CN106847283A - Intelligent electrical appliance control and device - Google Patents
Intelligent electrical appliance control and device Download PDFInfo
- Publication number
- CN106847283A CN106847283A CN201710110645.4A CN201710110645A CN106847283A CN 106847283 A CN106847283 A CN 106847283A CN 201710110645 A CN201710110645 A CN 201710110645A CN 106847283 A CN106847283 A CN 106847283A
- Authority
- CN
- China
- Prior art keywords
- wake
- word
- speech recognition
- recognition modeling
- voice messaging
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Abstract
The invention discloses a kind of intelligent electrical appliance control and device, wherein, method is comprised the following steps:Obtain the voice messaging of user input;Speech recognition modeling identification voice messaging based on training in advance, the speech recognition modeling of training in advance is multiple;It is determined that correctly recognizing the speech recognition modeling of voice messaging, and obtain wake-up word corresponding with the speech recognition modeling of correct identification voice messaging;Intelligent appliance is waken up according to word is waken up.The method passes through the voice messaging that multiple speech recognition modeling identifying users are input into, and obtain wake-up word corresponding with the speech recognition modeling of correct identification voice messaging, household electrical appliances are waken up according to the wake-up word, so as to realize can be used more diversified wake-up word to wake up household electrical appliances.
Description
Technical field
The present invention relates to household electrical appliance technical field, more particularly to a kind of intelligent electrical appliance control and device.
Background technology
With the continuous progress of science and technology, various intellectual technologies are increasingly used on household electrical appliance, to improve the intelligence of household electrical appliances
Change.For example, speech recognition technology is applied into household electrical appliances, when user input voice wakes up word, household electrical appliances can be waken up by waking up word.
It is presently used for waking up the wake-up word of household electrical appliances, is typically defined by manufacturer, such as the wake-up word of ding-dong audio amplifier is " to sting
Rub-a-dub ding-dong ".Ding-dong audio amplifier can wake up ding-dong audio amplifier when the sound of " ding-dong ding-dong " is received from resting state.But,
Because the wake-up word for using is relatively simple, user is not intended to use this wake-up word sometimes, therefore, it is impossible to meet user to waking up
The diversified demand of word, makes Consumer's Experience be deteriorated.
The content of the invention
It is contemplated that at least solving one of technical problem in correlation technique to a certain extent.Therefore, of the invention
First purpose is to propose a kind of intelligent electrical appliance control, and the method passes through multiple speech recognition modeling identifying users and is input into
Voice messaging, and obtain wake-up word corresponding with the speech recognition modeling of correct identification voice messaging, called out according to the wake-up word
Awake household electrical appliances, so as to realize can be used more diversified wake-up word to wake up household electrical appliances.
Second object of the present invention is to propose a kind of intelligent electrical appliance control device.
To achieve these goals, first aspect present invention embodiment proposes a kind of intelligent electrical appliance control, including:
Obtain the voice messaging of user input;Speech recognition modeling identification voice messaging based on training in advance, the voice of training in advance
Identification model is multiple;It is determined that correctly recognizing the speech recognition modeling of voice messaging, and obtain and correctly recognize voice messaging
The corresponding wake-up word of speech recognition modeling;Intelligent appliance is waken up according to word is waken up.
The intelligent electrical appliance control of the embodiment of the present invention, the voice being input into by multiple speech recognition modeling identifying users
Information, and wake-up word corresponding with the speech recognition modeling of correct identification voice messaging is obtained, household electrical appliances are waken up according to the wake-up word,
So as to realize can be used more diversified wake-up word to wake up household electrical appliances.
It is that, up to above-mentioned purpose, second aspect present invention embodiment proposes a kind of intelligent electrical appliance control device, including:Obtain
Module, the voice messaging for obtaining user input;Identification module, language is recognized for the speech recognition modeling based on training in advance
Message ceases, and the speech recognition modeling of training in advance is multiple;Determining module, for determining that the voice for correctly recognizing voice messaging is known
Other model, and obtain wake-up word corresponding with the speech recognition modeling of correct identification voice messaging;Wake module, calls out for basis
Word of waking up wakes up intelligent appliance.
The intelligent electrical appliance control device of the embodiment of the present invention, the voice being input into by multiple speech recognition modeling identifying users
Information, and wake-up word corresponding with the speech recognition modeling of correct identification voice messaging is obtained, household electrical appliances are waken up according to the wake-up word,
So as to realize can be used more diversified wake-up word to wake up household electrical appliances.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partly become from the following description
Obtain substantially, or recognized by practice of the invention.
Brief description of the drawings
Fig. 1 is the flow chart of intelligent electrical appliance control according to an embodiment of the invention;
Fig. 2 is according to a flow chart for the intelligent electrical appliance control of specific embodiment of the invention;
Fig. 3 is the separate effect diagram of each speech recognition modeling according to an embodiment of the invention;
Fig. 4 is the effect diagram that word is waken up by switch control knob's selection according to an embodiment of the invention;
Fig. 5 is the flow chart of intelligent air-conditioner control method according to an embodiment of the invention;
Fig. 6 is the structural representation of intelligent electrical appliance control device according to an embodiment of the invention;
Fig. 7 is according to a structural representation for the intelligent electrical appliance control device of specific embodiment of the invention;
Fig. 8 is the structural representation of the intelligent electrical appliance control device according to another specific embodiment of the invention.
Specific embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from start to finish
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
It is exemplary to scheme the embodiment of description, it is intended to for explaining the present invention, and be not considered as limiting the invention.
Below with reference to the accompanying drawings the intelligent electrical appliance control and device of the embodiment of the present invention described.
Fig. 1 is the flow chart of intelligent electrical appliance control according to an embodiment of the invention.
As shown in figure 1, the intelligent electrical appliance control includes:
S101, obtains the voice messaging of user input.
At present, various intellectual technologies are increasingly used on household electrical appliance, to improve the intellectuality of household electrical appliances.For example, can be by language
Sound identification technology is applied on household electrical appliances, and when user input phonetic order, the sound identification module in household electrical appliances is to user input
Phonetic order is parsed and is converted into corresponding order, and household electrical appliances complete corresponding operation by performing corresponding order.
In one embodiment of the invention, voice recognition chip is mounted with intelligent appliance, voice recognition chip can be right
The voice messaging of user input is identified.
For example, certain user is due to being cold, looks on the bright side of things and open the heating function of air-conditioning.Now, a voice messaging can be first input into, with
Wake up air-conditioning.After air-conditioning is waken up, air-conditioning can further be controlled, such as phonetic order adjusts temperature or directly uses
Remote control adjusts temperature.Specifically, user Ke Chao air-conditionings direction is spoken:" dazzle cruel small U.S. ", air-conditioning can by voice recognition chip,
Device etc. obtains the voice messaging of user input.
S102, the speech recognition modeling based on training in advance recognizes voice messaging, and the speech recognition modeling of training in advance is
It is multiple.
After the voice messaging for obtaining user input, the acoustic feature of voice messaging is can extract, and be sequentially inputted to multiple
In the speech recognition modeling of training in advance, acoustic feature is recognized by speech recognition modeling, believed with the voice that identifying user is input into
Breath.
S103, it is determined that the correctly speech recognition modeling of identification voice messaging, and obtain the language with correct identification voice messaging
The corresponding wake-up word of sound identification model.
After the language identification Model Identification that the voice messaging for receiving sequentially passes through multiple training in advance, can be to each voice
The voice messaging result that identification model is identified is judged, to determine whether recognition result is correct.
Specifically, voice messaging is identified using one of language identification model, obtains recognition result, and will know
The other result word that wakes up corresponding with the language identification model knowledge is matched, if the match is successful, is obtained and the speech recognition
The corresponding wake-up word of model.If it fails to match, show that the speech recognition modeling fails the voice letter of correct identifying user input
Breath, then be identified using next language identification model to voice messaging, obtains recognition result, and by recognition result and the language
The corresponding word that wakes up of sound identification model is matched.If the match is successful, the corresponding wake-up word of the speech recognition modeling is obtained.
If it fails to match, continue with next speech recognition modeling and voice messaging is identified, until there is speech recognition mould
The corresponding wake-up word of the recognition result of type is untill the match is successful.
S104, intelligent appliance is waken up according to word is waken up.
After wake-up word is obtained, corresponding order is performed according to wake-up word, household electrical appliances is instructed into wait from sleep pattern
Pattern, that is, wake up household electrical appliances.
Additionally, user is in input voice information, may be affected by the ambient so that in the voice messaging of input
With noise, or with certain accent during user input voice messaging, or enunciated not during user input voice messaging
Clear etc., these factors may influence the recognition result of speech recognition modeling, and then influence to the correct acquisition for waking up word.
Therefore, in order to improve the accuracy rate of speech recognition modeling recognition result, can be recognized in the speech recognition modeling based on training in advance
Before institute's voice messaging, speech recognition modeling is first trained, as shown in Fig. 2 step may include:
S105, selection meets pre-conditioned wake-up word sample.
In one embodiment of the invention, the wake-up word sample of selection needs to meet certain pre-conditioned, if called out
Wake up word sample including syllable very little or may result in the speech recognition modeling for training comprising polyphone etc. and do not reach just
Really recognize the purpose of voice messaging.For example, choosing, word sample is waken up for " precious deposits ", because the wake-up word sample is by two Chinese character groups
Into and " Tibetan " be polyphone, training speech recognition modeling when speech recognition modeling " zang " may be identified as " cang ", when
Speech recognition modeling can not correctly recognize voice messaging when user says " precious deposits ", and then can not wake up household electrical appliances with the wake-up word.
In addition, if it is common-use words or the name of certain brand to wake up word sample, false wake-up household electrical appliances are may result in.Example
Such as, if waking up word sample from " cygnet " conduct, when appearance " cygnet " three words in the cygnet advertisement televised
When, household electrical appliances are may result in by false wake-up.
Therefore, in one embodiment of the invention, selection takes the pre-conditioned of wake-up word sample and may include to wake up word sample
This at least includes four syllables (correspondence Chinese is at least made up of 4 Chinese characters), wakes up word sample not comprising having polyphone, wake up word
Sample is not everyday expressions, wakes up word sample not comprising brand name etc..
S106, according to wake-up word sample training speech recognition modeling.
Meet pre-conditioned wake-up word sample training speech recognition modeling according to what is chosen, for example, can multiple voice
Input wakes up word sample or the multiple phonetic entry wake-up word sample in the case where there is a small amount of noise, to train speech recognition mould
Type so that model is more accurate when voice is recognized.
In order to increase diversity, multiple word samples that wake up can be chosen and be respectively trained multiple speech recognition modelings, each voice
It is separate between identification model.
As shown in figure 3, word engine is waken up there is provided 8 wake-up words, and without friendship between each corresponding circle of wake-up word
Collection, i.e., it is separate so that the voice for waking up household electrical appliances is more diversified.
The intelligent electrical appliance control of the embodiment of the present invention, the voice being input into by multiple speech recognition modeling identifying users
Information, and wake-up word corresponding with the speech recognition modeling of correct identification voice messaging is obtained, household electrical appliances are waken up according to the wake-up word,
So as to realize can be used more diversified wake-up word to wake up household electrical appliances.
Additionally, in one embodiment of the invention, each speech recognition modeling can respectively have corresponding switch
Control button, that is to say, that each wakes up word has corresponding switch control knob.When user grasps to switch control knob
When making, the corresponding wake-up word of switch control knob can be turned on or off according to the operation of the user for receiving.
For example, certain user has downloaded application program corresponding with certain household electrical appliances arousal function on mobile phone, word is waken up in mobile phone
In options, it is available for user to select as shown in figure 4, there are 8 to wake up word, user can be by right with wake-up word 1 (in figure shown in 41)
The switch control knob (in Fig. 4 shown in 42) answered, opens and wakes up word 1 (in figure shown in 41), and same can also be turned on or off
Other wake up word.Wake-up word 1 (in figure shown in 41) is opened in Fig. 4, word 2 (in figure shown in 43) is waken up, is waken up word 5 (44 in figure
It is shown) and word 6 (in figure shown in 45) is waken up, wake-up word 3 (in figure shown in 46) is closed, word 4 (in figure shown in 47) is waken up, is waken up
Word 7 (in figure shown in 48) and wake-up word 8 (in figure shown in 49).
Therefore, multiple wake-up words can be selected by switch control knob, also can wake up selection one in words from multiple call out
Awake word, so as to enrich the selection of user, more conforms to user personality demand.
Describe intelligent electrical appliance control proposed by the present invention in detail by taking intelligent air condition as an example below.
Fig. 5 is the flow chart of intelligent air-conditioner control method according to an embodiment of the invention.
As shown in figure 5, the step of intelligent air-conditioner control method is:
S501, selection meets pre-conditioned wake-up word sample.
Specifically, can choose at least include four syllables, not comprising have polyphone, be not everyday expressions, not comprising product
The pre-conditioned word such as board title is used as wake-up word sample.For example, choosing " dazzling cruel small U.S. ", " small U.S., go into operation " etc. conduct
Wake up word sample.
S502, according to wake-up word sample training speech recognition modeling.
Wake-up word sample according to choosing is trained respectively, so as to obtain multiple speech recognition modelings, and each voice
Identification model has corresponding wake-up word respectively, and each speech recognition modeling is separate.
S503, selection wakes up word " small U.S., go into operation " and " dazzling cruel small U.S. ".
Specifically, user downloads on mobile phone application program corresponding with air-conditioning arousal function, by mobile phone open
Application program " the waking up selected ci poem to select " item, selection is opened and wakes up word " small U.S., go into operation " and " dazzling cruel small U.S. " and close other wake-ups
Word, that is to say, that open speech recognition modeling corresponding with the wake-up word of selection, close other speech recognition modelings.
S504, user input voice messaging " dazzles cruel small U.S. ".
Due to being warm, user looks on the bright side of things and opens the cooling function of air-conditioning.Now, user can first be input into a voice messaging, to call out
Awake air-conditioning.Specifically, user Ke Chao air-conditionings direction is spoken " dazzling cruel small U.S. ", and air-conditioning can be obtained by voice recognition chip, device etc.
Take the voice messaging " dazzling cruel small U.S. " of user input.
S505, the speech recognition modeling identification voice messaging based on training in advance.
Specifically, after the voice messaging " dazzle cruel small U.S. " for receiving user input, respectively with wake up word " small U.S., go into operation "
And with wake up word " dazzle cruel small U.S. " corresponding speech recognition modeling, the voice messaging " dazzling cruel small U.S. " of identifying user input.
S506, obtains wake-up word corresponding with the speech recognition modeling of correct identification voice messaging.
Specifically, by the way that after the voice messaging that two speech recognition modeling identifying users are input into, " small U.S., opens with word is waken up
The speech recognition modeling of work " fails correctly to recognize voice messaging that corresponding speech recognition modeling is just with word " dazzling cruel small U.S. " is waken up
Voice messaging is really identified, and obtains wake-up word " dazzling cruel small U.S. ".
S507, air-conditioning is waken up according to word " dazzling cruel small U.S. " is waken up.
After acquisition wakes up word, order accordingly is performed according to word " dazzling cruel small U.S. " is waken up, air-conditioning is entered by sleep state
Enter to wait the state of instruction, that is, wake up air-conditioning.After air-conditioning is waken up, user can be adjusted by phonetic order temperature or directly to be made
Temperature is adjusted with remote control.
The intelligent electrical appliance control device that the embodiment of the present invention is proposed is described with reference to Fig. 6.Fig. 6 is according to this hair
The structural representation of the intelligent electrical appliance control device of bright one embodiment.
As shown in fig. 6, the intelligent electrical appliance control device may include:Acquisition module 610, identification module 620, determining module
630th, wake module 640.
Acquisition module 610 is used to obtain the voice messaging of user input.
Identification module 620 is used for the speech recognition modeling identification voice messaging based on training in advance, the voice of training in advance
Identification model is multiple.
Determining module 630 is used to determine correctly to recognize the speech recognition modeling of voice messaging, and obtains and correct identification language
The corresponding wake-up word of speech recognition modeling of message breath.
Wake module 640 is used to wake up intelligent appliance according to wake-up word.
Additionally, as shown in fig. 7, on the basis of Fig. 6, the intelligent electrical appliance control device may also include training module 650.
Training module 650 was used for before the speech recognition modeling identification voice messaging based on training in advance, trained voice
Identification model, each speech recognition modeling has corresponding wake-up word respectively, and separate.
Specifically, training module 650 meets pre-conditioned wake-up word sample for choosing, according to wake-up word sample training
Speech recognition modeling.
Wherein, it is pre-conditioned including scenario described below in one or more:Waking up word sample at least includes four syllables, calls out
Word sample of waking up does not include polyphone, wake up word sample is not everyday expressions, wakes up word sample not comprising brand name etc..
Further, as shown in figure 8, on the basis of Fig. 7, intelligent electrical appliance control device may also include control module 660.
Control module 660 is used to receive operation of the user to switch control knob, and is turned on and off and opens according to operation
Close the corresponding wake-up word of control button.
It should be noted that the foregoing explanation to intelligent electrical appliance control embodiment is also applied for the embodiment
Intelligent electrical appliance control device, here is omitted.
In sum, the intelligent electrical appliance control device of the embodiment of the present invention, by multiple speech recognition modeling identifying users
The voice messaging of input, and wake-up word corresponding with the speech recognition modeling of correct identification voice messaging is obtained, according to the wake-up
Word wakes up household electrical appliances, so as to realize can be used more diversified wake-up word to wake up household electrical appliances.
In the description of this specification, reference term:" one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means to combine specific features, structure, material or spy that the embodiment or example are described
Point is contained at least one embodiment of the invention or example.In this manual, to the schematic representation of above-mentioned term not
Identical embodiment or example must be directed to.And, the specific features of description, structure, material or feature can be with office
Combined in an appropriate manner in one or more embodiments or example.Additionally, in the case of not conflicting, the skill of this area
Art personnel can be tied the feature of the different embodiments or example described in this specification and different embodiments or example
Close and combine.
Although embodiments of the invention have been shown and described above, it is to be understood that above-described embodiment is example
Property, it is impossible to limitation of the present invention is interpreted as, one of ordinary skill in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, changes, replacing and modification.
Claims (10)
1. a kind of intelligent electrical appliance control, it is characterised in that including:
Obtain the voice messaging of user input;
Speech recognition modeling based on training in advance recognizes the voice messaging, and the speech recognition modeling of the training in advance is many
It is individual;
It is determined that correctly recognize the speech recognition modeling of the voice messaging, and obtain and correctly to recognize the voice messaging with described
The corresponding wake-up word of speech recognition modeling;
Intelligent appliance is waken up according to the wake-up word.
2. the method for claim 1, it is characterised in that in the speech recognition modeling identification institute predicate based on training in advance
Before message breath, also include:
The speech recognition modeling is trained, each speech recognition modeling has corresponding wake-up word respectively, and separate.
3. method as claimed in claim 2, it is characterised in that the training speech recognition modeling, including:
Selection meets pre-conditioned wake-up word sample, the speech recognition modeling according to the wake-up word sample training.
4. method as claimed in claim 3, it is characterised in that described pre-conditioned one kind or many including in scenario described below
Kind:The wake-up word sample at least includes four syllables, the wake-up word sample not comprising having polyphone, the wake-up word sample
For everyday expressions, the wake-up word sample do not include brand name.
5. the method for claim 1, it is characterised in that each speech recognition modeling has corresponding switch respectively
Control button, methods described also includes:
Receive operation of the user to switch control knob, and according to the operation be turned on and off with the switch control by
The corresponding wake-up word of button.
6. a kind of intelligent electrical appliance control device, it is characterised in that including:
Acquisition module, the voice messaging for obtaining user input;
Identification module, the voice messaging, the language of the training in advance are recognized for the speech recognition modeling based on training in advance
Sound identification model is multiple;
Determining module, the speech recognition modeling of the voice messaging is correctly recognized for determination, and obtain and the correct identification
The corresponding wake-up word of speech recognition modeling of the voice messaging;
Wake module, for waking up intelligent appliance according to the wake-up word.
7. device as claimed in claim 6, it is characterised in that also include:
Training module, for before the speech recognition modeling based on training in advance recognizes the voice messaging, training institute's predicate
Sound identification model, each speech recognition modeling has corresponding wake-up word respectively, and separate.
8. device as claimed in claim 7, it is characterised in that the training module, is used for:
Selection meets pre-conditioned wake-up word sample, the speech recognition modeling according to the wake-up word sample training.
9. device as claimed in claim 8, it is characterised in that described pre-conditioned one kind or many including in scenario described below
Kind:The wake-up word sample at least includes four syllables, the wake-up word sample not comprising having polyphone, the wake-up word sample
For everyday expressions, the wake-up word sample do not include brand name.
10. device as claimed in claim 6, it is characterised in that each speech recognition modeling has corresponding opening respectively
Control button is closed, described device also includes:
Control module, for receiving operation of the user to switch control knob, and according to the operation be turned on and off with
The corresponding wake-up word of the switch control knob.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710110645.4A CN106847283A (en) | 2017-02-28 | 2017-02-28 | Intelligent electrical appliance control and device |
PCT/CN2017/090587 WO2018157526A1 (en) | 2017-02-28 | 2017-06-28 | Smart home appliance control method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710110645.4A CN106847283A (en) | 2017-02-28 | 2017-02-28 | Intelligent electrical appliance control and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106847283A true CN106847283A (en) | 2017-06-13 |
Family
ID=59134437
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710110645.4A Pending CN106847283A (en) | 2017-02-28 | 2017-02-28 | Intelligent electrical appliance control and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106847283A (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108093540A (en) * | 2017-12-25 | 2018-05-29 | 佛山市车品匠汽车用品有限公司 | A kind of method and apparatus based on smart home acoustic control lamps and lanterns |
CN108196812A (en) * | 2017-12-26 | 2018-06-22 | 广东美的厨房电器制造有限公司 | A kind of cooking equipment menu control method, device and cooking equipment |
WO2018157526A1 (en) * | 2017-02-28 | 2018-09-07 | 广东美的制冷设备有限公司 | Smart home appliance control method and device |
CN108595406A (en) * | 2018-01-04 | 2018-09-28 | 广东小天才科技有限公司 | A kind of based reminding method of User Status, device, electronic equipment and storage medium |
CN108628653A (en) * | 2018-03-30 | 2018-10-09 | 上海思愚智能科技有限公司 | Ground cushion management method and terminal |
CN108766420A (en) * | 2018-05-31 | 2018-11-06 | 中国联合网络通信集团有限公司 | Interactive voice equipment wakes up word generation method and device |
CN108831477A (en) * | 2018-06-14 | 2018-11-16 | 出门问问信息科技有限公司 | A kind of audio recognition method, device, equipment and storage medium |
CN109119071A (en) * | 2018-09-26 | 2019-01-01 | 珠海格力电器股份有限公司 | A kind of training method and device of speech recognition modeling |
CN109584860A (en) * | 2017-09-27 | 2019-04-05 | 九阳股份有限公司 | A kind of voice wakes up word and defines method and system |
CN110364147A (en) * | 2019-08-29 | 2019-10-22 | 厦门市思芯微科技有限公司 | A kind of wake-up training word acquisition system and method |
CN110515449A (en) * | 2019-08-30 | 2019-11-29 | 北京安云世纪科技有限公司 | Wake up the method and device of smart machine |
CN110634481A (en) * | 2019-08-06 | 2019-12-31 | 惠州市德赛西威汽车电子股份有限公司 | Voice integration method for outputting optimal recognition result |
CN111369992A (en) * | 2020-02-27 | 2020-07-03 | Oppo(重庆)智能科技有限公司 | Instruction execution method and device, storage medium and electronic equipment |
CN111696560A (en) * | 2019-03-14 | 2020-09-22 | 本田技研工业株式会社 | Agent device, control method for agent device, and storage medium |
CN112259085A (en) * | 2020-09-28 | 2021-01-22 | 上海声瀚信息科技有限公司 | Two-stage voice awakening algorithm based on model fusion framework |
CN113257241A (en) * | 2020-02-11 | 2021-08-13 | 青岛海尔空调器有限总公司 | Intelligent household appliance and voice control method thereof |
WO2023169382A1 (en) * | 2022-03-11 | 2023-09-14 | 青岛海尔洗衣机有限公司 | Knocking-based device control method and apparatus, and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103292437A (en) * | 2013-06-17 | 2013-09-11 | 广东美的制冷设备有限公司 | Voice interactive air conditioner and control method thereof |
US20160180837A1 (en) * | 2014-12-17 | 2016-06-23 | Qualcomm Incorporated | System and method of speech recognition |
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 |
-
2017
- 2017-02-28 CN CN201710110645.4A patent/CN106847283A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103292437A (en) * | 2013-06-17 | 2013-09-11 | 广东美的制冷设备有限公司 | Voice interactive air conditioner and control method thereof |
US20160180837A1 (en) * | 2014-12-17 | 2016-06-23 | Qualcomm Incorporated | System and method of speech recognition |
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 |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018157526A1 (en) * | 2017-02-28 | 2018-09-07 | 广东美的制冷设备有限公司 | Smart home appliance control method and device |
CN109584860A (en) * | 2017-09-27 | 2019-04-05 | 九阳股份有限公司 | A kind of voice wakes up word and defines method and system |
CN108093540A (en) * | 2017-12-25 | 2018-05-29 | 佛山市车品匠汽车用品有限公司 | A kind of method and apparatus based on smart home acoustic control lamps and lanterns |
CN108196812A (en) * | 2017-12-26 | 2018-06-22 | 广东美的厨房电器制造有限公司 | A kind of cooking equipment menu control method, device and cooking equipment |
CN108595406A (en) * | 2018-01-04 | 2018-09-28 | 广东小天才科技有限公司 | A kind of based reminding method of User Status, device, electronic equipment and storage medium |
CN108628653A (en) * | 2018-03-30 | 2018-10-09 | 上海思愚智能科技有限公司 | Ground cushion management method and terminal |
CN108766420A (en) * | 2018-05-31 | 2018-11-06 | 中国联合网络通信集团有限公司 | Interactive voice equipment wakes up word generation method and device |
CN108831477A (en) * | 2018-06-14 | 2018-11-16 | 出门问问信息科技有限公司 | A kind of audio recognition method, device, equipment and storage medium |
CN108831477B (en) * | 2018-06-14 | 2021-07-09 | 出门问问信息科技有限公司 | Voice recognition method, device, equipment and storage medium |
CN109119071A (en) * | 2018-09-26 | 2019-01-01 | 珠海格力电器股份有限公司 | A kind of training method and device of speech recognition modeling |
CN111696560A (en) * | 2019-03-14 | 2020-09-22 | 本田技研工业株式会社 | Agent device, control method for agent device, and storage medium |
CN110634481A (en) * | 2019-08-06 | 2019-12-31 | 惠州市德赛西威汽车电子股份有限公司 | Voice integration method for outputting optimal recognition result |
CN110634481B (en) * | 2019-08-06 | 2021-11-16 | 惠州市德赛西威汽车电子股份有限公司 | Voice integration method for outputting optimal recognition result |
CN110364147A (en) * | 2019-08-29 | 2019-10-22 | 厦门市思芯微科技有限公司 | A kind of wake-up training word acquisition system and method |
CN110364147B (en) * | 2019-08-29 | 2021-08-20 | 厦门市思芯微科技有限公司 | Awakening training word acquisition system and method |
CN110515449A (en) * | 2019-08-30 | 2019-11-29 | 北京安云世纪科技有限公司 | Wake up the method and device of smart machine |
CN110515449B (en) * | 2019-08-30 | 2021-06-04 | 北京安云世纪科技有限公司 | Method and device for awakening intelligent equipment |
CN113257241A (en) * | 2020-02-11 | 2021-08-13 | 青岛海尔空调器有限总公司 | Intelligent household appliance and voice control method thereof |
CN111369992A (en) * | 2020-02-27 | 2020-07-03 | Oppo(重庆)智能科技有限公司 | Instruction execution method and device, storage medium and electronic equipment |
CN112259085A (en) * | 2020-09-28 | 2021-01-22 | 上海声瀚信息科技有限公司 | Two-stage voice awakening algorithm based on model fusion framework |
WO2023169382A1 (en) * | 2022-03-11 | 2023-09-14 | 青岛海尔洗衣机有限公司 | Knocking-based device control method and apparatus, and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106847283A (en) | Intelligent electrical appliance control and device | |
CN108000526B (en) | Dialogue interaction method and system for intelligent robot | |
CN109410927A (en) | Offline order word parses the audio recognition method combined, device and system with cloud | |
CN105843381B (en) | Data processing method for realizing multi-modal interaction and multi-modal interaction system | |
CN109326289A (en) | Exempt to wake up voice interactive method, device, equipment and storage medium | |
CN108363706A (en) | The method and apparatus of human-computer dialogue interaction, the device interacted for human-computer dialogue | |
CN106653021A (en) | Voice wake-up control method and device and terminal | |
CN107704275A (en) | Smart machine awakening method, device, server and smart machine | |
CN106886170A (en) | The control method of household electrical appliance, system and audio amplifier | |
CN110534099A (en) | Voice wakes up processing method, device, storage medium and electronic equipment | |
CN107483493A (en) | Interactive calendar prompting method, device, storage medium and intelligent domestic system | |
JP2004527809A (en) | Environmentally responsive user interface / entertainment device that simulates personal interaction | |
CN108882454B (en) | Intelligent voice recognition interactive lighting method and system based on emotion judgment | |
CN106804076A (en) | A kind of illuminator of smart home | |
JP2017059043A (en) | Awakening control system for vehicle | |
CN110060677A (en) | Voice remote controller control method, device and computer readable storage medium | |
JP2004527808A (en) | Self-updating user interface / entertainment device that simulates personal interaction | |
JP2004513444A (en) | User interface / entertainment device that simulates personal interactions and augments external databases with relevant data | |
JP2010094799A (en) | Humanoid robot | |
CN106502712A (en) | APP improved methods and system based on user operation | |
CN109243462A (en) | A kind of voice awakening method and device | |
CN102404278A (en) | Song request system based on voiceprint recognition and application method thereof | |
CN105895105A (en) | Speech processing method and device | |
CN111145721A (en) | Personalized prompt language generation method, device and equipment | |
CN109429416A (en) | Illumination control method, apparatus and system for multi-user scene |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170613 |