CN115240678B - Intelligent voice recognition device - Google Patents
Intelligent voice recognition device Download PDFInfo
- Publication number
- CN115240678B CN115240678B CN202211147253.2A CN202211147253A CN115240678B CN 115240678 B CN115240678 B CN 115240678B CN 202211147253 A CN202211147253 A CN 202211147253A CN 115240678 B CN115240678 B CN 115240678B
- Authority
- CN
- China
- Prior art keywords
- sound
- module
- control
- box
- recognition
- 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.)
- Active
Links
- 210000000613 ear canal Anatomy 0.000 claims abstract description 27
- 230000005484 gravity Effects 0.000 claims description 14
- 230000000694 effects Effects 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 10
- 230000005684 electric field Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 229920001746 electroactive polymer Polymers 0.000 description 4
- 238000000034 method Methods 0.000 description 4
- 230000003321 amplification Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000003199 nucleic acid amplification method Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R1/00—Details of transducers, loudspeakers or microphones
- H04R1/08—Mouthpieces; Microphones; Attachments therefor
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Selective Calling Equipment (AREA)
Abstract
The invention discloses an intelligent voice recognition device which comprises a base and a sound pickup box, wherein the sound pickup box is arranged on the base, the sound pickup box is rotated by 360 degrees through the base, the sound pickup box collects sound, the sound pickup box amplifies sound waves, a recognition system is arranged in the sound pickup box, the recognition system compares the waveform, the frequency and the amplitude of the sound, the recognition system recognizes a sent command, and the recognition system controls external equipment. The sound collecting box is provided with a structure similar to an auricle and an external auditory canal, collects and amplifies sound, and improves the accuracy of the recognition system for voice recognition.
Description
Technical Field
The invention relates to the technical field of voice recognition, in particular to an intelligent voice recognition device.
Background
Household appliances are indispensable parts in daily households, but household appliances used at present are manually opened or closed, and doors are also manually opened and closed; the high-grade household appliances can be controlled by using operating equipment such as a mobile phone or a remote controller, however, with the increase of household products, the number of remote controllers and manual switches is increased, and the increased remote controllers and switches are manually operated by users, which causes great inconvenience in use.
The intelligent home is characterized in that the intelligent home is formed by connecting various devices in the home together by using a house as a platform through the Internet of things technology, and commands are recognized by a voice recognition device to enable various homes to complete instructions, so that the convenience, comfort, artistry, safety and the like of the home are improved, and the environment-friendly and energy-saving living environment is realized.
The existing voice recognition device is too simple in structure, and when the existing voice recognition device is placed, if the existing voice recognition device is fixed and not firm enough, the whole voice recognition device is damaged, and therefore people need an intelligent voice recognition device to solve the problems.
Disclosure of Invention
The present invention is directed to an intelligent speech recognition device to solve the problems set forth in the background art.
In order to solve the technical problems, the invention provides the following technical scheme: an intelligent voice recognition device comprises a base and a sound pickup box, wherein the sound pickup box is arranged on the base, the base enables the sound pickup box to rotate for 360 degrees, the sound pickup box collects sound, and the sound pickup box amplifies sound waves; the sound collecting box is provided with a structure similar to an auricle and an external auditory canal, collects and amplifies sound, and improves the accuracy of the recognition system for voice recognition.
A rotating motor is arranged above the base and is fixed with the pickup box; the rotating motor enables the sound pickup box to rotate 360 degrees on the base in the horizontal direction.
Four groups of posture rings are arranged on the sound pickup box, each group of posture rings is provided with an ear profile plate, and ear canal tubes are arranged in the sound pickup box at positions corresponding to the ear profile plates; the gesture ring provides the support for the installation of auricle board, the auricle board is like human auricle, recognition module carries out the analysis to time difference and sound intensity difference between every two sets of adapters, the realization is to the collection of sound, the ear canal pipe is like human external auditory canal, the realization is to the enlargement of sound wave, the sound pick-up box passes through the setting of auricle board and ear canal pipe, the realization is to the collection of external sound and the enlargement of sound wave, thereby make recognition system can discern and the analysis to clear pronunciation.
The voice recognition device also comprises a recognition system, wherein the recognition system is arranged in the sound pick-up box, the recognition system compares the waveform, the frequency and the amplitude of sound, the recognition system recognizes the sent instruction, and the recognition system controls external equipment;
the recognition system comprises four groups of pickups, a recognition module and a control box, wherein the pickups are arranged on four groups of ear tubes respectively, each group of pickups is electrically connected with the recognition module, the control box is electrically connected with the recognition module, and the control box controls external equipment. The sound that the adapter transmitted to the ear canal pipe is gathered, and identification module carries out the analysis to the sound that the adapter was gathered, including the control command to the wave form of vibration, the frequency of sound wave, the amplitude of sound and user's sending, and the control box is controlled external equipment according to the control command that identification module analysis goes out to realize user's control requirement.
Every group all seted up on the gesture ring and rotated the groove, the power groove has all been seted up at the both ends that lie in the rotation groove on the gesture ring, every group all be provided with the linkage board on the ear profile board, the linkage board is located and rotates inslot portion, and the both ends of linkage board all are provided with the linkage post, every group the other end of linkage post all is located the power groove, the inside positive plate that is provided with of power groove, one side that the positive plate was kept away from to the linkage post is provided with the negative plate, be provided with the expansion pipe between positive plate and the negative plate, positive plate, negative plate all with control box electric connection. Gesture ring realizes rotating with auricle board through rotating mutually supporting of groove and linkage board and is connected, and positive plate and negative plate mutually support and form plus electric field in the expansion pipe outside, and the expansion pipe is inside to be provided with electroactive polymer, and the inflation takes place for the inside electroactive polymer of expansion pipe under the effect of outer electric field to produce the motive force to the negative plate, thereby make linkage board drive the auricle board and rotate on the gesture ring, thereby realize opening of auricle board, realize the collection to sound.
The outside that lies in every group gesture ring on the pickup box all is provided with the gear groove, every group all be provided with driven gear on the gesture ring, driven gear all is located the gear groove, the inside carrier ring that is provided with of pickup box, the spread groove has been seted up to the position that the inside corresponding gear groove lower extreme of pickup box, the position that corresponds every group link groove on the carrier ring all is provided with the driving gear, every group the driving gear all is connected with driven gear rotation through the spread groove, all is provided with the gesture motor on every group driving gear, the gesture motor is located the below of carrier ring. The gesture motor passes through the driving gear and makes driven gear rotate to make the gesture ring rotate on the sound pick-up box, realize the adjustment to the auricle board orientation through the rotation of gesture ring, thereby make the auricle board just to the sound source, thereby improve the collection of sound pick-up box to sound.
The control box is internally provided with a control module, a temperature module, a gravity sensing module and a wireless module, and the identification module, the temperature module, the gravity sensing module and the wireless module are all electrically connected with the control module;
the positive plate and the negative plate are electrically connected with the control module;
the sound that the adapter transmitted the ear canal pipe is gathered, the sound that identification module gathered the adapter carries out the analysis, include the control command that sends the amplitude and the user of the wave form, the frequency of sound wave, sound of vibration, temperature module detects the temperature of surrounding environment, and gravity response module detects this speech recognition device's inclination and direction, wireless module carries out wireless connection with outside smart machine.
The recognition system comprises an input mode and a recognition mode, when the recognition system is in the input mode, the recognition module analyzes the sound collected by the sound pickup and inputs a database, the analysis and the input of the amplitude of the sound, the frequency of the sound wave and the waveform of the vibration are included, the input of a control order is also included, the database is a database for storing the sound of a user, the control order is a control instruction which is input to the voice recognition device by the user and is used for controlling external equipment, and the control order is used for controlling the external equipment
Guide language
Number of
Object
The leading language is a control language and is a control language which is set by a user independently and accords with self habits, the leading language comprises opening, closing, increasing, decreasing, opening and closing, the number is the number of the controlled external equipment, the user does not need to add the number when standing in front of the external equipment needing to be controlled, the objects are the external equipment needing to be controlled and comprise automatic curtains, air conditioners, lamps and the like, the parameters are numerical values which the external equipment needs to adjust or numerical values which the external equipment needs to adjust, and the user selects the added parameters or does not add the parameters independently, such as opening the air conditioner, increasing the air conditioner air speed, increasing the air conditioner 2 degrees, increasing the air conditioner to 26 degrees and the like.
When the recognition mode is adopted, the recognition module analyzes and compares the sound collected by the sound pickup with the sound data in the database, the recognition mode comprises the analysis of user sound and the comparison of control command modes, the recognition module compares the collected sound with the sound in the database, the recognition module compares the amplitude of the sound, the frequency of the sound wave and the waveform of vibration, and the control module controls external equipment through correct control commands analyzed by the recognition module.
The recognition module records the time and the sound intensity of collecting the sound by each group of sound pickup, analyzes the time difference and the sound intensity difference between each two groups of sound pickup, calculates the propagation speed of the sound in the air by the temperature of the surrounding environment detected by the temperature module, judges the direction and the distance of the sound source by the recognition module through the time difference effect and the sound intensity difference effect, and controls the external equipment by the control order and the direction of the sound source. The control module comprises a layout diagram of a house and a distribution diagram of external equipment, analyzes the external equipment near the position of the sound source through the direction of the sound source and combining the distribution diagram of the external equipment, and screens out and controls the external equipment to be controlled by combining a control command.
The recognition module analyzes the time and the sound intensity of collected sound, finds out the first pickup which collects the sound and has the maximum sound intensity, and the control module rotates the rotating motor to enable the first pickup which collects the sound and has the maximum sound intensity to just face the direction of the sound source.
The base below is provided with the slipmat, and the inside power module that is provided with of base, power module and rotating electrical machines, adapter, identification module, temperature module, gravity-feed tank response module, wireless module and control module electric connection.
Compared with the prior art, the invention has the following beneficial effects:
1. in the invention, an external sound pickup device is not needed, thus solving the technical problem that the wall body is damaged due to the sound pickup problem; in the invention, the identification system firstly detects the temperature of the surrounding environment through the temperature module, calculates the propagation speed of sound in the air, then the identification module judges the azimuth and the distance of the sound source through the time difference effect and the sound intensity difference effect, and the identification module can clearly judge the position of the external equipment to be controlled through the sent control command and the position of the sound source, such as: the user station is in front of the curtain to be opened and sends a control command, the control command is to open the curtain, and the control module controls the external equipment near the position of the sound source through the position of the sound source and the control command analyzed by the identification module, namely the curtain is opened.
2. Install the structure of similar auricle and external auditory canal on the sound-picking box, the auricle board is like human auricle, realizes the collection to sound, and the ear canal pipe is like human external auditory canal, realizes the enlargiing to the sound wave, and the sound-picking box passes through the setting of ear outline board and ear canal pipe, realizes the collection of external sound and the enlargiing of sound wave to make identification system can discern and the analysis to clear pronunciation, improve identification system's accuracy to speech recognition.
3. The gesture motor passes through the driving gear and makes driven gear rotate to make the gesture ring rotate on the sound pick-up box, realize the adjustment to the auricle board orientation through the rotation of gesture ring, thereby make the auricle board just to the sound source, thereby improve the collection of sound pick-up box to sound.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic view of the overall structure of the present invention;
FIG. 2 is a schematic diagram of the structure of the present invention in recognition mode;
FIG. 3 is a schematic view of the overall internal structure of the present invention;
FIG. 4 is a schematic view of the connection structure of the position ring and the ear profile plate of the present invention;
FIG. 5 is a schematic structural view of the region A in FIG. 4 according to the present invention;
fig. 6 is a schematic view of the structure between the positive and negative plates and the expansion tube of the present invention.
In the figure: 1. a base; 2. a sound pickup box; 1-1, a non-slip mat; 1-2, rotating an electric machine; 2-1, a posture ring; 2-2, auricle board; 2-3, ear canal; 2-4, bearing plates; 2-5, driven gear; 2-6, a driving gear; 2-7, an attitude motor; 2-8, a bearing ring; 2-11, a power groove; 2-12, a positive plate; 2-13, expansion pipe; 2-14, a spring; 2-21, a negative plate; 3-1, a sound pick-up; 3-2, identifying the module; 3-3, a control box.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1 to 6, the present invention provides a technical solution:
the utility model provides an intelligence speech recognition device, this speech recognition device includes base 1, sound pick-up box 2, and sound pick-up box 2 rotates and installs on base 1, and base 1 makes sound pick-up box 2 carry out 360 rotations, and sound pick-up box 2 is collected sound, and sound pick-up box 2 enlargies the sound wave.
A rotary motor 1-2 is arranged in the middle position above the base 1, and the rotary motor 1-2 is fixed with the sound pick-up box 2; the rotating motor 1-2 makes the sound pickup box 2 rotate 360 degrees on the base in the horizontal direction.
The anti-slip mat is arranged below the base 1, the power supply module is arranged at the lower end inside the base 1, the power supply module enables the center of gravity of the whole device to move downwards, the whole device is placed more stably, and the power supply module is electrically connected with the rotating motor 1-2, the sound pickup 3-1, the recognition module 3-2, the temperature module, the gravity sensing module, the wireless module and the control module.
Four groups of posture rings 2-1 are rotatably mounted on the sound pickup box 2, ear contour plates 2-2 are rotatably mounted on each group of posture rings 2-1, ear canal tubes 2-3 are fixed in positions corresponding to each group of ear contour plates 2-2 in the sound pickup box 2, the shapes of the ear canal tubes 2-3 are similar to the shapes of external auditory canals of a human body, a bearing plate 2-4 is arranged above the ear canal tubes 2-3 in the sound pickup box 2, and sound transmission channels are formed in positions corresponding to each group of ear canal tubes 2-3 in the bearing plate 2-4;
the ear outline plate 2-2 is like the auricle of a human body to realize the collection of sound, the ear canal tube 2-3 is like the external ear canal of the human body to realize the amplification of sound waves, and the sound pickup box 2 realizes the collection of external sound and the amplification of sound waves through the arrangement of the ear outline plate 2-2 and the ear canal tube 2-3, so that the recognition system can recognize and analyze clear voice.
Gear grooves are formed in the outer side of each group of posture rings 2-1 on the sound picking box 2, each group of posture rings 2-1 is provided with an annular driven gear 2-5, the driven gears 2-5 are located in the gear grooves, bearing rings 2-8 are fixed inside the sound picking box 2, connecting grooves are formed in positions corresponding to the lower ends of the gear grooves in the sound picking box 2, driving gears 2-6 are rotatably installed on the bearing rings 2-8 corresponding to the connecting grooves in each group, each group of driving gears 2-6 are rotatably connected with the driven gears 2-5 through the connecting grooves, posture motors 2-7 are installed on the driving gears 2-6 in each group, the posture motors 2-7 are located below the bearing rings 2-8, the posture motors 2-7 are fixed with the bearing rings 2-8, and the driving gears 2-6 and the driven gears 2-5 are helical gears.
Each group of posture rings 2-1 is provided with a rotating groove, two ends of each posture ring 2-1, which are positioned in the rotating grooves, are provided with power grooves 2-11, each group of auricles 2-2 is provided with a linkage plate, the linkage plates are positioned in the rotating grooves, two ends of each linkage plate are provided with linkage columns, the other ends of each group of linkage columns are positioned in the power grooves 2-11, positive plates 2-12 are fixed in the power grooves 2-11, one sides, which are far away from the positive plates 2-12, of the linkage columns are provided with negative plates 2-21, expansion pipes 2-13 and springs 2-14 are arranged between the positive plates 2-12 and the negative plates 2-21, the expansion pipes 2-13 enable the auricles 2-2 to rotate on the posture rings 2-1 through expansion, the springs 2-14 enable the auricles 2-2 to be completely attached to the posture rings 2-1, and the positive plates 2-12 and the negative plates 2-21 are electrically connected with a control box 3-3.
The positive plate 2-12 and the negative plate 2-21 are matched with each other to form an external electric field outside the expansion pipe 2-13, an electroactive polymer is arranged inside the expansion pipe 2-13, and the electroactive polymer inside the expansion pipe 2-13 expands under the action of the external electric field, so that a driving force is generated on the negative plate 2-21, the linkage plate drives the ear profile plate 2-2 to rotate on the posture ring 2-1, the ear profile plate 2-2 is opened, and sound collection is achieved.
The device also comprises an identification system, wherein the identification system is arranged in the sound pickup box 2, compares the waveform, the frequency and the amplitude of sound, identifies the sent instruction by the identification system, and controls external equipment by the identification system;
the recognition system comprises four groups of sound pickups 3-1, a recognition module 3-2 and a control box 3-3, wherein the four groups of sound pickups 3-1 are respectively arranged on four sound transmission channels of a bearing plate 2-4, the recognition module 3-2 is arranged on the bearing plate 2-4, each group of sound pickups 3-1 are electrically connected with the recognition module 3-2, the control box 3-3 is electrically connected with the recognition module 3-2, and the control box 3-3 controls external equipment.
The sound pickup 3-1 collects the sound transmitted by the ear canal tube 2-3, the recognition module 3-2 analyzes the sound collected by the sound pickup 3-1, the sound comprises a vibration waveform, a sound wave frequency, a sound amplitude and a control instruction sent by a user, and the control box 3-3 controls external equipment according to the control instruction analyzed by the recognition module 3-2, so that the control requirement of the user is met.
A control module, a temperature module, a gravity sensing module and a wireless module are arranged in the control box 3-3, and the identification module 3-2, the temperature module, the gravity sensing module and the wireless module are all electrically connected with the control module;
the positive plate 2-12 and the negative plate 2-21 are electrically connected with the control module;
the temperature module detects the temperature of the surrounding environment, the wireless module is in wireless connection with external intelligent equipment, the wireless module comprises an intelligent home, a mobile phone, a notebook computer and the like which are installed by a user, the user is in wireless connection with the voice recognition device through the mobile phone, and the voice recognition device is remotely controlled, such as air conditioner control, lamp control and the like.
The gravity sensing module detects the inclination angle and the direction of the voice recognition device, the gravity sensing module also monitors the distance between the voice recognition device and the ground or the desktop, and when the voice recognition device inclines, the control module controls the rotating motor 1-2 according to the inclined angle and the inclined direction, so that the ear profile plate 2-2 is firstly contacted with the desktop or the ground, and the voice recognition device is prevented from toppling over through the support of the ear profile plate 2-2.
When the voice recognition device is weightless, namely falls from a high place, the control module controls the rotating motor 1-2 to enable the rotating motor 1-2 to rotate at a high speed, and controls the posture motor 2-7 simultaneously, so that the ear plate 2-2 is in an inclined state on the sound pick-up box 2 and serves as a propeller blade, the power supply module adjusts the gravity center of the voice recognition device to enable the voice recognition device to be in a vertical state, the base 1 is arranged below the sound pick-up box 2, and the voice recognition device slowly falls down through the high-speed rotation of the sound pick-up box 2.
The recognition system comprises an entry mode and a recognition mode;
in the recording mode, the recognition module 3-2 analyzes and records the sound collected by the sound pickup 3-1 into a database, wherein the database analyzes and records the amplitude, the frequency and the waveform of vibration of the sound, and also records a control order, the database is a database for storing the sound of a user, the control order is a control instruction which is input into the voice recognition device by the user and is used for controlling external equipment, and the control order is used for controlling the external equipment
Guide language
Number of
Object
The number of the parameters is the number of the controlled external equipment, and when the user station is in front of the external equipment to be controlled, the user station does not need to add the parameters, wherein the guide words are control languages and control languages which are set by the user independently and accord with habits of the user, and the control languages comprise opening, closing, increasing, decreasing, opening, closing and the likeThe number of the objects is external equipment to be controlled, the objects comprise automatic curtains, air conditioners, lamps and the like, the parameters are values which need to be adjusted or values which need to be adjusted by the external equipment, and a user can independently select to add or not add parameters, such as turning on the air conditioner, increasing the air speed of the air conditioner, adjusting the air conditioner to 2 degrees, adjusting the air conditioner to 26 degrees and the like;
when the pattern is identified, the identification module 3-2 analyzes and compares the sound collected by the sound pickup 3-1 with the sound data in the database, including the analysis of the sound of the user and the comparison of the control command pattern, the identification module 3-2 compares the collected sound with the sound in the database, including the comparison of the amplitude of the sound, the frequency of the sound wave and the waveform of vibration, the control command included in the sound analyzed by the user and the sound emitted by the user, and the control module controls the external device through the correct control command analyzed by the identification module 3-2.
The recognition module 3-2 records the time and sound intensity of sound collected by each group of sound pick-up 3-1, the recognition module 3-2 analyzes the time difference and sound intensity difference between each two groups of sound pick-up 3-1, the control module calculates the propagation speed of sound in the air according to the temperature of the surrounding environment detected by the temperature module, the recognition module 3-2 judges the direction and distance of the sound source according to the time difference effect and the sound intensity difference effect, and the control module controls external equipment according to a control command and the direction of the sound source.
When only one external device is provided, for example, only one air conditioner is provided, the control module turns on only one air conditioner according to the control command, and under the condition, the position of the user is not analyzed.
The recognition module 3-2 analyzes the time and the sound intensity of the collected sound to find out a first sound pickup 3-1 which collects the sound and has the maximum sound intensity, and marks the first sound pickup 3-1 as a first sound pickup 3-1, simultaneously marks the sound pickup 3-1 opposite to the first sound pickup 3-1 as a fourth sound pickup 3-1, and marks the sound pickups 3-1 at the left side and the right side as a second sound pickup 3-1 and a third sound pickup 3-1 respectively;
the control module enables the rotating motor 1-2 to rotate, enables the first sound pickup 3-1 to face the direction of a sound source, enables the fourth sound pickup 3-1 opposite to the first sound pickup 3-1 to be closed, and enables the auricle plate 2-2 corresponding to the fourth sound pickup 3-1 to be closed, so that the influence of sound transmitted in other directions on the collection and recognition of user voice is prevented, the control module adjusts the auricle plates 2-2 on the outer sides of the second sound pickup 3-1 and the third sound pickup 3-1, the control module enables the character bar ring 2-1 to rotate on the sound pickup box 2 through controlling the posture motor 2-7, the auricle plates 2-2 face the direction of the sound source, and therefore the sound collection effect of the second sound pickup 3-1 and the third sound pickup 3-1 is improved.
The working principle of the invention is as follows:
the control module controls the power-on and power-off of the positive plates 2-12 and the negative plates 2-21, when the voice of a user is recognized, the control module controls the positive plates 2-12 and the negative plates 2-21 to be powered on, and the expansion pipes 2-13 are expanded through an external electric field, so that the ear contour plates 2-2 rotate on the posture rings 2-1, and the ear canal pipes 2-3 are opened.
User's sound is transmitted to the sound pick-up 3-1 from the ear canal 2-3, four groups of sound pick-up 3-1 collect the sound, and transmit the collected sound data to the recognition module 3-2, the recognition module 3-2 records the time and sound intensity of the sound collected by each group of sound pick-up 3-1, the recognition module 3-2 analyzes the time difference and sound intensity difference between each two groups of sound pick-up 3-1, the control module calculates the propagation speed of the sound in the air through the temperature of the surrounding environment detected by the temperature module, the recognition module 3-2 judges the direction and distance of the sound source through the time difference effect and sound intensity difference effect, and the control module controls the external device through the control command and the direction of the sound source.
The recognition module 3-2 analyzes the time and the sound intensity of the collected sound to find out a first sound pickup 3-1 which collects the sound and has the maximum sound intensity, and marks the first sound pickup 3-1 as a first sound pickup 3-1, simultaneously marks the sound pickup 3-1 opposite to the first sound pickup 3-1 as a fourth sound pickup 3-1, and marks the sound pickups 3-1 at the left side and the right side as a second sound pickup 3-1 and a third sound pickup 3-1 respectively;
the control module enables the rotating motor 1-2 to rotate, enables the first sound pickup 3-1 to face the direction of a sound source, enables the fourth sound pickup 3-1 opposite to the first sound pickup 3-1 to be closed, and enables the auricle plate 2-2 corresponding to the fourth sound pickup 3-1 to be closed, so that the influence of sound transmitted in other directions on the collection and recognition of user voice is prevented, the control module adjusts the auricle plates 2-2 on the outer sides of the second sound pickup 3-1 and the third sound pickup 3-1, the control module enables the character bar ring 2-1 to rotate on the sound pickup box 2 through controlling the posture motor 2-7, the auricle plates 2-2 face the direction of the sound source, and therefore the sound collection effect of the second sound pickup 3-1 and the third sound pickup 3-1 is improved.
The recognition module 3-2 analyzes the sound, and the collected sound is compared with the sound data in the database, including the comparison of the amplitude of the sound, the frequency of the sound wave and the waveform of the vibration, the sound of the user and the control order contained in the sound sent by the user are analyzed, the control module controls the external equipment through the correct control order analyzed by the recognition module 3-2, and if the control module turns on the air conditioner according to the control order sent by the user, the air conditioner is turned on.
It should be noted that, in this document, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. An intelligent speech recognition device, characterized in that: the voice recognition device comprises a base (1) and a sound pickup box (2), wherein the sound pickup box (2) is arranged on the base (1), the sound pickup box (2) is rotated by the base (1), sound is collected by the sound pickup box (2), and sound waves are amplified by the sound pickup box (2);
four groups of posture rings (2-1) are arranged on the sound pickup box (2), ear contour plates (2-2) are arranged on each group of posture rings (2-1), and ear canal tubes (2-3) are arranged in the sound pickup box (2) at positions corresponding to each group of ear contour plates (2-2);
the voice recognition device further comprises a recognition system, the recognition system is arranged in the sound pickup box (2), the recognition system comprises four groups of sound pickups (3-1), a recognition module (3-2) and a control box (3-3), the four groups of sound pickups (3-1) are respectively arranged on the four groups of ear canal tubes (2-3), each group of sound pickups (3-1) is electrically connected with the recognition module (3-2), the recognition module (3-2) analyzes time difference and sound intensity difference between each two groups of sound pickups (3-1), the control box (3-3) is electrically connected with the recognition module (3-2), and the control box (3-3) controls external equipment;
a rotating motor (1-2) is arranged above the base (1), and the rotating motor (1-2) is fixed with the pickup box (2);
each group of posture rings (2-1) is provided with a rotating groove, the two ends of each posture ring (2-1) located in the rotating groove are provided with power grooves (2-11), each group of ear clearance plates (2-2) is provided with a linkage plate, the linkage plate is located inside the rotating groove, the two ends of the linkage plate are provided with linkage columns, the other end of each group of linkage columns is located in the power grooves (2-11), positive plates (2-12) are arranged inside the power grooves (2-11), one sides of the linkage columns, far away from the positive plates (2-12), are provided with negative plates (2-21), expansion pipes (2-13) are arranged between the positive plates (2-12) and the negative plates (2-21), and the positive plates (2-12) and the negative plates (2-21) are electrically connected with a control box (3-3).
2. The intelligent speech recognition device of claim 1, wherein: gear grooves are formed in the outer side of each group of posture rings (2-1) on the sound pickup box (2), driven gears (2-5) are arranged on the posture rings (2-1) of each group, the driven gears (2-5) are located in the gear grooves, bearing rings (2-8) are arranged inside the sound pickup box (2), connecting grooves are formed in the positions, corresponding to the lower ends of the gear grooves, inside the sound pickup box (2), of the sound pickup box, driving gears (2-6) are arranged on the bearing rings (2-8) in positions corresponding to the connecting grooves of each group, the driving gears (2-6) of each group are rotatably connected with the driven gears (2-5) through the connecting grooves, posture motors (2-7) are arranged on the driving gears (2-6) of each group, and the posture motors (2-7) are located below the bearing rings (2-8).
3. The intelligent speech recognition device of claim 1, wherein: the control box (3-3) is internally provided with a control module, a temperature module, a gravity sensing module and a wireless module, and the identification module (3-2), the temperature module, the gravity sensing module and the wireless module are all electrically connected with the control module;
the positive plates (2-12) and the negative plates (2-21) are electrically connected with the control module;
the sound pickup device is characterized in that sound transmitted by an ear canal tube (2-3) is collected by the sound pickup device (3-1), the sound collected by the sound pickup device (3-1) is analyzed by the recognition module (3-2), and the sound includes a waveform of vibration, frequency of sound wave, amplitude of sound and a control instruction sent by a user, the temperature module detects the temperature of the surrounding environment, the gravity sensing module detects the inclination angle and direction of the voice recognition device, and the wireless module is in wireless connection with external intelligent equipment.
4. An intelligent speech recognition device according to claim 3, wherein: the recognition system comprises an input mode and a recognition mode, and when the recognition system is in the input modeThe recognition module (3-2) analyzes and records the sound collected by the sound pickup (3-1) into a database, the database analyzes and records the amplitude of the sound, the frequency of the sound and the waveform of vibration, and also records a control order, the database is a database for storing the sound of a user, the control order is a control instruction which is input into the voice recognition device by the user and is used for controlling external equipment, and the control order = a guide word
Number of
Object
The object is the external equipment to be controlled, and the parameter is a numerical value which needs to be adjusted or a numerical value which needs to be adjusted of the external equipment.
5. The intelligent speech recognition device of claim 4, wherein: when the pattern is identified, the identification module (3-2) analyzes and compares the sound collected by the sound pickup (3-1) with the sound data in the database, the analysis of the user sound and the comparison of the control command pattern are included, the identification module (3-2) compares the collected sound with the sound in the database, the comparison of the amplitude of the sound, the frequency of the sound wave and the waveform of vibration is included, and the control module controls external equipment through correct control commands analyzed by the identification module (3-2).
6. The intelligent speech recognition device of claim 5, wherein: the sound control system is characterized in that the recognition module (3-2) records the time and sound intensity of sound collected by each group of sound pick-up devices (3-1), the recognition module (3-2) analyzes the time difference and sound intensity difference between every two groups of sound pick-up devices (3-1), the control module calculates the propagation speed of the sound in the air through the temperature of the surrounding environment detected by the temperature module, the recognition module (3-2) judges the direction and distance of the sound source through the time difference effect and the sound intensity difference effect, and the control module controls external equipment through a control command and the direction of the sound source.
7. The intelligent speech recognition device of claim 6, wherein: the recognition module (3-2) analyzes the time and the sound intensity of collected sound to find out a first sound collector (3-1) which collects the sound and has the maximum sound intensity, and the control module enables the rotating motor (1-2) to rotate so that the first sound collector (3-1) which collects the sound and has the maximum sound intensity is opposite to the direction of the sound source.
8. The intelligent speech recognition device of claim 1, wherein: the anti-skid device is characterized in that an anti-skid pad (1-1) is arranged below the base (1), a power module is arranged inside the base (1), and the power module is electrically connected with the rotating motor (1-2), the sound pickup (3-1), the identification module (3-2), the temperature module, the gravity sensing module, the wireless module and the control module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211147253.2A CN115240678B (en) | 2022-09-21 | 2022-09-21 | Intelligent voice recognition device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211147253.2A CN115240678B (en) | 2022-09-21 | 2022-09-21 | Intelligent voice recognition device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115240678A CN115240678A (en) | 2022-10-25 |
| CN115240678B true CN115240678B (en) | 2022-12-09 |
Family
ID=83681935
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211147253.2A Active CN115240678B (en) | 2022-09-21 | 2022-09-21 | Intelligent voice recognition device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115240678B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109298642A (en) * | 2018-09-20 | 2019-02-01 | 三星电子（中国）研发中心 | The method and device being monitored using intelligent sound box |
| JP2019176332A (en) * | 2018-03-28 | 2019-10-10 | 株式会社フュートレック | Speech extracting device and speech extracting method |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1544635B1 (en) * | 2002-08-30 | 2012-01-18 | Nittobo Acoustic Engineering Co.,Ltd. | Sound source search system |
| JP5867799B2 (en) * | 2011-06-23 | 2016-02-24 | 国立研究開発法人産業技術総合研究所 | Sound collecting / reproducing apparatus, program, and sound collecting / reproducing method |
| JP5889752B2 (en) * | 2012-08-30 | 2016-03-22 | 本田技研工業株式会社 | Artificial movable ear device and method for specifying sound source direction |
| KR102549689B1 (en) * | 2015-12-24 | 2023-06-30 | 삼성전자 주식회사 | Electronic device and method for controlling an operation thereof |
| JP2018007256A (en) * | 2016-07-04 | 2018-01-11 | イーエム−テック・カンパニー・リミテッドＥＭ−ＴＥＣＨ．Ｃｏ．，Ｌｔｄ． | Voice amplifier with audio focusing function |
| WO2018027880A1 (en) * | 2016-08-12 | 2018-02-15 | 森声数字科技（深圳）有限公司 | Fixed device and audio capturing device |
| JP6903933B2 (en) * | 2017-02-15 | 2021-07-14 | 株式会社Ｊｖｃケンウッド | Sound collecting device and sound collecting method |
| CN109257682B (en) * | 2018-09-29 | 2020-04-24 | 歌尔科技有限公司 | Sound pickup adjusting method, control terminal and computer readable storage medium |
| CN110853641A (en) * | 2019-11-14 | 2020-02-28 | 刘飞 | Pickup system and using method thereof |
| CN211063758U (en) * | 2020-01-21 | 2020-07-21 | 佛山博智医疗科技有限公司 | Adjustable sound collection device and hearing aid equipment applying same |
| JP6910519B1 (en) * | 2020-09-15 | 2021-07-28 | 秀毅 和田 | Headphone type sound collector |
| CN213303494U (en) * | 2020-10-27 | 2021-05-28 | 苏州芯沃科电子科技有限公司 | Display with voice control and voice direction recognition |
-
2022
- 2022-09-21 CN CN202211147253.2A patent/CN115240678B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019176332A (en) * | 2018-03-28 | 2019-10-10 | 株式会社フュートレック | Speech extracting device and speech extracting method |
| CN109298642A (en) * | 2018-09-20 | 2019-02-01 | 三星电子（中国）研发中心 | The method and device being monitored using intelligent sound box |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115240678A (en) | 2022-10-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103148436A (en) | Natural light and electric power mixed illuminating system based on internet of things | |
| CN115240678B (en) | Intelligent voice recognition device | |
| CN109875371A (en) | One kind is intelligent to push away curtain device and its control system | |
| CN204697289U (en) | Based on identification of sound source system and the intelligent appliance equipment of microphone | |
| CN204460507U (en) | Portable air-conditioning | |
| CN204985008U (en) | Fan control system based on thing networking | |
| CN108836199A (en) | A kind of electric system with cleaning and air blowing function | |
| CN216159921U (en) | Environmental data collection system that intelligence electrical apparatus was used | |
| CN208926219U (en) | A kind of electric system with cleaning and air blowing function | |
| CN105696898A (en) | Solar self-adaptation window control device | |
| CN206618083U (en) | A kind of Intelligent central air conditioner energy-saving control system | |
| CN110567071B (en) | Intelligent indoor air conditioning integrated system based on automatic window | |
| CN114033272A (en) | Internet of things intelligent window achieving automatic control based on environment monitoring | |
| CN103110330A (en) | Automatic curtain control device | |
| CN210148081U (en) | Intelligent household robot capable of automatically searching light and charging | |
| CN206816139U (en) | A kind of built-in intelligent shutter based on photovoltaic full-glass component | |
| CN207766462U (en) | A kind of Intelligent microphone holder device that can be followed automatically | |
| CN220451670U (en) | Side-open type electric window | |
| CN206380400U (en) | A kind of greenhouse thermostat | |
| CN206430325U (en) | A kind of adaptive device of radiator valve | |
| CN220211359U (en) | Irrigation control integrated equipment is gathered to collection environment | |
| CN214089078U (en) | Photovoltaic sterilization automatic clothes airing device | |
| CN211058681U (en) | Multifunctional intelligent curtain | |
| CN205713651U (en) | A kind of solar energy self adaptation window controls device | |
| CN114759866B (en) | Solar energy storage device capable of accurately compensating heated dislocation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |