CN113040660A - Floor sweeping robot - Google Patents
Floor sweeping robot Download PDFInfo
- Publication number
- CN113040660A CN113040660A CN202110368843.7A CN202110368843A CN113040660A CN 113040660 A CN113040660 A CN 113040660A CN 202110368843 A CN202110368843 A CN 202110368843A CN 113040660 A CN113040660 A CN 113040660A
- Authority
- CN
- China
- Prior art keywords
- noise
- signal
- sweeping robot
- microphone
- sweeping
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000010408 sweeping Methods 0.000 title claims abstract description 134
- 238000012545 processing Methods 0.000 claims abstract description 35
- 238000004891 communication Methods 0.000 claims abstract description 15
- 230000009467 reduction Effects 0.000 claims description 43
- 230000006870 function Effects 0.000 claims description 14
- 238000012546 transfer Methods 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 230000002093 peripheral effect Effects 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 19
- 239000000428 dust Substances 0.000 description 10
- 238000000034 method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000007246 mechanism Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000012535 impurity Substances 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
- A47L11/24—Floor-sweeping machines, motor-driven
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
- A47L11/40—Parts or details of machines not provided for in groups A47L11/02 - A47L11/38, or not restricted to one of these groups, e.g. handles, arrangements of switches, skirts, buffers, levers
- A47L11/4002—Installations of electric equipment
-
- 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
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L2201/00—Robotic cleaning machines, i.e. with automatic control of the travelling movement or the cleaning operation
-
- 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 application provides a robot of sweeping floor. This application sets up the pickup microphone on the casing of robot of sweeping the floor, sets up corresponding noise processing unit in the robot of sweeping the floor, from this through noise processing unit according to the current work noise signal of robot of sweeping the floor to the signal that pickup microphone gathered fall the noise processing, extract clear user speech signal. Therefore, the sweeping robot can be connected to the server through the wireless communication unit, the voice of a user can be flexibly and accurately recognized by the server, and the sweeping robot is driven to accurately execute corresponding instruction operation. The problem of current robot voice command discernment difficulty, the degree of accuracy of sweeping the floor can be overcome in this application, and the interoperation flexibility is poor, influences work efficiency.
Description
Technical Field
The application relates to the field of intelligent household appliances, in particular to a floor sweeping robot.
Background
The floor sweeping robot can automatically clean the ground, and brings convenience for household cleaning. With the development of natural language processing technology, floor sweeping robots with voice control functions are gradually emerging. The sweeping robot with the voice control function can automatically recognize a voice command spoken by a user and then respond to the recognition result of the voice command to execute corresponding operation.
However, the sweeping robot generates significant noise when operating. The user voice is annihilated in the working noise of the machine and the external environment noise, so that the signal-to-noise ratio of the voice is extremely low, the accuracy of voice recognition is seriously influenced, and even the voice instruction cannot be recognized frequently. When the existing sweeping robot executes a voice instruction, the interaction experience is poor, and the interactive instruction is extremely limited, so that the working efficiency is poor.
Disclosure of Invention
The utility model provides a robot of sweeping floor to prior art's not enough, this application weakens the noise signal by synchronous collection in the speech signal collection process through the technique of making an uproar of falling to resume user speech signal in order to improve follow-up speech recognition's the degree of accuracy. The technical scheme is specifically adopted in the application.
First, in order to achieve the above object, a sweeping robot is provided, which includes: the sound pickup microphone is arranged on a shell of the sweeping robot; the noise processing unit is used for determining a working noise signal of the sweeping robot at the position of the pickup microphone and carrying out noise reduction processing on a collected signal of the pickup microphone according to the working noise signal so as to extract a user voice signal; and the wireless communication unit is connected with the noise processing unit and is used for uploading the user voice signal to a server and receiving a first control instruction which is returned by the server and matched with the user voice signal, so that the sweeping robot executes the first control instruction.
Optionally, the sweeping robot is provided with a sound collecting microphone, wherein the sound collecting microphone is arranged on an upper surface or a side surface of the housing; the pickup microphone is an omnidirectional microphone or a directional microphone, wherein the pickup direction of the directional microphone faces the upper side or the lateral side of the shell.
Optionally, the sweeping robot as described in any of the above, wherein the noise processing unit includes: the working condition signal interface is used for acquiring a working condition signal of the sweeping robot; the noise analysis module is used for determining the working noise signal according to the working condition signal; and the noise reduction module is used for carrying out noise cancellation processing on the collected signals of the pickup microphone according to the working noise signals to extract the user voice signals.
Optionally, the sweeping robot as described in any of the above, wherein the operating condition signal includes any one or a combination of the following: the sweeping robot comprises a rotating speed signal of a motor inside the sweeping robot, a gear signal of the sweeping robot, a power signal of the sweeping robot and a current signal of the sweeping robot.
Optionally, the sweeping robot as described in any of the above, wherein the noise processing unit includes: the noise-picking microphone is arranged in a preset noise-picking area inside the shell; the noise analysis module is used for determining the working noise signal according to the collected signal of the noise pickup microphone; and the noise reduction module is used for carrying out noise cancellation processing on the collected signals of the pickup microphone according to the working noise signals to extract the user voice signals.
Optionally, the sweeping robot as described in any of the above, wherein the preset noise picking area includes any one or a combination of the following: the sweeping robot comprises a central area on a chassis of the sweeping robot, a peripheral area of a motor inside the sweeping robot and an air channel structure of the sweeping robot.
Optionally, the sweeping robot as described in any of the above, wherein the air duct structure includes an active noise reduction system, and the noise pickup microphone is a reference microphone in the active noise reduction system; the noise analysis module is used for determining the working noise signal according to the collected signal of the noise-picking microphone and a predetermined sound field transfer function; the sound field transfer function is a transfer function corresponding to a sound field transmission path between the position of the reference microphone and the position of the pickup microphone.
Optionally, the sweeping robot is configured to move the reference microphone to a position corresponding to the suction cavity of the air duct structure; the active noise reduction system further comprises: the signal processing unit is used for determining a noise reduction signal according to the collected signal of the noise pickup microphone; a speaker disposed in the outflow cavity of the air duct structure for outputting noise reduction sound waves in response to the noise reduction signal.
Optionally, the sweeping robot as described in any of the above, further comprising: the voice recognition unit is connected with the noise processing unit and used for determining a second control instruction matched with the user voice signal based on the user voice signal so as to enable the sweeping robot to execute the second control instruction; and storing the mapping of the user speech signal and the first control instruction locally.
Optionally, the sweeping robot as described in any of the above, wherein the voice recognition unit includes: a language module for determining prior text sequence information based on the user speech signal; and the acoustic module is used for determining the second control instruction or the first control instruction based on the prior voice signal corresponding to the prior character sequence information and the user voice signal.
Advantageous effects
This application sets up the pickup microphone on the casing of robot of sweeping the floor, sets up corresponding noise processing unit in the robot of sweeping the floor, from this through noise processing unit according to the current work noise signal of robot of sweeping the floor to the signal that pickup microphone gathered fall the noise processing, extract clear user speech signal. Therefore, the sweeping robot can be connected to the server through the wireless communication unit, the voice of a user can be flexibly and accurately recognized by the server, and the sweeping robot is driven to accurately execute corresponding instruction operation. The problem of current robot voice command discernment difficulty, the degree of accuracy of sweeping the floor can be overcome in this application, and the interoperation flexibility is poor, influences work efficiency.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the application.
Drawings
The accompanying drawings are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application and not limit the application. In the drawings:
fig. 1 is a schematic side view of a sweeping robot according to the present application in an operating state;
fig. 2 is a bottom view of the sweeping robot of the present application;
fig. 3 is a perspective view of a bottom structure of the sweeping robot in the present application;
FIG. 4 is a schematic view of the air duct structure of FIG. 2 in phantom;
fig. 5 is a schematic view of another air duct structure adopted by the sweeping robot of the present application;
fig. 6 is a block diagram of an apparatus of a sweeping robot according to an embodiment of the present application.
In the drawings, 11 denotes a housing; 12 denotes an air duct structure; 121 denotes a dust suction port; 122 denotes an air outlet; and 20 denotes a sound pickup microphone.
Detailed Description
In order to make the purpose and technical solutions of the embodiments of the present application clearer, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings of the embodiments of the present application. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the application without any inventive step, are within the scope of protection of the application.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The meaning of "and/or" as used herein is intended to include both the individual components or both.
The meaning of "inside and outside" in the application means that the direction from the surface of the shell to the internal air duct structure is inside, and vice versa, relative to the sweeping robot per se; and not as a specific limitation on the mechanism of the device of the present application.
The term "connected" as used herein may mean either a direct connection between components or an indirect connection between components via other components.
The meaning of "up and down" in this application means that when the user is facing the forward direction of the sweeping robot, the direction from the dust suction port to the top of the housing is up, otherwise, the direction is down, and the device mechanism is not specifically limited.
Fig. 1 is a sweeping robot according to the present application, which drives a fan to rotate at a high speed through an internal motor, generates an air flow in the air duct structure 12 in fig. 2 or 3, sucks dust and impurities near the dust suction port 121 of the air duct structure 12 into the air duct, filters the dust and impurities through a filter screen, and collects solid particles through a dust box, so as to discharge clean air from the air outlet 122 of the air duct structure 12.
When the sweeping robot runs, the rotating mechanism runs at a high speed, broadband wind noise caused by airflow and vibration generated by the airframe structure under the action of the airflow are generated, so that the overall working noise of the sweeping robot is higher. Therefore, the pickup microphone arranged on the sweeping robot as the front end of the voice recognition system can inevitably collect strong working noise while collecting the voice signal of the user. When the noise component is more, the signal-to-noise ratio of the signal collected by the pickup microphone is too low, which will affect the accurate recognition of the user voice.
As shown in fig. 6, in the robot sweeping control system of the present application, a noise processing unit and a wireless communication unit are further disposed and connected to each other, and the wireless communication unit may be in communication connection with a server through a home network. Therefore, the sweeping robot can determine a working noise signal corresponding to the position of the pickup microphone through the noise processing unit, and perform noise reduction processing on the collected signal of the pickup microphone according to the working noise signal to extract a user voice signal, so that the user voice signal is uploaded to the server through the wireless communication unit, and after the server end completes recognition of the user voice signal, the sweeping robot receives a first control instruction matched with the user voice signal and returned by the server, and then correspondingly executes the first control instruction.
First stage, the process of making an uproar falls in the pronunciation in this application robot of sweeping the floor:
referring specifically to fig. 1, the sound pickup microphone 20 may be disposed on an upper surface or a side surface of the housing 11, and may be, for example, an omni-directional type microphone having a maximum sound pickup distance of several meters or tens of meters. In other embodiments, in order to reduce the collection of the working noise of the sweeping robot inside the housing as much as possible, the sound pickup microphone 20 on the upper surface or the side surface of the housing 11 may also be preferably a directional microphone, and the sound pickup direction of the directional microphone is set to be directed toward the upper side of the housing 11 or the outer side of the housing 11. Compared with an omnidirectional microphone which collects sound signals in all directions with the same sensitivity, the directional microphone can obviously inhibit the receiving of working noise signals from the inside of the shell 11 through the arrangement of the sound collecting direction, and directly improve the signal-to-noise ratio of the signals collected by the sound collecting microphone 20. The pickup range of the directional microphone can be selected to be heart-shaped, half heart-shaped and the like, and the signal to noise ratio of picked voice is improved in advance from the hardware level.
Looking down along the direction a in fig. 1, the internal mechanical structure of the chassis of the sweeping robot is shown in fig. 2 and 3. The robot of sweeping the floor includes inside: in the curved air duct structure 12 shown in fig. 4 or the linear air duct structure 12 shown in fig. 5, each of the air duct structures 12 includes a dust suction port 121 and an air outlet 122, and the motor drives the fan to rotate at a high speed to generate an air flow so as to suck dirt on the ground near the dust suction port 121, and the dirt is processed by a corresponding filter screen and a corresponding dust box. The difference between the two duct structures 12 shown in fig. 4 or 5 is that a section of the outflow chamber is arranged in the form of an elbow or a straight tube, respectively. An air duct for circulating air flow inside the sweeping robot is formed inside the air duct structure 12, and an active noise reduction system can be further arranged in the air duct structure, so that the sweeping robot with an active noise reduction function is formed. The speaker disposed at the end of the air duct structure 12 (at the end of the air outlet 122) and flowing out of the cavity is used for outputting noise reduction sound waves, so as to reduce the noise level radiated from the sweeping robot to the indoor through the open air duct structure 12 in an active noise reduction manner, thereby making the indoor space quiet and comfortable for people to listen to. Even if the directional microphone is selected as the pickup microphone, because the pickup side lobe of the pickup microphone cannot achieve ideal null, certain working noise signals actually exist in the collected signals. Therefore, the mixed working noise signal is eliminated from the collected signal of the pickup microphone, and the signal-to-noise ratio of the picked voice is further improved from a software level.
Since the working noise generated by the sweeping robot and radiated to the environment is highly correlated with the stable operation condition thereof, the working noise of the sweeping robot based on which the noise of the user voice is reduced can be determined specifically by the working condition signal of the sweeping robot in some implementation manners. Therefore, after the noise processing unit determines the working noise signal corresponding to the current working state of the sweeping robot through the working condition signal, noise cancellation processing can be carried out on the collected signal of the pickup microphone correspondingly, and a user voice signal is extracted.
For realizing above-mentioned pronunciation and falling the process of making an uproar, fall and fall the user's pronunciation that has mixed robot work noise of sweeping the floor, resume comparatively pure user speech signal in order to improve speech signal SNR to improve robot speech recognition's the degree of accuracy of sweeping the floor, promote robot work efficiency of sweeping the floor, this application can specifically set up noise processing unit to include:
the working condition signal interface is used for acquiring working condition signals of the sweeping robot, such as a rotating speed signal of a motor inside the sweeping robot, a gear signal of the sweeping robot, a power signal of the sweeping robot and a current signal of the sweeping robot; in this embodiment, for example, the working condition signal from the sweeping robot control bus may be acquired in real time through the working condition signal interface;
the noise analysis module is used for determining a working noise signal matched with the position of the pickup microphone according to the working condition signal; under different working conditions, working noise signals corresponding to the pickup microphone positions can be calibrated in advance in the product design stage. For a sweeping robot with limited working conditions, such as limited wind power gears, working noise signals corresponding to the position of the pickup microphone under each working condition can be predetermined before leaving a factory, and are associated with the working condition signals of the sweeping robot, and the matched working noise signals are directly determined when the sweeping robot operates in a certain working condition;
and the noise reduction module is used for carrying out noise cancellation processing on the collected signals of the pickup microphone according to the working noise signals and extracting user voice signals.
In other implementation manners, the working noise at the sound pickup microphone based on which the noise reduction is performed on the voice of the user can also be determined by the noise pickup microphone arranged in the sweeping robot. In this implementation, the noise processing unit may be specifically configured to include:
the noise-picking microphone is arranged in a preset noise-picking area inside the shell 11, and for example, the noise-picking microphone can be arranged in a central area on a chassis of the sweeping robot, a peripheral area of a motor inside the sweeping robot, and an air duct structure 12 of the sweeping robot;
the noise analysis module is used for determining a working noise signal which is matched with the collected signal of the noise pickup microphone and corresponds to the position of the noise pickup microphone according to the collected signal of the noise pickup microphone;
and the noise reduction module is used for carrying out noise cancellation processing on the collected signals of the pickup microphone according to the working noise signals and extracting user voice signals.
In order to save hardware cost of devices, for the sweeping robot with the active noise reduction function, the noise pickup microphone required by voice noise reduction can be realized by sharing the reference microphone in the active noise reduction system of the sweeping robot.
A reference microphone in the active noise reduction system is simultaneously used as a noise pickup microphone in the voice noise reduction system, and can be arranged in a suction cavity (one end of the dust suction port 121) of the air duct structure 12 to collect a working noise signal (namely, a noise source signal) close to an original sweeping robot; the signal processing unit in the active noise reduction system determines a corresponding noise reduction signal according to the signal, and drives the speaker in the outflow cavity of the air duct structure 12 to output noise reduction sound waves. At this time, the preset noise picking-up area corresponds to the suction cavity, is overlapped with the optimal noise picking-up area of the active noise reduction system, and is close to the working noise source. Therefore, the noise analysis module can determine the working noise signal at the pickup microphone 20 according to the signal collected by the reference microphone in the active noise reduction system of the sweeping robot and the predetermined sound field transfer function.
The sound field transfer function is a transfer function corresponding to a sound field transmission path from the position of the reference microphone to the position of the sound pickup microphone 20, which is measured in advance in the product design stage. Therefore, the noise analysis module can deduce a working noise signal corresponding to the position of the pickup microphone through a sound field transfer function between the microphones according to the signal collected by the reference microphone in the active noise reduction system of the sweeping robot, so that the working noise signal is further removed from the signal collected by the pickup microphone by using the noise reduction module, and a purer user voice signal is extracted to improve the voice recognition effect.
The second stage, the speech recognition process among the robot is swept floor in this application:
in some embodiments, the clean user voice signal obtained after the front-end voice noise reduction is uploaded to the server through the wireless communication unit, the server executes the voice recognition operation, and the sweeping robot receives the first control instruction obtained by the server recognition through the wireless communication unit. At the moment, the server side is used as the rear end of the voice recognition system of the sweeping robot.
In other embodiments, the user voice signal can also control the sweeping robot through the local voice recognition unit of the sweeping robot. At the moment, the sweeping robot carries the complete front end and the complete back end of the voice recognition system. Wherein the speech recognition unit comprises:
the language module is connected with the noise processing unit and used for determining prior character sequence information based on the user voice signals subjected to noise reduction;
and the acoustic module is connected with the voice module so as to determine a second control instruction matched with the user voice signal based on the prior voice signal corresponding to the prior character sequence information and the user voice signal subjected to noise reduction through the characteristic comparison sub-module and the instruction determination sub-module, so that the sweeping robot executes the second control instruction.
The characteristic comparison submodule is used for comparing the prior voice signal corresponding to the prior character sequence information with the characteristic of the user voice signal subjected to noise reduction to obtain a comparison result;
and the instruction determining submodule is used for determining a second control instruction based on the comparison result and the prior character sequence information.
The process of performing voice recognition by the local back end specifically includes:
inputting the user voice signal after noise reduction into a voice recognition unit, and searching a plurality of prior character sequences through a language module
And constructs the probability of a sentence by itself
Sorting; simultaneously in a given text sequence by an acoustic module
On the premise that the probability corresponding to the feature X of the input speech signal is determined
Search results are obtained
And
and taking the character sequence with the maximum product as a voice recognition result, namely a second control instruction for the sweeping robot.
The voice recognition unit in the sweeping robot can also be used for locally storing mapping between the voice signal of the user and the first control instruction returned by the server, namely updating an instruction word bank of the local voice recognition unit through the recognition result of the server, and expanding a second control instruction which can be automatically recognized by the voice recognition unit.
The application discloses robot of sweeping floor, its speech recognition process can be carried out at high in the clouds server, consequently does not receive robot of sweeping floor product itself and deploys the restriction of complexity, learning cost and memory capacity of speech recognition unit. The word stock of the voice recognition unit deployed at the server side can be made to be arbitrarily large, so that massive words are covered, and real-time learning and updating are supported.
The local deployment of the voice recognition unit in the sweeping robot is limited by factors such as learning cost and storage capacity, and the recognition of strange words (first control instructions) outside the instruction word bank is difficult to realize. However, considering that the instruction words for controlling the sweeping robot are usually limited and fixed, in some embodiments, the voice recognition unit may be further deployed in the local place of the sweeping robot on the basis of voice recognition by the cloud server through the wireless communication unit, so as to perform real-time recognition on a limited plurality of commonly used preset instruction words (second control instructions), such as "turn left", "45 °", "advance", "increase power", "pause", and the like, and avoid wireless communication delay to improve the response efficiency of the sweeping robot.
Therefore, when the local voice recognition unit of the sweeping robot judges that the recognition of the preset instruction words can be processed, the wireless communication unit can directly perform the voice recognition locally without sending a request and a voice signal to the server; and when the voice recognition unit judges that the recognition of the instruction words which are not preset cannot be processed, the request and the voice signals can be sent to the server end through the wireless communication unit, the voice recognition is carried out at the server end, and the result is returned to the local, so that the real-time performance, the accuracy and the flexibility of the voice recognition are considered.
In conclusion, the sweeping robot provided by the application can recover to obtain a pure voice signal by accurately picking up voice of a user and effectively reducing noise, and is connected with a server through a wireless communication unit in the sweeping robot, so that the voice signal is identified at the cloud end, a user instruction is accurately and flexibly analyzed, and the sweeping robot can accurately execute corresponding operation.
The above are merely embodiments of the present application, and the description is specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the protection scope of the present application.
Claims (10)
1. A sweeping robot is characterized by comprising:
the sound pickup microphone is arranged on a shell of the sweeping robot;
the noise processing unit is used for determining a working noise signal of the sweeping robot at the position of the pickup microphone and carrying out noise reduction processing on a collected signal of the pickup microphone according to the working noise signal so as to extract a user voice signal;
and the wireless communication unit is connected with the noise processing unit and is used for uploading the user voice signal to a server and receiving a first control instruction which is returned by the server and matched with the user voice signal, so that the sweeping robot executes the first control instruction.
2. The sweeping robot of claim 1, wherein the pickup microphone is disposed on an upper surface or a side surface of the housing;
the pickup microphone is an omnidirectional microphone or a directional microphone, wherein the pickup direction of the directional microphone faces the upper side or the lateral side of the shell.
3. The sweeping robot of claim 1, wherein the noise processing unit comprises:
the working condition signal interface is used for acquiring a working condition signal of the sweeping robot;
the noise analysis module is used for determining the working noise signal according to the working condition signal;
and the noise reduction module is used for carrying out noise cancellation processing on the collected signals of the pickup microphone according to the working noise signals to extract the user voice signals.
4. A sweeping robot according to claim 3, wherein the working condition signals include any one or combination of the following: the sweeping robot comprises a rotating speed signal of a motor inside the sweeping robot, a gear signal of the sweeping robot, a power signal of the sweeping robot and a current signal of the sweeping robot.
5. The sweeping robot of claim 1, wherein the noise processing unit comprises:
the noise-picking microphone is arranged in a preset noise-picking area inside the shell;
the noise analysis module is used for determining the working noise signal according to the collected signal of the noise pickup microphone;
and the noise reduction module is used for carrying out noise cancellation processing on the collected signals of the pickup microphone according to the working noise signals to extract the user voice signals.
6. The sweeping robot of claim 5, wherein the preset noise picking area comprises any one or a combination of the following:
the sweeping robot comprises a central area on a chassis of the sweeping robot, a peripheral area of a motor inside the sweeping robot and an air channel structure of the sweeping robot.
7. The sweeping robot of claim 6, wherein the air duct structure includes an active noise reduction system, and the noise pickup microphone is a reference microphone in the active noise reduction system;
the noise analysis module is used for determining the working noise signal according to the collected signal of the noise-picking microphone and a predetermined sound field transfer function; the sound field transfer function is a transfer function corresponding to a sound field transmission path between the position of the reference microphone and the position of the pickup microphone.
8. A sweeping robot according to claim 7, wherein the reference microphone is disposed in a suction cavity of the air duct structure;
the active noise reduction system further comprises:
the signal processing unit is used for determining a noise reduction signal according to the collected signal of the noise pickup microphone;
a speaker disposed in the outflow cavity of the air duct structure for outputting noise reduction sound waves in response to the noise reduction signal.
9. The sweeping robot of claim 1, further comprising:
the voice recognition unit is connected with the noise processing unit and used for determining a second control instruction matched with the user voice signal based on the user voice signal so as to enable the sweeping robot to execute the second control instruction; and storing the mapping of the user speech signal and the first control instruction locally.
10. The sweeping robot of claim 9, wherein the voice recognition unit comprises:
a language module for determining prior text sequence information based on the user speech signal;
and the acoustic module is used for determining the second control instruction or the first control instruction based on the prior voice signal corresponding to the prior character sequence information and the user voice signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110368843.7A CN113040660B (en) | 2021-04-06 | 2021-04-06 | Floor sweeping robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110368843.7A CN113040660B (en) | 2021-04-06 | 2021-04-06 | Floor sweeping robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113040660A true CN113040660A (en) | 2021-06-29 |
| CN113040660B CN113040660B (en) | 2022-05-20 |
Family
ID=76517568
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110368843.7A Active CN113040660B (en) | 2021-04-06 | 2021-04-06 | Floor sweeping robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113040660B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106388700A (en) * | 2016-06-06 | 2017-02-15 | 北京小米移动软件有限公司 | Active noise reduction device for automatic cleaning equipment and automatic cleaning equipment |
| CN108682428A (en) * | 2018-08-27 | 2018-10-19 | 珠海市微半导体有限公司 | The processing method of robot voice control system and robot to voice signal |
| CN109841208A (en) * | 2017-11-29 | 2019-06-04 | 宁波方太厨具有限公司 | A kind of sound enhancement method applied in range hood |
| US20190355354A1 (en) * | 2018-05-21 | 2019-11-21 | Baidu Online Network Technology (Beijing) Co., Ltd . | Method, apparatus and system for speech interaction |
| KR20200046262A (en) * | 2018-10-24 | 2020-05-07 | 주식회사 케이티 | Speech recognition processing method for noise generating working device and system thereof |
| CN112435648A (en) * | 2020-11-12 | 2021-03-02 | 北京安声浩朗科技有限公司 | Floor sweeping robot |
-
2021
- 2021-04-06 CN CN202110368843.7A patent/CN113040660B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106388700A (en) * | 2016-06-06 | 2017-02-15 | 北京小米移动软件有限公司 | Active noise reduction device for automatic cleaning equipment and automatic cleaning equipment |
| CN109841208A (en) * | 2017-11-29 | 2019-06-04 | 宁波方太厨具有限公司 | A kind of sound enhancement method applied in range hood |
| US20190355354A1 (en) * | 2018-05-21 | 2019-11-21 | Baidu Online Network Technology (Beijing) Co., Ltd . | Method, apparatus and system for speech interaction |
| CN108682428A (en) * | 2018-08-27 | 2018-10-19 | 珠海市微半导体有限公司 | The processing method of robot voice control system and robot to voice signal |
| KR20200046262A (en) * | 2018-10-24 | 2020-05-07 | 주식회사 케이티 | Speech recognition processing method for noise generating working device and system thereof |
| CN112435648A (en) * | 2020-11-12 | 2021-03-02 | 北京安声浩朗科技有限公司 | Floor sweeping robot |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113040660B (en) | 2022-05-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107464564B (en) | Voice interaction method, device and equipment | |
| US11830479B2 (en) | Voice recognition method and apparatus, and air conditioner | |
| CN112020864A (en) | Smart beam control in microphone arrays | |
| CN106708041A (en) | Intelligent sound box and intelligent sound box directional movement method and device | |
| WO2017190552A1 (en) | Robot and determination method and device for sound source position | |
| CN103529726A (en) | Intelligent switch with voice recognition function | |
| CN106782519A (en) | A kind of robot | |
| CN108389586A (en) | A kind of long-range audio collecting device, monitoring device and long-range collection sound method | |
| CN106251878A (en) | Meeting affairs voice recording device | |
| CN102967026A (en) | Intelligent air conditioner and control method thereof | |
| CN106888347A (en) | A kind of video camera with human body tracking and body-sensing function | |
| CN106356050A (en) | Automatic noise elimination method in teaching scene | |
| CN112116918A (en) | Speech signal enhancement processing method and earphone | |
| CN113040660B (en) | Floor sweeping robot | |
| CN106328154A (en) | Front-end audio processing system | |
| CN111883161A (en) | Method and device for audio acquisition and position identification | |
| CN110517702A (en) | The method of signal generation, audio recognition method and device based on artificial intelligence | |
| CN113100668A (en) | Floor sweeping robot | |
| CN111524499B (en) | Air conditioner and active noise reduction debugging method based on APP | |
| CN114252906A (en) | Sound event detection method and device, computer equipment and storage medium | |
| CN208538474U (en) | Speech recognition system | |
| CN106358123A (en) | Intelligent community environment monitoring system | |
| CN106162431A (en) | The beam positioning system of giant-screen mobile terminal | |
| CN110099328A (en) | A kind of intelligent sound box | |
| CN108360942B (en) | Intelligent window, control method thereof and intelligent window management system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |