CN108831483A - A kind of artificial intelligent voice identifying system - Google Patents
A kind of artificial intelligent voice identifying system Download PDFInfo
- Publication number
- CN108831483A CN108831483A CN201811040006.6A CN201811040006A CN108831483A CN 108831483 A CN108831483 A CN 108831483A CN 201811040006 A CN201811040006 A CN 201811040006A CN 108831483 A CN108831483 A CN 108831483A
- Authority
- CN
- China
- Prior art keywords
- voice
- module
- acquisition
- microphone
- sound source
- 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.)
- Withdrawn
Links
- 230000004807 localization Effects 0.000 claims abstract description 11
- 238000001514 detection method Methods 0.000 claims abstract description 5
- 238000000034 method Methods 0.000 claims description 8
- 230000002708 enhancing effect Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 230000003313 weakening effect Effects 0.000 claims description 4
- 238000010408 sweeping Methods 0.000 abstract description 8
- 230000004913 activation Effects 0.000 abstract description 2
- 239000000284 extract Substances 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000002360 preparation method 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
- G10L15/26—Speech to text systems
-
- 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
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Manipulator (AREA)
Abstract
The invention discloses a kind of artificial intelligent voice identifying system, terminal wake-up module obtains the voice messaging of acquisition and is marked；Auditory localization module calculates sound source position according to the position coordinates harmony phonometer of microphone；Voice collecting locating module relative to the relative position coordinates of robot terminal and obtains Sounnd source direction according to sound source position Coordinate generation sound source；The order voice that the storage of second voice acquisition device obtains；Command recognition module output detection signal.The present invention allows sweeping robot to reach designated place by phonetic order, system is intelligently convenient, provides more conveniences for house life by the first keyword activation system of identification, and by identifying that the second keyword issues an order to sweeping robot.
Description
Technical field
The invention belongs to field of artificial intelligence more particularly to a kind of artificial intelligent voice identifying systems.
Background technique
Intelligent sweeping robot also known as sweeps machine, intelligent dust suction, robot cleaner etc. automatically, is controlling intelligent household appliances
One kind, can rely on certain artificial intelligence, automatically in the room complete floor cleaning work.It is general to be swept and vacuum side using brush
Ground sundries is first received the rubbish storage box into itself, to complete the function of land clearing by formula.It in general, will be complete
At cleaning, dust suction, wiping the robot that works, it is also uniformly classified as intelligent sweeping robot.
Summary of the invention
It is an object of the invention to overcome problem above of the existing technology, a kind of artificial intelligent voice identification system is provided
System.
To realize above-mentioned technical purpose and the technique effect, the invention is realized by the following technical scheme：
A kind of artificial intelligent voice identifying system, including terminal wake-up module, auditory localization module, the first voice acquisition device,
Second voice acquisition device, voice collecting locating module and command recognition module；
First voice acquisition device includes multiple microphones being set in room, and microphone acquires acoustic information, and will
Acoustic information is transmitted to terminal wake-up module；
Whether the terminal wake-up module obtains the voice messaging of acquisition and judges in voice messaging to include the first Key word voice,
If the acoustic information of first Key word voice is marked in terminal wake-up module comprising the first Key word voice；
The auditory localization module calculates sound source position according to the position coordinates harmony phonometer of microphone；
Relative position of the voice collecting locating module according to sound source position Coordinate generation sound source relative to robot terminal is sat
It marks and obtains Sounnd source direction；
Second voice acquisition device carries out the sound of Sounnd source direction by adjusting the delay compensation weight of Beam-former
Enhancing processing, and weakening process is carried out to the sound of non-Sounnd source direction, and store the order voice of acquisition；
Whether the command recognition module obtains the order voice of acquisition and judges in order voice to include the second Key word voice,
If comprising the second Key word voice, output detection signal.
Further, the microphone is put to form acquisition array according to room location, and microphone position is stored in system
Position coordinates in the array.
Further, with time of origin stamp, intensity of sound and the reception voice messaging in the voice messaging
Microphone apparatus sequence number.
Further, each second keyword is associated with a position coordinates.
The beneficial effects of the invention are as follows：
The invention discloses a kind of artificial intelligent voice identifying systems, by identifying the first keyword activation system, and pass through knowledge
Other second keyword issues an order to sweeping robot, and sweeping robot is allowed to reach designated place by phonetic order,
System is intelligently convenient, provides more conveniences for house life.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings：
Fig. 1 is system structure diagram of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained all other under the premise of creative work at no work
Embodiment shall fall within the protection scope of the present invention.
A kind of sweeping robot control system based on speech recognition, including robot localization control system and speech recognition
System, wherein speech recognition system includes terminal wake-up module, auditory localization module, the first voice acquisition device, the second voice
Acquisition device, voice collecting locating module and command recognition module, robot localization control system include microcontroller end, section rule
Draw module, terminal positioning module and position data collecting module；
First voice acquisition device includes multiple microphones being set in room, and microphone acquires acoustic information, and will
Acoustic information is transmitted to terminal wake-up module；
Preferably, the microphone is put to form acquisition array according to room location, and microphone is stored in system positioned at described
Position coordinates in array；
Whether terminal wake-up module obtains the voice messaging of acquisition and judges comprising the first Key word voice in voice messaging, if packet
Containing the first Key word voice, the acoustic information of first Key word voice is marked in terminal wake-up module；
Wherein, the microphone with time of origin stamp, intensity of sound and the reception voice messaging in the voice messaging is set
Standby sequence number；
The auditory localization module calculates sound source position according to the position coordinates harmony phonometer of microphone；
The terminal positioning module includes multiple bluetooth acquisition devices and the bluetooth sending device that is installed on robot terminal, blue
Tooth sending device externally sends broadcasting packet, and bluetooth acquisition device identifies sending device physical address after receiving broadcasting packet, and
Storage identifies successful broadcasting packet；
Preferably, with time of origin stamp, message intensity and the equipment sequence for receiving the broadcasting packet in the broadcasting packet
Row number；
Preferably, multiple bluetooth acquisition devices are put to form acquisition array according to room location, and bluetooth acquisition is stored in system
Device is located at the position coordinates in the array；
Position coordinates and message Strength co-mputation robot terminal position of the position data collecting module according to bluetooth acquisition device；
Relative position of the voice collecting locating module according to sound source position Coordinate generation sound source relative to robot terminal is sat
It marks and obtains Sounnd source direction；
The microcontroller end is used to adjust the direction of robot terminal and controls robot and travels to target position, the microcontroller
End includes signal receiving unit, two wheel guide robot driving unit；
The signal receiving unit sends corresponding signal to motor after obtaining starting, Stop message, and signal receiving unit is according to sound
Source generates the angle of deviation of the current sound source relative to the current direction of robot relative to the relative position coordinates of robot terminal, and will
Deviation angle information is sent to two wheel guide robot driving unit；
The two wheel guide robot driving unit is for controlling robot terminal steering, and robot terminal left and right wheels are by two motor controls
System, two wheel guide robot driving unit control robot terminal by control motor speed difference and turn to；
Second voice acquisition device carries out the sound of Sounnd source direction by adjusting the delay compensation weight of Beam-former
Enhancing processing, and weakening process is carried out to the sound of non-Sounnd source direction, and store the order voice of acquisition；
Whether the command recognition module obtains the order voice of acquisition and judges in order voice to include the second Key word voice,
If comprising the second Key word voice, output detection signal；
Preferably, each second keyword is associated with a position coordinates, and the second keyword includes but are not limited to bedroom, kitchen
Room, toilet；
Route planning module generates travelling route according to robot terminal current location and target position, and travelling route is sent
To microcontroller end；
Preferably, it extracts and the associated position coordinates of the second Key word voice and is generated as target position.
A kind of sweeping robot control method based on speech recognition, this method comprises the following steps：
S1-1, microphone acquire acoustic information, and acoustic information are transmitted to terminal wake-up module；
S1-2, terminal wake-up module obtain the voice messaging of acquisition, and by the voice messaging and preset first key column
The first Key word voice in table is matched, if successful match, is determined to contain the first Key word voice, be closed to described first
The acoustic information of key word voice is marked, and otherwise, ignores the acoustic information；
S1-3, auditory localization module extract the equipment Serial Number for sending the microphone of the acoustic information, and according to equipment sequence
Number matching position coordinate, auditory localization module searches the acoustic information that one or more similar in time of origin is labeled, and mentions
The intensity of sound having in the position coordinates and the acoustic information for the microphone for sending the acoustic information is taken, according to microphone
Position coordinates harmony phonometer calculate sound source position；
S1-4, voice collecting locating module are sat the relative position according to sound source position Coordinate generation sound source relative to robot terminal
It marks and obtains Sounnd source direction；
Coordinate calculates sound source to the space length between robot terminal depending on the relative position for S1-5, the second voice acquisition device,
And the space length is obtained into the propagation of arrival robot terminal after sound source sounding divided by the aerial spread speed of sound
Time, and according to propagation time calculation delay compensate weight, the second voice acquisition device by adjusting Beam-former time delay
Compensation weight carries out enhancing processing to the sound of Sounnd source direction, and carries out weakening process to the sound of non-Sounnd source direction, and store
The order voice of acquisition；
S1-6, command recognition module obtain the order voice of acquisition and by the order voices and preset second Keyword List
In the second Key word voice matched, if successful match, determine contain the second Key word voice, and export detection letter
Number；
S2-1, bluetooth sending device externally send broadcasting packet, and bluetooth acquisition device identifies sending device after receiving broadcasting packet
Physical address, and store the successful broadcasting packet of identification；
S2-2, position data collecting module extract the equipment Serial Number for sending the microphone of the acoustic information, and according to equipment
Sequence numbers match position coordinates, and the broadcasting packet of the storage of one or more similar in time of origin is searched, it extracts described in sending
The message intensity being had in the position coordinates and the broadcasting packet of the bluetooth acquisition device of broadcasting packet, position data collecting mould
Position coordinates and message Strength co-mputation robot terminal position of the root tuber according to bluetooth acquisition device；
S2-3, signal receiving unit generate the angle of deviation of the current sound source relative to the current direction of robot according to Sounnd source direction, and
Deviation angle information is sent to two wheel guide robot driving unit；
S2-4, two wheel guide robot driving unit control robot terminal by control motor speed difference and turn to；
S2-5, the extraction of route planning module and the associated position coordinates of the second Key word voice are simultaneously generated as target position, and root
Travelling route is generated according to robot terminal current location and target position, and travelling route is sent to microcontroller end；
S2-6, signal receiving unit send enabling signal to motor after obtaining travelling route, and signal receiving unit receives present bit
It sets after coordinate falls into target position domain and closes motor；
Preferably, the target position domain is using target position as the center of circle, and radius is the circle of 1-2m.
In the description of this specification, the description of reference term " one embodiment ", " example ", " specific example " etc. means
Particular features, structures, materials, or characteristics described in conjunction with this embodiment or example are contained at least one implementation of the invention
In example or example.In the present specification, schematic expression of the above terms may not refer to the same embodiment or example.
Moreover, particular features, structures, materials, or characteristics described can be in any one or more of the embodiments or examples to close
Suitable mode combines.
The basic principles, main features and advantages of the present invention have been shown and described above.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this
The principle of invention, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these changes
Change and improvement all fall within the protetion scope of the claimed invention.
Claims (4)
1. a kind of artificial intelligent voice identifying system, which is characterized in that including terminal wake-up module, auditory localization module, first
Voice acquisition device, the second voice acquisition device, voice collecting locating module and command recognition module；
First voice acquisition device includes multiple microphones being set in room, and microphone acquires acoustic information, and will
Acoustic information is transmitted to terminal wake-up module；
Whether the terminal wake-up module obtains the voice messaging of acquisition and judges in voice messaging to include the first Key word voice,
If the acoustic information of first Key word voice is marked in terminal wake-up module comprising the first Key word voice；
The auditory localization module calculates sound source position according to the position coordinates harmony phonometer of microphone；
Relative position of the voice collecting locating module according to sound source position Coordinate generation sound source relative to robot terminal is sat
It marks and obtains Sounnd source direction；
Second voice acquisition device carries out the sound of Sounnd source direction by adjusting the delay compensation weight of Beam-former
Enhancing processing, and weakening process is carried out to the sound of non-Sounnd source direction, and store the order voice of acquisition；
Whether the command recognition module obtains the order voice of acquisition and judges in order voice to include the second Key word voice,
If comprising the second Key word voice, output detection signal.
2. a kind of artificial intelligent voice identifying system according to claim 1, it is characterised in that：The microphone is according to room
Between position put to form acquisition array, the position coordinates that microphone is located in the array are stored in system.
3. a kind of artificial intelligent voice identifying system according to claim 1, it is characterised in that：Band in the voice messaging
There are time of origin stamp, intensity of sound and the microphone apparatus sequence number for receiving the voice messaging.
4. a kind of artificial intelligent voice identifying system according to claim 1, it is characterised in that：Each described second is crucial
Word is associated with a position coordinates.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811040006.6A CN108831483A (en) | 2018-09-07 | 2018-09-07 | A kind of artificial intelligent voice identifying system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811040006.6A CN108831483A (en) | 2018-09-07 | 2018-09-07 | A kind of artificial intelligent voice identifying system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108831483A true CN108831483A (en) | 2018-11-16 |
Family
ID=64149633
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811040006.6A Withdrawn CN108831483A (en) | 2018-09-07 | 2018-09-07 | A kind of artificial intelligent voice identifying system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108831483A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109994114A (en) * | 2019-04-09 | 2019-07-09 | 昆山古鳌电子机械有限公司 | A kind of intelligence control system |
| CN110335313A (en) * | 2019-06-17 | 2019-10-15 | 腾讯科技（深圳）有限公司 | Audio collecting device localization method and device, method for distinguishing speek person and system |
| CN110970049A (en) * | 2019-12-06 | 2020-04-07 | 广州国音智能科技有限公司 | Multi-person voice recognition method, device, equipment and readable storage medium |
| CN111179938A (en) * | 2019-12-26 | 2020-05-19 | 安徽仁昊智能科技有限公司 | Speech recognition garbage classification system based on artificial intelligence |
| CN111477232A (en) * | 2020-04-03 | 2020-07-31 | 江苏安全技术职业学院 | Artificial intelligence identification system based on computer |
| WO2020228270A1 (en) * | 2019-05-10 | 2020-11-19 | 平安科技（深圳）有限公司 | Speech processing method and device, computer device and storage medium |
| CN114468898A (en) * | 2019-04-03 | 2022-05-13 | 北京石头创新科技有限公司 | Robot voice control method, device, robot and medium |
| CN114994604A (en) * | 2022-04-21 | 2022-09-02 | 深圳市倍思科技有限公司 | Human-computer interaction position determining method and device, robot and storage medium |
| WO2024000853A1 (en) * | 2022-06-28 | 2024-01-04 | 歌尔科技有限公司 | Wearable device control method and apparatus, terminal device, and storage medium |
| CN118522285A (en) * | 2024-07-25 | 2024-08-20 | 辽宁汉华信息工程有限公司 | Interactive user voice recognition method for AI intelligent agent |
-
2018
- 2018-09-07 CN CN201811040006.6A patent/CN108831483A/en not_active Withdrawn
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114468898A (en) * | 2019-04-03 | 2022-05-13 | 北京石头创新科技有限公司 | Robot voice control method, device, robot and medium |
| CN109994114A (en) * | 2019-04-09 | 2019-07-09 | 昆山古鳌电子机械有限公司 | A kind of intelligence control system |
| CN109994114B (en) * | 2019-04-09 | 2021-07-23 | 昆山古鳌电子机械有限公司 | Intelligent control system |
| WO2020228270A1 (en) * | 2019-05-10 | 2020-11-19 | 平安科技（深圳）有限公司 | Speech processing method and device, computer device and storage medium |
| CN110335313B (en) * | 2019-06-17 | 2022-12-09 | 腾讯科技（深圳）有限公司 | Audio acquisition equipment positioning method and device and speaker identification method and system |
| CN110335313A (en) * | 2019-06-17 | 2019-10-15 | 腾讯科技（深圳）有限公司 | Audio collecting device localization method and device, method for distinguishing speek person and system |
| CN110970049A (en) * | 2019-12-06 | 2020-04-07 | 广州国音智能科技有限公司 | Multi-person voice recognition method, device, equipment and readable storage medium |
| CN111179938A (en) * | 2019-12-26 | 2020-05-19 | 安徽仁昊智能科技有限公司 | Speech recognition garbage classification system based on artificial intelligence |
| CN111477232A (en) * | 2020-04-03 | 2020-07-31 | 江苏安全技术职业学院 | Artificial intelligence identification system based on computer |
| CN114994604A (en) * | 2022-04-21 | 2022-09-02 | 深圳市倍思科技有限公司 | Human-computer interaction position determining method and device, robot and storage medium |
| WO2024000853A1 (en) * | 2022-06-28 | 2024-01-04 | 歌尔科技有限公司 | Wearable device control method and apparatus, terminal device, and storage medium |
| CN118522285A (en) * | 2024-07-25 | 2024-08-20 | 辽宁汉华信息工程有限公司 | Interactive user voice recognition method for AI intelligent agent |
| CN118522285B (en) * | 2024-07-25 | 2024-09-24 | 辽宁汉华信息工程有限公司 | Interactive user voice recognition method for AI intelligent agent |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108831483A (en) | A kind of artificial intelligent voice identifying system | |
| CN109272998A (en) | A kind of artificial intelligent voice detection and control method | |
| CN108814449A (en) | A kind of artificial intelligence sweeping robot control method based on phonetic order | |
| CN108968828A (en) | A kind of artificial intelligence sweeping robot control system | |
| WO2020076510A3 (en) | Localized data mapping for indoor and outdoor applications | |
| CN109571499A (en) | A kind of intelligent navigation leads robot and its implementation | |
| US6684176B2 (en) | Three dimensional (3-D) object locator system for items or sites using an intuitive sound beacon: system and method of operation | |
| CN101816615B (en) | Blind guiding system | |
| WO2018228203A1 (en) | Human and machine intelligence cooperation-based robot system having sweeping function | |
| CN207397097U (en) | City river sewage draining exit inspection system | |
| ATE281245T1 (en) | MEDIA CHANGE DEVICE AND METHOD IN A COATING MEDIA SPRAYING SYSTEM | |
| CA2270326A1 (en) | A method of and a device for speech recognition employing neural network and markov model recognition techniques | |
| CN107328426A (en) | A kind of indoor positioning air navigation aid and system suitable for people with visual impairment | |
| CN106301566B (en) | A kind of positioning system based on light and the method and device positioned using mobile terminal | |
| CN106780926A (en) | Control of bluetooth access system and management method | |
| CN107437419A (en) | A kind of method, instruction set and the system of the movement of Voice command service robot | |
| GB2418600A (en) | Bagless vacuum cleaner system | |
| CN102981148A (en) | Positioning system and method thereof | |
| CN108910355A (en) | A kind of intelligent garbage recyclable device and control method | |
| CN104333906A (en) | Positioning system and method based on indoor wireless signal | |
| CN107863106A (en) | Voice identification control method and device | |
| CN105163382A (en) | Indoor region location optimization method and system | |
| CN107045308A (en) | Intelligent interaction service robot | |
| CN105783908A (en) | Navigation method, device, user terminal, server, and navigation computing device | |
| CN105898635A (en) | Pickup device for outdoor long-distance use |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181116 |