CN205029734U - Keyword pronunciation awaken system and mobile terminal up - Google Patents
Keyword pronunciation awaken system and mobile terminal up Download PDFInfo
- Publication number
- CN205029734U CN205029734U CN201520245503.5U CN201520245503U CN205029734U CN 205029734 U CN205029734 U CN 205029734U CN 201520245503 U CN201520245503 U CN 201520245503U CN 205029734 U CN205029734 U CN 205029734U
- Authority
- CN
- China
- Prior art keywords
- keyword
- mobile terminal
- unit
- voice
- instruction
- 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
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Mobile Radio Communication Systems (AREA)
Abstract
The utility model relates to a speech signal processing technique field especially relates to a keyword pronunciation awaken system and mobile terminal up. Include: acquisition unit for it gathers signal output to form one, judge the unit, connect acquisition unit, awaken the unit up, connect judge the unit. The utility model discloses having preset the keyword and having waken the instruction up, the keyword wakes the instruction up and can set up by oneself according to user's hobby, and mobile terminal only can all be in the standby mode by the activation of specific keyword under the state that is not activated, and the consumption is lower, and has effectively improved the rate of accuracy that mobile terminal activated, greatly reduced operating rate by mistake. Furtherly, acquisition unit can adopt the microphone, and furtherly, microphone can be for the MEMS microphones, adopt the microphone as acquisition unit, microphone simple structure, easily integrated, the while cost is lower.
Description
Technical field
The utility model relates to a kind of voice process technology field, particularly relates to a kind of keyword voice waken system and mobile terminal.
Background technology
The word adopted in human speech communication process normally vocal cord vibration produce vowel arrange in pairs or groups this vibration larynx, tongue, lip, jaw, intraoral air-flow formed consonant combine formed, i.e. vowel meeting produce power, consonant is only gas sound, major part has the word of essence implication all first to start with consonant, and be mostly auxiliary words of mood with the word that vowel starts, as " ", " " " " ... it is all the word started with vowel Deng word.
In existing mobile terminal, waken system mainly contains manual waken system, namely conventional by starting to start push button exciting mobile terminal; This kind of mode, Long-Time Service, easily causes the malfunctioning of button, and power consumption is larger simultaneously; Action waken system, namely in mobile terminal, acceleration transducer is provided with, acceleration transducer detect whether have acceleration (such as movement lie low place mobile terminal namely there is an acceleration) produce, when acceleration meets predetermined condition, activate mobile terminal, this kind of mode needs collocation acceleration transducer, and cost is higher, and acceleration transducer power consumption is larger; Such as brandish mobile terminal and can activate mobile terminal; Voice waken system, voice waken system detects the activity of human speech, as long as any vowel or consonant namely detected, can activate the mobile terminal be in holding state, adopt voice waken system, power consumption is lower, and cost is lower, but only hearing that human speech information can activate, easily there is misoperation, can mobile terminal be activated per capita arbitrarily in this kind of voice waken system, in the occasion that number is more, mobile terminal is always in running order, and power consumption is comparatively large, activates accuracy rate low.
Utility model content
For the deficiencies in the prior art, the utility model provide a kind of low in energy consumption, activate that accuracy rate is high, a kind of keyword voice waken system that misoperation is low and mobile terminal.
A kind of keyword voice waken system, is applied to mobile terminal, wherein:
Above-mentioned keyword voice waken system, wherein: described collecting unit gathers described voice signal when described voice signal reaches a default amplitude.
Above-mentioned keyword voice waken system, wherein: also comprise a nonvolatile memory cell, connects described judging unit, wakes instruction up in order to store default described keyword.
Above-mentioned keyword voice waken system, wherein: also comprise a training unit, be connected between described collecting unit and described nonvolatile memory cell, be used to described running of mobile terminal under a training mode, the a plurality of voice sent in order to receive user wake instruction up, and wake instruction up according to a plurality of described voice and form default described keyword and wake instruction up, and export described nonvolatile memory cell to and store.
Above-mentioned keyword voice waken system, wherein: described training unit comprises
One computing unit, connects described collecting unit, wakes the standard energy information of instruction, standard amplitude information in order to calculate default described keyword up;
One timing unit, connects described collecting unit, wakes the standard time information of instruction in order to calculate default described keyword up.
Above-mentioned keyword voice waken system, wherein: described default keyword wakes instruction up and at least comprises standard energy information, standard amplitude information, standard time information,
The described judged result that described judging unit exports when described collection signal at least mates described standard energy information and described standard amplitude information and described standard time information activates described mobile terminal for allowing.
Above-mentioned keyword voice waken system, wherein: described computing unit is Fourier transform unit, carry out in order to wake instruction up to the described keyword preset standard energy information, the standard amplitude information that the default described keyword of Fourier transform acquisition wakes instruction up.
Above-mentioned keyword voice waken system, wherein: described training mode is controlled to be formed by the control unit of described mobile terminal.
A kind of mobile terminal, wherein: comprise the keyword voice waken system described in above-mentioned any one, described keyword voice waken system is arranged in described mobile terminal, be used to receive one include the voice signal of predetermined described keyword after, the operational mode of described mobile terminal is switched to mode of operation from standby mode.
Compared with prior art, the utility model has the advantages that:
The utility model is preset with keyword and wakes instruction up, keyword wakes instruction up and can arrange voluntarily according to the hobby of user, mobile terminal only can by specifically keyword-activated, all standby mode is under the state be not activated, power consumption is lower, and effectively improve the accuracy rate of mobile terminal activating, greatly reduce misuse rate.Further, collecting unit can adopt microphone, and further, microphone can be MEMS microphone, and adopt microphone as collecting unit, microphone structure is simple, is easy to integrated, and cost is lower simultaneously.
Accompanying drawing explanation
Fig. 1 is the structural representation of the utility model keyword voice waken system.
Embodiment
Below in conjunction with the drawings and specific embodiments, the utility model is described in further detail, but not as restriction of the present utility model.
Below in conjunction with the accompanying drawing in the utility model embodiment, be clearly and completely described the technical scheme in the utility model embodiment, obviously, described embodiment is only the utility model part embodiment, instead of whole embodiments.Based on the embodiment in the utility model, the every other embodiment that those of ordinary skill in the art obtain under the prerequisite of not making creative work, all belongs to the scope of the utility model protection.
It should be noted that, when not conflicting, the embodiment in the utility model and the feature in embodiment can combine mutually.
Below in conjunction with the drawings and specific embodiments, the utility model is described in further detail, but not as restriction of the present utility model.
As shown in Figure 1, a kind of keyword voice waken system, is applied to mobile terminal, wherein: comprising:
One collecting unit, in order to gather the voice signal of preset frequency in the current described environment of described mobile terminal, and forming a collection signal output, collecting unit inside also can comprise a calculation element, calculates the time that the amplitude information of collection signal, energy information and collection signal continue.Wherein, the 300Hz ~ 3KHz of preset frequency.The frequency that collecting unit can gather voice signal is 20Hz ~ 20KHz, and the frequency of human sound is generally 300Hz ~ 3KHz, and the sound lower than 300Hz is generally environmental noise, therefore will not gather, reduce the collection capacity of signal, indirectly reduce amount of calculation, improve the speed of calculating.
One judging unit, connects described collecting unit, in order to receive the described collection signal that described collecting unit exports, and judges whether described collection signal mates a keyword preset and wake instruction up, and exports corresponding judged result;
One wakeup unit, connects described judging unit, and in order to receive the described judged result that described judging unit exports, be used to described collection signal and mate described keyword when waking instruction up, described wakeup unit activates described mobile terminal.
The operation principle of keyword voice waken system: collecting unit gathers the voice signal in the current described environment of described mobile terminal, and form a collection signal output; Judging unit receives the described collection signal that described collecting unit exports, and judges whether described collection signal mates a keyword preset and wake instruction up, and exports corresponding judged result; Wakeup unit receives the described judged result that described judging unit exports, and be used to described collection signal and mate described keyword when waking instruction up, described wakeup unit activates described mobile terminal.The utility model is preset with keyword and wakes instruction up, keyword wakes instruction up and can arrange voluntarily according to the hobby of user, such as arrange one " Xiao Ming ", when the signal that collecting unit gathers is " obviously ", " little red ", mobile terminal all can not be activated, and only only can be activated when collecting " Xiao Ming ".Adopt this kind of mode, mobile terminal only can by specifically keyword-activated, and under the state be not activated, be all in standby mode, power consumption is lower, and effectively improves the accuracy rate of mobile terminal activating, greatly reduces misuse rate.Further, collecting unit can adopt microphone, and further, microphone can be MEMS microphone, and adopt microphone as collecting unit, microphone structure is simple, is easy to integrated, and cost is lower simultaneously.
As further preferred embodiment, above-mentioned keyword voice waken system, wherein: described collecting unit gathers described voice signal when described voice signal reaches a default amplitude.Predetermined amplitude usually can by user's sets itself, also can the basic volume of human speech as predetermined amplitude, do not limit herein.The collection of signal is carried out when voice signal reaches predetermined amplitude, effectively avoid gathering by mistake, such as when voice signal too low or too high, collecting unit does not gather this signal, under the state that usual sound is too low or too high, user may be in abnormal condition, and mobile terminal can not be activated.If but user can not normally send voice status under (such as in session process in), can exciting mobile terminal by other means, such as conventional push button exciting mobile terminal, or fingerprint activated mobile terminal.Namely mobile terminal can adopt multiple Starting mode to cooperatively interact to activate mobile terminal.
As further preferred embodiment, above-mentioned keyword voice waken system, wherein: also comprise a nonvolatile memory cell, connects described judging unit, wakes instruction up in order to store default described keyword.Nonvolatile memory cell is namely under the state of power down, and keyword wakes instruction up and not easily loses.Nonvolatile memory cell can be MTP memory cell (can repeatedly programmed logic memory cell), OTP memory cell (OneTimeProgramming, One Time Programmable), EEPROM (ElectricallyErasableProgrammableRead-OnlyMemory is with EEPROM (Electrically Erasable Programmable Read Only Memo)) memory cell, Flash (FlashMemory flash memory).
As further preferred embodiment, above-mentioned keyword voice waken system, wherein: also comprise a training unit, be connected between described collecting unit and described nonvolatile memory cell, be used to described running of mobile terminal under a training mode, the a plurality of voice sent in order to receive user wake instruction up, and wake instruction up according to a plurality of described voice and form default described keyword and wake instruction up, and export described nonvolatile memory cell to and store.Training unit mainly wakes instruction up in order to arrange keyword, and user in training mode, sends ten times " Xiao Ming ", training unit receives ten times " Xiao Ming ", according to the voice messaging of ten times " Xiao Ming ", keyword is revised, wake instruction up to form keyword.Because the energy of the amplitude of each voice messaging of the mankind, time, pronunciation is not identical, so increase a training unit, instruction is waken up in order to form keyword, it is that the keyword sent user is trained and revises that this keyword wakes instruction up, under the state allowing user to occur part deviation at the keyword sent, still mobile terminal can be activated.
As further preferred embodiment, above-mentioned keyword voice waken system, wherein: described training unit comprises
One computing unit, connects described collecting unit, wakes the standard energy information of instruction, standard amplitude information in order to calculate default described keyword up; Further, described computing unit is Fourier transform unit, carries out in order to wake instruction up to the described keyword preset standard energy information, the standard amplitude information that the default described keyword of Fourier transform acquisition wakes instruction up.First segmentation is carried out to voice signal, frequency domain conversion is carried out to the signal in every section, energy information and the standard amplitude information that frequency-domain calculations obtains its standard is carried out to the energy information in frequency domain conversion.
One timing unit, connects described collecting unit, wakes the standard time information of instruction in order to calculate default described keyword up.
As further preferred embodiment, above-mentioned keyword voice waken system, wherein: described default keyword wakes instruction up and at least comprises standard energy information, standard amplitude information, standard time information, the described judged result that described judging unit exports when described collection signal at least mates described standard energy information and described standard amplitude information and described standard time information activates described mobile terminal for allowing.Several comparators can be comprised, in order to compare energy information, amplitude information, the temporal information of collection signal respectively in described judging unit.
Above-mentioned keyword voice waken system, wherein: described training mode is controlled to be formed by the control unit of described mobile terminal.Training mode has the control unit of mobile terminal to control usually, and under being in training mode, collecting unit is only connected with training unit, i.e. the voice signal of collecting unit collection only transfers to training unit.
A kind of mobile terminal, wherein: comprise the keyword voice waken system described in above-mentioned any one, described keyword voice waken system is arranged in described mobile terminal, be used to receive one include the voice signal of predetermined described keyword after, the operational mode of described mobile terminal is switched to mode of operation from standby mode.
The foregoing is only the utility model preferred embodiment; not thereby execution mode of the present utility model and protection range is limited; to those skilled in the art; should recognize and all should be included in the scheme that equivalent replacement done by all utilization the utility model specifications and diagramatic content and apparent change obtain in protection range of the present utility model.
Claims (8)
1. a keyword voice waken system, is applied to mobile terminal, it is characterized in that: comprising:
One collecting unit, in order to gather the voice signal in the current residing environment of described mobile terminal, and forms a collection signal output; Described collecting unit gathers described voice signal when described voice signal reaches a default amplitude;
One judging unit, connects described collecting unit, in order to receive the described collection signal that described collecting unit exports, and judges whether described collection signal mates a keyword preset and wake instruction up, and exports corresponding judged result;
One wakeup unit, connects described judging unit, and in order to receive the described judged result that described judging unit exports, be used to described collection signal and mate described keyword when waking instruction up, described wakeup unit activates described mobile terminal.
2. keyword voice waken system according to claim 1, is characterized in that: also comprise a nonvolatile memory cell, connects described judging unit, wakes instruction up in order to store default described keyword.
3. keyword voice waken system according to claim 2, it is characterized in that: also comprise a training unit, be connected between described collecting unit and described nonvolatile memory cell, be used to described running of mobile terminal under a training mode, the a plurality of voice sent in order to receive user wake instruction up, and wake instruction up according to a plurality of described voice and form default described keyword and wake instruction up, and export described nonvolatile memory cell to and store.
4. keyword voice waken system according to claim 3, is characterized in that: described training unit comprises
One computing unit, connects described collecting unit, wakes the standard energy information of instruction, standard amplitude information in order to calculate default described keyword up;
One timing unit, connects described collecting unit, wakes the standard time information of instruction in order to calculate default described keyword up.
5. keyword voice waken system according to claim 1, is characterized in that: described default keyword wakes instruction up and at least comprises standard energy information, standard amplitude information, standard time information,
Described judging unit exports described judged result and activates described mobile terminal for allowing when described collection signal at least mates described standard energy information and described standard amplitude information and described standard time information.
6. keyword voice waken system according to claim 4, it is characterized in that: described computing unit is Fourier transform unit, the described keyword carrying out Fourier transform acquisition default in order to wake instruction up to the described keyword preset wakes the described standard energy information of instruction, described standard amplitude information up.
7. keyword voice waken system according to claim 3, is characterized in that: described training mode is controlled to be formed by the control unit of described mobile terminal.
8. a mobile terminal, it is characterized in that: comprise the keyword voice waken system described in any one of the claims 1 ~ 7, described keyword voice waken system is arranged in described mobile terminal, be used to receive one include the voice signal of predetermined described keyword after, the operational mode of described mobile terminal is switched to mode of operation from standby mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201520245503.5U CN205029734U (en) | 2015-04-20 | 2015-04-20 | Keyword pronunciation awaken system and mobile terminal up |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201520245503.5U CN205029734U (en) | 2015-04-20 | 2015-04-20 | Keyword pronunciation awaken system and mobile terminal up |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN205029734U true CN205029734U (en) | 2016-02-10 |
Family
ID=55262235
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201520245503.5U Active CN205029734U (en) | 2015-04-20 | 2015-04-20 | Keyword pronunciation awaken system and mobile terminal up |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN205029734U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105812573A (en) * | 2016-04-28 | 2016-07-27 | 努比亚技术有限公司 | Voice processing method and mobile terminal |
-
2015
- 2015-04-20 CN CN201520245503.5U patent/CN205029734U/en active Active
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105812573A (en) * | 2016-04-28 | 2016-07-27 | 努比亚技术有限公司 | Voice processing method and mobile terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106161755A (en) | A kind of key word voice wakes up system and awakening method and mobile terminal up | |
| CN105009204B (en) | Speech recognition power management | |
| CN107704275B (en) | Intelligent device awakening method and device, server and intelligent device | |
| TWI474317B (en) | Signal processing apparatus and signal processing method | |
| CN106157950A (en) | Speech control system and awakening method, Rouser and household electrical appliances, coprocessor | |
| CN106155621B (en) | Keyword voice awakening system and method capable of identifying sound source position and mobile terminal | |
| CN106714023A (en) | Bone conduction earphone-based voice awakening method and system and bone conduction earphone | |
| CN103901782B (en) | A kind of acoustic-controlled method, electronic equipment and sound-controlled apparatus | |
| CN204856459U (en) | Keyword pronunciation of distinguishable sound source position awaken system and mobile terminal up | |
| CN101795323A (en) | Electronic alarm operation method, electronic alarm and mobile communication terminal | |
| CN110265036A (en) | Voice awakening method, system, electronic equipment and computer readable storage medium | |
| WO2016078214A1 (en) | Terminal processing method, device and computer storage medium | |
| CN103956164A (en) | Voice awakening method and system | |
| CN203504751U (en) | Microphone with function of voice awakening and mobile terminal | |
| CN110473544A (en) | A kind of low-power consumption voice awakening method and device | |
| CN104952219A (en) | Intelligent device-based method for searching articles and intelligent device | |
| CN205029734U (en) | Keyword pronunciation awaken system and mobile terminal up | |
| CN108093350B (en) | Microphone control method and microphone | |
| CN110956968A (en) | Voice wake-up and voice wake-up function triggering method and device, and terminal equipment | |
| CN112995833B (en) | Earphone voice collecting method, earphone and readable storage medium | |
| CN105430155A (en) | Wearable equipment and control method thereof based on speech signals | |
| CN203167204U (en) | Sound control microphone | |
| CN116386676B (en) | Voice awakening method, voice awakening device and storage medium | |
| CN109427336A (en) | Voice object identifying method and device | |
| CN210843015U (en) | Novel bluetooth headset |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |