data is matched with the word of local dictionary；
If successful match, using the word of successful match as the recognition result；
If it fails to match, by the audio data transmitting to cloud, and the recognition result of cloud return is obtained.
5. a kind of electronic equipment, which is characterized in that the electronic equipment includes:
Obtain module, for voice control key triggering when, acquire voice data, and obtain collected voice data number
Word audio frequency；
Judgment module, for judging whether the voice data is voice data according to the digital audio frequency；
Setup module, if for detecting voice data within the preset sound collection time, according to the digital audio frequency
Rate setting acquisition extends the time, and when the voice control key is closed, and extends sound collection according to the acquisition extension time；
Wherein, the judgment module includes:
Comparing unit by digital audio frequency collected and is preset for acquiring the digital audio frequency of the voice data
Sound frequency range be compared；
Judging unit, if for digital audio frequency collected in the preset sound band limits, and the number
The number that audio each second occurs then judges the voice data for voice in the corresponding numbers range of preset sound frequency range
Data.
6. electronic equipment as claimed in claim 5, which is characterized in that the electronic equipment further include:
Stopping modular, if stopping the voice data when reaching the preset sound collection time for non-speech data
Acquisition.
7. electronic equipment as claimed in claim 5, which is characterized in that the electronic equipment further include:
Identification module obtains recognition result for voice data collected to be carried out speech recognition；
Sending module, for recognition result to be sent to smart machine, to instruct as smart machine input to the intelligence
Energy equipment is operated.
8. electronic equipment as claimed in claim 7, which is characterized in that the identification module includes:
Matching unit, for matching the voice data with the word of local dictionary；
First recognition unit, if successful match is used for, using the word of successful match as the recognition result；
Second recognition unit, if by the audio data transmitting to cloud, and obtaining the knowledge of cloud return for it fails to match
Other result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410768009.7A CN105741841B (en) | 2014-12-12 | 2014-12-12 | Sound control method and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410768009.7A CN105741841B (en) | 2014-12-12 | 2014-12-12 | Sound control method and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105741841A CN105741841A (en) | 2016-07-06 |
| CN105741841B true CN105741841B (en) | 2019-12-03 |
Family
ID=56241450
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410768009.7A Active CN105741841B (en) | 2014-12-12 | 2014-12-12 | Sound control method and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105741841B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106782552B (en) * | 2016-12-06 | 2020-05-22 | 深圳Tcl数字技术有限公司 | Tail sound identification method and voice remote controller |
| CN107895579B (en) * | 2018-01-02 | 2021-08-17 | 联想(北京)有限公司 | Voice recognition method and system |
| CN109243447A (en) * | 2018-10-12 | 2019-01-18 | 西安蜂语信息科技有限公司 | Voice sends triggering method and device |
| CN110970054B (en) * | 2019-11-06 | 2022-06-24 | 广州视源电子科技股份有限公司 | Method and device for automatically stopping voice acquisition, terminal equipment and storage medium |
| CN111627441B (en) * | 2020-05-26 | 2021-10-08 | 北京百度网讯科技有限公司 | Control method, device, equipment and storage medium of electronic equipment |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886860A (en) * | 2014-02-21 | 2014-06-25 | 联想(北京)有限公司 | Information processing method and electronic device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009034686A1 (en) * | 2007-09-11 | 2009-03-19 | Panasonic Corporation | Sound judging device, sound sensing device, and sound judging method |
| CN102541505A (en) * | 2011-01-04 | 2012-07-04 | 中国移动通信集团公司 | Voice input method and system thereof |
| CN102324241A (en) * | 2011-05-04 | 2012-01-18 | 鸿富锦精密工业（深圳）有限公司 | Electronic device with voice-controlling function and voice-controlling method |
| CN104038804B (en) * | 2013-03-05 | 2017-09-29 | 三星电子（中国）研发中心 | Captioning synchronization apparatus and method based on speech recognition |
| CN103713876B (en) * | 2014-01-16 | 2016-10-05 | 联想(北京)有限公司 | Data processing method and electronic equipment |
-
2014
- 2014-12-12 CN CN201410768009.7A patent/CN105741841B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886860A (en) * | 2014-02-21 | 2014-06-25 | 联想(北京)有限公司 | Information processing method and electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105741841A (en) | 2016-07-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105741841B (en) | Sound control method and electronic equipment | |
| CN108346433A (en) | A kind of audio-frequency processing method, device, equipment and readable storage medium storing program for executing | |
| CN108010526B (en) | Voice processing method and device | |
| CN103391347B (en) | A kind of method and device of automatic recording | |
| CN105847921A (en) | Image display apparatus and method of controlling the same | |
| CN102568478A (en) | Video play control method and system based on voice recognition | |
| CN104575504A (en) | Method for personalized television voice wake-up by voiceprint and voice identification | |
| CN105282345A (en) | Method and device for regulation of conversation volume | |
| CN109271533A (en) | A kind of multimedia document retrieval method | |
| CN112074900A (en) | Audio analysis for natural language processing | |
| CN108847221B (en) | Voice recognition method, voice recognition device, storage medium and electronic equipment | |
| KR20160014625A (en) | Method and system for identifying location associated with voice command to control home appliance | |
| GB2583420A (en) | Speaker identification | |
| CN110223711A (en) | Interactive voice based on microphone signal wakes up electronic equipment, method and medium | |
| CN108198569A (en) | A kind of audio-frequency processing method, device, equipment and readable storage medium storing program for executing | |
| CN110428806A (en) | Interactive voice based on microphone signal wakes up electronic equipment, method and medium | |
| CN110097875A (en) | Interactive voice based on microphone signal wakes up electronic equipment, method and medium | |
| CN110111776A (en) | Interactive voice based on microphone signal wakes up electronic equipment, method and medium | |
| CN105355195A (en) | Audio frequency recognition method and audio frequency recognition device | |
| CN104285452A (en) | Spatial audio signal filtering | |
| CN111343028A (en) | Distribution network control method and device | |
| CN105897686A (en) | Smart television user account speech management method and smart television | |
| CN103426429B (en) | Sound control method and device | |
| CN107767860B (en) | Voice information processing method and device | |
| CN104851423B (en) | Sound information processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |