CN105096946A - Voice activation detection based awakening device and method - Google Patents
Voice activation detection based awakening device and method Download PDFInfo
- Publication number
- CN105096946A CN105096946A CN201410193199.4A CN201410193199A CN105096946A CN 105096946 A CN105096946 A CN 105096946A CN 201410193199 A CN201410193199 A CN 201410193199A CN 105096946 A CN105096946 A CN 105096946A
- Authority
- CN
- China
- Prior art keywords
- signal
- voice
- voice activation
- microphone
- frequency
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Abstract
The invention relates to a field of electronic technology and specifically relates to an awakening device and method. The voice activation detection based awakening device includes a microphone used for sensing sound signals and converting the sound signals to electric signals; a first signal extracting unit connected to the output terminal of the microphone and used for extracting base frequency signals in the output signals of the microphone; a comparison unit connected to the first signal extracting unit and comparing the base frequency signals with a reference base frequency range indicating voice features and generating a first comparison result; and a controller connected to a comparison unit and producing an awakening signal under the effect of the output signals of the comparison unit. According to the invention, the device can identify the distance of a sounder besides recognizing whether the voice signals are consistent to features of human voice or not, so that interference on normal voice activation detection due to irrelevant voice signals can be avoided and voice awakening can be realized effectively.
Description
Technical field
The present invention relates to electronic technology field, be specifically related to a kind of Rouser and method.
Background technology
Along with the constantly integrated of electronic installation and development, the electronic installation with speech recognition technology more and more receives an acclaim, it can perform correlation function by voice command to control electronic installation when user is not easy to operating electronic devices, wherein, the function being waken up electronic installation by voice command is paid close attention to widely, in the speech recognition technology of prior art, waking distance up is not controlled, also usually erroneous judgement can be produced for voice noisy at a distance, as also having response to the sound of 2 meters or 5 meters far away, disturb the normal use of user; And opening voice waken system causes system power dissipation excessive too continually.
Summary of the invention
The object of the invention is to, a kind of Rouser detected based on voice activation is provided, solves above technical matters;
The present invention also aims to, a kind of awakening method detected based on voice activation is provided, solves above technical matters.
Technical matters solved by the invention can realize by the following technical solutions:
Based on the Rouser that voice activation detects, wherein, comprise,
One microphone, is converted to electric signal for acoustic signals;
One first signal extraction unit, is connected with the output terminal of described microphone, for extracting the fundamental frequency signal in described microphone output signal;
One comparing unit, described comparing unit is connected with described first signal extraction unit, and the reference base frequency range described fundamental frequency signal and being characterized to people's acoustical signature compares, and generates one first comparative result;
One controller, is connected with described comparing unit, under the output signal effect of described comparing unit, produce a wake-up signal.
Preferably, also comprise a secondary signal extraction unit, be connected with the output terminal of described microphone, for extracting the higher hamonic wave signal in described microphone output signal;
Described comparing unit is also connected with the output terminal of described secondary signal extraction unit, compares for described higher hamonic wave signal and one are set limit value, generates one second comparative result.
Preferably, also comprise a frequency-domain transform unit, the output terminal of described microphone is connected with described frequency-domain transform unit, for carrying out frequency domain conversion to the output signal of described microphone, the output terminal of described frequency-domain transform unit connects described first signal extraction unit and secondary signal extraction unit respectively.
Preferably, described first signal extraction unit adopts a bandpass filter, and described secondary signal extraction unit adopts a Hi-pass filter.
Preferably, described frequency-domain transform unit adopts a Fourier transformer.
Preferably, also comprise switching device shifter, be connected with described controller, switch between sleep pattern and mode of operation under the effect of described wake-up signal.
Preferably, comprise a storage unit, store described with reference to base frequency range and described setting limit value.
The present invention also provides a kind of awakening method detected based on voice activation, and wherein, concrete steps are as follows:
Step 1, sensing external sound signal is converted to electric signal;
Step 2, extracts the fundamental frequency signal in described electric signal and higher hamonic wave signal respectively;
Step 3, the reference base frequency range described fundamental frequency signal and being characterized to people's acoustical signature compares, and when described fundamental frequency signal is positioned within described reference base frequency range, is judged as voice;
Step 4, on the basis being judged as voice, set limit value to described higher hamonic wave signal and one to compare, when described higher hamonic wave signal is less than described setting limit value, sound source distance is described, does not respond, when described higher hamonic wave signal is greater than described setting limit value, illustrate that sound source distance is near, produce a wake-up signal.
Preferably, the step of described electric signal being carried out to frequency domain conversion is also comprised between step 1 and step 2.
Preferably, described frequency domain conversion adopts Fourier transform.
Beneficial effect: owing to adopting above technical scheme, the present invention is except whether recognition of speech signals meets people's acoustical signature, the distance of sounder distance can also be identified, to avoid the normal voice activation of incoherent voice signal interference to detect, can effectively carry out voice and wake up.
Accompanying drawing explanation
Fig. 1 is a kind of circuit connection diagram of the present invention;
Fig. 2 is another kind of circuit connection diagram of the present invention;
Fig. 3 is awakening method process flow diagram of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, 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 protection of the invention.
It should be noted that, when not conflicting, the embodiment in the present invention and the feature in embodiment can combine mutually.
Below in conjunction with the drawings and specific embodiments, the invention will be further described, but not as limiting to the invention.
With reference to Fig. 1, based on the Rouser that voice activation detects, wherein, comprise,
One microphone 1, is converted to electric signal for acoustic signals;
One first signal extraction unit 21, is connected with the output terminal of microphone 1, for extracting the fundamental frequency signal in microphone 1 output signal;
One comparing unit 3, comparing unit 3 is connected with the first signal extraction unit 21, and reference base frequency range fundamental frequency signal and being characterized to people's acoustical signature compares, and generates one first comparative result;
One controller 4, is connected with comparing unit 3, under the output signal effect of comparing unit 3, produce a wake-up signal.
The sound that the present invention utilizes people to send has specific base frequency range, and the transmission attenuation of fundamental frequency is less, relative larger distance can be propagated, extract the fundamental frequency signal in voice signal, compare, due to the difference of phonatory organ physiology aspect, the base frequency range of masculinity and femininity is different, the base frequency range of the male sex is 50 ~ 250Hz, the base frequency range of women is 120 ~ 500Hz, above-mentioned reference base frequency range can be stored in a storage unit, also can produce with reference to fundamental frequency signal generator by one.
Because fundamental frequency can identify that who is speaking, further, the fundamental frequency signal of a specific people can also be simulated by an analog signal generator, as reference fundamental frequency signal, when detecting that the fundamental frequency signal in voice signal is with when matching with reference to fundamental frequency signal, just carries out subsequent treatment.
As a kind of preferred embodiment of the present invention, also comprise a secondary signal extraction unit 22, be connected with the output terminal of microphone 1, for extracting the higher hamonic wave signal in microphone 1 output signal;
Comparing unit 3 is also connected with the output terminal of secondary signal extraction unit 22, compares for higher hamonic wave signal and one are set limit value, generates one second comparative result.
Sound is in communication process medium-high frequency easily by attenuation by absorption, and the skyborne decay of signal of a certain frequency of sound is all difinite quality rule; By analyzing the higher harmonic component in the signal of microphone 1 acquisition, when radio-frequency component decays to below a setting limit value, can think that sound source is distant, does not make a decision.The present invention, except whether recognition of speech signals meets people's acoustical signature, can also identify the distance of sounder distance, to determine effective voice, to avoid the normal voice activation of incoherent voice signal interference to detect, can effectively carry out voice and wake up.The present invention, preferably for the signal of certain frequency, propagates the attenuation ratio after 1 meter or 1.5 meters of distances as setting limit value.
The extraction of fundamental frequency signal can be extracted from time-domain signal, also can extract from frequency-region signal, as a kind of preferred embodiment of the present invention, with reference to Fig. 2, a frequency-domain transform unit 6 can be comprised, the output terminal of microphone 1 is connected with frequency-domain transform unit 6, and for carrying out frequency domain conversion to the output signal of microphone 1, the output terminal of frequency-domain transform unit 6 connects the first signal extraction unit 21 and secondary signal extraction unit 22 respectively; Frequency-domain transform unit 6 can adopt a Fourier transformer to realize.
As a kind of preferred embodiment of the present invention, the first signal extraction unit 21 can adopt a bandpass filter.Secondary signal extraction unit can adopt a Hi-pass filter.Can also carry out in conjunction with the extracting method of the fundamental frequency of prior art or higher hamonic wave signal.
As a kind of preferred embodiment of the present invention, also comprise switching device shifter 7, be connected with controller 4, switch between sleep pattern and mode of operation under the effect of wake-up signal.
As a kind of preferred embodiment of the present invention, comprise a storage unit 5, store with reference to base frequency range and setting limit value.
With reference to Fig. 3, the present invention also provides a kind of awakening method detected based on voice activation, and wherein, concrete steps are as follows:
Step 1, sensing external sound signal is converted to electric signal;
Step 2, extracts the fundamental frequency signal in electric signal and higher hamonic wave signal respectively;
Step 3, reference base frequency range fundamental frequency signal and being characterized to people's acoustical signature compares, and when fundamental frequency signal is positioned within reference base frequency range, is judged as voice;
Step 4, on the basis being judged as voice, sets limit value to higher hamonic wave signal and one and compares, when higher hamonic wave signal is less than setting limit value, sound source distance is described, does not respond, when higher hamonic wave signal is greater than setting limit value, illustrates that sound source distance is near, produce a wake-up signal.
As a kind of preferred embodiment of the present invention, between step 1 and step 2, also comprise the step of electric signal being carried out to frequency domain conversion.
As a kind of preferred embodiment of the present invention, frequency domain conversion adopts Fourier transform.
The present invention by identifying whether frequency spectrum meets people's acoustical signature, and identifies the distance of sounder distance, to determine effective voice, avoids the normal voice activation of incoherent voice signal interference to detect, can effectively carry out voice and wake up.
The foregoing is only preferred embodiment of the present invention; not thereby embodiments of the present invention and protection domain is limited; to those skilled in the art; should recognize and all should be included in the scheme that equivalent replacement done by all utilizations instructions of the present invention and diagramatic content and apparent change obtain in protection scope of the present invention.
Claims (10)
1., based on the Rouser that voice activation detects, it is characterized in that, comprise,
One microphone, is converted to electric signal for acoustic signals;
One first signal extraction unit, is connected with the output terminal of described microphone, for extracting the fundamental frequency signal in described microphone output signal;
One comparing unit, described comparing unit is connected with described first signal extraction unit, and the reference base frequency range described fundamental frequency signal and being characterized to people's acoustical signature compares, and generates one first comparative result;
One controller, is connected with described comparing unit, under the output signal effect of described comparing unit, produce a wake-up signal.
2. the Rouser detected based on voice activation according to claim 1, is characterized in that, also comprise a secondary signal extraction unit, be connected with the output terminal of described microphone, for extracting the higher hamonic wave signal in described microphone output signal;
Described comparing unit is also connected with the output terminal of described secondary signal extraction unit, compares for described higher hamonic wave signal and one are set limit value, generates one second comparative result.
3. the Rouser detected based on voice activation according to claim 2, it is characterized in that, also comprise a frequency-domain transform unit, the output terminal of described microphone is connected with described frequency-domain transform unit, for carrying out frequency domain conversion to the output signal of described microphone, the output terminal of described frequency-domain transform unit connects described first signal extraction unit and secondary signal extraction unit respectively.
4. the Rouser detected based on voice activation according to claim 2, it is characterized in that, described first signal extraction unit adopts a bandpass filter, and described secondary signal extraction unit adopts a Hi-pass filter.
5. the Rouser detected based on voice activation according to claim 3, it is characterized in that, described frequency-domain transform unit adopts a Fourier transformer.
6. the Rouser detected based on voice activation according to claim 1, is characterized in that, also comprise switching device shifter, be connected with described controller, switch under the effect of described wake-up signal between sleep pattern and mode of operation.
7. the Rouser detected based on voice activation according to claim 1, is characterized in that, comprise a storage unit, stores described with reference to base frequency range and described setting limit value.
8., based on the awakening method that voice activation detects, it is characterized in that, concrete steps are as follows:
Step 1, sensing external sound signal is converted to electric signal;
Step 2, extracts the fundamental frequency signal in described electric signal and higher hamonic wave signal respectively;
Step 3, the reference base frequency range described fundamental frequency signal and being characterized to people's acoustical signature compares, and when described fundamental frequency signal is positioned within described reference base frequency range, is judged as voice;
Step 4, on the basis being judged as voice, set limit value to described higher hamonic wave signal and one to compare, when described higher hamonic wave signal is less than described setting limit value, sound source distance is described, does not respond, when described higher hamonic wave signal is greater than described setting limit value, illustrate that sound source distance is near, produce a wake-up signal.
9. the awakening method detected based on voice activation according to claim 7, is characterized in that, also comprise the step of described electric signal being carried out to frequency domain conversion between step 1 and step 2.
10. the awakening method detected based on voice activation according to claim 9, is characterized in that, described frequency domain conversion adopts Fourier transform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410193199.4A CN105096946B (en) | 2014-05-08 | 2014-05-08 | Awakening device and method based on voice activation detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410193199.4A CN105096946B (en) | 2014-05-08 | 2014-05-08 | Awakening device and method based on voice activation detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105096946A true CN105096946A (en) | 2015-11-25 |
| CN105096946B CN105096946B (en) | 2020-09-29 |
Family
ID=54577232
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410193199.4A Active CN105096946B (en) | 2014-05-08 | 2014-05-08 | Awakening device and method based on voice activation detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105096946B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106157950A (en) * | 2016-09-29 | 2016-11-23 | 合肥华凌股份有限公司 | Speech control system and awakening method, Rouser and household electrical appliances, coprocessor |
| CN106296890A (en) * | 2016-07-22 | 2017-01-04 | 北京小米移动软件有限公司 | The unlocking method of mobile terminal, device and mobile terminal |
| CN107465974A (en) * | 2016-06-03 | 2017-12-12 | 恩智浦有限公司 | Voice signal detector |
| CN107564520A (en) * | 2017-09-01 | 2018-01-09 | 联想(北京)有限公司 | A kind of control method and electronic equipment |
| CN108377605A (en) * | 2018-04-03 | 2018-08-07 | 海盐瑞科光电科技有限公司 | A kind of bathroom voice control intelligent switch |
| CN108375923A (en) * | 2018-04-03 | 2018-08-07 | 海盐瑞科光电科技有限公司 | A kind of bathroom intelligent control switch |
| CN110097875A (en) * | 2019-06-03 | 2019-08-06 | 清华大学 | Interactive voice based on microphone signal wakes up electronic equipment, method and medium |
| CN110648660A (en) * | 2018-06-27 | 2020-01-03 | 深圳联友科技有限公司 | Voice activation method of BS (base station) end |
| CN111343410A (en) * | 2020-02-14 | 2020-06-26 | 北京字节跳动网络技术有限公司 | Mute prompt method and device, electronic equipment and storage medium |
| CN112995821A (en) * | 2021-03-01 | 2021-06-18 | 歌尔微电子股份有限公司 | Microphone control method, microphone system and wearable device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040128137A1 (en) * | 1999-12-22 | 2004-07-01 | Bush William Stuart | Hands-free, voice-operated remote control transmitter |
| CN101236250A (en) * | 2007-01-30 | 2008-08-06 | 富士通株式会社 | Sound determination method and sound determination apparatus |
| CN103052001A (en) * | 2011-10-17 | 2013-04-17 | 联想(北京)有限公司 | Intelligent device and control method thereof |
| CN203504751U (en) * | 2013-08-16 | 2014-03-26 | 上海耐普微电子有限公司 | Microphone with function of voice awakening and mobile terminal |
| CN203882609U (en) * | 2014-05-08 | 2014-10-15 | 钰太芯微电子科技（上海）有限公司 | Awakening apparatus based on voice activation detection |
-
2014
- 2014-05-08 CN CN201410193199.4A patent/CN105096946B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040128137A1 (en) * | 1999-12-22 | 2004-07-01 | Bush William Stuart | Hands-free, voice-operated remote control transmitter |
| CN101236250A (en) * | 2007-01-30 | 2008-08-06 | 富士通株式会社 | Sound determination method and sound determination apparatus |
| CN103052001A (en) * | 2011-10-17 | 2013-04-17 | 联想(北京)有限公司 | Intelligent device and control method thereof |
| CN203504751U (en) * | 2013-08-16 | 2014-03-26 | 上海耐普微电子有限公司 | Microphone with function of voice awakening and mobile terminal |
| CN203882609U (en) * | 2014-05-08 | 2014-10-15 | 钰太芯微电子科技（上海）有限公司 | Awakening apparatus based on voice activation detection |
Non-Patent Citations (1)
| Title |
|---|
| 张福学: "《传感器电子学》", 31 December 1991, 国防工业出版社 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107465974A (en) * | 2016-06-03 | 2017-12-12 | 恩智浦有限公司 | Voice signal detector |
| CN107465974B (en) * | 2016-06-03 | 2021-03-09 | 恩智浦有限公司 | Sound signal detector |
| CN106296890A (en) * | 2016-07-22 | 2017-01-04 | 北京小米移动软件有限公司 | The unlocking method of mobile terminal, device and mobile terminal |
| CN106157950A (en) * | 2016-09-29 | 2016-11-23 | 合肥华凌股份有限公司 | Speech control system and awakening method, Rouser and household electrical appliances, coprocessor |
| CN107564520A (en) * | 2017-09-01 | 2018-01-09 | 联想(北京)有限公司 | A kind of control method and electronic equipment |
| CN108377605A (en) * | 2018-04-03 | 2018-08-07 | 海盐瑞科光电科技有限公司 | A kind of bathroom voice control intelligent switch |
| CN108375923A (en) * | 2018-04-03 | 2018-08-07 | 海盐瑞科光电科技有限公司 | A kind of bathroom intelligent control switch |
| CN110648660A (en) * | 2018-06-27 | 2020-01-03 | 深圳联友科技有限公司 | Voice activation method of BS (base station) end |
| CN110097875A (en) * | 2019-06-03 | 2019-08-06 | 清华大学 | Interactive voice based on microphone signal wakes up electronic equipment, method and medium |
| CN111343410A (en) * | 2020-02-14 | 2020-06-26 | 北京字节跳动网络技术有限公司 | Mute prompt method and device, electronic equipment and storage medium |
| CN112995821A (en) * | 2021-03-01 | 2021-06-18 | 歌尔微电子股份有限公司 | Microphone control method, microphone system and wearable device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105096946B (en) | 2020-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN203882609U (en) | Awakening apparatus based on voice activation detection | |
| CN105096946A (en) | Voice activation detection based awakening device and method | |
| CN204390737U (en) | A kind of home voice disposal system | |
| CN106782591B (en) | Device and method for improving speech recognition rate under background noise | |
| TWI474317B (en) | Signal processing apparatus and signal processing method | |
| CN104091603B (en) | Endpoint detection system and its computational methods based on fundamental frequency | |
| US10645481B2 (en) | Earphone control device, earphone and control method for earphone | |
| CN104580699B (en) | Acoustic control intelligent terminal method and device when a kind of standby | |
| CN107477793A (en) | A kind of air purifier, control system of air purifier and method | |
| CN106328151B (en) | ring noise eliminating system and application method thereof | |
| DE112015004522T5 (en) | Acoustic device with low power consumption and method of operation | |
| CN107195304A (en) | The voice control circuit and method of a kind of electric equipment | |
| CN203984647U (en) | There is the microphone that voice activation detects | |
| CN103686962A (en) | Low-power-consumption mobile terminal awakening method and device | |
| CN103901782A (en) | Sound control method, electronic device and sound control apparatus | |
| CN110473544A (en) | A kind of low-power consumption voice awakening method and device | |
| CN106094598B (en) | Audio-switch control method, system and audio-switch | |
| CN112951243A (en) | Voice awakening method, device, chip, electronic equipment and storage medium | |
| CN104282303A (en) | Method for conducting voice recognition by voiceprint recognition and electronic device thereof | |
| CN104952446A (en) | Digital building presentation system based on voice interaction | |
| CN104780483A (en) | Microphone with voice activity detection function | |
| CN101446812A (en) | Control method and control device of state of equipment and equipment | |
| CN105430155A (en) | Wearable equipment and control method thereof based on speech signals | |
| TWI684912B (en) | Voice wake-up apparatus and method thereof | |
| CN111128164B (en) | Control system for voice acquisition and recognition and implementation method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |