CN107527616A - Intelligent identification Method and robot - Google Patents
Intelligent identification Method and robot Download PDFInfo
- Publication number
- CN107527616A CN107527616A CN201710910864.0A CN201710910864A CN107527616A CN 107527616 A CN107527616 A CN 107527616A CN 201710910864 A CN201710910864 A CN 201710910864A CN 107527616 A CN107527616 A CN 107527616A
- Authority
- CN
- China
- Prior art keywords
- voice messaging
- information
- robot
- label information
- sounder
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/78—Detection of presence or absence of voice signals
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Abstract
The present embodiments relate to artificial intelligence field, discloses a kind of intelligent identification Method and robot.In the present invention, intelligent identification Method, applied to robot, including：The voice messaging of sounder is received, detects in voice messaging whether include label information；Wherein, label information is the information being superimposed upon in voice messaging or the information deleted on the basis of voice messaging；If voice messaging includes label information, sounder is determined as artificial person so that it is robot or natural person that robot, which can distinguish sounder,.
Description
Technical field
The present embodiments relate to artificial intelligence field, more particularly to a kind of intelligent identification Method and robot.
Background technology
Artificial intelligence (Artificial Intelligence, referred to as " AI ") is research, develop for simulating, extend and
Extend a new technological sciences of the intelligent theory of people, method, technology and application system.It attempts to understand the reality of intelligence
Matter, and a kind of new intelligence machine that can be made a response in a manner of human intelligence is similar is produced, the research in the field includes
Robot, language identification, image recognition, natural language processing and expert system etc..Artificial intelligence is since the birth, theoretical and skill
Art is increasingly mature, and application field also constantly expands, it is contemplated that the sci-tech product that following artificial intelligence is brought, it will is the mankind
" container " of wisdom.
But inventor has found that at least there are the following problems in the prior art：As robot is further intelligent, robot
Sound also increasingly as natural person, when the sound of robot and the sound of natural person can listen Chu Lai difference, robot
Cannot be distinguished by sounder is robot or natural person.
The content of the invention
The purpose of embodiment of the present invention is to provide a kind of intelligent identification Method and robot so that robot being capable of area
It is robot or natural person to divide sounder.
In order to solve the above technical problems, embodiments of the present invention provide a kind of intelligent identification Method, including：Receive hair
The voice messaging of sound person, detect in voice messaging whether include label information；Wherein, label information is to be superimposed upon in voice messaging
Information or the information deleted on the basis of voice messaging；If voice messaging includes label information, sounder is determined as non-
Natural person.
Embodiments of the present invention additionally provide a kind of robot, including：At least one processor；And with least one
The memory of individual processor communication connection；Wherein, memory storage, which has, to instruct quilt by the instruction of at least one computing device
At least one computing device, so that at least one processor is able to carry out above-mentioned intelligent identification Method.
Embodiment of the present invention is in terms of existing technologies, right by after the voice messaging of sounder is received
Whether detected in voice messaging comprising label information, wherein, label information be the information that is superimposed upon in voice messaging or
The information deleted on the basis of voice messaging, if detecting that voice messaging includes label information, by sounder be determined as it is non-from
Right people.Because each robot can be handled the voice messaging that will be sent, include its voice messaging sent
Label information, and the label information does not have an impact to the semanteme of voice messaging so that robot is receiving sounder
It is that robot or natural person judge to sounder by the detection of voice messaging, if in voice messaging after voice messaging
Include the label information, then sounder is robot；If not including the label information in voice messaging, sounder is
Natural person, it is robot or the purpose of natural person to reach differentiation sounder.
In addition, being superimposed upon the information in voice messaging, it is specially：In one of following section or its any combination, superposition
Make an uproar at bottom：Ultrasonic wave, infrasound, not in the low frequency section of natural person's sounding limit, not in the high frequency section of natural person's sounding limit.
By bottom is made an uproar be superimposed upon ultrasonic wave, infrasound, not in the low frequency section of natural person's sounding limit, not in natural person's sounding limit
High frequency section in one of any or its meaning combination, the label information for making to be superimposed upon in voice messaging can be with flexible and changeable reality
It is existing.
In addition, label information is located at the fundamental tone position of voice messaging.Because in general sound is all sent by enunciator
What a series of different vibration of frequencies, amplitude was combined, the sound sent in these vibrations by the minimum vibration of frequency is just
It is fundamental tone, wherein, fundamental tone part is most loud and easily identifies.Therefore, label information is located to the fundamental tone of voice messaging
Position, so do, be advantageous to robot and more convenient identification is carried out to label information.
In addition, label information is located at the fundamental tone position of voice messaging and all overtone positions.Because all sounding bodies are sent
Sound, in addition to a fundamental tone, the overtone of also many different frequencies (speed of vibration) is adjoint, be exactly these overtones determine
The different tone colors of different sounding bodies, so our cans go to differentiate different sounding bodies by different tone colors.Therefore, will
Label information selects to be added to the fundamental tone position of voice messaging and all overtone positions rather than only selects to add by label information
To the fundamental tone position of voice messaging, when can preferably identifying that multiple natural persons or multiple robots speak, these overtones
Ownership main body.
In addition, after sounder is determined as into artificial person, in addition to：Label information is analyzed, obtains sounding
The identity information of person.Setting not phase during due to that different robots can be superimposed or be deleted in voice messaging in advance information
Same processing rule so that after robot is received comprising the voice messaging of label information, by dividing label information
Analysis, it is informed in voice messaging and is superimposed or deletes information and handled according to which kind of rule, so it is inverse according to the rule
To the identity information for releasing the robot for specifically sending voice messaging.
Brief description of the drawings
One or more embodiments are illustrative by the picture in corresponding accompanying drawing, these exemplary theorys
The bright restriction not formed to embodiment, the element for having same reference numbers label in accompanying drawing are expressed as similar element, removed
Non- have a special statement, and composition does not limit the figure in accompanying drawing.
Fig. 1 is a kind of flow chart of intelligent identification Method in first embodiment of the invention；
Fig. 2 is a kind of flow chart of intelligent identification Method in second embodiment of the invention；
Fig. 3 is a kind of structural representation of robot in third embodiment of the invention.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with accompanying drawing to the present invention
Each embodiment be explained in detail.However, it will be understood by those skilled in the art that in each embodiment party of the present invention
In formula, in order that reader more fully understands the application and proposes many ins and outs.But even if without these ins and outs
With many variations based on following embodiment and modification, the application technical scheme claimed can also be realized.
The first embodiment of the present invention is related to a kind of intelligent identification Method.The core of present embodiment is to receive sounding
The voice messaging of person, detect in voice messaging whether include label information；Wherein, label information is to be superimposed upon in voice messaging
Information or the information deleted on the basis of voice messaging；If voice messaging includes label information, by sounder be determined as it is non-from
Right people.Details, which is specifically described, to be realized to a kind of intelligent identification Method of present embodiment below, herein below is only
It is convenient to understand that what is provided realizes details, not implement the necessary of this programme.
The first embodiment of the present invention is related to a kind of intelligent identification Method, applied to robot, idiographic flow such as Fig. 1 institutes
Show, including：
Step 101, the voice messaging of sounder is received.
Specifically, it is necessary to which it is that natural person sends first to judge, still after the voice messaging of robot reception sounder
What artificial person sent, then operated accordingly further according to result of determination.For example, if the finger that natural person sends
Order, robot can perform corresponding operating according to the instruction, but if being the instruction that robot is sent, then robot is just not required to
Perform.For example the voice messaging of " giving me water of falling cup " for being sent in TV or in recorder, robot avoid the need for
Perform.Therefore, after the voice messaging of sounder is received, into step 102.
Step 102, detect in voice messaging whether include label information.Wherein, label information is to be superimposed upon voice messaging
In information or the information deleted on the basis of voice messaging.If detecting and label information being included in voice messaging, enter step
Rapid 103, i.e. sounder is determined as artificial person；Otherwise, into step 104, sounder is determined as natural person.
Specifically, when label information is the information being superimposed upon in voice messaging, the information that is superimposed upon in voice messaging
It can be made an uproar the bottom of for.If that is, being made an uproar in the voice messaging that robot receives the bottom of comprising, sounder can be determined as
Artificial person.Preferably, in order that the robot for receiving voice messaging specifically understands the identity for the robot for sending voice messaging
Information, bottom, which is made an uproar, to be the content similar to " I is robot, and my model is 001, and I speaks, the words duration 1 minute ".
Wherein, bottom is made an uproar synchronously is carried out with voice messaging, i.e., plays while stop simultaneously.When sounder is robot, in machine
When people plays voice messaging, just bottom is made an uproar and played together with voice messaging, if robot stops playing voice messaging,
Bottom is made an uproar also to stop therewith, and when there is voice messaging again, bottom is made an uproar and also played therewith again.Certainly, bottom mentioned here, which is made an uproar, to be
What is prerecorded can also be synthesized with voice messaging, be not specifically limited herein.
Wherein, the information mentioned here being superimposed upon in voice messaging, can in ultrasonic wave, infrasound, not in natural person
The low frequency section of the sounding limit or not one of high frequency section of natural person's sounding limit or its any combination in be superimposed.Namely
Say, can in ultrasonic wave, infrasound, not in the low frequency section of natural person's sounding limit or not in the high frequency of natural person's sounding limit
Superposition bottom is made an uproar in one of section or its any combination.Wherein, bottom is made an uproar and is added in different positions, produce different effects,
Concrete analysis is as follows：
(1) bottom is made an uproar and be superimposed upon in ultrasonic wave or infrasound.Due to can be sent and received between robot ultrasonic wave or
Infrasound, and natural person can not directly send and receive ultrasonic wave or infrasound, therefore do not interfered with by both modes
The sense of hearing of user.But a disadvantage is that natural person can not hear the particular content for the information that robot is sent.Such as in robot
In the voice messaging that A is sent, an infrasound for being less than 20 hertz is added, this wave band is not involved in the particular content spoken, when
Robot with sounder when talking with, it is only necessary to detects and infrasound is included in voice messaging, it is possible to prove that robot is current
Talk with robot.
(2) bottom is made an uproar and be superimposed upon not in the low frequency section of natural person's sounding limit or not in the high frequency of natural person's sounding limit
Section.Increase to due to bottom being made an uproar not at the low frequency section of natural person's sounding limit (such as between 20 hertz to 50 hertz),
Natural person can by play back this section recording, by this section recording frequency response region sound amplify, it is possible between hear this
The particular content for the information that robot is sent.Bottom is made an uproar increase to not the high frequency section of natural person's sounding limit (such as
1.5k hertz is between 20k hertz) when, advantage increases to the not class at the low frequency section of natural person's sounding limit with bottom is made an uproar
Seemingly, but due to that can not produce ear-piercing sensation in the high frequency section of natural person's sounding limit, children are again to high frequency section in addition
Sound sensitive.Therefore, bottom is made an uproar increases to not at the high frequency section of natural person's sounding limit, and shortcoming becomes apparent from.
In addition, when label information is in the information deleted on the basis of voice messaging, the information deleted can be：In voice
The information for the second preset duration deleted in information every the first preset duration, wherein, it is default that the second preset duration is less than first
The 1/N of duration, N are more than pre-determined threshold.Similar to the mode in perforating on paper tape, for example, if robot A is sounder,
The voice messaging that will be sent can so be deleted in robot A, can all delete 0.001 every the place of 0.1 second
The information of second, due to only having deleted the information of relatively brief a period of time, the true intention of voice messaging can't be represented
Any influence is produced, therefore, when robot detects the information deleted in the voice messaging of sounder comprising described in, by sounding
Person is determined as robot, otherwise, sounder is determined as into natural person.Preferably, because natural person can not be believed the voice sent
Breath is accomplished so accurately to delete, and robot can accomplish, for example, pre-setting the voice messaging that robot A is sent is
The information of 0.001 second is all deleted in place every 0.1 second, and it is every 0.2 second to pre-set the voice messaging that robot B is sent
All delete the information of 0.002 second in place.And hence it is also possible to all deleted by detecting the place in voice messaging every 0.2 second
The information of 0.002 second, and judge sounder for robot B.
Or label information is the information deleted on the basis of voice messaging, the information deleted can also be：Believe in voice
The information for the 3rd preset duration deleted in predeterminated frequency in breath；Wherein, the 3rd preset duration is less than preset duration thresholding.Together
Sample is similar to the mode in perforating on paper tape, for example, if robot A is sounder, then can be to will in robot A
The voice messaging sent is deleted, and can be removed the sound of 111 hertz of its sound 0.1 second, then remove 113 hertz
0.1 second, such delete equally will not represent to produce any influence on the true intention of voice messaging, and natural person also can not be identified
Come, and robot can easily identify this details, be included when in the voice messaging that robot detects sounder
It is described delete information when, sounder is determined as robot, otherwise, sounder is determined as natural person.
It should be noted that because in general sound is all that a series of frequencies for being sent by enunciator, amplitude are different
Vibration be combined.There is the minimum vibration of a frequency in these vibrations, the sound sent by it is exactly fundamental tone, and remaining is general
Sound.Wherein, the fundamental tone of sounder is most loud and is easiest to what is identified.Therefore, label information can be located at voice messaging
Fundamental tone position, so do, be advantageous to robot and more convenient identification is carried out to label information.
It is, of course, also possible to label information is located at the fundamental tone position of voice messaging and all overtone positions.Due to all hairs
The sound that sound body is sent, in addition to a fundamental tone, the overtone of also many different frequencies (speed of vibration) is adjoint, is exactly these
Overtone determines the different tone colors of different sounding bodies, and so our cans go to differentiate different sounding by different tone colors
Body.Therefore, label information is selected to be added to the fundamental tone position of voice messaging and all overtone positions rather than only believed mark
Breath selection is added to the fundamental tone position of voice messaging, can preferably identify multiple natural persons or when multiple robots speak
Wait, the ownership main body of these overtones.
Step 103, sounder is determined as artificial person.
If including label information in voice messaging that is, detecting, sounder is determined as artificial person.
Step 104, sounder is determined as natural person.
That is, if detecting does not have label information in voice messaging, sounder is determined as natural person.
Compared with prior art, a kind of intelligent identification Method that embodiment of the present invention provides, by receiving sounding
After the voice messaging of person, to whether being detected in voice messaging comprising label information, wherein, label information is is superimposed upon language
Information or the information deleted on the basis of voice messaging in message breath, if detecting that voice messaging includes label information,
Sounder is determined as artificial person.Because each robot can be handled the voice messaging that will be sent, make its hair
The voice messaging gone out includes label information, and the label information does not have an impact to the semanteme of voice messaging so that machine
People is that robot or natural person are carried out to sounder by the detection of voice messaging after the voice messaging of sounder is received
Judge, if including the label information in voice messaging, sounder is robot；If the mark is not included in voice messaging
Remember information, then sounder is natural person, and it is robot or the purpose of natural person to reach differentiation sounder.
Second embodiment of the invention is related to a kind of intelligent identification Method.Present embodiment is the base in first embodiment
Further improvement has been done on plinth, has specifically been theed improvement is that：It is further right by after sounder is determined as into artificial person
Label information is analyzed, to obtain the identity information of sounder.Due to can be in advance to different robots in voice messaging
Middle superposition or the processing rule that setting differs when deleting information so that receive the voice comprising label information in robot
After information, by analyzing label information, being informed in voice messaging and being superimposed or delete information is entered according to which kind of rule
Row processing, and then be specifically the identity information for the robot for sending voice messaging according to the reverse release of the rule.Specific stream
Journey as shown in Fig. 2 including：
Step 201, the voice messaging of sounder is received.
Step 202, detect in voice messaging whether include label information.Wherein, label information is to be superimposed upon voice messaging
In information or the information deleted on the basis of voice messaging.Label information is included in voice messaging if detecting, into step
203,；Otherwise, into step 204.
Step 203, sounder is determined as artificial person.After sounder is determined as into artificial person, into step
205。
Step 204, sounder is determined as natural person.
Step 205, label information is analyzed, obtains the identity information of sounder.
Specifically, after sounder is determined as into artificial person, label information is analyzed, obtains sounder
Identity information.Can it be differed according to setting when different robots being superimposed or deleted in voice messaging in advance information
Processing rule so that after robot is received comprising the voice messaging of label information, by analyzing label information, obtain
Know that information is superimposed or deleted in voice messaging to be handled according to which kind of rule, and then released according to the rule is reverse
The voice messaging that specifically which robot is sent.Wherein, the identity information of acquired sounder is the body of robot
Part information, can be the contents such as the operating right of the numbering of robot, the type of robot, date of manufacture and robot, this
Place is not especially limited.
In addition, it is necessary to explanation, can also be made an uproar the bottom of with to express the identity information of robot.This, which is sentenced, makes an uproar bottom superposition
Illustrated exemplified by ultrasonic wave or infrasound：Such as in the voice messaging that robot A is sent, add one and be less than
20 hertz of infrasound, bottom is made an uproar and added in this infrasound, content that this bottom is made an uproar can be that " I is robot, my model
It is 001, I speaks, the words duration 1 minute ".When robot is when with natural person or robot dialogue, it is only necessary to
Detect and infrasound is included in voice messaging, turn out robot and talk with present with robot, further, judging sounder
After robot, the voice messaging that can be sent to robot carries out semantic analysis, draws the robot for sending voice messaging
Identity information.So do, not only contribute to the communication exchange between robot, can also be in robot to receiving voice messaging
Robot under when sending instructions, the machine for sending instruction can be got based on its identity information by receiving the robot of voice messaging
The Permission Levels of people, are advantageous to further determine whether to need to send the instruction that the robot of instruction sent according to machine and perform phase
It should operate.
Because step 201 is big to step 104 with the step 101 in first embodiment to step 204 in present embodiment
Cause identical, it is intended to receive the voice messaging of sounder, detect in voice messaging whether include label information；Wherein, label information
For the information being superimposed upon in voice messaging or the information deleted on the basis of voice messaging；If voice messaging includes label information,
Sounder is then determined as artificial person, here is omitted.
Compared with prior art, a kind of intelligent identification Method that present embodiment provides, by being determined as by sounder
After artificial person, further label information is analyzed, to obtain the identity information of sounder.Due to can be in advance to not
Same robot sets different processing rule when information is superimposed or deleted in voice messaging so that received in robot
To after the voice messaging comprising label information, by analyzing label information, it is informed in voice messaging and is superimposed or deletes
Information is handled according to which kind of rule, and then is specifically to send the machine of voice messaging according to the reverse release of the rule
The identity information of people.
The step of various methods divide above, be intended merely to describe it is clear, can be merged into when realizing a step or
Some steps are split, are decomposed into multiple steps, as long as including identical logical relation, all protection domain in this patent
It is interior；To either adding inessential modification in algorithm in flow or introducing inessential design, but its algorithm is not changed
Core design with flow is all in the protection domain of the patent.
Third embodiment of the invention is related to a kind of robot, as shown in figure 3, including：At least one processor 301；With
And the memory 302 with the communication connection of at least one processor 301；Wherein, be stored with can be by least one place for memory 302
The instruction that device 301 performs is managed, instructs and is performed by least one processor 301, so that at least one processor 301 is able to carry out
The intelligent identification Method stated.
Wherein, memory 302 is connected with processor 301 using bus mode, and bus can include any number of interconnection
Bus and bridge, bus one or more processors 301 and the various of memory 302 are electrically connected to together.Bus may be used also
So that the various other of such as ancillary equipment, voltage-stablizer and management circuit or the like to be electrically connected to together, these are all
It is known in the art, therefore, no longer it is described further herein.EBI provides between bus and transceiver
Interface.Transceiver can be an element or multiple element, such as multiple receivers and transmitter, there is provided for
The unit to be communicated on transmission medium with various other devices.Through processor 301 handle data by antenna on the radio medium
It is transmitted, further, antenna also receives data and transfers data to processor 301.
Processor 301 is responsible for bus and common processing, can also provide various functions, including timing, periphery connects
Mouthful, voltage-regulation, power management and other control functions.And memory 302 can be used for storage processor 301 and perform
Used data during operation.
It will be understood by those skilled in the art that realize that all or part of step in above-described embodiment method is to pass through
Program instructs the hardware of correlation to complete, and the program storage is in the storage medium, including some instructions are causing one
Individual equipment (can be single-chip microcomputer, chip etc.) or processor (processor) perform each embodiment methods described of the application
All or part of step.And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store journey
The medium of sequence code.
It will be understood by those skilled in the art that the respective embodiments described above are to realize the specific embodiment of the present invention,
And in actual applications, can to it, various changes can be made in the form and details, without departing from the spirit and scope of the present invention.
Claims (9)
- A kind of 1. intelligent identification Method, it is characterised in that applied to robot, including：The voice messaging of sounder is received, detects in the voice messaging whether include label information；Wherein, the label information For the information being superimposed upon in voice messaging or the information deleted on the basis of the voice messaging；If the voice messaging includes the label information, the sounder is determined as artificial person.
- 2. intelligent identification Method according to claim 1, it is characterised in that the label information is to be superimposed upon voice messaging In information, wherein, the information being superimposed upon in voice messaging, specially bottom is made an uproar.
- 3. intelligent identification Method according to claim 2, it is characterised in that the information being superimposed upon in voice messaging, Specially：In one of following section or its any combination, it is superimposed the bottom and makes an uproar：Ultrasonic wave, infrasound, not in the low frequency section of natural person's sounding limit, not in the high frequency section of natural person's sounding limit.
- 4. intelligent identification Method according to claim 1, it is characterised in that the label information is in the voice messaging On the basis of the information deleted, the information deleted, be specially：Deleted in the voice messaging every the first preset duration The information of second preset duration；Wherein, second preset duration is less than the 1/N of first preset duration, and the N is more than pre- Gating limits.
- 5. intelligent identification Method according to claim 1, it is characterised in that the label information is in the voice messaging On the basis of the information deleted, the information deleted, be specially：The information for the 3rd preset duration deleted in predeterminated frequency in the voice messaging；Wherein, the described 3rd it is default when Length is less than preset duration thresholding.
- 6. intelligent identification Method according to claim 1, it is characterised in that including：The label information is located at institute's predicate The fundamental tone position of message breath.
- 7. intelligent identification Method according to claim 1, it is characterised in that the label information is located at the voice messaging Fundamental tone position and all overtone positions.
- 8. intelligent identification Method according to claim 1, it is characterised in that it is described by the sounder be determined as it is non-from After right people, in addition to：The label information is analyzed, obtains the identity information of the sounder.
- A kind of 9. robot, it is characterised in that including：At least one processor；AndThe memory being connected with least one processor communication；Wherein,The memory storage has can be by the instruction of at least one computing device, and the instruction is by least one place Manage device to perform, so that at least one processor is able to carry out the Intelligent Recognition side as described in any in claim 1 to 8 Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710910864.0A CN107527616A (en) | 2017-09-29 | 2017-09-29 | Intelligent identification Method and robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710910864.0A CN107527616A (en) | 2017-09-29 | 2017-09-29 | Intelligent identification Method and robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107527616A true CN107527616A (en) | 2017-12-29 |
Family
ID=60684129
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710910864.0A Pending CN107527616A (en) | 2017-09-29 | 2017-09-29 | Intelligent identification Method and robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107527616A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700018A (en) * | 2015-03-31 | 2015-06-10 | 江苏祥和电子科技有限公司 | Identification method for intelligent robots |
| CN105139857A (en) * | 2015-09-02 | 2015-12-09 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | Countercheck method for automatically identifying speaker aiming to voice deception |
| CN105185381A (en) * | 2015-08-26 | 2015-12-23 | 江苏久祥汽车电器集团有限公司 | Intelligent robot-based voice identification system |
| CN105869630A (en) * | 2016-06-27 | 2016-08-17 | 上海交通大学 | Method and system for detecting voice spoofing attack of speakers on basis of deep learning |
| US20170040030A1 (en) * | 2015-08-04 | 2017-02-09 | Honda Motor Co., Ltd. | Audio processing apparatus and audio processing method |
| CN106971715A (en) * | 2016-01-14 | 2017-07-21 | 芋头科技（杭州）有限公司 | A kind of speech recognition equipment applied to robot |
-
2017
- 2017-09-29 CN CN201710910864.0A patent/CN107527616A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700018A (en) * | 2015-03-31 | 2015-06-10 | 江苏祥和电子科技有限公司 | Identification method for intelligent robots |
| US20170040030A1 (en) * | 2015-08-04 | 2017-02-09 | Honda Motor Co., Ltd. | Audio processing apparatus and audio processing method |
| CN105185381A (en) * | 2015-08-26 | 2015-12-23 | 江苏久祥汽车电器集团有限公司 | Intelligent robot-based voice identification system |
| CN105139857A (en) * | 2015-09-02 | 2015-12-09 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | Countercheck method for automatically identifying speaker aiming to voice deception |
| CN106971715A (en) * | 2016-01-14 | 2017-07-21 | 芋头科技（杭州）有限公司 | A kind of speech recognition equipment applied to robot |
| CN105869630A (en) * | 2016-06-27 | 2016-08-17 | 上海交通大学 | Method and system for detecting voice spoofing attack of speakers on basis of deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105788599B (en) | Method of speech processing, router and intelligent sound control system | |
| CN1894740B (en) | Information processing system, information processing method, and information processing program | |
| US20200186912A1 (en) | Audio headset device | |
| CN108681440A (en) | A kind of smart machine method for controlling volume and system | |
| CN107124230B (en) | Sound wave communication method, terminal and server | |
| CN106714081A (en) | Networking method and intelligent device | |
| CN106356067A (en) | Recording method, device and terminal | |
| JP2019536070A (en) | User positioning method, information push method, and related apparatus | |
| CN107277260A (en) | A kind of contextual model method of adjustment, device and mobile terminal | |
| CN103886857A (en) | Method and device for controlling noise | |
| CN108922528A (en) | Method and apparatus for handling voice | |
| CN106033676A (en) | Audio play control method and device and electronic device | |
| CN109215679A (en) | Dialogue method and device based on user emotion | |
| WO2018105266A1 (en) | Information processing apparatus, information processing method, program, and information processing system | |
| KR20180099721A (en) | Crowd source database for sound identification | |
| CN110503968A (en) | A kind of audio-frequency processing method, device, equipment and readable storage medium storing program for executing | |
| CN109147764A (en) | Voice interactive method, device, equipment and computer-readable medium | |
| CN107742516B (en) | Intelligent recognition method, robot and computer readable storage medium | |
| CN109800724A (en) | A kind of loudspeaker position determines method, apparatus, terminal and storage medium | |
| CN104490570B (en) | Embedding type voiceprint identification and finding system for blind persons | |
| CN106782498A (en) | Voice messaging player method, device and terminal | |
| CN107527616A (en) | Intelligent identification Method and robot | |
| US20200278832A1 (en) | Voice activation for computing devices | |
| CN107704230A (en) | A kind of wheat sequence controlling method and control device | |
| CN104079703B (en) | A kind of information processing method and electronic equipment |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171229 |
|
| WD01 | Invention patent application deemed withdrawn after publication |