CN110428850A - Voice pick-up method, device, storage medium and mobile robot - Google Patents
Voice pick-up method, device, storage medium and mobile robot Download PDFInfo
- Publication number
- CN110428850A CN110428850A CN201910713166.0A CN201910713166A CN110428850A CN 110428850 A CN110428850 A CN 110428850A CN 201910713166 A CN201910713166 A CN 201910713166A CN 110428850 A CN110428850 A CN 110428850A
- Authority
- CN
- China
- Prior art keywords
- sound source
- time
- initial
- mobile robot
- voice signal
- 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 82
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 82
- 230000008569 process Effects 0.000 claims abstract description 46
- 230000004807 localization Effects 0.000 claims abstract description 17
- 230000001133 acceleration Effects 0.000 claims description 38
- 230000033001 locomotion Effects 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 12
- SDIXRDNYIMOKSG-UHFFFAOYSA-L disodium methyl arsenate Chemical compound [Na+].[Na+].C[As]([O-])([O-])=O SDIXRDNYIMOKSG-UHFFFAOYSA-L 0.000 claims description 12
- 239000004568 cement Substances 0.000 claims description 8
- 239000000284 extract Substances 0.000 claims description 3
- 230000002618 waking effect Effects 0.000 claims description 3
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 238000010408 sweeping Methods 0.000 description 89
- 238000010586 diagram Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 7
- 238000004140 cleaning Methods 0.000 description 6
- 238000005259 measurement Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000002452 interceptive effect Effects 0.000 description 4
- 239000007787 solid Substances 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 3
- 241001417527 Pempheridae Species 0.000 description 2
- 241000209140 Triticum Species 0.000 description 2
- 235000021307 Triticum Nutrition 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 102200012170 rs10084168 Human genes 0.000 description 2
- 102220171488 rs760746448 Human genes 0.000 description 2
- 238000005406 washing Methods 0.000 description 2
- 230000003313 weakening effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003137 locomotive effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/18—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using ultrasonic, sonic, or infrasonic waves
-
- 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
- G10L15/26—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
- 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
- G10L21/0208—Noise filtering
- G10L21/0216—Noise filtering characterised by the method used for estimating noise
-
- 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
-
- 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
- G10L21/0208—Noise filtering
- G10L21/0216—Noise filtering characterised by the method used for estimating noise
- G10L2021/02161—Number of inputs available containing the signal or the noise to be suppressed
- G10L2021/02166—Microphone arrays; Beamforming
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Manipulator (AREA)
- Toys (AREA)
Abstract
This application discloses a kind of voice pick-up method, device, storage medium and mobile robots, voice pick-up method includes: in the moving process for receiving the voice signal that stationary sound source issues, auditory localization is carried out to stationary sound source according to the voice signal received is carved at the beginning, initial position message of the stationary sound source relative to mobile robot is carved at the beginning to obtain, wherein, initial time is the earliest moment for receiving voice signal;Obtain the exercise data in moving process;According to initial position message, exercise data and preset algorithm, target position information of the stationary sound source in given time relative to mobile robot is calculated, wherein given time is initial time at the time of being spaced after at least one preset time;According to target position information, built-in microphone array is controlled according to predetermined way, pickup is carried out to stationary sound source.The voice pick-up method can solve mobile robot in moving process, it is difficult to the problem of preferably carrying out pickup.
Description
Technical field
This application involves field of communication technology is arrived, especially relate to a kind of voice pick-up method, device, storage medium and
Mobile robot.
Background technique
Recently as the fast development of speech recognition technology, the application scenarios that people carries out interactive voice with machine become to get over
Come it is more common, for example, user can wake up the intelligent mobile robots such as intelligent air condition, smart television by voice, be remotely controlled
Deng operation, this brings great convenience to the life of user and enjoyment.
Wherein, voice pickup is the key that realize interactive voice, and the voice under the environment of far field, which picks up, at present mainly uses wheat
Gram wind array pickup, condition be people, machine position be it is fixed known to, but at mobile robot (such as sweeping robot)
In, the position of sound source is mobile relative to robot, therefore mobile robot can be made to be difficult to preferably carry out pickup.
Summary of the invention
The application's is designed to provide a kind of voice pick-up method, device, storage medium and mobile robot, it is intended to solve
Certainly mobile robot is in moving process, it is difficult to the problem of preferably carrying out pickup.
The application proposes a kind of voice pick-up method, is applied to mobile robot, this method comprises:
In the moving process for receiving the voice signal that stationary sound source issues, believe according to the voice received is carved at the beginning
Number auditory localization is carried out to stationary sound source, carves initial bit confidence of the stationary sound source relative to mobile robot at the beginning to obtain
Breath, wherein initial time is the earliest moment that mobile robot receives voice signal, and initial position message includes inceptive direction
Angle and initial distance;
Obtain exercise data of the mobile robot in moving process;
According to initial position message, exercise data and preset algorithm, stationary sound source is calculated in given time relative to shifting
The target position information of mobile robot, wherein given time is initial time at the time of being spaced after at least one preset time,
Exercise data includes the first kinematic parameter in initial time, and target position information includes target direction angle and target range;
According to target position information, built-in microphone array is controlled according to predetermined way, pickup is carried out to stationary sound source.
Further, according to target position information, built-in microphone array is controlled according to predetermined way to stationary sound source
After the step of carrying out pickup, further includes:
Detect whether the voice signal received meets preset wake-up condition;
If so, waking up mobile robot.
Further, the step of whether voice signal received meets preset wake-up condition detected, comprising:
Speech recognition is carried out to voice signal, obtains text information corresponding with voice signal;
Judge whether text information is identical as preset text information;
If so, determining that the voice signal received meets preset wake-up condition.
Further, the step of speech recognition being carried out to voice signal, obtaining text information corresponding with voice signal
Before, further includes:
Extract the voiceprint of voice signal;
Judge whether voiceprint is identical as preset voiceprint;
Speech recognition is carried out to voice signal if so, executing, obtains the step of text information corresponding with voice signal
Suddenly.
Further, exercise data further includes the second kinematic parameter in given time, and the first kinematic parameter includes first
Speed and the first acceleration, the second kinematic parameter include second speed and the second acceleration, and preset algorithm includes the first pre- imputation
Method, the second preset algorithm and third preset algorithm;According to initial position message, exercise data and preset algorithm, fixation is calculated
Sound source is target position information of the given time relative to mobile robot the step of, comprising:
According to the first kinematic parameter, the second kinematic parameter and the first preset algorithm, mobile robot is calculated when specified
Between move distance in section, wherein time interval of the designated time period between initial time and given time;
According to move distance, inceptive direction angle, initial distance and the second preset algorithm, target range is calculated;
According to initial distance, target range, move distance and third preset algorithm, target direction angle is calculated.
Further, the first kinematic parameter includes First Speed, the first acceleration and deflection angle, and preset algorithm includes the 4th
Preset algorithm, the 5th preset algorithm and the 6th preset algorithm;According to initial position message, exercise data and preset algorithm, calculate
Stationary sound source is target position information of the given time relative to mobile robot the step of out, comprising:
According to First Speed, the first acceleration, deflection angle and the 4th preset algorithm, mobile robot is calculated when specified
Between move distance in section, wherein time interval of the designated time period between initial time and given time;
According to deflection angle, move distance, inceptive direction angle, initial distance and the 5th preset algorithm, target range is calculated;
According to initial distance, target range, move distance and the 6th preset algorithm, target direction angle is calculated.
Further, according to target position information, built-in microphone array is controlled according to predetermined way to stationary sound source
The step of carrying out pickup, comprising:
According to given time, target range and pre-defined algorithm, the voice signal for calculating stationary sound source sending reaches target
The sodar moment of position, wherein target position is mobile robot the location of in given time;
It is oriented speech enhan-cement according to target direction angle, and control microphone array is listed in the sodar moment to voice signal
It is picked up.
The application also proposes a kind of voice pick device, is applied to mobile robot, which includes:
Auditory localization module, for receive stationary sound source issue voice signal moving process in, according to initial
The voice signal that reception arrives carries out auditory localization to stationary sound source, carves stationary sound source at the beginning relative to movement to obtain
The initial position message of robot, wherein initial time is the earliest moment that mobile robot receives voice signal, initial bit
Confidence breath includes inceptive direction angle and initial distance;
Module is obtained, for obtaining exercise data of the mobile robot in moving process;
Computing module, for calculating stationary sound source specified according to initial position message, exercise data and preset algorithm
Target position information of the moment relative to mobile robot, wherein at least one is default at interval for initial time for given time
At the time of after time, exercise data includes the first kinematic parameter in initial time, and target position information includes target direction angle
And target range;
Control module, for according to target position information, controlling built-in microphone array according to predetermined way to fixation
Sound source carries out pickup.
The application also proposes a kind of storage medium, is computer-readable storage medium, is stored thereon with computer journey
Sequence realizes voice pick-up method above-mentioned when computer program is executed by processor.
The application also proposes a kind of mobile robot, including memory, processor and storage are on a memory and can be
The computer program run on processor, processor realize voice pick-up method above-mentioned when executing computer program.
The beneficial effect of the application is: the voice pick-up method that the application proposes first passes through language received by the earliest moment
Then sound signal acquires mobile machine to determine that mobile robot carves the relative position between stationary sound source at the beginning
The exercise data of people in the process of moving, and then based on the initial position message and collected exercise data determined, lead to
The relative position being arbitrarily designated between moment stationary sound source and mobile robot in moving process can be calculated by crossing preset algorithm, into
And built-in microphone array can be controlled accurately according to the relative position between given time stationary sound source and mobile robot
Pickup is oriented to stationary sound source, to greatly increase the pickup ability of mobile robot, efficiently solves movement
Robot is in moving process, it is difficult to the problem of preferably carrying out pickup.
Detailed description of the invention
Fig. 1 is the flow diagram of voice pick-up method in one embodiment of the application;
Fig. 2 is the movement locus schematic diagram of mobile robot in one embodiment of the application;
Fig. 3 is the movement locus schematic diagram of mobile robot in another embodiment of the application;
Fig. 4 is the structural schematic diagram of voice pick device in one embodiment of the application;
Fig. 5 is the structural schematic diagram of voice pick device in another embodiment of the application;
Fig. 6 is the structural schematic diagram of detection module in one embodiment of the application;
Fig. 7 is the structural schematic diagram of auditory localization module in one embodiment of the application;
Fig. 8 is the structural schematic diagram of computing module in one embodiment of the application;
Fig. 9 is the structural schematic diagram of computing module in another embodiment of the application;
Figure 10 is the structural schematic diagram of mobile robot in one embodiment of the application.
The embodiments will be further described with reference to the accompanying drawings for realization, functional characteristics and the advantage of the application purpose.
Specific embodiment
It should be appreciated that specific embodiment described herein is only used to explain the application, it is not used to limit the application.
Referring to Fig.1, the embodiment of the present application proposes a kind of voice pick-up method, is applied to mobile robot, the movement machine
Artificial a kind of intelligent electronic device with locomotive function and voice interactive function, such as sweeping robot, medical transportation robot
Deng not limiting specifically this, for convenience of understanding, the application is illustrated by taking sweeping robot as an example.The voice pickup side
Method includes:
S11, in the moving process for receiving the voice signal that stationary sound source issues, according to carving the language received at the beginning
Sound signal carries out auditory localization to stationary sound source, carves initial bit of the stationary sound source relative to mobile robot at the beginning to obtain
Confidence breath, wherein initial time is the earliest moment that mobile robot receives voice signal, and initial position message includes initial
Deflection and initial distance;
S12 obtains exercise data of the mobile robot in moving process;
It is opposite in given time to calculate stationary sound source according to initial position message, exercise data and preset algorithm by S13
In the target position information of mobile robot, wherein given time is initial time after being spaced at least one preset time
Moment, exercise data include the first kinematic parameter in initial time, target position information include target direction angle and target away from
From;
S14 controls built-in microphone array and picks up according to predetermined way to stationary sound source according to target position information
Sound.
In above-mentioned S11, above-mentioned stationary sound source refers to user, and voice signal refers to that user is carrying out language with sweeping robot
The continuous voice signal issued when sound interaction, in general application scenarios, user and sweeping robot carry out voice friendship
In mutual process, user is usually fixed, and sweeping robot is typically at moving condition after entering working condition
's.In this step, specifically, in sweeping robot moving process, since the location of sweeping robot is variation,
Therefore sweeping robot at the time of different location receives voice signal can difference (due to the mobile speed of sweeping robot
Degree is generally slower, and the speed of sound transmission is quickly, therefore this species diversity is usually the other difference of Millisecond), specifically, sweep the floor
Robot can be using voice signal received by the earliest moment, and by existing auditory localization technology, (such as steerable beam is formed
Technology, the auditory localization technology based on the estimation of high-resolution spectrogram, auditory localization technology based on sodar delay inequality etc.) to fixation
Sound source carries out auditory localization, gets and carves initial position message of the stationary sound source relative to sweeping robot at the beginning.
In above-mentioned S12, during sweeping robot is mobile, built-in motion sensor (such as speed biography can be passed through
Sensor, acceleration transducer etc.) in real time acquisition sweeping robot exercise data (such as speed, acceleration), wherein sweeper
Exercise data in device people's moving process include initial time the first kinematic parameter (as carve at the beginning speed, accelerate
Degree etc.).
In above-mentioned S13, above-mentioned preset algorithm is the algorithm (such as uniformly accelerated motion formula) specially designed, is specified
Depending on moment can be by preset time, which is generally Millisecond, can be set by the user himself, and it is silent to be also possible to system
Setting is recognized without modifiable, this is not limited specifically, illustratively, it is assumed that initial time t1, given time t2, in advance
If the time is t, then there is t2=t1+ nt, wherein n is positive integer;In some embodiments, the initial position of sweeping robot is obtained
After the data such as information, the first kinematic parameter, these data can be calculated by preset algorithm, calculate stationary sound source and referring to
The target position information relative to mobile robot is carved in timing, illustratively, referring to Fig. 2, it is assumed that A point is sweeping robot initial
The location of when the moment, B point is that (i.e. first of sweeping robot specifies sweeping robot after being spaced a preset time
Moment) the location of, using built-in velocity sensor and acceleration transducer can real-time measurement go out sweeping robot and moving
The size of the speed v and acceleration a of any moment during dynamic, if the distance between A point and B point s, when initial in A point
Carving is t1, collecting speed of the sweeping robot in A point is v1, acceleration a1, the given time in B point is t2, t1With
t2Between preset time be t, preset time t is short enough, then during this period acceleration a be considered as it is constant (it is understood that
It is that, when uniform motion, 0) value of a is that sweeping robot does uniformly accelerated motion, then by by collected sweeper
Speed v of the device people in A point1With acceleration a1It is updated to preset kinematics formula
In calculated, the distance between A point and B point s (i.e. move distance) can be calculated, so far between known A point and B point away from
From the distance between s and A point and O point s1(i.e. above-mentioned initial distance), (wherein, β is above-mentioned inceptive direction to ∠ BAO=π-β
Angle), if the distance between B point and O point are s2, then geometric formula can be obtained by the cosine law:And then the distance s between O point can be calculated in B point by the geometric formula2(i.e.
Target range), known the distance between the distance between A point and B point s, A point and O point s at this time1And between B point and O point
Distance s2If stationary sound source is α relative to the target direction angle of sweeping robot in given time, then can be obtained by the cosine law
Geometric formula:And then can calculate target direction angle by the geometric formula is α, to calculate solid
Determine target position information of the sound source in first given time relative to mobile robot, similarly, further, obtains the target
It, can be using the target position information as next given time (i.e. second given time of sweeping robot) after location information
Initial position message, and then sweeping robot is acquired in the movement number of first given time by built-in motion sensor
According to, it recycles preset algorithm to be calculated, sweeping robot can be calculated in the target position information of second given time, from
And the position of each given time sweeping robot in moving process can be calculated in this way, that is, in sweeping robot
In mobile process, can real-time measurement go out the relative position between stationary sound source and sweeping robot.
In above-mentioned S14, sweeping robot is obtained after the target position information of given time, can be believed according to target position
The microphone array built in the control of target direction angle in breath is oriented speech enhan-cement, so that sweeping robot is in mobile mistake
Cheng Zhong, built-in microphone array only carry out speech enhan-cement to the voice signal from stationary sound source direction always, and right
Weakening process is then carried out in the voice signal of other non-Sounnd source directions, so as to filter out most of useless noise, is greatly mentioned
The high pickup ability of sweeping robot, efficiently solves sweeping robot in moving process, it is difficult to preferably be picked up
The problem of sound.
In the present embodiment, which first passes through voice signal received by the earliest moment, to determine
Mobile robot carves the relative position between stationary sound source at the beginning, then acquires mobile robot in the process of moving
Exercise data can be calculated by preset algorithm and then based on the initial position message and collected exercise data determined
The relative position between moment stationary sound source and mobile robot is arbitrarily designated in moving process out, and then can be according to given time
Relative position between stationary sound source and mobile robot controls built-in microphone array and accurately determines stationary sound source
To pickup, to greatly increase the pickup ability of mobile robot, mobile robot is efficiently solved in moving process
In, it is difficult to the problem of preferably carrying out pickup.
In an alternative embodiment, above-mentioned according to target position information, built-in microphone array is controlled according to pre-
Determine mode to stationary sound source carry out pickup the step of after, further includes:
S15, detects whether the voice signal received meets preset wake-up condition;
If the voice signal received meets preset wake-up condition, S16 is executed, wakes up mobile robot.
In the present embodiment, specifically, it can be judged by detecting to the voice signal that microphone array picks up
Whether meet preset wake-up condition, if voice signal meets preset wake-up condition, sweeping robot is waken up;And
If voice signal is unsatisfactory for preset wake-up condition, user can be prompted to carry out by way of voice prompting again through voice
It wakes up, wherein wake-up condition is generally that producer is pre-set, and different producers defaults in the wake-up bars in sweeping robot
Part will be different.
In an alternative embodiment, whether the voice signal that above-mentioned detection receives meets preset wake-up condition
Step, comprising:
S151 carries out speech recognition to voice signal, obtains text information corresponding with voice signal;
S152 judges whether text information is identical as preset text information;
If text information is identical as preset text information, S153 is executed, it is pre- to determine that the voice signal received meets
If wake-up condition.
In the present embodiment, when in use, user needs to first pass through the modes such as keyword and wakes up sweeping robot, to realize
Interactive voice specifically carries out voice knowledge to the voice signal that microphone array picks up by existing speech recognition technology
Not, the voice signal picked up can be converted to corresponding text information, and then by obtained text information and preset text
Information is compared, both judge it is whether consistent, if unanimously, can determine that pickup to voice signal meet preset wake-up bars
Part, and then wake up sweeping robot;If inconsistent, user can be prompted to carry out by way of voice prompting again through voice
It wakes up.
In an alternative embodiment, above-mentioned that speech recognition is carried out to voice signal, it obtains corresponding with voice signal
Text information the step of before, further includes:
S15a extracts the voiceprint of voice signal;
S15b judges whether voiceprint is identical as preset voiceprint;
If voiceprint is identical as preset voiceprint, above-mentioned S151 is executed, speech recognition is carried out to voice signal,
Obtain text information corresponding with voice signal.
In the present embodiment, before the use, can in sweeping robot preparatory typing one or more user vocal print
Information, so in moving process user by speech control sweeping robot execute relevant action (as stop clean) before,
Sweeping robot first can carry out Application on Voiceprint Recognition to the voice picked up, and then whether judge active user according to Application on Voiceprint Recognition result
With the permission used, so that can avoid sweeping robot is arbitrarily used (such as by child as toy use).Specifically, it sweeps
After floor-washing robot picks up the voice signal issued to user by built-in microphone array, by the voice signal picked up
Carry out feature extraction, can get the voiceprint of voice signal, so by obtained voiceprint and preset voiceprint into
Row compares, and judges whether the two is consistent, if unanimously, illustrating that active user has the permission using sweeping robot, sweeping at this time
Floor-washing robot can execute above-mentioned steps S151 accordingly, and if it is inconsistent, illustrate that active user does not have using sweeping robot
Permission, can inform user by way of issuing voice prompting at this time, such as " sorry, you are not small fertile owner, it is small it is fertile not
If you can be listened ".
In an alternative embodiment, above-mentioned in the moving process for receiving the voice signal that stationary sound source issues, root
Auditory localization is carried out to stationary sound source according to the voice signal received is carved at the beginning, carves stationary sound source phase at the beginning to obtain
For mobile robot initial position message the step of, comprising:
S111 calculates stationary sound source using preset TDOA algorithm according to the voice signal received is carved at the beginning
Sound source position;
S112 establishes the coordinate position relationship between stationary sound source and mobile robot according to sound source position;
S113 determines initial position message according to coordinate position relationship.
In the present embodiment, TDOA (i.e. T imeDi fferenceofArr i va l, sodar delay inequality) calculation can be used
Method calculates the sound source position of stationary sound source, specifically, first calculates stationary sound source and reaches each microphone in microphone array
The relative time delay of array element is (between so-called relative time delay refers to that same signal source reaches the different microphone array elements in microphone array
Time difference), then relative time delay is recycled to calculate the range difference that stationary sound source reaches each microphone array element, finally by several
Where method can calculate sound source position, it will be understood by those skilled in the art that repeating no more to this;Obtain the sound of stationary sound source
Behind source position, then using sound source position as origin, plane right-angle coordinate is established, to set up stationary sound source and sweeping robot
Between coordinate position relationship can determine that stationary sound source relative to mobile robot finally according to the coordinate position relationship
Initial position message, schematically, as shown in Fig. 2, A point is sweeping robot the location of when carving at the beginning, according to
The coordinate position relationship established between the stationary sound source and sweeping robot played it is found that carve, sweeping robot at the beginning
The distance between stationary sound source is s1, sweeping robot is located at the direction of stationary sound source west by north (0.5 π-β), correspondingly, solid
Determine the direction that sound source is located at sweeping robot east by south (0.5 π-β), then initial position of the stationary sound source relative to sweeping robot
Information can use coordinate (β, s1) indicate, wherein β is inceptive direction angle, s1For initial distance.
In an alternative embodiment, exercise data further includes the second kinematic parameter in given time, the first movement
Parameter includes First Speed and the first acceleration, and the second kinematic parameter includes second speed and the second acceleration, preset algorithm packet
Include the first preset algorithm, the second preset algorithm and third preset algorithm;It is above-mentioned according to initial position message, exercise data and default
Algorithm calculates stationary sound source target position information of the given time relative to mobile robot the step of, comprising:
S13a calculates mobile robot and is referring to according to the first kinematic parameter, the second kinematic parameter and the first preset algorithm
The move distance fixed time in section, wherein time interval of the designated time period between initial time and given time;
S13b calculates target range according to move distance, inceptive direction angle, initial distance and the second preset algorithm;
S13c calculates target direction angle according to initial distance, target range, move distance and third preset algorithm.
In above-mentioned S13a, generally, the cleaning path of sweeping robot is bow font, at this point, illustratively, movement away from
From specific calculating process it is as follows:
As shown in Fig. 2, the cleaning path of sweeping robot is bow font, A point carves when institute for sweeping robot at the beginning
The position at place, B point (i.e. first given time of sweeping robot) institute after being spaced a preset time for sweeping robot
The position at place, using built-in velocity sensor and acceleration transducer can real-time measurement go out sweeping robot in moving process
The size of the speed v and acceleration a of any moment, if the distance between A point and B point s, the initial time in A point is t1, adopt
Integrate First Speed of the sweeping robot in A point as v1, the first acceleration be a1, the given time in B point is t2, acquisition
It is v to second speed of the sweeping robot in B point2, the second acceleration be a2, t1And t2Between preset time be t, preset
Time, t was short enough, then during this period acceleration a be considered as it is constant (it is understood that when uniform motion, the value of a is
0), sweeping robot does uniformly accelerated motion, then passes through the First Speed and by collected sweeping robot in A point
One acceleration and second speed in B point and the second acceleration are updated to preset kinematics formula(wherein, a can be taken as a1) in calculated, can calculate between A point and B point
Distance s (i.e. move distance).
In above-mentioned S13b, illustratively, the specific calculating process of target range is as follows:
As shown in Fig. 2, the distance between the distance between A point and B point s and A point and O point s known at this time1, ∠ BAO=
π-β, if the distance between B point and O point are s2, then geometric formula can be obtained by the cosine law:And then the distance s between O point can be calculated in B point by the geometric formula2(i.e.
Target range).
In above-mentioned S13c, illustratively, the specific calculating process at target direction angle is as follows:
As shown in Fig. 2, the distance between the distance between A point and B point s, A point and O point s known at this time1And B point and O
The distance between point s2If stationary sound source is α relative to the target direction angle of sweeping robot in given time, then determined by cosine
Geometric formula can be obtained in reason:And then can calculate target direction angle by the geometric formula is α, similarly,
Further, after obtaining target range and target direction angle, it can regard the target range and target direction angle as next finger
Inceptive direction angle and the initial distance of (i.e. second given time of sweeping robot) are carved in timing, and then pass through built-in movement
Sensor acquires sweeping robot in the velocity and acceleration of second given time, and preset algorithm is recycled to be calculated, can
Sweeping robot is calculated in the target position information of second given time, thus, it can calculate in movement in this way
The position of each given time sweeping robot in the process, that is, during sweeping robot is mobile, can real-time measurement go out it is solid
Determine the relative position between sound source and sweeping robot.
In the present embodiment, it when the cleaning path of sweeping robot is bow font, is being moved by acquiring sweeping robot
Velocity information and acceleration information during dynamic, and then relevant calculation is carried out using preset algorithm, fixation can be obtained in real time
Target position information of the sound source in given time relative to mobile robot, thus even if sweeping robot is in moving condition,
Also the relative position between stationary sound source and sweeping robot can be determined in real time, it is subsequent preferably to fixed sound so as to be convenient for
Source carries out pickup.
In another alternative embodiment, the first kinematic parameter includes First Speed, the first acceleration and deflection angle, in advance
Imputation method includes the 4th preset algorithm, the 5th preset algorithm and the 6th preset algorithm;It is above-mentioned according to initial position message, movement number
According to and preset algorithm, calculate stationary sound source target position information of the given time relative to mobile robot the step of, packet
It includes:
S13A calculates mobile robot and exists according to First Speed, the first acceleration, deflection angle and the 4th preset algorithm
Move distance in designated time period, wherein time interval of the designated time period between initial time and given time;
S13B calculates target according to deflection angle, move distance, inceptive direction angle, initial distance and the 5th preset algorithm
Distance;
S13C calculates target direction angle according to initial distance, target range, move distance and the 6th preset algorithm.
In above-mentioned S13A, distinguishingly, when the cleaning path of sweeping robot is non-bow font, illustratively, movement
The specific calculating process of distance is as follows:
As shown in figure 3, the cleaning path of sweeping robot is non-bow font, when A point is that sweeping robot is carved at the beginning
Location, B point are sweeping robot (i.e. first given time of sweeping robot) after being spaced a preset time
When the location of, using built-in velocity sensor, acceleration transducer and gyroscope can real-time measurement go out sweeping robot
The speed v of any moment, acceleration a and instantaneous deflection angle theta in moving process, if the distance between A point and B point s, in A
Initial time when point is t1, collecting First Speed of the sweeping robot in A point is v1, the first acceleration be a1, deflection angle
For θ, the given time in B point is t2, t1And t2Between preset time be t, preset time t is short enough, then during this period plus
Speed a is considered as that constant (it is understood that when uniform motion, the value of a is 0), then to have the acceleration of horizontal direction
ax=a1× cos θ, the acceleration a of vertical directiony=a1× sin θ, horizontal velocity Vx=v1× cos θ, vertical speed Vv=v1×
Sin θ then has horizontal displacementVertical displacement In conjunction with formula: s=AC2+BC2, so as to calculate A point and B point
The distance between s (i.e. move distance).
In above-mentioned S13B, illustratively, the specific calculating process of target range is as follows:
As shown in figure 3, deflection angle theta known at this time, the distance between A point and B point s, inceptive direction angle beta and A point and O point
The distance between s1If the distance between B point and O point are s2, then geometric formula can be obtained by the cosine law:And then the distance s between O point can be calculated in B point by the geometric formula2
(i.e. target range).
In above-mentioned S13C, illustratively, the specific calculating process at target direction angle is as follows:
As shown in figure 3, the distance between the distance between A point and B point s, A point and O point s known at this time1And B point and O
The distance between point s2If stationary sound source is α relative to the target direction angle of sweeping robot in given time, then determined by cosine
Geometric formula can be obtained in reason:And then target can be calculated by the geometric formula
Deflection is α, similarly, further, can be by the target range and target direction angle after obtaining target range and target direction angle
Regard inceptive direction angle and the initial distance of next given time (i.e. second given time of sweeping robot) as, in turn
Sweeping robot is acquired in the speed, acceleration and deflection angle of first given time, then benefit by built-in motion sensor
It is calculated with preset algorithm, sweeping robot can be calculated in the target position information of second given time, thus, pass through
This mode can calculate the position of each given time sweeping robot in moving process, that is, mobile in sweeping robot
In the process, can real-time measurement go out the relative position between stationary sound source and sweeping robot.
In the present embodiment, when the cleaning path of sweeping robot is bow font (deflection angle is 90 ° at this time) or non-bow
When font, pass through velocity information, acceleration information and deflection angle information of the acquisition sweeping robot in moving process, Jin Erli
Relevant calculation is carried out with preset algorithm, target position of the stationary sound source in given time relative to mobile robot can be obtained in real time
Confidence breath, thus even if sweeping robot is in moving condition, it can also determine between stationary sound source and sweeping robot in real time
Relative position, so as to convenient for it is subsequent preferably to stationary sound source carry out pickup.
In an alternative embodiment, above-mentioned according to target position information, built-in microphone array is controlled according to pre-
Determine the step of mode carries out pickup to stationary sound source, comprising:
S141, according to given time, target range and pre-defined algorithm, the voice signal for calculating stationary sound source sending is reached
The sodar moment of target position, wherein target position is mobile robot the location of in given time;
S142 is oriented speech enhan-cement according to target direction angle, and control microphone array is listed in the sodar moment to language
Sound signal is picked up.
In above-mentioned S141, referring to Fig. 2 or Fig. 3, if given time is t2, target range s2, the sodar moment is tr, then
Pass through scheduled formula: tr=t2+s2/ c (in formula, c is the aerial spread speed of sound, can use 340m/s), can calculate
The voice signal that stationary sound source issues out reaches the sodar moment t of target positionr。
It, can be according to target after calculating target direction angle α by preset algorithm referring to Fig. 2 or Fig. 3 in above-mentioned S142
The built-in microphone array of direction angle alpha control is oriented speech enhan-cement, so that sweeping robot is in the process of moving, it is built-in
Microphone array speech enhan-cement only is carried out to the voice signal from stationary sound source direction always, and for other non-sound
The voice signal in source direction then carries out weakening process, while can be picked up in sodar moment t to voice signal, without all
The voice signal at moment is all picked up, so that the pickup of directional beam signal is completed, so that most useless noise can quilt
It filters out, realizes accurate pickup over time and space, so that microphone array can be more accurately to fixed sound
Source is oriented pickup, greatly increases the pickup ability of mobile robot, efficiently solves mobile robot in movement
In the process, it is difficult to the problem of preferably carrying out pickup.
In the above embodiments of the present application, it should be noted that be previously with regard to the associated description of microphone array, be by
Microphone array is considered as an entirety to describe and (regard all microphone array elements as an entirety), for example, front is counted
Strictly speaking the data such as the target direction angle of calculating, target range are but remaining wheats for single microphone array element
Gram wind array element also can be used identical mode and calculate the data such as corresponding target direction angle, target range, those skilled in the art
Member is it is appreciated that repeat no more this.
Referring to Fig. 4, the embodiment of the present application also proposes a kind of voice pick device, is applied to mobile robot, the device packet
It includes:
Auditory localization module 11, for receive stationary sound source issue voice signal moving process in, according to first
The voice signal that beginning reception arrives carries out auditory localization to stationary sound source, carves stationary sound source at the beginning relative to shifting to obtain
The initial position message of mobile robot, wherein initial time is the earliest moment that mobile robot receives voice signal, initially
Location information includes inceptive direction angle and initial distance;
Module 12 is obtained, for obtaining exercise data of the mobile robot in moving process;
Computing module 13, for calculating stationary sound source and referring to according to initial position message, exercise data and preset algorithm
The target position information relative to mobile robot is carved in timing, wherein at interval, at least one is pre- for initial time for given time
If at the time of after the time, exercise data includes the first kinematic parameter in initial time, target position information includes target direction
Angle and target range;
Control module 14, for according to target position information, controlling built-in microphone array according to predetermined way to solid
Determine sound source and carries out pickup.
Referring to Fig. 5, in an alternative embodiment, above-mentioned voice pick device, further includes:
Detection module 15, for detecting whether the voice signal received meets preset wake-up condition;
Wake-up module 16, for waking up mobile robot when the voice signal received meets preset wake-up condition.
Referring to figure 5 and figure 6, in an alternative embodiment, above-mentioned detection module 15, comprising:
Voice recognition unit 151 obtains text corresponding with voice signal for carrying out speech recognition to voice signal
Information;
First judging unit 152, for judging whether text information is identical as preset text information;
Judging unit 153, for determining the voice signal received when text information is identical as preset text information
Meet preset wake-up condition.
Referring to figure 5 and figure 6, in an alternative embodiment, above-mentioned detection module 15, further includes:
Voiceprint extraction unit 15a, for extracting the voiceprint of voice signal;
Second judgment unit 15b, for judging whether voiceprint is identical as preset voiceprint.
Above-mentioned voice recognition unit 151 is specifically used for when voiceprint is identical as preset voiceprint, believes voice
Number speech recognition is carried out, obtains corresponding with voice signal text information.
Referring to Fig. 4 and Fig. 7, in an alternative embodiment, above-mentioned auditory localization module 11, comprising:
Computing unit 111, for being calculated using preset TDOA algorithm according to the voice signal received is carved at the beginning
The sound source position of stationary sound source out;
Unit 112 is established, is closed for according to sound source position, establishing the coordinate position between stationary sound source and mobile robot
System;
Determination unit 113, for determining initial position message according to coordinate position relationship.
Referring to Fig. 4 and Fig. 8, in an alternative embodiment, exercise data further includes the second movement in given time
Parameter, the first kinematic parameter include First Speed and the first acceleration, and the second kinematic parameter includes that second speed and second accelerate
Degree, preset algorithm include the first preset algorithm, the second preset algorithm and third preset algorithm;Above-mentioned computing module 13, comprising:
First computing unit 13a, for calculating according to the first kinematic parameter, the second kinematic parameter and the first preset algorithm
The mobile robot at the appointed time move distance in section out, wherein designated time period is between initial time and given time
Time interval;
Second computing unit 3b, for according to move distance, inceptive direction angle, initial distance and the second preset algorithm, meter
Calculate target range;
Third computing unit 13c, for calculating according to initial distance, target range, move distance and third preset algorithm
Target direction angle out.
Referring to Fig. 4 and Fig. 9, in another alternative embodiment, the first kinematic parameter includes First Speed, the first acceleration
Degree and deflection angle, preset algorithm include the 4th preset algorithm, the 5th preset algorithm and the 6th preset algorithm;Above-mentioned computing module
13, comprising:
4th computing unit 13A, for calculating according to First Speed, the first acceleration, deflection angle and the 4th preset algorithm
The mobile robot at the appointed time move distance in section out, wherein designated time period is between initial time and given time
Time interval;
5th computing unit 13B, for default according to deflection angle, move distance, inceptive direction angle, initial distance and the 5th
Algorithm calculates target range;
6th computing unit 13C, for calculating according to initial distance, target range, move distance and the 6th preset algorithm
Target direction angle out.
Referring to Fig. 5, in an alternative embodiment, above-mentioned control module 14, comprising:
7th computing unit 141, for calculating stationary sound source hair according to given time, target range and pre-defined algorithm
Voice signal out reaches the sodar moment of target position, wherein target position is that mobile robot is locating in given time
Position;
Pickup unit 142, for being oriented speech enhan-cement according to target direction angle, and control microphone array is listed in sound
Voice signal is picked up up to the moment.
It should be noted that for above-mentioned apparatus embodiment, since it is substantially corresponding with above method embodiment,
Specific embodiment can be found in the explanation of embodiment of the method part, it will be understood by those skilled in the art that no longer superfluous to this
It states.
The embodiment of the present application also proposes a kind of storage medium, is computer-readable storage medium, is stored thereon with meter
Calculation machine program realizes the voice pick-up method in any of the above-described embodiment when computer program is executed by processor.
Referring to Fig.1 0, the embodiment of the present application also proposes a kind of mobile robot 100, including memory 200, processor 300
And it is stored in the computer program 400 that can be run on memory 200 and on processor 300, processor 300 executes computer
The voice pick-up method in any of the above-described embodiment is realized when program 400.
It will be understood by those skilled in the art that the mobile robot 100 of the embodiment of the present application is above-mentioned involved for holding
One or more equipment in row the application in method.These equipment can specially design and manufacture for required purpose,
It or also may include known device in general purpose computer.These equipment have the computer program 400 that is stored in it or
Application program, these computer programs 400 are selectively activated or are reconstructed.Such computer program 400 can be stored in
In equipment (for example, computer) readable medium or it is stored in and is suitable for storing e-command and is coupled to any class of bus respectively
In the medium of type, computer-readable medium include but is not limited to any kind of disk (including floppy disk, hard disk, CD, CD-ROM,
And magneto-optic disk), ROM (Read-Only Memory, read-only memory), RAM (Random Access Memory, random storage
Device), EPROM (Erasable Programmable Read-Only Memory, Erarable Programmable Read only Memory),
(Electrically Erasable Programmable Read-Only Memory, electric erazable programmable is read-only to be deposited EEPROM
Reservoir), flash memory, magnetic card or light card.It is, readable medium includes by equipment (for example, computer) can read
Form storage or transmission information any medium.
The foregoing is merely preferred embodiment of the present application, are not intended to limit the scope of the patents of the application, all utilizations
Equivalent structure or equivalent flow shift made by present specification and accompanying drawing content is applied directly or indirectly in other correlations
Technical field, similarly include in the scope of patent protection of the application.
Claims (10)
1. a kind of voice pick-up method, which is characterized in that be applied to mobile robot, which comprises
In the moving process for receiving the voice signal that stationary sound source issues, believe according to the voice received is carved at the beginning
Number to the stationary sound source carry out auditory localization, with obtain the stationary sound source described in the initial time relative to the moving machine
The initial position message of device people, wherein the initial time is that the mobile robot receives the earliest of the voice signal
Moment, the initial position message include inceptive direction angle and initial distance;
Obtain exercise data of the mobile robot in the moving process;
According to the initial position message, the exercise data and preset algorithm, the stationary sound source is calculated in given time
Target position information relative to the mobile robot, wherein the given time is that the initial time is being spaced at least
At the time of after one preset time, the exercise data includes the first kinematic parameter in the initial time, the target position
Confidence breath includes target direction angle and target range;
According to the target position information, controls built-in microphone array and the stationary sound source is picked up according to predetermined way
Sound.
2. voice pick-up method according to claim 1, which is characterized in that described according to the target position information, control
After the step of built-in microphone array of system carries out pickup to the stationary sound source according to predetermined way, further includes:
Detect whether the voice signal received meets preset wake-up condition;
If so, waking up the mobile robot.
3. voice pick-up method according to claim 2, which is characterized in that described to detect the voice signal received
The step of whether meeting preset wake-up condition, comprising:
Speech recognition is carried out to the voice signal, obtains text information corresponding with the voice signal;
Judge whether the text information is identical as preset text information;
If so, determining that the voice signal received meets the preset wake-up condition.
4. voice pick-up method according to claim 3, which is characterized in that described to carry out voice knowledge to the voice signal
Not, before the step of obtaining text information corresponding with the voice signal, further includes:
Extract the voiceprint of the voice signal;
Judge whether the voiceprint is identical as preset voiceprint;
If so, executing described to voice signal progress speech recognition, acquisition text corresponding with the voice signal
The step of information.
5. voice pick-up method according to claim 1, which is characterized in that the exercise data further includes described specified
Second kinematic parameter at moment, first kinematic parameter include First Speed and the first acceleration, second kinematic parameter
Including second speed and the second acceleration, the preset algorithm includes that the first preset algorithm, the second preset algorithm and third are default
Algorithm;It is described according to the initial position message, the exercise data and preset algorithm, calculate the stationary sound source specified
The step of target position information of the moment relative to the mobile robot, comprising:
According to first kinematic parameter, second kinematic parameter and first preset algorithm, the moving machine is calculated
The device people at the appointed time move distance in section, wherein the designated time period is the initial time and the given time
Between time interval;
According to the move distance, the inceptive direction angle, the initial distance and second preset algorithm, calculate described
Target range;
According to the initial distance, the target range, the move distance and the third preset algorithm, the mesh is calculated
Mark deflection.
6. voice pick-up method according to claim 1, which is characterized in that first kinematic parameter includes the first speed
Degree, the first acceleration and deflection angle, the preset algorithm include the 4th preset algorithm, the 5th preset algorithm and the 6th pre- imputation
Method;It is described according to the initial position message, the exercise data and preset algorithm, calculate the stationary sound source when specified
The step of carving the target position information relative to the mobile robot, comprising:
According to the First Speed, first acceleration, the deflection angle and the 4th preset algorithm, the shifting is calculated
The mobile robot at the appointed time move distance in section, wherein the designated time period is the initial time and described specified
Time interval between moment;
According to the deflection angle, the move distance, the inceptive direction angle, the initial distance and the 5th pre- imputation
Method calculates the target range;
According to the initial distance, the target range, the move distance and the 6th preset algorithm, the mesh is calculated
Mark deflection.
7. voice pick-up method according to any one of claim 1 to 6, which is characterized in that described according to the target
Location information controls the step of built-in microphone array carries out pickup to the stationary sound source according to predetermined way, comprising:
According to the given time, the target range and pre-defined algorithm, the voice that the stationary sound source issues is calculated
The sodar moment of signal arrival target position, wherein the target position is the mobile robot in the given time
Location;
It is oriented speech enhan-cement according to the target direction angle, and the control microphone array is listed in the sodar moment pair
The voice signal is picked up.
8. a kind of voice pick device, which is characterized in that be applied to mobile robot, described device includes:
Auditory localization module, in the moving process for receiving the voice signal that stationary sound source issues, according to carving at the beginning
The voice signal received carries out auditory localization to the stationary sound source, to obtain the fixed sound described in the initial time
Initial position message of the source relative to the mobile robot, wherein the initial time is that the mobile robot receives
The earliest moment of the voice signal, the initial position message include inceptive direction angle and initial distance;
Module is obtained, for obtaining exercise data of the mobile robot in the moving process;
Computing module, for calculating the fixed sound according to the initial position message, the exercise data and preset algorithm
Target position information of the source in given time relative to the mobile robot, wherein when the given time is described initial
At the time of being engraved in after being spaced at least one preset time, the exercise data includes the first movement ginseng in the initial time
Number, the target position information includes target direction angle and target range;
Control module, for according to the target position information, controlling built-in microphone array according to predetermined way to described
Stationary sound source carries out pickup.
9. a kind of storage medium, which is characterized in that it is computer-readable storage medium, is stored thereon with computer program,
The voice pick-up method as described in any one of claims 1 to 7 is realized when the computer program is executed by processor.
10. a kind of mobile robot, which is characterized in that including memory, processor and be stored on the memory and can
The computer program run on the processor, the processor realize such as claim 1 when executing the computer program
To voice pick-up method described in any one of 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910713166.0A CN110428850A (en) | 2019-08-02 | 2019-08-02 | Voice pick-up method, device, storage medium and mobile robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910713166.0A CN110428850A (en) | 2019-08-02 | 2019-08-02 | Voice pick-up method, device, storage medium and mobile robot |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110428850A true CN110428850A (en) | 2019-11-08 |
Family
ID=68413960
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910713166.0A Pending CN110428850A (en) | 2019-08-02 | 2019-08-02 | Voice pick-up method, device, storage medium and mobile robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110428850A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111883186A (en) * | 2020-07-10 | 2020-11-03 | 上海明略人工智能(集团)有限公司 | Recording device, voice acquisition method and device, storage medium and electronic device |
CN112612444A (en) * | 2020-12-28 | 2021-04-06 | 南京紫牛软件科技有限公司 | Sound source position positioning method, sound source position positioning device, electronic equipment and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102305925A (en) * | 2011-07-22 | 2012-01-04 | 北京大学 | Robot continuous sound source positioning method |
CN103257338A (en) * | 2013-04-23 | 2013-08-21 | 中国科学技术大学 | Indoor positioning method and system |
CN103941223A (en) * | 2013-01-23 | 2014-07-23 | Abb技术有限公司 | Sound source positioning system and method |
CN104092936A (en) * | 2014-06-12 | 2014-10-08 | 小米科技有限责任公司 | Automatic focusing method and apparatus |
CN107577449A (en) * | 2017-09-04 | 2018-01-12 | 百度在线网络技术(北京)有限公司 | Wake up pick-up method, device, equipment and the storage medium of voice |
CN108231075A (en) * | 2017-12-29 | 2018-06-29 | 北京视觉世界科技有限公司 | Control method, device, equipment and the storage medium of cleaning equipment |
CN110051289A (en) * | 2019-04-03 | 2019-07-26 | 北京石头世纪科技股份有限公司 | Robot voice control method and device, robot and medium |
-
2019
- 2019-08-02 CN CN201910713166.0A patent/CN110428850A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102305925A (en) * | 2011-07-22 | 2012-01-04 | 北京大学 | Robot continuous sound source positioning method |
CN103941223A (en) * | 2013-01-23 | 2014-07-23 | Abb技术有限公司 | Sound source positioning system and method |
CN103257338A (en) * | 2013-04-23 | 2013-08-21 | 中国科学技术大学 | Indoor positioning method and system |
CN104092936A (en) * | 2014-06-12 | 2014-10-08 | 小米科技有限责任公司 | Automatic focusing method and apparatus |
CN107577449A (en) * | 2017-09-04 | 2018-01-12 | 百度在线网络技术(北京)有限公司 | Wake up pick-up method, device, equipment and the storage medium of voice |
CN108231075A (en) * | 2017-12-29 | 2018-06-29 | 北京视觉世界科技有限公司 | Control method, device, equipment and the storage medium of cleaning equipment |
CN110051289A (en) * | 2019-04-03 | 2019-07-26 | 北京石头世纪科技股份有限公司 | Robot voice control method and device, robot and medium |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111883186A (en) * | 2020-07-10 | 2020-11-03 | 上海明略人工智能(集团)有限公司 | Recording device, voice acquisition method and device, storage medium and electronic device |
CN111883186B (en) * | 2020-07-10 | 2022-12-23 | 上海明略人工智能(集团)有限公司 | Recording device, voice acquisition method and device, storage medium and electronic device |
CN112612444A (en) * | 2020-12-28 | 2021-04-06 | 南京紫牛软件科技有限公司 | Sound source position positioning method, sound source position positioning device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3923273B1 (en) | Voice recognition method and device, storage medium, and air conditioner | |
US9958950B2 (en) | Detector | |
FI117308B (en) | gesture Control | |
CN110434853B (en) | Robot control method, device and storage medium | |
CN110428850A (en) | Voice pick-up method, device, storage medium and mobile robot | |
TW201218023A (en) | Efficient gesture processing | |
CN106210511A (en) | A kind of method and apparatus positioning user | |
CN104125523A (en) | Dynamic earphone system and application method thereof | |
CN104297519B (en) | Human motion gesture recognition method and mobile terminal | |
CN104731307A (en) | Somatic action identifying method and man-machine interaction device | |
CN110972112B (en) | Subway running direction determining method, device, terminal and storage medium | |
CN109955248A (en) | A kind of robot and its face follower method | |
CN110767228B (en) | Sound acquisition method, device, equipment and system | |
CN107255339A (en) | Air conditioning control method, terminal device and storage medium based on terminal device | |
CN110505549A (en) | The control method and device of earphone | |
CN105893982A (en) | Method and system for fingerprint recognition based on supersonic waves | |
CN109711350A (en) | A kind of identity identifying method merged based on lip movement and voice | |
CN108318042A (en) | Navigation mode-switching method, device, terminal and storage medium | |
CN110379221A (en) | A kind of pronunciation of English test and evaluation system | |
CN112634897A (en) | Equipment awakening method and device, storage medium and electronic device | |
CN107346207B (en) | Dynamic gesture segmentation recognition method based on hidden Markov model | |
CN108536314A (en) | Method for identifying ID and device | |
CN105867595A (en) | Human-machine interaction mode combing voice information with gesture information and implementation device thereof | |
CN110852200A (en) | Non-contact human body action detection method | |
CN109378001A (en) | A kind of voice interactive method, device, electronic equipment and readable storage medium storing program for executing |
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: 20191108 |