CN108877788A - Electronic device and its operating method with voice arousal function - Google Patents
Electronic device and its operating method with voice arousal function Download PDFInfo
- Publication number
- CN108877788A CN108877788A CN201710323994.4A CN201710323994A CN108877788A CN 108877788 A CN108877788 A CN 108877788A CN 201710323994 A CN201710323994 A CN 201710323994A CN 108877788 A CN108877788 A CN 108877788A
- Authority
- CN
- China
- Prior art keywords
- detector
- signal
- sound signal
- human speech
- wake
- 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.)
- Granted
Links
- 238000011017 operating method Methods 0.000 title claims abstract description 23
- 230000037007 arousal Effects 0.000 title claims abstract description 22
- 230000005236 sound signal Effects 0.000 claims abstract description 91
- 238000000034 method Methods 0.000 claims description 15
- 238000005284 basis set Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 13
- 230000003321 amplification Effects 0.000 description 4
- 238000003199 nucleic acid amplification method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 235000015096 spirit Nutrition 0.000 description 2
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005059 dormancy Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000002618 waking effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/485—Task life-cycle, e.g. stopping, restarting, resuming execution
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/22—Interactive procedures; Man-machine interfaces
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/26—Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
-
- 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
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Power Sources (AREA)
- Electric Clocks (AREA)
Abstract
The embodiment of the present invention provides a kind of electronic device and its operating method with voice arousal function.The electronic device can be by the preposition signal detector using additional and detect to the sound signal of analogy form, and when the sound signal of the analogy form, which is judged as, meets a preset condition, preposition signal detector will wake up analog digital converter and human speech detector.Therefore, when the host system of electronic device enters dormant state by normal operating conditions, analog digital converter and human speech detector can be enters dormant state together, the effect of to reach power saving.
Description
Technical field
The invention relates to a kind of electronic device and its operating methods, and especially a kind of with voice wake-up (Wake
On Voice) function electronic device and its operating method.
Background technique
With the development of science and technology, voice arousal function is widely used in all kinds of electronic devices, as low as mobile handsets,
Greatly to general electrical home appliances, may all have voice arousal function, and what so-called voice arousal function referred to is exactly, when electronics fills
When setting (or referred to as standby mode) in a dormant state, user can be directed through the voice of the mankind to wake up electronic device,
Electronic device is enabled to be detached from dormant state and return to normal operating conditions.For example, referring to Fig. 1, Fig. 1 is known has
The function block schematic diagram of the electronic device of voice arousal function.As shown in Figure 1, electronic device 1 mainly includes microphone
(microphone) Mic, microphone preamplifier (pre-amplifier) 100, analog digital converter (analog-to-
Digital converter, ADC) 120, human speech detector (human voice detector) 140, at digital signal
Manage device (digital signal processor, DSP) 160 and host system (host system) HS.
(also that is, when host system HS enters dormant state), microphone when electronic device 1 enters a dormant state
Mic can carry out radio reception from environment, and by received ambient sound (not being painted) via microphone preamplifier 100
Amplify, and after being converted into a digital signals (not being painted) by analog digital converter 120 again, human speech detector
140 can just be used to judge whether the ambient sound is a human speech.Wherein, when the ambient sound is not human speech,
Human speech detector 140 then will not wake up digital signal processor 160 and host system HS, and when the ambient sound is the mankind
When voice, human speech detector 140 then can first wake up digital signal processor 160, so that 160 energy of digital signal processor
Yet further judge whether the human speech meets default crucial voice.
If do not meet, digital signal processor 160 will voluntarily return to dormant state, with waiting being called out next time
It wakes up；If meet, digital signal processor 160 will wake-up master system HS so that electronic device 1 can be detached from dormant state
And return to normal operating conditions.Then, as shown in Figure 1, in order to enable digital signal processor 160 carrying out speech recognition
The processing of any sound, therefore microphone Mic, microphone preamplifier will not be omitted when (speech recognition)
100, analog digital converter 120 and human speech detector 140 must be maintained at a permanent shape for opening (Always-On)
State, to cause the consumption of excrescent electric power.In view of this, for how effectively to solve when electronic device 1 is (also that is, host system
HS) in a dormant state under power problems, really be fields urgent need to resolve the problem of.
Summary of the invention
The embodiment of the present invention provides a kind of electronic device with voice arousal function.The electronic device includes host system
System, microphone, the first microphone preamplifier, preposition signal detector and crucial voice decision circuitry.Microphone is used to connect
An ambient sound is received, and is an ambient sound signal by the output of this ambient sound.First microphone preamplifier is used to receive
And amplify this ambient sound signal, by the sound signal in the form of one analogy of generation.Preposition signal detector is used to receive and judge
Whether the sound signal of analogy form meets a preset condition, and after host system enters a dormant state, works as analogy
The sound signal of form is judged as when meeting preset condition, and preposition signal detector then exports one first wake up instruction, to wake up
Crucial voice decision circuitry.Crucial voice decision circuitry is then waken up to receive and process the sound signal of analogy form, to sentence
Whether disconnected ambient sound meets a preset crucial voice, and when ambient sound is judged as and meets preset crucial voice,
Crucial voice decision circuitry exports host wake-up instruction, and host system is waken up from dormant state.
The embodiment of the present invention separately provides a kind of operating method for the electronic device with voice arousal function.Wherein,
The electronic device is to establish according to previous embodiment, and the operating method comprises the steps of.Firstly, utilizing Mike
Wind receives an ambient sound, and is an ambient sound signal by the output of this ambient sound.Secondly, preposition using the first microphone
Amplifier, to receive and amplify this ambient sound signal, by the sound signal in the form of one analogy of generation.Then, preposition news are utilized
Number detector, to receive and judge whether the sound signal of analogy form meets a preset condition, and host system into
Enter to after a dormant state, when the sound signal of analogy form, which is judged as, meets preset condition, preposition signal detector is then defeated
One first wake up instruction out, to wake up crucial voice decision circuitry.Finally, crucial voice decision circuitry is then waken up to receive simultaneously
The sound signal of analogy form is handled, to judge whether ambient sound meets a preset crucial voice, and works as ambient sound
It is judged as that crucial voice decision circuitry exports host wake-up instruction, certainly by host system when meeting preset crucial voice
It is waken up in dormant state.
Preferably, the crucial voice decision circuitry may include analog digital converter, human speech detector and numerical digit
Signal processor.Wherein, after host system enters dormant state, when preposition signal detector exports the first wake up instruction
When, analog digital converter is then waken up the sound news that amplified ambient sound signal is converted into a digital form
Number, and whether the sound signal that human speech detector is then waken up to judge digital form meets a human speech.Work as numerical digit
The sound signal of form is judged as when meeting human speech, and human speech detector exports one second wake up instruction, to wake up number
Position signal processor.Then, digital signal processor is waken up to judge whether this human speech meets preset crucial voice,
And when this mankind's phonetic decision is to meet preset crucial voice, digital signal processor exports host wake-up instruction, with
Host system is waken up from dormant state.Therefore, when the host system of the electronic device is entered by a normal operating conditions
When to dormant state, analog digital converter, human speech detector and digital signal processor are then that can all enter to stop together
Dormancy state.
In conclusion there is the electronic device and its operating method of voice arousal function provided by the embodiment of the present invention,
It will can be and be totally different from existing technological means, but come first with additional increased preposition signal detector to analogy form
Sound signal detected, to make speech recognition result faster and tentatively, and work as the sound signal of analogy form
It is judged as that preposition signal detector can then wake up analog digital converter and human speech detector when meeting a preset condition,
To ensure when the host system of electronic device enters dormant state by normal operating conditions, analog digital converter, the mankind
Voice detector and digital signal processor are then that can all enter dormant state together, to be effectively improved current power consumption up to 1
Times or more.
Be further understood that feature and technology contents of the invention to be enabled, please refer to below in connection with it is of the invention specifically
Bright and attached drawing, but these explanations are intended merely to illustrate the present invention with institute's accompanying drawings, rather than interest field of the invention is appointed
What limitation.
Detailed description of the invention
Fig. 1 is the function block schematic diagram of the known electronic device with voice arousal function.
Fig. 2 is the function block schematic diagram of the electronic device provided by the embodiment of the present invention with voice arousal function.
Fig. 3 A be the key that in the electronic device with voice arousal function of Fig. 2 under a preferred embodiment phonetic decision
The function block schematic diagram of circuit.
Fig. 3 B is the key that voice is sentenced under another preferred embodiment in the electronic device with voice arousal function of Fig. 2
The function block schematic diagram of deenergizing.
Fig. 4 is the stream provided by the embodiment of the present invention for the operating method of the electronic device with voice arousal function
Journey schematic diagram.
Fig. 5 is the flow diagram of the step S411 to step S415 in the operating method of Fig. 4 under a preferred embodiment.
Fig. 6 is the process signal of the step S411 to step S415 in the operating method of Fig. 4 under another preferred embodiment
Figure.
【Symbol description】
1,2：Electronic device
Mic：Microphone
100,200,300：Microphone preamplifier
210：Preposition signal detector
20：Crucial voice decision circuitry
120,220：Analog digital converter
140,240：Human speech detector
160,260：Digital signal processor
HS：Host system
EV：Ambient sound signal
AVS：The sound signal of analogy form
DVS：The sound signal of digital form
WS1：First wake up instruction
WS2：Second wake up instruction
WS0：Host wake-up instruction
S401~S415, S501~S513, S601~S605：Process step
Specific embodiment
Hereinafter, it will illustrate that various embodiments of the present invention carry out the present invention is described in detail by schema.However, of the invention
Concept may embody in many different forms, and should not be construed as limited by exemplary embodiments set forth herein.In addition,
Same reference numbers can be used to indicate similar element in the drawings.
Firstly, referring to Fig. 2, Fig. 2 is the electronic device provided by the embodiment of the present invention with voice arousal function
Function block schematic diagram.In the present embodiment, electronic device 2 includes host system HS, microphone Mic, the preposition amplification of microphone
Device 200, preposition signal detector 210 and crucial voice decision circuitry 20.Wherein, it is put before above-mentioned host system HS, microphone
Big device 200, preposition signal detector 210 and crucial voice decision circuitry 20 can be through pure hardware circuit and realize, or
It is to be realized through hardware circuit collocation firmware or software.To sum up, the present invention is not intended to limit the specific implementation of electronic device 2
Mode.In addition to this, above-mentioned each element can be integration or be provided separately, and the present invention is also not limited system.
Furthermore, it is understood that microphone Mic (is not drawn for receiving an ambient sound from the space where electronic device 2
Show), and be an ambient sound signal EV by the output of this ambient sound, and microphone preamplifier 200 is then coupled to Mike
Wind Mic, and be used to receive and amplify this ambient sound signal EV, by the sound signal AVS in the form of one analogy of generation, such as Fig. 2 institute
Show.Wherein, since the operation principles of microphone Mic and microphone preamplifier 200 are all to have in the art usually
Known by skill, therefore just do not add to repeat about this is dissolved in its thin portion.In addition, preposition signal detector 210 then coupling
It is connected to microphone preamplifier 200, and crucial voice decision circuitry 20 is then coupled to preposition signal detector 210 and host system
Unite HS.
Preposition signal detector 210 is used to receive and judge whether the sound signal AVS of analogy form meets a default item
Part (is not painted), and after host system HS enters a dormant state, when the sound signal AVS of analogy form is judged as full
When sufficient preset condition, preposition signal detector 210 then exports one first wake up instruction WS1, to wake up crucial voice decision circuitry
20.Crucial voice decision circuitry 20 is then waken up to receive and process the sound signal AVS of analogy form, to judge ambient sound
Whether meet a preset crucial voice (not being painted), and when ambient sound is judged as and meets preset crucial voice, closes
Key phonetic decision circuit 20 exports a host wake-up and instructs WS0, and host system HS is waken up from dormant state, is thereby made
Electronic device 2 can be detached from dormant state and be back to normal operating conditions.
It should be noted that the preset condition of the present embodiment can be for example according to set by preset crucial voice, but
System that the present invention is not limited thereto.Then, in order to further explain the realization details about crucial voice decision circuitry 20, this
Invention further provides for one such embodiment.Also referring to Fig. 3 A, Fig. 3 A is Fig. 2 with voice arousal function
The function block schematic diagram of crucial voice decision circuitry in electronic device under a preferred embodiment.Under it is worth noting that,
Embodiment used by stating also is herein only to illustrate, and it is not intended to limiting the invention.In other words, the embodiment of the present invention
It is not intended to limit the detailed implementation in relation to crucial voice decision circuitry 20, therefore the usually intellectual of having can be according in the art
It is designed according to actual demand or application.
In the embodiment in fig. 3 a, crucial voice decision circuitry 20 may include that analog digital converter 220, human speech are detectd
Survey device 240 and digital signal processor 260.Wherein, due to analog digital converter 220, human speech detector 240 and numerical digit
The operation principles of signal processor 260 are all to have known by usually intellectual in the art, therefore about its thin portion
This is inside dissolved in just not add to repeat.It is apparent that the electronic device 1 compared to Fig. 1, the electronic device 2 of the embodiment of the present invention is more
Contain a preposition signal detector 21.In the present embodiment, preposition signal detector 210 may be, for example, a structure letter
Single circuit for detecting, is detected and is handled for the sound signal AVS to analogy form.
However, since the circuit for detecting of the signal of processing analogy form is can be directed through indivisible analog circuit member
Part (such as operational amplifier etc.) is realized, therefore the power consumption of preposition signal detector 210 is also just usually smaller, so, in
In practice, preposition signal detector 210 can be maintained at the state permanently opened, and without having to especially worrying its power consumption.
In addition, the treatment process of the signal due to analogy form, the treatment process more than the signal in digital form is come simply and fastly
Speed, therefore the first main spirits of the embodiment of the present invention are, can using the additional increased preposition signal detector 210 of institute come
The sound signal AVS of the analogy form is detected, to make speech recognition result faster and tentatively.
Specifically, electronic device 2 in a dormant state in the case where (also that is, host system HS enters suspend mode shape
After state), when the sound signal AVS that preposition signal detector 210 determines the analogy form meets a preset condition (not being painted)
When, preposition signal detector 210 will export the first wake up instruction WS1 first to wake up the analogy in crucial voice decision circuitry 20
Digital converter 220 and human speech detector 240.Therefore, teaching according to the above has usual in the art
Skill should be appreciated that, Fig. 1 in the prior art, when host system HS enters dormant state by normal operating conditions
When, electronic device 1 is only to have digital signal processor 160 to enter dormant state together.But in embodiments of the present invention,
When host system HS enters dormant state by normal operating conditions, electronic device 2 is then to have analog digital converter
220, human speech detector 240 and digital signal processor 260 can all enter dormant state, therefore the embodiment of the present invention together
Electronic device 2 more can effectively improve current power consumption up to 1 times or more.
That is, electronic device 2 in a dormant state in the case where, the embodiment of the present invention only remaining can have wheat
Gram wind Mic, microphone preamplifier 200 and preposition signal detector 210 are maintained at the state permanently opened, therefore and make
The power consumption (power consumption) for obtaining entire electronic device 2 can be lower so as to dropping to.More carefully for, such as Fig. 3 A
It is shown, after host system HS enters dormant state, when preposition signal detector 210 exports the first wake up instruction WS1, class
The sound news that amplified ambient sound signal EV is converted into a digital form can be then waken up than digital converter 220
Number DVS, and human speech detector 240 can also be waken up to judge whether the sound signal DVS of this digital form meets the mankind
Voice (is not painted).
When the sound signal DVS of digital form, which is judged as, meets human speech, human speech detector 240 then exports one
The second wake up instruction WS2 wakes up digital signal processor 260.As described in previous contents, it should be appreciated that in host system
After system HS enters dormant state, and the case where human speech detector 240 and analog digital converter 220 are waken up
Under, when the sound signal DVS of digital form, which is judged as, does not meet human speech, human speech detector 240 and analog/digital
Converter 220 is then that can voluntarily return to dormant state respectively, with waiting being waken up next time.
Similarly, after host system HS enters dormant state, refer to when the output of human speech detector 240 second wakes up
When enabling WS2, digital signal processor 260 can then be waken up to judge whether this human speech meets preset crucial voice (not
It is painted), and when this mankind's phonetic decision is to meet preset crucial voice, digital signal processor 260 exports host and calls out
Wake up instruction WS0, and host system HS is waken up from dormant state.It should also be understood that being entered in host system HS
After dormant state, and has in digital signal processor 260, human speech detector 240 and the analog digital converter 220 and called out
In the case where waking up, when this mankind's phonetic decision is not meet preset crucial voice, digital signal processor 260, Ren Leiyu
Sound detector 240 and the analog digital converter 220 are then that can voluntarily return to dormant state respectively, with waiting being called out next time
It wakes up.Wherein, detailed content is as in the foregoing embodiment, therefore just no longer adds redundant in this.
Theoretically, the signal of analogy form refers to that mathematical form in the time domain is the signal of continuous function, therefore analogy
The signal of form will directly can be expressed by the model (pattern) using some physical attributes, so, in the present embodiment
In, what so-called " judging whether the sound signal AVS of the analogy form meets a preset condition " referred to is exactly to judge the analogy shape
Whether the sound signal AVS of formula meets a preset model (pattern), this preset model (pattern) can be according to people
The physical attribute of class voice is set, and is also possible to be set according to the physical attribute of preset crucial voice, but the present invention is all
It is not limited system.However, because the sound signal AVS of analogy form is easy to be influenced by noise and generate distortion, analogy
The sound signal AVS of form might not come more accurate than the sound signal DVS of digital form.Then, when preposition signal
When detector 210 judges that the sound signal AVS of the analogy form meets a certain preset model, preposition signal detector 210
It determines to wake up analog digital converter 220 and human speech detector 240, to carry out more accurately speech recognition.
In addition, because quantization error, the sound signal of analogy form is not present in the sound signal AVS of analogy form
AVS can also make the description most approached to the true value of ambient sound.Therefore, in the present embodiment, so-called " to judge such
Whether the sound signal AVS than form meets a preset condition " that also refer to is exactly the sound signal AVS for judging the analogy form
An amplitude (amplitude), a period (period) or a frequency (frequency) whether be more than or equal to its institute corresponding one
Threshold value.For example, the frequency of human speech is distributed in 500 hertz (Hz) to 2000 hertz (Hz) mostly.Therefore, when preposition
Signal detector 210 judges when the frequency of the sound signal AVS of the analogy form is greater than 500 hertz (also that is, frequency institute is corresponding
Threshold value is set as 500 hertz), preposition signal detector 210 just can may contain the sound of the mankind in the preliminary judgement ambient sound
Sound, so that preposition signal detector 210 can determine to wake up analog digital converter 220 and human speech detector 240, with into
Row more accurately speech recognition.In another embodiment, preposition signal detector 210 judges the sound signal of the analogy form
Whether the amplitude and duration of AVS meets a range corresponding to preset crucial voice just can preliminary judgement if meeting
The ambient sound may be preset crucial voice.To sum up, each implementation used by above-mentioned is all only illustrated herein,
It is not intended to limiting the invention, therefore the usually intellectual of having should can carry out according to actual demand or application in the art
Relevant design.
On the other hand, it should be appreciated that the microphone preamplifier 200 of Fig. 3 A be can be seen as be Fig. 1 Mike
Wind preamplifier 100, but the present invention is not limited thereto system.For example, also referring to Fig. 3 B is arrived, Fig. 3 B is Fig. 2
The function block of crucial voice decision circuitry in electronic device with voice arousal function under another preferred embodiment is shown
It is intended to.Wherein, part element identical with Fig. 3 A is indicated in Fig. 3 B with identical figure number, therefore no longer adds to be described in detail it carefully in this
Section.
It is worth noting that, the functional block diagram compared to Fig. 3 A, the crucial voice decision circuitry 20 of Fig. 3 B more include
One microphone preamplifier 300.Wherein, microphone preamplifier 300 is coupled to microphone Mic, preposition signal
Between detector 210 and analog digital converter 220.
In the embodiment of Fig. 3 B, after host system HS enters dormant state, when preposition signal detector 210 exports
When the first wake up instruction WS1, microphone preamplifier 300 can just be waken up to amplify ambient sound signal EV, and
And export amplified ambient sound signal EV to analog digital converter 220, so that analog digital converter 220 and the mankind
Voice detector 240 can just continue to execute follow-up function.Therefore, teaching according to the above has logical in the art
Normal skill should be appreciated that, when host system HS enters dormant state by normal operating conditions, the preposition amplification of microphone
Device 300 is then that can also enter dormant state together.
Similarly, after host system HS enters dormant state, and in microphone preamplifier 300, human speech
In the case that detector 240 and analog digital converter 200 are waken up, when the sound signal AVS of the digital form is judged as
When not meeting human speech, microphone preamplifier 300 is then that also can voluntarily return to dormant state, to wait quilt next time
It wakes up.To sum up, detailed content is as in the foregoing embodiment, therefore just no longer add redundant in this.
It is noted that the present invention does not also limit the specific implementation of microphone preamplifier 300, therefore this technology
Having usually intellectual in field should can be designed according to actual demand or application.It should be noted that in the present embodiment
In, power consumption when microphone preamplifier 300 is run, can be greater than microphone preamplifier 200 it is run when
Power consumption.Therefore, teaching according to the above, the usually intellectual of having should be appreciated that in the art, the present embodiment
The another of main spirits be just, be changed to the microphone preamplifier first with some low-power consumption (for example, microphone is preposition
Amplifier 200) to carry out ambient sound signal EV amplification just slightly, to produce the sound signal AVS in the form of the analogy,
And when preposition signal detector 210 judges that the sound signal AVS of analogy form meets preset condition, preposition signal detector
210 just can successfully wake up provide high power consumption microphone preamplifier 300 to carry out ambient sound signal EV it is complete
Amplification.
In this way, the electronic device 2 compared to Fig. 3 A, the electronic device 2 of Fig. 3 B then can more work as to be detectd in preposition signal
Before the detecting of survey device 210 and the sound signal AVS for determining analogy form meet preset condition, then more piece saves primary circuit element
Power consumption.To sum up, implementation used by above-mentioned is also only illustrated herein, it is not intended to limiting the invention, therefore this
Relevant design should can be carried out according to actual demand or application by having usually intellectual in technical field.
Finally, the present invention further provides its operation sides in order to further explain the operation workflow about electronic device 2
A kind of embodiment of method.Referring to Fig. 4, Fig. 4 is provided by the embodiment of the present invention for the electricity with voice arousal function
The flow diagram of the operating method of sub-device.Wherein, the electronic device 2 that operating method described in this example can be shown in Fig. 2
Middle execution, therefore please understood together according to Fig. 2 with benefit.In addition, detailed step process is as in the foregoing embodiment, only summarized in this
And no longer add redundant.
Firstly, using a microphone, receiving an ambient sound, and be one by the output of this ambient sound in step S401
Ambient sound signal.Secondly, in step S403, using one first microphone preamplifier, to receive and amplify this environment
Sound signal, by the sound signal in the form of one analogy of generation.Then, in step S405, enter a suspend mode shape in host system
After state, operating method then will do it step S407, and in step S 407, using a preposition signal detector, to receive simultaneously
Judge whether the sound signal of analogy form meets a preset condition, and when the sound of analogy form news are judged as that satisfaction is default
When condition, then it will do it step S409.
In step S409, preposition signal detector exports one first wake up instruction, to wake up crucial voice decision circuitry.
Furthermore in step S411, crucial voice decision circuitry is then waken up to receive and process the sound signal of analogy form, to sentence
Whether disconnected ambient sound meets a preset crucial voice, and when ambient sound is judged as and meets preset crucial voice,
It then will do it step S413, and in step S413, crucial voice decision circuitry exports host wake-up instruction, by host system
System wakes up from dormant state.Similarly, when ambient sound, which is judged as, does not meet preset crucial voice, then it will do it step
S415, and in step S415, crucial voice decision circuitry is voluntarily to return to dormant state, with waiting being called out next time
It wakes up.It needing to illustrate again, the preset condition of the present embodiment can be for example according to set by preset crucial voice, but this
Invention is not limited thereto system.
However, in order to further explain the realization for executing step S411 to step S415 about crucial voice decision circuitry
Details, the present invention further provides a kind of its embodiments.Referring to Fig. 5, Fig. 5 is preferably real in one in the operating method of Fig. 4
Apply the flow diagram of the step S411 to step S415 under example.Wherein, operating method described in Fig. 5 embodiment can be in Fig. 3 A
Embodiment electronic device 2 in execute, therefore please together according to Fig. 3 A with benefit understand.In addition, part is identical with Fig. 4 in Fig. 5
Process step is indicated with identical figure number, therefore no longer adds that its details is described in detail in this.
In the embodiment of Fig. 5, step S411 to step S415 more may include step S501~step S513.Firstly,
In step S501, an analog digital converter, which is then waken up, is converted into a digital form for amplified ambient sound signal
Sound signal.Secondly, in step S503, sound that a human speech detector is then also waken up to judge this digital form
Whether signal meets a human speech, and when the sound signal of this digital form is judged as and meets this human speech, then can
Step S505 is carried out, and in step S505, human speech detector exports one second wake up instruction, to wake up at digital signal
Manage device.Then, in step s 507, a digital signal processor is then waken up to judge it is preset whether this human speech meets
Crucial voice, and when this mankind's phonetic decision is to meet preset crucial voice, then it will do it step S509, and in step
S509, digital signal processor export the instruction of this host wake-up, host system are waken up from dormant state.
Similarly, in step S503, when the sound signal of this digital form, which is judged as, does not meet this human speech, then
It will do it step S511, and in step S511, human speech detector and analog digital converter are then voluntarily to return respectively
To dormant state, with waiting being waken up next time.Similarly, in step s 507, when this human speech do not meet it is default
When crucial voice, then it will do it step S513, and in step S513, digital signal processor, human speech detector and class
It is then that can voluntarily return to dormant state respectively than digital converter, with waiting being waken up next time.
Teaching according to the above, the usually intellectual of having should be appreciated that in the art, when in Fig. 3 A institute example
When the host system shown enters dormant state by a normal operating conditions, the analog digital converter of the present embodiment, Ren Leiyu
Sound detector and digital signal processor are then that can all enter dormant state together.
On the other hand, referring to Fig. 6, Fig. 6 be step S411 in the operating method of Fig. 4 under another preferred embodiment extremely
The flow diagram of step S415, and operating method described in Fig. 6 embodiment can be in the electronic device 2 of the embodiment of Fig. 3 B
It executes, therefore is please understood together according to Fig. 3 B with benefit.In addition, part process step identical with Fig. 4 is in Fig. 6 with identical figure number mark
Show, therefore no longer adds that its details is described in detail in this.
In the embodiment of Fig. 6, step S411 to step S415 more may include step S601, step S501~step S519
And step S603~step S605.Wherein, in step S601, a second microphone preamplifier is then waken up to ambient sound
Message number amplifies, and amplified ambient sound signal is exported to analog digital converter.In addition, in step S503
In, when the sound signal of this digital form, which is judged as, does not meet this human speech, then it will do it step S603, and in step
In S6031, human speech detector, analog digital converter and second microphone preamplifier are then voluntarily to return to respectively
Dormant state, with waiting being waken up next time.Similarly, in step s 507, when this human speech does not meet default pass
When key voice, then it will do it step S605, and in step s 605, digital signal processor, human speech detector, analogy number
Bit pad and second microphone preamplifier are then that can voluntarily return to dormant state respectively, with waiting being called out next time
It wakes up.
Similarly, when the host system illustrated by Fig. 3 B enters dormant state by a normal operating conditions, this reality
Analog digital converter, human speech detector, digital signal processor and the second microphone preamplifier for applying example be then
Dormant state will be entered together.It should be noted that power consumption when second microphone preamplifier is run, it can be such as
Power consumption when run greater than the first microphone preamplifier.Therefore, teaching according to the above, has in the art
Usually intellectual should be appreciated that, before proceeding to step S409, the present embodiment then more again can save primary circuit more
The power consumption of element.
In conclusion there is the electronic device and its operating method of voice arousal function provided by the embodiment of the present invention,
It will can be and be totally different from existing technological means, but come first with additional increased preposition signal detector to analogy form
Sound signal detected, to make speech recognition result faster and tentatively, and work as the sound signal of analogy form
It is judged as that preposition signal detector can then wake up analog digital converter and human speech detector when meeting a preset condition,
To ensure when the host system of electronic device enters dormant state by normal operating conditions, analog digital converter, the mankind
Voice detector and digital signal processor are then that can all enter dormant state together, to be effectively improved current power consumption up to 1
Times or more.
The above description is only an embodiment of the present invention, not to limit to the scope of the patents of the invention.
Claims (10)
1. a kind of electronic device with voice arousal function, including：
One host system (host system)；
Ambient sound output for receiving an ambient sound, and is an ambient sound message by one microphone (microphone)
Number；
One first microphone preamplifier (microphone pre-amplifier), is coupled to the microphone, for receiving
And amplify the ambient sound signal, by the sound signal in the form of one analogy of generation；
One preposition signal detector (pre-signal detector), is coupled to first microphone preamplifier, for connecing
It receives and judges whether the sound signal of the analogy form meets a preset condition, and when the sound signal of the analogy form judges
When to meet the preset condition, one first wake up instruction is exported；And
One crucial voice decision circuitry, is coupled to the preposition signal detector and the host system, wherein the host system into
Enter to after a dormant state, when the preposition signal detector exports first wake up instruction, the key voice decision circuitry is then
It is waken up to receive and process the sound signal of the analogy form, to judge whether the ambient sound meets a preset Key Words
Sound, and when the ambient sound is judged as that the key voice decision circuitry exports a host when meeting the preset crucial voice
Wake up instruction wakes up the host system from the dormant state.
2. electronic device according to claim 1, wherein the key voice decision circuitry includes：
One analog digital converter (analog-to-digital converter, ADC), is coupled to the preposition signal detector；
One human speech detector (human voice detector), is coupled to the preposition signal detector and the analog/digital
Converter, wherein referring to after the host system enters the dormant state when the preposition signal detector exports first wake-up
When enabling, which is then waken up the sound that the amplified ambient sound signal is converted into a digital form
Message number, and whether the sound signal that the human speech detector is then waken up to judge the digital form meets mankind's language
Sound, and when the sound signal of the digital form is judged as and meets the human speech, human speech detector output one second
Wake up instruction；And
One digital signal processor (digital signal processor, DSP), is coupled to the human speech detector,
In after the host system enters the dormant state, when the human speech detector exports second wake up instruction, the number
Position signal processor is then waken up to judge whether the human speech meets the preset crucial voice, and works as the human speech
It is judged as that the digital signal processor exports host wake-up instruction, by the host system when meeting the preset crucial voice
System wakes up from the dormant state.
3. electronic device according to claim 2, wherein the host system when the electronic device works normally shape by one
When state enters the dormant state, the analog digital converter, the human speech detector and the digital signal processor are then
Enter the dormant state together.
4. electronic device according to claim 1, wherein it is default to judge whether the sound signal of the analogy form meets this
What condition referred to is exactly to judge whether the sound signal of the analogy form meets a preset model (pattern), wherein the default mould
Type is according to set by the physical attribute of the human speech or the physical attribute of the preset crucial voice.
5. electronic device according to claim 3, which is further included：
One second microphone preamplifier is coupled to the microphone, the preposition signal detector and the analog digital converter
Between, after the host system enters the dormant state, when the preposition signal detector exports first wake up instruction, this
Two microphone preamplifiers are then waken up to amplify the ambient sound signal, and by the amplified ambient sound message
The analog digital converter is given in number output.
6. electronic device according to claim 5, wherein when the host system of the electronic device is by the normal work shape
When state enters the dormant state, which is then also to enter the dormant state together.
7. electronic device according to claim 6, power consumption when wherein the second microphone preamplifier is run, greatly
Power consumption when first microphone preamplifier is run.
8. a kind of operating method for the electronic device with voice arousal function, wherein the electronic device includes a host system
The crucial voice decision circuitry of system, a microphone, one first microphone preamplifier, a preposition signal detector and one, the behaviour
Include as method：
It to receive an ambient sound, and is an ambient sound signal by ambient sound output using the microphone；
Using first microphone preamplifier, to receive and amplify the ambient sound signal, in the form of one analogy of generation
Sound signal；
Using the preposition signal detector, to receive and judge whether the sound signal of the analogy form meets a preset condition,
And after the host system enters a dormant state, meet the preset condition when the sound signal of the analogy form is judged as
When, which exports one first wake up instruction, to wake up the key voice decision circuitry；And the key voice
Decision circuitry is then waken up to receive and process the sound signal of the analogy form, and meets one when the ambient sound is judged as
When preset key voice, which exports a host wake-up and instructs, by the host system from the suspend mode
It is waken up in state.
9. operating method according to claim 8, wherein the key voice decision circuitry include an analog digital converter,
One human speech detector and a digital signal processor, and the operating method further includes：
It, should when the preposition signal detector exports first wake up instruction after the host system enters the dormant state
Analog digital converter is then waken up the sound signal that the amplified ambient sound signal is converted into a digital form,
And whether the sound signal that the human speech detector is then waken up to judge the digital form meets a human speech, and works as
The sound signal of the digital form is judged as when meeting the human speech, and human speech detector output one second, which wakes up, to be referred to
It enables, to wake up the digital signal processor；And
The digital signal processor is then waken up to judge whether the human speech meets the preset crucial voice, and working as should
Human speech is judged as that the digital signal processor exports the host wake-up and instructs when meeting the preset crucial voice, will
The host system wakes up from the dormant state.
10. operating method according to claim 8, wherein it is default to judge whether the sound signal of the analogy form meets this
What condition referred to is exactly to judge whether the sound signal of the analogy form meets a preset model, and wherein the preset model is basis
Set by the physical attribute of the human speech or the physical attribute of the preset crucial voice.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710323994.4A CN108877788B (en) | 2017-05-08 | 2017-05-08 | Electronic device with voice wake-up function and operation method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710323994.4A CN108877788B (en) | 2017-05-08 | 2017-05-08 | Electronic device with voice wake-up function and operation method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108877788A true CN108877788A (en) | 2018-11-23 |
| CN108877788B CN108877788B (en) | 2021-06-11 |
Family
ID=64287491
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710323994.4A Active CN108877788B (en) | 2017-05-08 | 2017-05-08 | Electronic device with voice wake-up function and operation method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108877788B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020228095A1 (en) * | 2019-05-16 | 2020-11-19 | 深圳市豪恩声学股份有限公司 | Real-time voice wake-up audio device, operation method and apparatus, and storage medium |
| CN115376545A (en) * | 2021-05-21 | 2022-11-22 | 漳州立达信光电子科技有限公司 | Sound detection method, device, equipment and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020116196A1 (en) * | 1998-11-12 | 2002-08-22 | Tran Bao Q. | Speech recognizer |
| CN103561175A (en) * | 2013-11-05 | 2014-02-05 | 广东欧珀移动通信有限公司 | Method using mobile terminal to carry out voice awakening and device thereof |
| CN104038864A (en) * | 2013-03-08 | 2014-09-10 | 亚德诺半导体股份有限公司 | Microphone Circuit Assembly And System With Speech Recognition |
| CN104216677A (en) * | 2013-05-31 | 2014-12-17 | 塞瑞斯逻辑公司 | Low-power voice gate for device wake-up |
| US20150255070A1 (en) * | 2014-03-10 | 2015-09-10 | Richard W. Schuckle | Managing wake-on-voice buffer quality based on system boot profiling |
| CN105376389A (en) * | 2014-08-19 | 2016-03-02 | 中兴通讯股份有限公司 | Voice wake-up method and device |
| CN105723451A (en) * | 2013-12-20 | 2016-06-29 | 英特尔公司 | Transition from low power always listening mode to high power speech recognition mode |
| CN105931640A (en) * | 2015-02-27 | 2016-09-07 | 想象技术有限公司 | Low Power Detection Of Activation Phrase |
| CN106453859A (en) * | 2016-09-23 | 2017-02-22 | 维沃移动通信有限公司 | Voice control method and mobile terminal |
| CN106448663A (en) * | 2016-10-17 | 2017-02-22 | 海信集团有限公司 | Voice wakeup method and voice interaction device |
-
2017
- 2017-05-08 CN CN201710323994.4A patent/CN108877788B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020116196A1 (en) * | 1998-11-12 | 2002-08-22 | Tran Bao Q. | Speech recognizer |
| CN104038864A (en) * | 2013-03-08 | 2014-09-10 | 亚德诺半导体股份有限公司 | Microphone Circuit Assembly And System With Speech Recognition |
| CN104216677A (en) * | 2013-05-31 | 2014-12-17 | 塞瑞斯逻辑公司 | Low-power voice gate for device wake-up |
| CN103561175A (en) * | 2013-11-05 | 2014-02-05 | 广东欧珀移动通信有限公司 | Method using mobile terminal to carry out voice awakening and device thereof |
| CN105723451A (en) * | 2013-12-20 | 2016-06-29 | 英特尔公司 | Transition from low power always listening mode to high power speech recognition mode |
| US20150255070A1 (en) * | 2014-03-10 | 2015-09-10 | Richard W. Schuckle | Managing wake-on-voice buffer quality based on system boot profiling |
| CN105376389A (en) * | 2014-08-19 | 2016-03-02 | 中兴通讯股份有限公司 | Voice wake-up method and device |
| CN105931640A (en) * | 2015-02-27 | 2016-09-07 | 想象技术有限公司 | Low Power Detection Of Activation Phrase |
| CN106453859A (en) * | 2016-09-23 | 2017-02-22 | 维沃移动通信有限公司 | Voice control method and mobile terminal |
| CN106448663A (en) * | 2016-10-17 | 2017-02-22 | 海信集团有限公司 | Voice wakeup method and voice interaction device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020228095A1 (en) * | 2019-05-16 | 2020-11-19 | 深圳市豪恩声学股份有限公司 | Real-time voice wake-up audio device, operation method and apparatus, and storage medium |
| CN115376545A (en) * | 2021-05-21 | 2022-11-22 | 漳州立达信光电子科技有限公司 | Sound detection method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108877788B (en) | 2021-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108735209B (en) | Wake-up word binding method, intelligent device and storage medium | |
| TWI643123B (en) | Electronic device having wake on voice function and operating method thereof | |
| US20190198043A1 (en) | Analog voice activity detector systems and methods | |
| CN106782591A (en) | A kind of devices and methods therefor that phonetic recognization rate is improved under background noise | |
| WO2018059405A1 (en) | Voice control system, wakeup method and wakeup apparatus therefor, electrical appliance and co-processor | |
| CN204390737U (en) | A kind of home voice disposal system | |
| US20140343949A1 (en) | Smart microphone device | |
| CN108810280A (en) | Processing method, device, storage medium and the electronic equipment of voice collecting frequency | |
| TW201421353A (en) | Voice-controlled device and voice control method | |
| WO2020244257A1 (en) | Method and system for voice wake-up, electronic device, and computer-readable storage medium | |
| CN109151637A (en) | Wireless headset, intelligent sound control system and method for wireless headset | |
| DE112015004522T5 (en) | Acoustic device with low power consumption and method of operation | |
| US11038348B2 (en) | Two stage power control system for automotive devices | |
| CN108848264A (en) | Control method, device, storage medium and the electronic equipment of microphone | |
| US11639944B2 (en) | Methods and apparatus for detecting individual health related events | |
| CN106612367A (en) | Speech wake method based on microphone and mobile terminal | |
| CN110473544A (en) | A kind of low-power consumption voice awakening method and device | |
| CN108877788A (en) | Electronic device and its operating method with voice arousal function | |
| CN103543814A (en) | Signal processing device and signal processing method | |
| CN207910992U (en) | A kind of sound Rouser for standby system | |
| CN205408096U (en) | Digital microphone wind and electronic equipment | |
| CN105430543A (en) | Digital microphone and electronic device | |
| CN208538474U (en) | Speech recognition system | |
| CN106686488A (en) | Microphone | |
| CN106653060B (en) | Air blowing sound identification system and air blowing identification method adopting same |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |