CN109788116A - The method for detecting voice input pattern - Google Patents
The method for detecting voice input pattern Download PDFInfo
- Publication number
- CN109788116A CN109788116A CN201711106463.6A CN201711106463A CN109788116A CN 109788116 A CN109788116 A CN 109788116A CN 201711106463 A CN201711106463 A CN 201711106463A CN 109788116 A CN109788116 A CN 109788116A
- Authority
- CN
- China
- Prior art keywords
- input pattern
- time
- voice input
- voice
- user
- 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.)
- Withdrawn
Links
Abstract
It is a kind of detect voice input pattern method be used for electronic device.The behavioral difference of the start button of electronic device is pinned according to user, and judges voice input pattern for short-press mode or long-pressing mode.The method of detection voice input pattern includes: to detect whether time of pinning of start button is less than and pins the threshold time；If so, judging voice input pattern for short-press mode；If it is not, then detection was pinned within the time, whether the speech utterance time of the received voice of microphone is greater than the speech utterance threshold time；If so, judging voice input pattern for long-pressing mode；If it is not, then judging voice input pattern for the short-press mode.
Description
Technical field
The present invention about it is a kind of detect voice input pattern method, especially a kind of operating habit according to user and
The method for detecting voice input pattern.
Background technique
General communication software, AI software or translation software mostly have speech voice input function, and user can be allowed direct
Read out text, to input in voice data to mobile phone, therefore user no longer need to take a significant amount of time click cell phone keyboard it is defeated
Enter text.
Communication software or translation software are in order to cooperate speech voice input function, it will usually long-pressing formula is provided on software interface
Voice operating key.The voice operating key of long-pressing formula is with for user's long-pressing, and during user pins the voice operating key,
User can also speak to mobile phone, and thus mobile phone will record down voice received during pinning button, and will
Voice under record cooperates communication software, AI software or translation software and executes cloud voice and upload or be converted to the functions such as text.
In addition, some software can also provide the voice operating key of short-press formula on software interface.The voice operating key of short-press formula with for
User is of short duration to be clicked, so that software activation sound-recording function, to record the voice of lower user；After user has recorded voice, user
The voice operating key or software that short-press formula can be again tapped on are judged automatically to close sound-recording function, and communication software or
The voice recorded can be executed cloud and upload or be converted to the functions such as text by translation software.
However, users usually can only get used to one of operation mode of long-pressing formula or short-press formula.Therefore, it uses
Family is when with different software, it is often necessary to give up the use habit of itself, and oneself go to be provided using different software reluctantly
Different operation modes.
Therefore, it is necessary to provide a kind of operating habit according to user, and detect and adjust the side of voice input pattern
Method.
Summary of the invention
The main object of the present invention, which ties up to, to be provided a kind of operating habit according to user and detects voice input pattern
Method.
To reach above-mentioned purpose, a kind of method of detection voice input pattern of the invention is used for an electronic device, electricity
Sub-device includes a microphone and a start button.Input of the microphone to receive a voice, start button is with for a use
Family is pinned to start a voice input pattern and inputs voice, wherein pinning the behavioral difference of start button according to user, and sentences
Conclusion sound input pattern is a short-press mode or a long-pressing mode.Detection voice input pattern method include: detection starting by
The one of key pins whether the time pins the threshold time less than one, wherein pinning the threshold time is between 0.001 second to 1.5 seconds；If
It is then to judge voice input pattern for short-press mode；If it is not, then detection was pinned within the time, the one of the received voice of microphone
Whether the speech utterance time is greater than the speech utterance threshold time, and wherein the speech utterance threshold time is between 0 second to 1.5 seconds；
If so, judging voice input pattern for long-pressing mode；If it is not, then judging voice input pattern for short-press mode.
One of according to the present invention embodiment, wherein pinning the threshold time is between 0.001 second to 0.8 second.
One of according to the present invention embodiment, wherein the speech utterance threshold time is between 0.2 second to 0.9 second.
One of according to the present invention embodiment, wherein the detection speech utterance time is that user presses start button and starts.
One of according to the present invention embodiment, wherein electronic device is a mobile phone, a computer or a tablet computer.
One of according to the present invention embodiment, wherein electronic device further includes a loudspeaker, and loudspeaker are to issue a prompt tone；Inspection
Point is being after loudspeaker play the prompt tone at the beginning of surveying the speech utterance time.
One of according to the present invention embodiment, wherein electronic device further includes an earphone, and earphone is to issue a prompt tone；Inspection
The start time point of speech utterance time is surveyed after being earphone playing alert tones.
One of according to the present invention embodiment, wherein user inputs one of voice when voice input pattern is long-pressing mode
End time point is the time point that user decontrols start button；Wherein when voice input pattern is short-press mode, user's input
One of voice end time point and non-user decontrol the time point of start button.
Detailed description of the invention
Fig. 1 is the system architecture diagram of the electronic device of the first embodiment of the present invention.
Fig. 2 is the step flow chart of the method for the detection voice input pattern of the first embodiment of the present invention.
Fig. 3 is the schematic diagram of the electronic device of the first embodiment of the present invention.
Fig. 4 is the system architecture diagram of the electronic device of the second embodiment of the present invention.
Fig. 5 is that the cooperation earphone of the second embodiment of the present invention uses the step process for the method for detecting voice input pattern
Figure.
Fig. 6 is the schematic diagram of the electronic device of the second embodiment of the present invention.
Wherein appended drawing reference are as follows:
101: detecting the one of start button and pin whether the time pins the threshold time less than one, wherein pinning the threshold time and being
Between 0.001 second to 1.5 seconds
102: judging voice input pattern for short-press mode
103: detection was pinned within the time, and whether the speech utterance time of the received voice of microphone is greater than voice hair
The glottis sill time, wherein the speech utterance threshold time is between 0 second to 1.5 seconds
104: judging voice input pattern for long-pressing mode
Electronic device 10,10a
Microphone 11,181
Start button 12,12a, 182
Loudspeaker 13
Touch Screen 14
Processor 15
Storage member 16
Communication interface 17
Earphone 18
Specific embodiment
For that can allow your juror that can know more about technology contents of the invention, spy lifts preferred embodiment and is described as follows.
Method please also refer to Fig. 1 to Fig. 3 about the detection voice input pattern of the first embodiment of the present invention below.
Fig. 1 is the system architecture diagram of the electronic device of the first embodiment of the present invention；Fig. 2 is the detection language of the first embodiment of the present invention
The step flow chart of the method for sound input pattern；Fig. 3 is the schematic diagram of the electronic device of the first embodiment of the present invention.
As shown in Figure 1 to Figure 3, among first embodiment, the method for detection voice input pattern is to be programmed to a meter
Calculation machine program, and it is applied to an electronic device 10.The method of detection voice input pattern can be accustomed to depending on the user's operation, and
Automatic detection user with voice input pattern be long-pressing mode or short-press mode.Electronic device 10 is, for example, a mobile phone, but
It is also possible to a computer or a tablet computer.Electronic device 10 includes a microphone 11, a start button 12, a loudspeaker
13, a Touch Screen 14, a processor 15 and a storage member 16.
Among the first embodiment of the present invention, voice of the microphone 11 to receive user.Touch Screen 14 is to aobvious
Registration is watched and is operated for user accordingly.Processor 15 is a central processing unit (Central Processing Unit, CPU),
It is electrically connected microphone 11, start button 12, loudspeaker 13, Touch Screen 14, storage member 16, to control those component operationals.
Storage member 16 is a memory, the computer program that the method to store detection voice input pattern is programmed.
Start button 12 is an entity button, can be used to pin for user to start a voice input pattern and input
Voice, wherein pin the behavioral difference of start button 12 according to user, can make voice input pattern be rendered as a short-press mode or
One long-pressing mode.If user pins start button 12 for a long time, then voice input pattern is long-pressing mode.In long-pressing mode
When, the time point at the beginning of user's input voice is the time point that user presses start button 12；One knot of user's input voice
Beam time point is the time point that user decontrols start button 12.If user is of short duration must to click start button 12, then voice inputs
Mode is short-press mode.In short-press mode, the time point at the beginning that user inputs voice is that user clicks start button 12
Time point；User inputs an end time point of voice and non-user decontrols the time point of start button 12, and user inputs voice
An end time point can be user again tap on the time point of start button 12 or user's short time input voice it
Stop the time point of input voice afterwards.However, start button 12 is not limited with entity button, for example, Touch Screen 14 can also
To form the start button 12a (general intelligence type mobile phone can be based on the start button 12a of virtual form) of a virtual form, with
It is pinned for user to start voice input pattern and inputs voice.
Computer program made of the method for detection voice input pattern of the invention programs can be designed as, and work as use
Person executes the program of any required input voice, and (such as translation software, communication software, artificial intelligence question and answer software search software
Etc.) when, the computer program for detecting the method for voice input pattern will start automatically on electronic device 10；Or detection
The computer program of the method for voice input pattern may be designed within the program for being built into and needing to input voice.In this hair
Among bright, it is for computer program to detect the method for voice input pattern is built into a translation software, as shown in figure 3,
When user opens translation software, translation software can cooperate the method for detection voice input pattern and provide on Touch Screen 14
The start button 12a of one virtual form, and the message of " pressing start button to input voice " is shown to inform that user can be with
Start to input voice.Then, user can be accustomed to according to oneself, be come using the sustained hold of long-pressing or the click mode of short-press
The start button 12 of entity or the start button 12a of virtual form are pressed, and the method for detecting voice input pattern will root
The operation behavior and the behavior of input voice later pressed the button according to user, to detect user's long-pressing mode to be penetrated or short-press
Mode and carry out voice input.Firstly, when user presses the start button 12 of entity or the start button 12a of virtual form
Afterwards, detect voice input pattern method will execute step 101: detect the one of start button pin the time whether less than one by
The firmly threshold time, wherein pinning the threshold time is between 0.001 second to 1.5 seconds.
After user presses any one of start button 12,12a, the start button 12 of entity or opening for virtual form
Dynamic user can be pressed start button 12 by key 12a, the time point of 12a is transferred to processor 15, and is also decontroled user and started
Key 12,12a time point be transferred to processor 15.Processor 15 can calculate time point for pressing the button and decontrol key when
Between time difference between point, and the time difference is that start button 12,12a one pin time P1.Processor 15 can also detect
Pin whether time P1 pins threshold time PT1 less than one；It is of the invention pin threshold time PT1 be 0.001 second to 1.5 seconds it
Between, it preferably may be designed as between 0.001 second to 0.8 second.Via inventor's actual observation and statistics user operation behavior, one
As user when carrying out the clicking operation of short-press, finger can averagely be touched by New York 0.6 second, and the clicking operation of maximum duration
It is not more than 1.5 seconds, therefore inventor will pin threshold time PT1 and be designed as between 0.001 second to 1.5 seconds.
If the detection of processor 15 pins time P1 and pins threshold time PT1 less than one, then carries out step 102: judging language
Sound input pattern is short-press mode.
In the first embodiment, it if user clicks start button 12, and has only touched 0.6 second and has just decontroled start button
12, then the time P1 that pins that processor 15 can calculate start button 12 is 0.6 second, is less than and pins the 1.5 of threshold time PT1
Second；Therefore processor 15 judge user be intended to this moment using voice input pattern be short-press mode, therefore processor 15 can be real
When adjustment translation software and start button 12,12a, allow translation software to activate sound-recording function, record lower user's voice to be inputted, and
And start button 12,12a is allowed to be ready to receive again tapping on for user, to stop recording；Or processor 15 can also be with
Translation software and start button 12,12a are adjusted, translation software is allowed to activate sound-recording function, records lower user's voice to be inputted, and
When microphone 11 can not receive the voice of user (when namely user no longer speaks), that is, stop recording.
If time P1 is pinned in the detection of processor 15 pins threshold time PT1 not less than one, then step 103 is carried out: detection
It pins within the time, whether a speech utterance time V1 of the received voice of microphone is greater than a speech utterance threshold time VT1,
Wherein speech utterance threshold time VT1 is between 0 second to 1.5 seconds.
Via the operation behavior of inventor's actual observation and statistics user, general user is inputted carrying out long-pressing mode
When voice, voice can be inputted while pinning start button 12, and user input voice time would generally 1.5 seconds with
On.Therefore, voice is inputted in order to judge whether user determines long-pressing mode to be used, processor 15 will start microphone 11
The voice inputted in time P1 is pinned receive that user pins start button 12.Microphone 11 can will pin time P1 and be inscribed
For the voice transfer received to processor 15, processor 15 can calculate a speech utterance time V1's of the received voice of microphone 11
Length of time；Processor 15 can also detect whether speech utterance time V1 is greater than a speech utterance threshold time VT1.Speech utterance
Threshold time VT1 is between 0 second to 1.5 seconds, preferably between 0.2 second to 0.9 second.In addition, it is noted that first embodiment
The starting point of detection speech utterance time V1 be designed as pinning the time point that voice is initially received in time P1, but examine
It surveys speech utterance time V1 and may be designed in user one and press start button 12 and start.
If the detection of processor 15 is being pinned within time P1, the speech utterance time V1 of the received voice of microphone 11 is big
In a speech utterance threshold time VT1, then can be confirmed user be intended to using voice input pattern be really long-pressing mode.Therefore
It will continue to carry out step 104: judging voice input pattern for long-pressing mode.
In the first embodiment, if processor 15 judges that speech utterance time V1 is greater than the speech utterance threshold time
VT1, then processor 15 judge user be intended to this moment using voice input pattern be long-pressing mode.Therefore processor 15 can be real-time
Adjust translation software and start button 12,12a, allow sound-recording function record lower user pin start button 12,12a pins the time
The voice that P1 is inputted, and start button 12,12a is allowed to prepare to stop recording when user decontrols start button 12,12a.
It returns to after step 103, if the detection of processor 15 is being pinned within time P1, the received voice of microphone 11
Speech utterance time V1 be not more than a speech utterance threshold time VT1, then can be confirmed user be intended to using voice input pattern
Not long-pressing mode；For example, some elder persons are relatively bad to operate electronic device 10, elder person pins start button 12 in length
Afterwards, of short duration voice can be only exported to microphone 11, therefore will appear that pin time P1 be more than to pin threshold PT1, but voice is sent out
Sound time V1 is not more than the situation of speech utterance threshold time VT1.If therefore there is such situation, the present invention can be routed to step
Rapid 102: judging voice input pattern for short-press mode.
If processor 15 judges that microphone 11 receives the speech utterance time V1 of the voice of user no more than voice hair
1.5 seconds (such as speech utterance time V1 only has 0.5 second) of glottis sill time VT1, then processor 15 judges user this moment
Be intended to using voice input pattern be short-press mode, therefore processor 15 can adjust translation software and start button 12,12a in real time,
It allows translation software to activate sound-recording function, records lower user's voice to be inputted, and start button 12,12a is allowed to be ready to receive
User's again taps on, to stop recording；Or processor 15 also adjustable translation software and start button 12,12a, it allows
Translation software activates sound-recording function, records lower user's voice to be inputted, and when microphone 11 can not receive the voice of user (
When being exactly that user no longer speaks), that is, stop recording.
Method please also refer to fig. 4 to fig. 6 about the detection voice input pattern of the second embodiment of the present invention below.
Fig. 4 is the system architecture diagram of the electronic device of the second embodiment of the present invention；Fig. 5 is the cooperation ear of the second embodiment of the present invention
Machine uses the step flow chart of the method for detection voice input pattern；Fig. 6 is the electronic device of the second embodiment of the present invention
Schematic diagram.
As shown in Figures 4 to 6, among second embodiment, electronic device further includes a communication interface 17 and an earphone 18.
Communication interface 17 and all electrically connected processing devices 15 of earphone 18.The communication interface 17 of second embodiment is, for example, a wireless module,
It can be electrically connected by wireless transmission function with other assemblies.Earphone 18 is, for example, the multifunctional headphone of a wired,
Sound can be released, and there are a microphone 181, a start button 182 and a loudspeaker 183.Microphone 181 to receive voice,
And the voice that microphone 181 receives can be transferred to processor 15.Pressing operation of the start button 182 to receive user,
And signal caused by the received pressing operation of start button 182 can be transferred to processor 15.Loudspeaker 13,183 are to issue
One prompt tone, to prompt user that can start to input voice.The earphone 18 of second embodiment is inserted in the earpiece holes of electronic device 10a
In (not shown), therefore earphone 18 and its microphone 181, start button 182 and loudspeaker 183 are also electrically connected through earpiece holes
To processor 15, therefore those components of earphone 18 can also cooperate the method for detection voice input pattern of the invention to make together
With.However, earphone 18 is not limited to the earphone of wired, it also can be wireless headset, and wireless headset can be electrically connected
It communicates with each other to communication interface 17 with processor 15.
In a second embodiment, if user will be used together the translation software of electronic device 10a with earphone 18
When, user can first open translation software, and be accustomed to according to oneself, be come using the sustained hold of long-pressing or the click mode of short-press
Press start button 182.At this point, earphone can execute step 301: receiving press signal and transmit press signal.
When user presses start button 182, start button 182 can receive user and press produced by start button 182
Press signal.The press signal received can be sent to processor 15 by earpiece holes by start button 182.
Then, processor 15 can execute step 201: receiving press signal, and record the time point for receiving press signal.
After processor 15 receives the press signal of start button 182, processor 15, which will record, receives press signal
Time point.
Then, if user decontrols start button 182, then earphone can execute step 302: receiving to decontrol signal and transmit and put
Open signal.
When user decontrols start button 182, start button 182 can receive user and decontrol produced by start button 182
Relieving signal.The relieving signal received can be sent to processor 15 by earpiece holes by start button 182.
Then, processor 15 can execute step 202: receiving and decontrol signal, and record the time point for receiving and decontroling signal.
After processor 15 receives the relieving signal of start button 182, processor 15, which will record to receive, decontrols signal
Time point.
Then, processor 15 can execute step 203: calculating and receive the time point for decontroling signal and receive press signal
Time point between difference time, one which is considered as start button pins the time.
Processor 15 can calculate the time point for receiving the relieving signal of start button 182 and receive start button 182
Difference time between the time point of press signal, and time P1 is pinned by what the difference time was considered as start button 182.
Then, processor 15 can execute step 204: detect when pinning the time and whether pinning threshold less than one of start button
Between, wherein pinning the threshold time is between 0.001 second to 1.5 seconds.
Processor 15 can detect pin time P1 whether pinned less than one 0.001 second to 1.5 seconds of threshold time PT1 it
Between.If the detection of processor 15 pins time P1 and pins threshold time PT1 less than one, then step 205 is carried out: judging that voice inputs
Mode is short-press mode.Due to step 204,205 be equivalent to first embodiment step 101,102, therefore herein not to step
204, it is repeated 205 more.In addition, the earphone 18 due to second embodiment is inserted in the earpiece holes of electronic device 10a, into
Among row step 205, processor 15 judge user be intended to this moment using voice input pattern for short-press mode after, processing
Device 15 can also transmit a prompt tone and play signal to earphone 18, so that earphone 18 receives prompt tone and plays signal and broadcast to user
A prompt tone is put, to prompt user that can start to record.
After step 204, if the detection of processor 15 pins time P1 and pins threshold time PT1 not less than one, then into
Row step 206: if it is not, then transmitting a prompt tone plays signal.
If time P1 is pinned in the detection of processor 15 pins threshold time PT1 not less than one, then the transmission of processor 15 one mentions
Show that sound plays signal to earphone 18.However, processor 15, which may be designed in transmission prompt tone, plays signal to loudspeaker 13.
Then, earphone 18 will do it step 303: receiving prompt tone and plays signal, and playing alert tones.
Earphone 18 can receive prompt tone and play signal and play a prompt tone to user, to prompt user that can start to record
Sound.After user hears prompt tone from earphone 18, so that it may speak microphone 181 to record.If however, place
Reason device 15 is designed as transmission prompt tone and plays signal to loudspeaker 13, then can be that loudspeaker 13 receive prompt tone broadcasting signal and play
Prompt tone.
After user speaks to record to microphone 181, earphone 18 will do it step 304: receiving voice, and transmits
Voice.
The microphone 181 of earphone 18 can receive the voice of user's input, and by the voice transfer to processor 15.
Then, processor will do it step 207: receiving voice, and records the time point for receiving voice.
Processor 15 can receive the voice that earphone 18 transmits, and record the time point for receiving voice, and processor 15 is remembered
The time point that record receives voice can be considered to be a start time point of detection speech utterance time V1.
After user stops inputting voice to microphone 181, earphone can execute step 305: stopping receiving voice, and transmit
Voice stop signal.
User stops after inputting voice to microphone 181, and ear microphone 181 would not receive voice, at this point, earphone 18
Microphone 181 can stop receive voice, and transmit a voice stop signal to processor 15.
Then, processor 15 can execute step 208: receiving voice stop signal, and record and receive voice stop signal
Time point.
Processor 15 can receive the voice stop signal that earphone 18 transmits, and record the time for receiving voice stop signal
Point, and processor 15 record receive voice stop signal time point can be considered to be detection speech utterance time V1 a knot
Beam time point.
Then, processor 15 can execute step 209: calculating the time point for receiving voice and receive voice stop signal
Time point between difference time, which is considered as to the speech utterance time of the received voice of microphone.
Processor 15 can calculate the time point for receiving voice and receive the difference between the time point of voice stop signal
Time, and the difference time is considered as to the speech utterance time V1 of the received voice of microphone 181.
Then, processor 15 will do it step 210: detection was pinned within the time, a voice of the received voice of microphone
Whether phonation time is greater than the speech utterance threshold time, and wherein the speech utterance threshold time is between 0 second to 1.5 seconds.And by
It is selected to carry out step 211 by the result of step 210: if so, judging voice input pattern for long-pressing mode；Or carry out step
212: if it is not, judging voice input pattern for short-press mode.Since step 210 is equivalent to the step 103 of first embodiment, step
211 are equivalent to step 104, and step 212 is equivalent to step 102, therefore herein not to repeating step 210,211,212 more.
By the method for detection voice input pattern of the invention, can be examined automatically according to the operating habit of user
Survey user be intended to using voice input pattern be long-pressing mode or short-press mode, to facilitate user more natural and convenient with electricity
Sub-device.
It is noted that above are only embodiment, rather than it is limited to embodiment.For example this does not depart from basic framework of the present invention
Person all should be the interest field that this patent is advocated, and should be subject to patent claim.
Claims (11)
1. a kind of method for detecting voice input pattern, is used for an electronic device, which is characterized in that the electronic device includes a wheat
Gram wind and a start button, to receive a voice, which is pinned with for a user to start a language microphone
Sound input pattern and input voice, wherein pin the behavioral difference of the start button according to the user, and judge the voice and input
Mode is a short-press mode or a long-pressing mode, and the method for the detection voice input pattern includes:
It detects the one of the start button and pins whether the time pins the threshold time less than one, wherein this is pinned the threshold time and is
Between 0.001 second to 1.5 seconds；
If so, judging the voice input pattern for the short-press mode；
It is pinned within the time if it is not, then detecting this, whether the speech utterance time of the received voice of the microphone is greater than one
The speech utterance threshold time, wherein the speech utterance threshold time is between 0 second to 1.5 seconds；
If so, judging the voice input pattern for the long-pressing mode；And
If it is not, then judging the voice input pattern for the short-press mode.
2. the method for detection voice input pattern as described in claim 1, which is characterized in that this is pinned the threshold time and is
Between 0.001 second to 0.8 second.
3. the method for detection voice input pattern as described in claim 1, which is characterized in that the speech utterance threshold time is
Between 0.2 second to 0.9 second.
4. the method for detection voice input pattern as described in claim 1, which is characterized in that the speech utterance threshold time is
Between 0.2 second to 0.9 second.
5. the method for detection voice input pattern as described in claim 1, which is characterized in that detecting the speech utterance time is
The user presses the start button and starts.
6. the method for detection voice input pattern as claimed in claim 4, which is characterized in that detecting the speech utterance time is
The user presses the start button and starts.
7. such as the method for detection voice input pattern described in any one of claims 1 to 6, which is characterized in that electronics dress
It is set to a mobile phone, a computer or a tablet computer.
8. such as the method for detection voice input pattern described in any one of claims 1 to 6, which is characterized in that electronics dress
It sets and further includes a loudspeaker, the loudspeaker are to issue a prompt tone；The start time point for detecting the speech utterance time is at this
Loudspeaker play after the prompt tone.
9. the method for detection voice input pattern as claimed in claim 7, which is characterized in that the electronic device further includes a loudspeaker
, the loudspeaker are to issue a prompt tone；The start time point for detecting the speech utterance time is to play this in the loudspeaker to mention
After showing sound.
10. the method for detection voice input pattern as claimed in claim 7, which is characterized in that the electronic device further includes one
Earphone, the earphone is to issue a prompt tone；The start time point for detecting the speech utterance time is to play to be somebody's turn to do in the earphone
After prompt tone.
11. the method for detection voice input pattern as described in claim 1, which is characterized in that when the voice input pattern is
When the long-pressing mode, which exports the time point that an end time point of voice decontrols the start button for the user；Wherein
When the voice input pattern is the short-press mode, the end time point which exports voice is not that the user decontrols this and opens
The time point of dynamic key.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711106463.6A CN109788116A (en) | 2017-11-10 | 2017-11-10 | The method for detecting voice input pattern |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711106463.6A CN109788116A (en) | 2017-11-10 | 2017-11-10 | The method for detecting voice input pattern |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109788116A true CN109788116A (en) | 2019-05-21 |
Family
ID=66485347
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711106463.6A Withdrawn CN109788116A (en) | 2017-11-10 | 2017-11-10 | The method for detecting voice input pattern |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109788116A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111933176A (en) * | 2020-09-22 | 2020-11-13 | 成都启英泰伦科技有限公司 | Method and device for positioning voice contents in batches |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012118955A (en) * | 2010-12-02 | 2012-06-21 | Mamoru Takemoto | Method for practically using sonant mark key on portable phone keyboard |
| CN104080026A (en) * | 2013-03-25 | 2014-10-01 | 联想(北京)有限公司 | Method of information processing and line control earphone |
-
2017
- 2017-11-10 CN CN201711106463.6A patent/CN109788116A/en not_active Withdrawn
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012118955A (en) * | 2010-12-02 | 2012-06-21 | Mamoru Takemoto | Method for practically using sonant mark key on portable phone keyboard |
| CN104080026A (en) * | 2013-03-25 | 2014-10-01 | 联想(北京)有限公司 | Method of information processing and line control earphone |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111933176A (en) * | 2020-09-22 | 2020-11-13 | 成都启英泰伦科技有限公司 | Method and device for positioning voice contents in batches |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10964300B2 (en) | Audio signal processing method and apparatus, and storage medium thereof | |
| US11251763B2 (en) | Audio signal adjustment method, storage medium, and terminal | |
| CN109087669B (en) | Audio similarity detection method and device, storage medium and computer equipment | |
| WO2021078116A1 (en) | Video processing method and electronic device | |
| MX2008016354A (en) | Detecting an answering machine using speech recognition. | |
| US11328711B2 (en) | User adaptive conversation apparatus and method based on monitoring of emotional and ethical states | |
| CN110364156A (en) | Voice interactive method, system, terminal and readable storage medium storing program for executing | |
| CN109994111B (en) | Interaction method, interaction device and mobile terminal | |
| CN109982228A (en) | A kind of microphone fault detection method and mobile terminal | |
| CN110556127A (en) | method, device, equipment and medium for detecting voice recognition result | |
| CN108174236A (en) | A kind of media file processing method, server and mobile terminal | |
| CN110225195B (en) | Voice communication method and terminal | |
| CN108989558A (en) | The method and device of terminal call | |
| CN111370018A (en) | Audio data processing method, electronic device and medium | |
| CN109726121B (en) | Verification code obtaining method and terminal equipment | |
| CN109379490A (en) | Audio frequency playing method, device, electronic equipment and computer-readable medium | |
| CN110519450A (en) | Ultrasonic processing method, device, electronic equipment and computer-readable medium | |
| CN107135452A (en) | Audiphone adaptation method and device | |
| CN115831155A (en) | Audio signal processing method and device, electronic equipment and storage medium | |
| CN109361797A (en) | A kind of vocal technique and mobile terminal | |
| CN111835522A (en) | Audio processing method and device | |
| KR20130122300A (en) | Method and apparatus for providing emotion analysis service during telephone conversation | |
| CN101163215B (en) | Method and apparatus for setting actual volume of television set | |
| CN110365371A (en) | The method and its system, electronic equipment that trigger signal realizes translation system control are provided based on bluetooth equipment | |
| CN109788116A (en) | The method for detecting voice input pattern |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190521 |
|
| WW01 | Invention patent application withdrawn after publication |