CN109990327B - Voice screening method of range hood - Google Patents
Voice screening method of range hood Download PDFInfo
- Publication number
- CN109990327B CN109990327B CN201711471901.9A CN201711471901A CN109990327B CN 109990327 B CN109990327 B CN 109990327B CN 201711471901 A CN201711471901 A CN 201711471901A CN 109990327 B CN109990327 B CN 109990327B
- Authority
- CN
- China
- Prior art keywords
- microphone
- sound
- voice
- sound signal
- limit
- 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
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24C—DOMESTIC STOVES OR RANGES ; DETAILS OF DOMESTIC STOVES OR RANGES, OF GENERAL APPLICATION
- F24C15/00—Details
- F24C15/20—Removing cooking fumes
- F24C15/2021—Arrangement or mounting of control or safety systems
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Circuit For Audible Band Transducer (AREA)
Abstract
The invention relates to a voice screening method of a range hood, which is characterized by comprising the following steps: the range hood is provided with a microphone consisting of M microphonesAn array; step 1, obtaining the time delay tau of a sound signal received by an ith microphone relative to the same sound signal received by a 1 st microphoneiStep 2, calculating the sound source direction angle theta of the microphone ii(ii) a Step 3, determining | θiWhether | is less than θlimitIf yes, countlimitAdding 1, and entering the step 4; otherwise, directly entering the step 4; step 4, i is added with 1, if i<M, entering the step 2, otherwise entering the step 5; and 5: judge countlimitWhether greater than countvoiceIf true, the flag bit isvoiceSet 1, otherwise flag bit isvoiceSet 0 and remove the sound signal. Compared with the prior art, the invention has the advantage of effectively eliminating the noise signals.
Description
Technical Field
The invention relates to a voice screening method of a range hood.
Background
In recent decades, speech recognition technology has been developing vigorously. The range hood with the voice control function is gradually applied to daily families and can replace the key function of the range hood. The user only needs to control the functions of the switch, the windshield speed regulation and the lamp switch of the range hood by voice in the actual cooking process, and the use is greatly facilitated.
However, the speech recognition system is applied to the range hood and has the problem that the noise is difficult to solve, and the main sources of the noise are as follows:
① periodic noises including rotation sound, electric interference and power frequency interference of fan in voice control system of range hood;
② impulse noise, wherein the microphone receives narrow impulse suddenly appearing in time domain signal, such as hissing sound when cooking;
③ broadband noise originating from various random noise sources, generally considered as white gaussian noise;
④ voice interference, in the smoke exhaust ventilator voice control system, other people speaking voice exists in a living room beside a kitchen, if the speaking voice of other people and the voice command of a user are generated simultaneously, the voice interference to the smoke exhaust ventilator voice control system is great, and even the voice command can not be correctly analyzed.
Therefore, in the actual operation engineering of the range hood, various noises can greatly influence the accuracy of voice recognition, which inevitably influences the use of the voice recognition function.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide a voice screening method for a range hood, which can determine a sound source area and reject sounds that are not in a preset area as noise, thereby improving voice recognition efficiency and preventing false triggering.
The technical scheme adopted by the invention for solving the technical problems is as follows: a voice screening method of a range hood is characterized in that: a microphone array consisting of M microphones is arranged on the range hood, the M microphones are uniformly arranged on the same horizontal straight line, the microphone on the leftmost side is the first microphone, and the microphone on the leftmost side is the second microphone and the Mth microphone of the third microphone … … in turn towards the right; the distance between two adjacent microphones is d, wherein M is a natural number more than or equal to 3; the following parameters are preset: parameter i, sound source direction angle limiting value thetalimit,θlimitPresetting the value of (A); number count of microphones in target range in sound source identification arealimitNumber threshold count of microphones in target rangevoiceGet itSetting flag bit isvoiceIndicating whether the received sound is a sound of a target area; after receiving the sound signal, the microphone array screens the sound by the following method to judge whether the sound signal is the sound of the target voice recognition area:
step 1, obtaining the time delay tau of a sound signal received by an ith microphone relative to the same sound signal received by a 1 st microphoneiSetting the initial value of i to 2, countlimitIs set to 0;
step 2, calculating the sound source direction angle theta of the microphone iiIs composed of
Wherein c is the propagation speed of sound in air;
step 3, determining | θiWhether | is less than θlimitIf yes, countlimit=countlimit+1, go to step 4; otherwise, directly entering the step 4;
step 4, if i is equal to i +1, if i is less than M, step 2 is entered, otherwise step 5 is entered;
and 5: judge countlimitWhether greater than countvoiceIf true, the flag bit isvoiceSetting 1, recognizing the received sound signal as the sound of the target speech recognition area, preparing for the next speech recognition, otherwise, marking the location isvoiceSetting 0, judging the received sound as the sound of the non-target voice recognition area, and removing the sound.
As an improvement, the sound signal received by the microphone array is xi(t) the time delay τ of the sound signal received by the ith microphone relative to the time delay τ of the sound signal received by the 1 st microphoneiObtained by the following method:
step a, setting the sound signal received by the 1 st microphone as x1(t), setting the time delay tau to 0, and setting i to 2;
step b, carrying out cross-correlation operation on the sound signal received by the first microphone and the sound signal received by the ith microphone, and expressing the cross-correlation operation as the sound signal
ComputingMaximum value of function, obtainingThe value of tau when the function is maximum is recorded as taui,τiI.e. the time delay tau of the sound signal received by the ith microphone relative to the same sound signal received by the 1 st microphonei;
And c, if the i is larger than M, finishing the time delay calculation, otherwise jumping to the step b.
The improvement is that when the microphone array receives the sound signal, the sound signal is judged to be the sound of the target speech recognition area, namely the mark location isvoiceAnd (2) enhancing the voice signal as 1, wherein the enhanced voice signal is defined as y (t):
then the voice recognition module recognizes y (t), and if a control instruction is recognized, the range hood is controlled;
when the microphone array receives the sound signal, and judges that the sound signal is the sound of the non-target speech recognition area, namely the mark location isvoiceThe speech recognition module does not work when it is 0.
Compared with the prior art, the method has the advantages that ① can screen noises in other directions, so that the recognition efficiency of a subsequent voice recognition module is greatly improved, particularly fan noises are used as main noise sources, the sound source direction of the fan noises is different from the voice direction, and the fan noises can be effectively inhibited, ② can inhibit the directivity of voices transmitted from other directions, such as voices of other people existing in a living room beside a kitchen, so that the voice recognition efficiency of a user of the range hood when the other people speak is improved, and false triggering is prevented.
Drawings
FIG. 1 is a schematic view of a panel of a range hood according to an embodiment of the present invention;
fig. 2 is a layout diagram of the range hood and the installation environment thereof according to the embodiment of the invention.
Detailed Description
The invention is described in further detail below with reference to the accompanying examples.
As shown in figure 1, the range hood has a microphone array 1 composed of M microphones on the panel of the range hood, the M microphones are uniformly arranged on the same horizontal straight line, the leftmost microphone is the first microphone, and the microphone is arranged in the horizontal straight lineThe right is the second microphone, the third microphone … … the Mth microphone in turn; the distance between two adjacent microphones is d, and the microphone arrays are placed above the central key of the panel of the range hood and are transversely arranged; the microphone array is preferably placed in the same plane as the user's mouth, which has the advantage that the sound reaches the microphone at the closest distance, reducing transmission losses. Determining a limited value theta of the direction angle of the sound source according to the area of the kitchen and the installation position of the range hoodlimitThe microphone array can identify the voice area of the user as the target voice identification area, and is used for judging whether the voice area is a possible voice instruction or not, and the sounds in other areas are all regarded as noise, which is shown in fig. 2.
The invention provides a voice screening method for judging whether a sound signal received by a microphone array is a sound signal emitted by a target voice recognition area, which comprises the following steps of: parameter i, sound source direction angle limiting value thetalimit,θlimitThe value of (A) is preset according to the area of a kitchen and the installation position of the range hood, and theta is more than or equal to 30 degreeslimitLess than or equal to 60 degrees; number count of microphones in target range in sound source identification arealimitNumber threshold count of microphones in target rangevoiceGet itSetting flag bit isvoiceIndicating whether the received sound is a sound of a target area; after receiving the sound signal, the microphone array screens the sound by the following method to judge whether the sound signal is the sound of the target voice recognition area:
step 1, obtaining the time delay tau of a sound signal received by an ith microphone relative to the same sound signal received by a 1 st microphoneiSetting the initial value of i to 2, countlimitIs set to 0;
step 2, calculating the sound source direction angle theta of the microphone iiIs composed of
Wherein c is the propagation speed of sound in air;
step 3, determining | θiWhether | is less than θlimitIf yes, countlimit=countlimit+1, go to step 4; otherwise, directly entering the step 4;
step 4, if i is equal to i +1, if i is less than M, step 2 is entered, otherwise step 5 is entered;
and 5: judge countlimitWhether greater than countvoiceIf true, the flag bit isvoiceSetting 1, recognizing the received sound signal as the sound of the target speech recognition area, preparing for the next speech recognition, otherwise, marking the location isvoiceSetting 0, judging the received sound as the sound of the non-target voice recognition area, and removing the sound.
In step 1, the time delay τ of the sound signal received by the ith microphone relative to the time delay τ of the sound signal received by the 1 st microphoneiObtained by setting the sound signal received by the microphone array to xi(t),:
Step a, setting the sound signal received by the 1 st microphone as x1(t), setting the time delay tau to 0, and setting i to 2;
step b, carrying out cross-correlation operation on the sound signal received by the first microphone and the sound signal received by the ith microphone, and expressing the cross-correlation operation as the sound signal
ComputingMaximum value of function, obtainingThe value of tau when the function is maximum is recorded as taui,τiI.e. the sound signal received by the ith microphone is received relative to the sound signal received by the 1 st microphoneTime delay tau of the same sound signali;
And c, if the i is larger than M, finishing the time delay calculation, otherwise jumping to the step b.
When the microphone array receives the sound signal, and judges that the sound signal is the sound of the target speech recognition area, namely the mark location isvoiceAnd (2) enhancing the voice signal as 1, wherein the enhanced voice signal is defined as y (t):
then the voice recognition module recognizes y (t), and if a control instruction is recognized, the range hood is controlled;
when the microphone array receives the sound signal, and judges that the sound signal is the sound of the non-target speech recognition area, namely the mark location isvoiceThe speech recognition module does not work when it is 0.
The operation principle and operation process of the speech recognition module are conventional in the art and will not be described in detail here.
According to the scheme of the invention, the microphone array can identify the voice area of the user for judging whether the voice instruction is possible, so that most of noise can be eliminated.
Claims (2)
1. A voice screening method of a range hood is characterized in that: a microphone array consisting of M microphones is arranged on the range hood, the M microphones are uniformly arranged on the same horizontal straight line, the microphone on the leftmost side is the first microphone, and the microphone on the leftmost side is the second microphone and the Mth microphone of the third microphone … … in turn towards the right; the distance between two adjacent microphones is d, wherein M is a natural number more than or equal to 3; the following parameters are preset: parameter i, sound source direction angle limiting value thetalimit,θlimitThe value of (a) is preset, and theta is more than or equal to 30 DEGlimitLess than or equal to 60 degrees; number count of microphones in target range in sound source identification arealimitTarget range number threshold of microphonesValue countvoiceGet it Setting flag bit isvoiceIndicating whether the received sound is a sound of a target area; after receiving the sound signal, the microphone array screens the sound by the following method to judge whether the sound signal is the sound of the target voice recognition area:
step 1, obtaining the time delay tau of a sound signal received by an ith microphone relative to the same sound signal received by a 1 st microphoneiSetting the initial value of i to 2, countlimitIs set to 0; the sound signal received by the microphone array is xi(t) the time delay τ of the sound signal received by the ith microphone relative to the time delay τ of the sound signal received by the 1 st microphoneiObtained by the following method:
step a, setting the sound signal received by the 1 st microphone as x1(t), setting the time delay tau to 0, and setting i to 2;
step b, the sound signal received by the first microphone and the sound signal x received by the ith microphonei(t) performing a cross-correlation operation, represented by
ComputingMaximum value of function, obtainingThe value of tau when the function is maximum is recorded as taui,τiI.e. when the sound signal received by the i-th microphone is relative to the same sound signal received by the 1 st microphoneDelay taui;
C, judging whether i is larger than M or not, if so, finishing time delay calculation, and otherwise, jumping to the step b;
step 2, calculating the sound source direction angle theta of the microphone iiIs composed of
Wherein c is the propagation speed of sound in air;
step 3, determining | θiWhether | is less than θlimitIf yes, countlimit=countlimit+1, go to step 4; otherwise, directly entering the step 4;
step 4, if i is equal to i +1, if i is less than M, step 2 is executed, otherwise step 5 is executed;
and 5: judge countlimitWhether greater than countvoiceIf true, the flag bit isvoiceSetting 1, recognizing the received sound signal as the sound of the target speech recognition area, preparing for the next speech recognition, otherwise, marking the location isvoiceSetting 0, judging the received sound as the sound of the non-target voice recognition area, and removing the sound.
2. The voice screening method of the range hood according to claim 1, characterized in that:
when the microphone array receives the sound signal, and judges that the sound signal is the sound of the target speech recognition area, namely the mark location isvoiceAnd (2) enhancing the voice signal as 1, wherein the enhanced voice signal is defined as y (t):
then the voice recognition module recognizes y (t), and if a control instruction is recognized, the range hood is controlled;
when the microphone array receives the sound signal, the judgment is madeThe sound signal is the sound of a non-target speech recognition region, i.e. the flag isvoiceThe speech recognition module does not work when it is 0.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711471901.9A CN109990327B (en) | 2017-12-29 | 2017-12-29 | Voice screening method of range hood |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711471901.9A CN109990327B (en) | 2017-12-29 | 2017-12-29 | Voice screening method of range hood |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109990327A CN109990327A (en) | 2019-07-09 |
CN109990327B true CN109990327B (en) | 2020-06-26 |
Family
ID=67109397
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711471901.9A Active CN109990327B (en) | 2017-12-29 | 2017-12-29 | Voice screening method of range hood |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109990327B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015029403A1 (en) * | 2013-09-02 | 2015-03-05 | パナソニックIpマネジメント株式会社 | Range hood |
CN107102296A (en) * | 2017-04-27 | 2017-08-29 | 大连理工大学 | A kind of sonic location system based on distributed microphone array |
CN107172018A (en) * | 2017-04-27 | 2017-09-15 | 华南理工大学 | The vocal print cryptosecurity control method and system of activation type under common background noise |
CN107289482A (en) * | 2017-07-20 | 2017-10-24 | 杭州老板电器股份有限公司 | A kind of lampblack absorber self study automatic noise reduction system and method |
CN206709169U (en) * | 2017-03-09 | 2017-12-05 | 佛山市云米电器科技有限公司 | Range hood sound-controlled apparatus |
-
2017
- 2017-12-29 CN CN201711471901.9A patent/CN109990327B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015029403A1 (en) * | 2013-09-02 | 2015-03-05 | パナソニックIpマネジメント株式会社 | Range hood |
CN206709169U (en) * | 2017-03-09 | 2017-12-05 | 佛山市云米电器科技有限公司 | Range hood sound-controlled apparatus |
CN107102296A (en) * | 2017-04-27 | 2017-08-29 | 大连理工大学 | A kind of sonic location system based on distributed microphone array |
CN107172018A (en) * | 2017-04-27 | 2017-09-15 | 华南理工大学 | The vocal print cryptosecurity control method and system of activation type under common background noise |
CN107289482A (en) * | 2017-07-20 | 2017-10-24 | 杭州老板电器股份有限公司 | A kind of lampblack absorber self study automatic noise reduction system and method |
Also Published As
Publication number | Publication date |
---|---|
CN109990327A (en) | 2019-07-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5622744B2 (en) | Voice recognition device | |
KR102339594B1 (en) | Object recognition method, computer device, and computer-readable storage medium | |
CN110265020B (en) | Voice wake-up method and device, electronic equipment and storage medium | |
GB2604496A (en) | Methods, apparatus and systems for biometric processes | |
CN108320739B (en) | Method and device for assisting voice instruction recognition according to position information | |
US11978478B2 (en) | Direction based end-pointing for speech recognition | |
CN107172018A (en) | The vocal print cryptosecurity control method and system of activation type under common background noise | |
CN106710603A (en) | Speech recognition method and system based on linear microphone array | |
WO2012079459A1 (en) | Method and apparatus for audio mixing of multiple microphones | |
CN105139858A (en) | Information processing method and electronic equipment | |
KR100822880B1 (en) | User identification system through sound localization based audio-visual under robot environments and method thereof | |
CN109308908A (en) | A kind of voice interactive method and device | |
CN104464722A (en) | Voice activity detection method and equipment based on time domain and frequency domain | |
CN106992010A (en) | Without the microphone array speech enhancement device under the conditions of direct sound wave | |
CN106653044A (en) | Dual-microphone noise reduction system and method for tracing noise source and target sound source | |
JP2012242609A (en) | Voice recognition device, robot, and voice recognition method | |
CN109990327B (en) | Voice screening method of range hood | |
WO2021108991A1 (en) | Control method and apparatus, and movable platform | |
CN111412587B (en) | Voice processing method and device of air conditioner, air conditioner and storage medium | |
CN109545210A (en) | A kind of devices and methods therefor promoting speech recognition robustness | |
CN110610706A (en) | Sound signal acquisition method and device, electrical equipment control method and electrical equipment | |
CN109994123A (en) | A kind of voice screening technique of range hood | |
Lim et al. | Speaker localization in noisy environments using steered response voice power | |
CN109994124A (en) | A kind of voice screening technique of range hood | |
CN114464184A (en) | Method, apparatus and storage medium for speech recognition |
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 |