CN106887227A - A kind of voice awakening method and system - Google Patents
A kind of voice awakening method and system Download PDFInfo
- Publication number
- CN106887227A CN106887227A CN201510944213.4A CN201510944213A CN106887227A CN 106887227 A CN106887227 A CN 106887227A CN 201510944213 A CN201510944213 A CN 201510944213A CN 106887227 A CN106887227 A CN 106887227A
- Authority
- CN
- China
- Prior art keywords
- information
- phonetic order
- wake
- voice
- audio
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000001514 detection method Methods 0.000 claims abstract description 17
- 230000002618 waking effect Effects 0.000 claims abstract description 11
- 230000002452 interceptive effect Effects 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000001914 filtration Methods 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
- G06F9/44—Arrangements for executing specific programs
- G06F9/445—Program loading or initiating
- G06F9/44505—Configuring for program initiating, e.g. using registry, configuration files
- G06F9/4451—User profiles; Roaming
-
- 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Computational Linguistics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Telephonic Communication Services (AREA)
Abstract
The present invention relates to smart machine field, more particularly to a kind of voice awakening method and system.Step S100, the voice messaging for receiving user input, extract audio-frequency information；Step S200, wake-up detection is carried out to audio-frequency information, until waking up successfully；Step S300, carry out wake up the match is successful prompting, obtain phonetic order；Step S400, speech recognition is carried out to phonetic order, obtain voice identification result；Step S500, whether effectively judge voice identification result, such as it is effective if perform voice identification result.Present invention has the advantages that：A kind of voice awakening method and system, can make the phonetic order of the more preferable identifying user of smart machine, accurately perform user instruction, improve the experience of user.
Description
Technical field
The present invention relates to smart machine field, more particularly to a kind of voice awakening method and system.
Background technology
With the increasingly raising of people's quality of life, intelligent robot has more and more entered family and has taken
Business industry, this is not only a hi-tech industry for great application prospect, or intelligent robot is current
One important focus of research, and formed a huge market.
At present, by the new interactive mode such as voice typing and identification, intelligent robot is allow directly to lead to
Cross and receive the phonetic order of user and complete the operation of dependent instruction, with voice typing and identification technology
Continue to develop the introducing with high in the clouds voice server, phonetic recognization rate has a very big lifting, but from actual property
Can see, using effect is unsatisfactory, also without full maturity, current intelligent robot refers to technology in reception
During order, because the influence of some surrounding environment, such as noise so that intelligent robot cannot be known
The phonetic order not received, user can only repeatedly send phonetic order, until intelligent robot can
Untill identification, the operation of mistake can be also performed because of identification mistake sometimes, reduce the experience of user
Effect.
The content of the invention
A kind of voice awakening method and system regarding to the issue above.
Specifically technical scheme is：
A kind of voice awakening method, is applied to smart machine, wherein, including：
Step S100, the voice messaging for receiving user input, obtain audio-frequency information；
Step S200, wake-up detection is carried out to the audio-frequency information, until waking up successfully；
Step S300, carry out it is described wake up the match is successful prompting, obtain phonetic order；
Step S400, speech recognition is carried out to the phonetic order, obtain voice identification result；
Step S500, judge institute's speech recognition result whether effectively, such as effectively if perform as described in voice knowledge
Other result.
Preferably, above-mentioned voice awakening method, wherein, in the step S100,
Step S110, the voice messaging to receiving are carried out except treatment of making an uproar；
Step S120, acquisition remove the audio-frequency information after making an uproar.
Preferably, above-mentioned voice awakening method, wherein, in the step S200, including step：
Step S210, prestore wake-up information for waking up the smart machine；
Step S220, the audio-frequency information for obtaining is carried out wake-up and matches with the wake-up information, it is described
Wake up that the match is successful then performs step S300；
Step S230, wake-up matching are unsuccessful, point out to re-enter the voice messaging, repeat institute
State step 210.
Preferably, above-mentioned voice awakening method, wherein, in the step S500, including step：
Step S510, pre-set to the instruction database of store instruction information, set up the command information with
The corresponding relation of execution information；
Step S520, by recognize the phonetic order carried out with the command information in the instruction database
Matching, it is the effective phonetic order that the match is successful；
The effective phonetic order of step S530, basis, obtains the execution information and simultaneously performs.
Preferably, above-mentioned voice awakening method, wherein, in the step S520,
If the phonetic order matches unsuccessful with the command information in the instruction database, point out again
Input phonetic order, and perform the step S400 after the new phonetic order is obtained.
Preferably, system also is waken up including a kind of voice, is applied to smart machine, wherein, including：
Receiving unit, the voice messaging for receiving user input, and further obtain audio-frequency information；
Detection unit, connects the receiving unit, for carrying out wake-up detection to the audio-frequency information, until
Wake up successfully；
Tip element, connects the detection unit, is successfully pointed out for being waken up, and obtain phonetic order；
Recognition unit, connects the Tip element, for carrying out speech recognition to the phonetic order, and obtains
Obtain voice identification result；
Judging unit, connects the recognition unit, and for judging, whether speech recognition result is effective；
Execution unit, connects the judging unit, and the effective phonetic order is judged for performing.
Preferably, above-mentioned voice interactive method, wherein, the receiving unit includes：
Except module of making an uproar, for carrying out the voice messaging for receiving except treatment of making an uproar；
Acquisition module, connection is described except module of making an uproar, and the audio-frequency information after making an uproar is removed for obtaining.
Preferably, above-mentioned voice interactive method, wherein, the detection unit includes：
Memory module, for prestoring the wake-up information for waking up the smart machine；
First matching module, connects the memory module, for the audio-frequency information for obtaining and the wake-up
Information, and wake-up is carried out with the wake-up information to the audio-frequency information match；
Preferably, above-mentioned voice interactive method, wherein, the execution unit also includes：
Library module is built, the instruction database for pre-setting store instruction information is set up the command information and held
The corresponding relation of row information；
Second matching module, connection is described to build library module, for will identification the phonetic order and the finger
The command information in storehouse is made to be matched, it is the effective phonetic order that the match is successful；
Performing module, connects second matching module, for according to the effective phonetic order, obtaining
The execution information is simultaneously performed.
Present invention has the advantages that：A kind of voice awakening method and system, can make smart machine more preferable
The phonetic order of identifying user, accurately performs user instruction, improves the experience of user.
Brief description of the drawings
Fig. 1 is in this preferred embodiment, the main-process stream of method is illustrated in a kind of voice awakening method and system
Figure；
During Fig. 2-4 is this preferred embodiment, on the basis of Fig. 1, a kind of voice awakening method and system
The part schematic flow sheet of middle method；
Fig. 5 is in this preferred embodiment, the general construction of system is illustrated in a kind of voice awakening method and system
Figure；
During Fig. 6-8 is this preferred embodiment, on the basis of Fig. 5, a kind of voice awakening method and system
The part-structure schematic diagram of middle system.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out
Clearly and completely describe, it is clear that described embodiment is only a part of embodiment of the invention, and
It is not all, of embodiment.Based on the embodiment in the present invention, those of ordinary skill in the art are without work
The every other embodiment obtained on the premise of going out creative work, belongs to the scope of protection of the invention.
It should be noted that in the case where not conflicting, the embodiment in the present invention and the spy in embodiment
Levying to be mutually combined.
The invention will be further described with specific embodiment below in conjunction with the accompanying drawings, but not as of the invention
Limit.
As shown in figure 1,
A kind of voice awakening method, is applied to smart machine, wherein, including：
Step S100, the voice messaging for receiving user input, extract audio-frequency information；
Step S200, wake-up detection is carried out to audio-frequency information, until waking up successfully；
Step S300, carry out wake up the match is successful prompting, obtain phonetic order；
Step S400, speech recognition is carried out to phonetic order, obtain voice identification result；
Step S500, whether effectively judge voice identification result, such as it is effective if perform voice identification result.
The present invention is to recognize the instruction for receiving, and execute instruction, wherein smart machine pair by smart machine
In the voice messaging for receiving, it is necessary first to extract audio-frequency information, audio-frequency information is extracted from voice messaging,
It is that may obscure the sound that smart machine is identified to shield be mingled with voice messaging, such as people around
Sound, the sound in broadcast, or some inhuman speech like sounds, it can remove noise to extract audio-frequency information, or
Person obtains audio-frequency information according to human sound frequency range is chosen, or according to the prior art means such as distance, passes through
Audio-frequency information to obtaining improves discrimination of the smart machine to voice messaging；
The audio-frequency information of extraction is carried out into wake-up detection, mainly has smart machine before user sends instruction
Current state is waken up to execution state, is waken up and successfully know the existing current state of equipment and change to performing shape
State, and will change to perform state information pointed out to user, prompting mode can be light dodge
It is bright, can be voice message etc., then smart machine receives the phonetic order that user sends, to voice
Instruction is identified, and whether the instruction of identifying user is the executable phonetic order for pre-setting, and is
No is effective phonetic order, and the phonetic order is performed if effectively.
In present pre-ferred embodiments, as shown in Fig. 2 in step S100,
Step S110, the voice messaging to receiving are carried out except treatment of making an uproar；
Step S120, acquisition remove the audio-frequency information after making an uproar.
The present invention using remove make an uproar by the way of audio-frequency information is obtained from voice messaging so that smart machine can be more
Good is identified to voice messaging.
In present pre-ferred embodiments, as shown in figure 3, in step S200, including step：
Step S210, prestore wake-up information for waking up smart machine；
Step S220, the audio-frequency information of acquisition and wake-up information are carried out into wake-up match, wake up that the match is successful
Then perform step S300；
Step S230, wake-up matching are unsuccessful, point out to re-enter voice messaging, repeat step 210.
In the present invention, wake up smart machine the step of be that early stage first sets up wake-up information, smart machine will pass through
Audio-frequency information after filtering is matched with wake-up information, the match is successful then smart machine entered by current state
Enter execution state, voice signal is otherwise received again.
In present pre-ferred embodiments, as shown in figure 4, in step S500, including step：
Step S510, pre-set to the instruction database of store instruction information, set up command information and perform
The corresponding relation of information；
Step S520, the phonetic order of identification is matched with the command information in instruction database, matched into
Work(is effective phonetic order；
Step S530, according to effective phonetic order, obtain execution information and simultaneously perform.
In advance by command information storage in instruction database, every command information setting up in instruction database with perform letter
The corresponding relation of breath so that after the match is successful for the phonetic order and command information for receiving, smart machine can
Execution information is transferred with by corresponding relation, smart machine is specifically performed the instruction of user.
On the basis of above-mentioned technical proposal, further, in step S520,
If phonetic order matches unsuccessful with the command information in instruction database, point out to re-enter voice and refer to
Order, and perform step S400 after new speech instruction is obtained.
When matching unsuccessful, then user is pointed out to re-enter phonetic order, to reach the purpose of user.
In present pre-ferred embodiments, as shown in figure 5, also including that a kind of voice wakes up system, is applied to
Smart machine, wherein, including：
Receiving unit 1, the voice messaging for receiving user input, and further obtain audio-frequency information；
Detection unit 2, connects receiving unit 1, for carrying out wake-up detection to audio-frequency information, until waking up
Success；
Tip element 3, connecting detection unit 2, successfully points out for being waken up, and obtains phonetic order；
Recognition unit 4, connects Tip element 3, for carrying out speech recognition to phonetic order, and obtains language
Sound recognition result；
Judging unit 5, connects recognition unit 4, for judging whether voice identification result is effective；
Execution unit 6, connection judgment unit 5 judges effective phonetic order for performing.
In the present system, by the association cooperation of said units, voice awakening method is realized, improves intelligence
Recognition efficiency of the equipment to wake-up voice.
In present pre-ferred embodiments, as shown in fig. 6, receiving unit 1 includes：
Except module 101 of making an uproar, for carrying out the voice messaging for receiving except treatment of making an uproar；
Acquisition module 102, connection removes the audio-frequency information after making an uproar except module 101 of making an uproar for obtaining.
In present pre-ferred embodiments, as shown in fig. 7, detection unit 2 includes：
Memory module 201, for prestoring the wake-up information for waking up smart machine；
First matching module 202, connects memory module 201, for the audio-frequency information and the information of wake-up that obtain,
And wake-up is carried out to audio-frequency information and wake-up information match；
In present pre-ferred embodiments, as shown in figure 8, execution unit 6 also includes：
Library module 601 is built, the instruction database for pre-setting store instruction information is set up command information and held
The corresponding relation of row information；
Library module 601 is built in second matching module 602, connection, for the phonetic order and instruction database that will recognize
In command information matched, the match is successful be effective phonetic order；
Performing module 603, connects the second matching module 602, for according to effective phonetic order, obtaining
Execution information is simultaneously performed.
The foregoing is only preferred embodiments of the present invention, not thereby limit embodiments of the present invention and
Protection domain, to those skilled in the art, should can appreciate that all utilization description of the invention
And the equivalent done by diagramatic content and the scheme obtained by obvious change, should include
Within the scope of the present invention.
Claims (9)
1. a kind of voice awakening method, is applied to smart machine, it is characterised in that including：
Step S100, the voice messaging for receiving user input, extract audio-frequency information；
Step S200, wake-up detection is carried out to the audio-frequency information, until waking up successfully；
Step S300, carry out it is described wake up the match is successful prompting, obtain phonetic order；
Step S400, speech recognition is carried out to the phonetic order, obtain voice identification result；
Step S500, judge institute's speech recognition result whether effectively, such as effectively if perform as described in voice knowledge
Other result.
2. voice awakening method according to claim 1, it is characterised in that the step S100
In,
Step S110, the voice messaging to receiving are carried out except treatment of making an uproar；
Step S120, acquisition remove the audio-frequency information after making an uproar.
3. voice interactive method according to claim 1, it is characterised in that the step S200
In, including step：
Step S210, prestore wake-up information for waking up the smart machine；
Step S220, the audio-frequency information for obtaining is carried out wake-up and matches with the wake-up information, it is described
Wake up that the match is successful then performs step S300；
Step S230, wake-up matching are unsuccessful, point out to re-enter the voice messaging, repeat institute
State step 210.
4. voice interactive method according to claim 1, it is characterised in that the step S500
In, including step：
Step S510, pre-set to the instruction database of store instruction information, set up the command information with
The corresponding relation of execution information；
Step S520, by recognize the phonetic order carried out with the command information in the instruction database
Matching, it is the effective phonetic order that the match is successful；
The effective phonetic order of step S530, basis, obtains the execution information and simultaneously performs.
5. voice interactive method according to claim 4, it is characterised in that the step S520
In,
If the phonetic order matches unsuccessful with the command information in the instruction database, point out again
Input phonetic order, and perform the step S400 after the new phonetic order is obtained.
6. a kind of voice wakes up system, is applied to smart machine, it is characterised in that including：
Receiving unit, the voice messaging for receiving user input, onestep extraction audio-frequency information of going forward side by side；
Detection unit, connects the receiving unit, for carrying out wake-up detection to the audio-frequency information, until
Wake up successfully；
Tip element, connects the detection unit, is successfully pointed out for being waken up, and obtain phonetic order；
Recognition unit, connects the Tip element, for carrying out speech recognition to the phonetic order, and obtains
Obtain voice identification result；
Judging unit, connects the recognition unit, and for judging, whether speech recognition result is effective；
Execution unit, connects the judging unit, and the effective phonetic order is judged for performing.
7. voice interactive method according to claim 6, it is characterised in that the receiving unit bag
Include：
Except module of making an uproar, for carrying out the voice messaging for receiving except treatment of making an uproar；
Acquisition module, connection is described except module of making an uproar, and the audio-frequency information after making an uproar is removed for obtaining.
8. voice interactive method according to claim 6, it is characterised in that the detection unit bag
Include：
Memory module, for prestoring the wake-up information for waking up the smart machine；
First matching module, connects the memory module, for the audio-frequency information for obtaining and the wake-up
Information, and wake-up is carried out with the wake-up information to the audio-frequency information match.
9. voice interactive method according to claim 6, it is characterised in that the execution unit is also
Including：
Library module is built, the instruction database for pre-setting store instruction information is set up the command information and held
The corresponding relation of row information；
Second matching module, connection is described to build library module, for will identification the phonetic order and the finger
The command information in storehouse is made to be matched, it is the effective phonetic order that the match is successful；
Performing module, connects second matching module, for according to the effective phonetic order, obtaining
The execution information is simultaneously performed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510944213.4A CN106887227A (en) | 2015-12-16 | 2015-12-16 | A kind of voice awakening method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510944213.4A CN106887227A (en) | 2015-12-16 | 2015-12-16 | A kind of voice awakening method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106887227A true CN106887227A (en) | 2017-06-23 |
Family
ID=59175344
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510944213.4A Pending CN106887227A (en) | 2015-12-16 | 2015-12-16 | A kind of voice awakening method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106887227A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108735210A (en) * | 2018-05-08 | 2018-11-02 | 宇龙计算机通信科技(深圳)有限公司 | A kind of sound control method and terminal |
| CN109812575A (en) * | 2019-01-31 | 2019-05-28 | 吉林微思智能科技有限公司 | Knob automobile shift system and voice with speech recognition wake up recognition methods |
| CN110390933A (en) * | 2018-04-20 | 2019-10-29 | 比亚迪股份有限公司 | State methods of exhibiting, device and the displaying vehicle system of vehicle intelligent voice system |
| CN110428825A (en) * | 2018-05-01 | 2019-11-08 | 国际商业机器公司 | Ignore the trigger word in streaming media contents |
| CN110800045A (en) * | 2017-10-24 | 2020-02-14 | 北京嘀嘀无限科技发展有限公司 | System and method for uninterrupted application wakeup and speech recognition |
| TWI692751B (en) * | 2017-06-29 | 2020-05-01 | 香港商阿里巴巴集團服務有限公司 | Voice wake-up method, device and electronic equipment |
| WO2020114213A1 (en) * | 2018-12-03 | 2020-06-11 | 华为技术有限公司 | Voice user interface display method and conference terminal |
| CN112416845A (en) * | 2020-11-05 | 2021-02-26 | 南京创维信息技术研究院有限公司 | Calculator implementation method and device based on voice recognition, intelligent terminal and medium |
| CN112951234A (en) * | 2021-03-31 | 2021-06-11 | 国网江苏省电力有限公司营销服务中心 | Load identification intelligent control method, system and device based on voice interaction |
| CN113808587A (en) * | 2021-11-17 | 2021-12-17 | 南京隆远电气技术有限公司 | Voice instruction autonomous recognition algorithm |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102932595A (en) * | 2012-10-22 | 2013-02-13 | 北京小米科技有限责任公司 | Method and device for sound-control photographing and terminal |
| CN103943105A (en) * | 2014-04-18 | 2014-07-23 | 安徽科大讯飞信息科技股份有限公司 | Voice interaction method and system |
| CN104469530A (en) * | 2014-11-28 | 2015-03-25 | 四川长虹电器股份有限公司 | Method for setting menus in smart television based on voice control |
| CN104464723A (en) * | 2014-12-16 | 2015-03-25 | 科大讯飞股份有限公司 | Voice interaction method and system |
| CN105139851A (en) * | 2015-09-17 | 2015-12-09 | 努比亚技术有限公司 | Desktop application icon organization mobile terminal and method |
-
2015
- 2015-12-16 CN CN201510944213.4A patent/CN106887227A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102932595A (en) * | 2012-10-22 | 2013-02-13 | 北京小米科技有限责任公司 | Method and device for sound-control photographing and terminal |
| CN103943105A (en) * | 2014-04-18 | 2014-07-23 | 安徽科大讯飞信息科技股份有限公司 | Voice interaction method and system |
| CN104469530A (en) * | 2014-11-28 | 2015-03-25 | 四川长虹电器股份有限公司 | Method for setting menus in smart television based on voice control |
| CN104464723A (en) * | 2014-12-16 | 2015-03-25 | 科大讯飞股份有限公司 | Voice interaction method and system |
| CN105139851A (en) * | 2015-09-17 | 2015-12-09 | 努比亚技术有限公司 | Desktop application icon organization mobile terminal and method |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI692751B (en) * | 2017-06-29 | 2020-05-01 | 香港商阿里巴巴集團服務有限公司 | Voice wake-up method, device and electronic equipment |
| CN110800045A (en) * | 2017-10-24 | 2020-02-14 | 北京嘀嘀无限科技发展有限公司 | System and method for uninterrupted application wakeup and speech recognition |
| CN110390933A (en) * | 2018-04-20 | 2019-10-29 | 比亚迪股份有限公司 | State methods of exhibiting, device and the displaying vehicle system of vehicle intelligent voice system |
| CN110428825A (en) * | 2018-05-01 | 2019-11-08 | 国际商业机器公司 | Ignore the trigger word in streaming media contents |
| CN108735210A (en) * | 2018-05-08 | 2018-11-02 | 宇龙计算机通信科技(深圳)有限公司 | A kind of sound control method and terminal |
| WO2020114213A1 (en) * | 2018-12-03 | 2020-06-11 | 华为技术有限公司 | Voice user interface display method and conference terminal |
| CN109812575A (en) * | 2019-01-31 | 2019-05-28 | 吉林微思智能科技有限公司 | Knob automobile shift system and voice with speech recognition wake up recognition methods |
| CN112416845A (en) * | 2020-11-05 | 2021-02-26 | 南京创维信息技术研究院有限公司 | Calculator implementation method and device based on voice recognition, intelligent terminal and medium |
| CN112951234A (en) * | 2021-03-31 | 2021-06-11 | 国网江苏省电力有限公司营销服务中心 | Load identification intelligent control method, system and device based on voice interaction |
| CN113808587A (en) * | 2021-11-17 | 2021-12-17 | 南京隆远电气技术有限公司 | Voice instruction autonomous recognition algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106887227A (en) | A kind of voice awakening method and system | |
| CN107665708B (en) | Intelligent voice interaction method and system | |
| WO2018059405A1 (en) | Voice control system, wakeup method and wakeup apparatus therefor, electrical appliance and co-processor | |
| CN106653021A (en) | Voice wake-up control method and device and terminal | |
| CN105006230A (en) | Voice sensitive information detecting and filtering method based on unspecified people | |
| CN105632486A (en) | Voice wake-up method and device of intelligent hardware | |
| CN109767769A (en) | Voice recognition method and device, storage medium and air conditioner | |
| CN103714815A (en) | Voice control method and device thereof | |
| CN104217152A (en) | Implementation method and device for mobile terminal to enter application program under stand-by state | |
| CN102932212A (en) | Intelligent household control system based on multichannel interaction manner | |
| CN102298694A (en) | Man-machine interaction identification system applied to remote information service | |
| CN106502649A (en) | A kind of robot service awakening method and device | |
| CN102413100A (en) | Voice-print authentication system having voice-print password picture prompting function and realization method thereof | |
| CN105261356A (en) | Voice recognition system and method | |
| CN108074571A (en) | Sound control method, system and the storage medium of augmented reality equipment | |
| CN106448654A (en) | Robot speech recognition system and working method thereof | |
| CN110570873A (en) | voiceprint wake-up method and device, computer equipment and storage medium | |
| CN104538034A (en) | Voice recognition method and system | |
| CN103106061A (en) | Voice input method and device | |
| CN105869639A (en) | Voice recognition method and system | |
| CN105744368A (en) | Method for television account-based user management by employing voiceprint recognition technology | |
| CN106709804A (en) | Interactive wealth planning consulting robot system | |
| CN107731226A (en) | Control method, device and electronic equipment based on speech recognition | |
| CN105869622B (en) | Chinese hot word detection method and device | |
| CN112499016A (en) | Garbage recycling method and device of intelligent garbage can and intelligent garbage can |
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: 20170623 |