CN115331677B - An end-to-end speech recognizer based on CTC structure - Google Patents
An end-to-end speech recognizer based on CTC structure Download PDFInfo
- Publication number
- CN115331677B CN115331677B CN202210969152.7A CN202210969152A CN115331677B CN 115331677 B CN115331677 B CN 115331677B CN 202210969152 A CN202210969152 A CN 202210969152A CN 115331677 B CN115331677 B CN 115331677B
- Authority
- CN
- China
- Prior art keywords
- fixedly connected
- shell
- fixing
- recognizer based
- structure according
- 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
- 238000007790 scraping Methods 0.000 claims abstract description 25
- 230000005540 biological transmission Effects 0.000 claims abstract description 16
- 230000017525 heat dissipation Effects 0.000 claims description 12
- 238000004804 winding Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 4
- 238000004140 cleaning Methods 0.000 abstract description 2
- 206010063385 Intellectualisation Diseases 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 8
- 239000000428 dust Substances 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 5
- 238000000034 method Methods 0.000 description 5
- 238000007789 sealing Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 210000003205 muscle Anatomy 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B08—CLEANING
- B08B—CLEANING IN GENERAL; PREVENTION OF FOULING IN GENERAL
- B08B1/00—Cleaning by methods involving the use of tools
- B08B1/10—Cleaning by methods involving the use of tools characterised by the type of cleaning tool
- B08B1/16—Rigid blades, e.g. scrapers; Flexible blades, e.g. wipers
- B08B1/165—Scrapers
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B08—CLEANING
- B08B—CLEANING IN GENERAL; PREVENTION OF FOULING IN GENERAL
- B08B1/00—Cleaning by methods involving the use of tools
- B08B1/30—Cleaning by methods involving the use of tools by movement of cleaning members over a surface
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05K—PRINTED CIRCUITS; CASINGS OR CONSTRUCTIONAL DETAILS OF ELECTRIC APPARATUS; MANUFACTURE OF ASSEMBLAGES OF ELECTRICAL COMPONENTS
- H05K7/00—Constructional details common to different types of electric apparatus
- H05K7/20—Modifications to facilitate cooling, ventilating, or heating
- H05K7/20009—Modifications to facilitate cooling, ventilating, or heating using a gaseous coolant in electronic enclosures
- H05K7/20136—Forced ventilation, e.g. by fans
- H05K7/20145—Means for directing air flow, e.g. ducts, deflectors, plenum or guides
Landscapes
- Engineering & Computer Science (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Physics & Mathematics (AREA)
- Thermal Sciences (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Cleaning In General (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Tables And Desks Characterized By Structural Shape (AREA)
Abstract
The invention relates to the technical field of voice recognizers and discloses an end-to-end voice recognizer based on a CTC structure, which comprises a mounting plate, wherein the top of the mounting plate is fixedly connected with a shell, a plurality of sound transmission holes are formed in the top of the shell, the inner wall of the top of the shell is fixedly connected with a fixing seat, the bottom of the fixing seat is provided with a second sliding groove, a sliding seat is movably connected in the second sliding groove, the inner wall of the top of the shell is fixedly connected with a fixing frame, the outer wall of the bottom of the fixing frame is fixedly connected with a motor, and one end of an output shaft of the motor penetrates through the fixing frame and is fixedly connected with a disc. The invention not only can clean the sound transmission Kong Dedao through the cooperation of the scraping plate and the torsion spring, and improves the cleaning effect of the device, but also can realize the end-to-end transmission with the Internet through the cooperation of the MCU module and the voice recognition module, improves the intellectualization of the device, and can clean the radiating holes through the scraping frame, thereby improving the scraping effect of the device.
Description
Technical Field
The invention relates to the technical field of voice recognizers, in particular to an end-to-end voice recognizer based on a CTC structure.
Background
With the progress of data processing technology and the rapid popularization of mobile internet, computer technology is widely applied to various fields of society, and mass data generation is brought along with the development of the computer technology, wherein voice data is more and more emphasized by people, in recent years, the voice recognition technology is remarkably improved, the laboratory is started to move to the market, the voice recognition technology belongs to an important branch in the artificial intelligence direction, a plurality of subjects are involved, the key links in man-machine natural interaction technology are involved, the application of the voice recognition technology is wide, and an end-to-end voice recognizer utilizing CTC network communication technology is provided.
The voice recognizer is generally provided with a sound transmission hole, so that electrical components inside the voice recognizer are convenient to perform voice recognition processing, however, after the voice recognizer is used for a long time, dust is easy to adhere to the sound transmission hole, and certain influence is caused on voice recognition, so that the end-to-end voice recognizer based on the CTC structure is very necessary.
Disclosure of Invention
(One) solving the technical problems
Aiming at the defects of the prior art, the invention provides an end-to-end voice recognizer based on a CTC structure, which mainly solves the problem that dust is easy to adhere to a sound transmission hole after the voice recognizer is used for a long time, and the voice recognition is affected to a certain extent.
(II) technical scheme
In order to achieve the above purpose, the present invention provides the following technical solutions:
The utility model provides an end-to-end speech recognizer based on CTC structure, includes the mounting panel, the top fixedly connected with shell of mounting panel, a plurality of sound holes have been seted up at the top of shell, the top inner wall fixedly connected with fixing base of shell, the second spout has been seted up to the bottom of fixing base, swing joint has the slide in the second spout, the top inner wall fixedly connected with mount of shell, the bottom outer wall fixedly connected with motor of mount, and the one end of motor output shaft passes mount and fixedly connected with disc, the top swing joint of disc has the connecting rod, and the connecting rod rotates with the slide to be connected, the top inner wall swing joint of shell has the axis of rotation, one side fixedly connected with two scrapers of axis of rotation, one side swing joint of axis of rotation has the torsional spring, and the both ends of torsional spring are fixed with axis and shell respectively, one side fixedly connected with of axis of rotation unreels the roller, one side round joint of unreels the roller has the stay cord, and the one end and the slide of stay cord are fixed mutually, the top fixedly connected with electrical component fixed plate of mounting panel.
Further, MCU module, SIM draw-in groove, speech recognition module, microphone and loudspeaker are fixedly connected with at the top of electrical component fixed plate, and MCU module, SIM draw-in groove, speech recognition module, microphone and loudspeaker electric connection.
On the basis of the scheme, a plurality of heat dissipation holes are formed in two sides of the shell, first sliding grooves are formed in inner walls of two sides of the shell, a scraping frame is movably connected in the first sliding grooves, a connecting plate is fixedly connected to one side of the scraping frame, and the connecting plate is fixed with the sliding seat.
As a still further scheme of the invention, the inner wall of the top of the shell is movably connected with two connecting shafts, one side of each connecting shaft is fixedly connected with an auxiliary blade, one side of each connecting shaft is fixedly connected with a fluted disc, one side of each connecting plate is fixedly connected with a fixing rod, one side of each fixing rod is fixedly connected with a rack, and the racks are meshed with the fluted disc.
Further, one side of each of the two fixing rods is fixedly connected with a fixing rib, and the fixing ribs are fixed with the connecting plate.
On the basis of the scheme, one side of the mounting plate is fixedly connected with a sealing gasket.
As a still further scheme of the invention, a camera is arranged at the top of the shell, and a plurality of anti-skid patterns are formed on the outer walls of the two sides of the shell.
Further, the outer walls of the two sides of the shell are fixedly connected with fixing lugs, and a plurality of fixing holes are formed in the bottoms of the fixing lugs.
(III) beneficial effects
Compared with the prior art, the invention provides the end-to-end voice recognizer based on the CTC structure, which has the following beneficial effects:
1. Through the cooperation of scraper blade and torsional spring, the motor rotates and drives the disc and rotate to make the scraper blade positive and negative rotation through connecting rod, slide, stay cord, unreel roller, axis of rotation, torsional spring, thereby make the scraper blade clean the sound hole, avoid long-time use the back, the sound Kong Zhan is attached the dust to the sound, causes certain influence to the speech recognition, has improved the cleaning performance of device.
2. Through the cooperation of MCU module and speech recognition module, the microphone can collect the sound that people sent to carry out discernment and convert into digital information through speech recognition module to the sound that sends, then carry out processing analysis to digital information through the MCU module, simultaneously, SIM draw-in groove installs SIM network communication card, thereby realize through SIM network communication card that digital information after the analysis carries out end-to-end transmission with the internet, then loudspeaker can carry out the voice prompt, has improved the intellectuality of device.
3. Through the setting of scraping the frame in the first spout of installation, the slide moves about and makes the connecting plate drive and scrape the frame and move about along first spout to make the louvre obtain cleanly through scraping the frame, avoid after long-time use, the louvre is blockked up by the dust, influences speech recognizer's radiating efficiency, has improved the effect of scraping of device.
4. Through the cooperation of auxiliary blade and connecting axle, the connecting plate moves about and makes the dead lever drive the rack and moves about, and the rack moves about and makes fluted disc drive connecting axle and auxiliary blade positive and negative rotation to make auxiliary blade carry out the vortex to the air in the shell, increase the inside air of shell and the outside air of shell from the speed that the louvre circulated, improved the radiating effect of device.
5. Through the setting of installation fixed muscle on the dead lever, the fixed muscle can make the dead lever be connected more firm with the connecting plate, avoids appearing cracked condition in the junction of dead lever and connecting plate after long-time use, has improved the steadiness of device.
Drawings
Fig. 1 is a schematic diagram of a front-side three-dimensional structure of an end-to-end speech recognizer based on a CTC structure according to the present invention;
FIG. 2 is a schematic diagram of the lower three-dimensional structure of an end-to-end speech recognizer based on CTC structure according to the present invention;
Fig. 3 is a schematic diagram of an internal structure of an end-to-end speech recognizer based on CTC structure according to the present invention;
fig. 4 is a schematic diagram of an exploded structure of an end-to-end speech recognizer based on CTC structure according to the present invention;
FIG. 5 is a schematic diagram of a partial cross-sectional structure of an end-to-end speech recognizer based on CTC structure according to the present invention;
fig. 6 is an enlarged schematic diagram of a portion a of an end-to-end speech recognizer based on a CTC structure according to the present invention;
Fig. 7 is a schematic diagram of a B-part enlarged structure of an end-to-end speech recognizer based on CTC structure according to the present invention;
Fig. 8 is a schematic diagram of an enlarged C-part structure of an end-to-end voice recognizer based on a CTC structure according to the present invention.
The device comprises a camera, a 2, a sound transmission hole, a 3, a shell, a 4, a fixing hole, a 5, a fixing lug, a 6, an anti-skid pattern, a 7, a heat dissipation hole, an 8, a sealing gasket, a 9, a mounting plate, a 10, a scraping plate, a 11, an electric element fixing plate, a 12, an MCU module, a 13, a SIM card slot, a 14, a voice recognition module, a 15, a microphone, a 16, a loudspeaker, a 17, a pull rope, a 18, a scraping frame, a 19, a first sliding groove, a 20, a disc, a 21, a fixing frame, a 22, a connecting plate, a 23, an unreeling roller, a 24, a rotating shaft, a 25, a torsion spring, a 26, a sliding seat, a 27, a connecting rod, a 28, a second sliding groove, a 29, a fixing seat, a 30, a fixing rib, a 31, a fixing rod, a 32, a fluted disc, a 33, a rack, a 34, a connecting shaft and an auxiliary blade.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-8, an end-to-end speech recognizer based on CTC structure includes a mounting plate 9, a housing 3 is fixed at the top of the mounting plate 9 by bolts, a plurality of sound transmission holes 2 are provided at the top of the housing 3, a fixing seat 29 is fixed at the top inner wall of the housing 3 by bolts, a second sliding groove 28 is provided at the bottom of the fixing seat 29, a slide seat 26 is slidably connected in the second sliding groove 28, a fixing frame 21 is fixed at the top inner wall of the housing 3 by bolts, a motor is fixed at the bottom outer wall of the fixing frame 21 by bolts, one end of an output shaft of the motor passes through the fixing frame 21 and is fixed with a disk 20 by bolts, a connecting rod 27 is rotatably connected at the top of the disk 20, and the connecting rod 27 is rotatably connected with a slide seat 26, a rotation shaft 24 is rotatably connected at the top inner wall of the housing 3, two scrapers 10 are fixed at one side of the rotation shaft 24 by bolts, a torsion spring 25 is sleeved at one side of the rotation shaft 24, and both ends of the torsion spring 25 are respectively fixed with the rotating shaft 24 and the shell 3, one side of the rotating shaft 24 is fixed with an unreeling roller 23 through a bolt, one side of the unreeling roller 23 is in a winding connection with a pull rope 17, one end of the pull rope 17 is fixed with a sliding seat 26, the top of the mounting plate 9 is fixed with an electric element fixing plate 11 through a bolt, when the sound transmission hole 2 needs to be cleaned, a motor is started firstly, the motor rotates to drive the disc 20 to rotate, the disc 20 rotates to drive a connecting rod 27 to drive the sliding seat 26 to move left and right along a second sliding groove 28, the sliding seat 26 moves rightwards to drive the pull rope 17 to drive the rotating shaft 24 to rotate through the unreeling roller 23, the rotating shaft 24 rotates to deform the torsion spring 25 and generate torsion force, simultaneously, the rotating shaft 24 rotates to drive the scraping plate 10 to rotate, and when the sliding seat 26 moves leftwards, the torsion spring 25 rebounds to reset to drive the scraping plate 10 to reversely rotate to reset, the reciprocating circulation is performed in this way, so that the scraping plate 10 cleans the sound transmission hole 2, and dust is prevented from adhering to the sound transmission hole 2 after long-time use, and a certain influence is caused on voice recognition.
Particularly, in the invention, the top of the electrical component fixing plate 11 is fixedly provided with the MCU module 12, the SIM card slot 13, the voice recognition module 14, the microphone 15 and the loudspeaker 16 through bolts, the MCU module 12, the SIM card slot 13, the voice recognition module 14, the microphone 15 and the loudspeaker 16 are electrically connected, the microphone 15 can collect sounds sent by people, the voice recognition module 14 can recognize the sent sounds and convert the sounds into digital information, then the MCU module 12 processes and analyzes the digital information, meanwhile, the SIM card slot 13 is provided with the SIM network communication card, so that the analyzed digital information and the Internet are transmitted end to end through the SIM network communication card, and then the loudspeaker 16 can carry out voice prompt.
It should be noted that, a plurality of heat dissipation holes 7 are all opened on both sides of the housing 3, the inner walls of both sides of the housing 3 are all opened with the first slide groove 19, the first slide groove 19 is connected with the scraping frame 18 in a sliding way, one side of the scraping frame 18 is fixed with the connecting plate 22 through bolts, and the connecting plate 22 is fixed with the sliding seat 26, the heat dissipation holes 7 can assist the voice recognizer to dissipate heat, meanwhile, the sliding seat 26 moves left and right to make the connecting plate 22 drive the scraping frame 18 to move left and right along the first slide groove 19, thereby the heat dissipation holes 7 are cleaned through the scraping frame 18, the heat dissipation holes 7 are prevented from being blocked by dust after long-term use, the heat dissipation efficiency of the voice recognizer is affected, the inner wall of the top of the housing 3 is connected with two connecting shafts 34 in a rotating way, one side of the connecting shafts 34 is fixed with the auxiliary blades 35 through bolts, one side of the connecting shafts 34 is connected with the fluted disc 32 through bolts, one side of the connecting plate 22 is fixed with the fixing rod 31 through bolts, a rack 33 is fixed on one side of the fixed rod 31 through bolts, the rack 33 is meshed with the fluted disc 32, meanwhile, the connecting plate 22 moves left and right to enable the fixed rod 31 to drive the rack 33 to move left and right, the fluted disc 32 moves left and right to enable the connecting shaft 34 and the auxiliary blades 35 to rotate positively and negatively, thereby enabling the auxiliary blades 35 to turbulence air in the outer shell 3, increasing the circulation rate of air in the outer shell 3 and air outside the outer shell 3 from the heat dissipation holes 7, fixing ribs 30 are fixed on one side of the two fixed rods 31 through bolts, the fixing ribs 30 are fixed with the connecting plate 22, the fixing ribs 30 can enable the connection between the fixed rod 31 and the connecting plate 22 to be firmer, the situation that the connecting part of the fixed rod 31 and the connecting plate 22 breaks after long-time use is avoided, a sealing gasket 8 is adhered on one side of the mounting plate 9, the sealing gasket 8 can enable the mounting plate 9 and the outer shell 3 to be adhered more tightly, the top of shell 3 is equipped with camera 1, and camera 1 can carry out real-time supervision, and a plurality of anti-skidding lines 6 have all been seted up to shell 3's both sides outer wall, and anti-skidding line 6 can increase shell 3's frictional force, and shell 3's both sides outer wall all has fixed ear 5 through the bolt fastening, and a plurality of fixed orificess 4 have been seted up to fixed ear 5's bottom, and fixed orificess 4 can make things convenient for the staff to install fixedly to speech recognizer.
The working principle of the embodiment is as follows: when the sound transmission hole 2 needs to be cleaned, firstly, the motor is started, the motor rotates to drive the disc 20 to rotate, the disc 20 rotates to enable the connecting rod 27 to drive the sliding seat 26 to move left and right along the second sliding groove 28, the sliding seat 26 moves rightwards to enable the pull rope 17 to drive the rotating shaft 24 to rotate through the unreeling roller 23, the rotating shaft 24 rotates to enable the torsion spring 25 to deform under stress and generate torsion force, meanwhile, the rotating shaft 24 rotates to drive the scraping plate 10 to rotate, when the sliding seat 26 moves leftwards, the torsion spring 25 rebounds to enable the rotating shaft 24 to drive the scraping plate 10 to reversely rotate to reset, and thus the reciprocating circulation is realized, the scraping plate 10 cleans the sound transmission hole 2, dust is prevented from being attached to the sound transmission hole 2 after long-time use, a certain influence is caused on sound identification, meanwhile, the sliding seat 26 moves leftwards and rightwards to enable the connecting plate 22 to drive the scraping frame 18 to move leftwards and rightwards along the first sliding groove 19, so that the heat dissipation hole 7 is cleaned through the scraping frame 18, the situation that after long-time use, the heat dissipation hole 7 is blocked by dust, the heat dissipation efficiency of the sound identification device is influenced, meanwhile, the connecting plate 22 moves leftwards and rightwards, the fixing rod 31 drives the rack 33 to move leftwards and rightwards, the rack 33 to enable the rack 33 to drive the toothed disc 32 to rotate and the blade 35 to rotate, and the auxiliary air 3 to rotate, and the front and the outer shell 3 rotates, and the air is correspondingly, and the front and the outer shell 3 rotates.
The electrical components are all connected with an external main controller and 220V mains supply, and the main controller can be conventional known equipment for controlling a computer and the like.
In this description, it should be noted that 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. Moreover, 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.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. The end-to-end voice recognizer based on the CTC structure comprises a mounting plate (9), and is characterized in that the top of the mounting plate (9) is fixedly connected with a shell (3), a plurality of sound transmission holes (2) are formed in the top of the shell (3), a fixed seat (29) is fixedly connected to the top inner wall of the shell (3), a second sliding groove (28) is formed in the bottom of the fixed seat (29), a sliding seat (26) is movably connected to the second sliding groove (28), a fixing frame (21) is fixedly connected to the top inner wall of the shell (3), a motor is fixedly connected to the bottom outer wall of the fixing frame (21), one end of an output shaft of the motor penetrates through the fixing frame (21) and is fixedly connected with a disc (20), a connecting rod (27) is movably connected to the top of the disc (20), the connecting rod (27) is rotatably connected with the sliding seat (26), one side of the top inner wall of the shell (3) is fixedly connected with a rotating shaft (24), two scraping plates (10) are fixedly connected to one side of the rotating shaft (24), one side of the rotating shaft (24) is movably connected with a torsion spring (25), two ends of the torsion spring (25) are respectively connected with the rotating shaft (24) and the rotating shaft (3) and one side of the rotating shaft (23) is fixedly connected with a winding roller (23), and one end of the pull rope (17) is fixed with the sliding seat (26), and the top of the mounting plate (9) is fixedly connected with an electric element fixing plate (11).
2. The end-to-end voice recognizer based on the CTC structure according to claim 1, wherein the top of the electrical component fixing plate (11) is fixedly connected with an MCU module (12), a SIM card slot (13), a voice recognition module (14), a microphone (15) and a speaker (16), and the MCU module (12), the SIM card slot (13), the voice recognition module (14), the microphone (15) and the speaker (16) are electrically connected.
3. The end-to-end voice recognizer based on the CTC structure according to claim 1, wherein a plurality of heat dissipation holes (7) are formed in two sides of the shell (3), first sliding grooves (19) are formed in two side inner walls of the shell (3), a scraping frame (18) is movably connected in the first sliding grooves (19), a connecting plate (22) is fixedly connected to one side of the scraping frame (18), and the connecting plate (22) is fixed with the sliding seat (26).
4. The end-to-end voice recognizer based on the CTC structure according to claim 3, wherein two connecting shafts (34) are movably connected to the inner wall of the top of the casing (3), one side of each connecting shaft (34) is fixedly connected with an auxiliary blade (35), one side of each connecting shaft (34) is fixedly connected with a fluted disc (32), one side of each connecting plate (22) is fixedly connected with a fixing rod (31), one side of each fixing rod (31) is fixedly connected with a rack (33), and the racks (33) are meshed with the fluted disc (32).
5. The end-to-end speech recognizer based on the CTC structure according to claim 4, wherein one side of each of the two fixing bars (31) is fixedly connected with a fixing rib (30), and the fixing ribs (30) are fixed with the connecting plate (22).
6. The end-to-end speech recognizer based on the CTC structure according to claim 1, wherein a gasket (8) is fixedly connected to one side of the mounting plate (9).
7. The end-to-end voice recognizer based on the CTC structure according to claim 5, wherein a camera (1) is arranged at the top of the shell (3), and a plurality of anti-skid patterns (6) are formed on the outer walls of two sides of the shell (3).
8. The end-to-end speech recognizer based on the CTC structure according to claim 7, wherein fixing lugs (5) are fixedly connected to outer walls of two sides of the shell (3), and a plurality of fixing holes (4) are formed in the bottoms of the fixing lugs (5).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210969152.7A CN115331677B (en) | 2022-08-12 | 2022-08-12 | An end-to-end speech recognizer based on CTC structure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210969152.7A CN115331677B (en) | 2022-08-12 | 2022-08-12 | An end-to-end speech recognizer based on CTC structure |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115331677A CN115331677A (en) | 2022-11-11 |
| CN115331677B true CN115331677B (en) | 2024-12-31 |
Family
ID=83924430
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210969152.7A Active CN115331677B (en) | 2022-08-12 | 2022-08-12 | An end-to-end speech recognizer based on CTC structure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115331677B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108399920A (en) * | 2018-04-24 | 2018-08-14 | 郑州小蝌蚪文化传播有限公司 | A kind of portable intelligent sound identification device |
| CN210199766U (en) * | 2019-09-03 | 2020-03-27 | 北京佳珥医学科技有限公司 | Voice recognition interaction device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU190695U9 (en) * | 2018-06-08 | 2019-09-11 | Открытое акционерное общество "ИСТОК-АУДИО ИНТЕРНЭШНЛ" (ОАО "ИАИ") | PORTABLE INFORMATION DEVICE FOR THE HEARING |
| CN210377606U (en) * | 2019-06-21 | 2020-04-21 | 江苏瀚天智能科技股份有限公司 | Speech recognition entrance guard's device |
| CN211699708U (en) * | 2020-01-17 | 2020-10-16 | 长沙师范学院 | Modular combined type customized voice recognition device |
| CN215450889U (en) * | 2021-08-06 | 2022-01-07 | 随机数(浙江)智能科技有限公司 | Speech recognition controller |
| CN215835410U (en) * | 2021-08-23 | 2022-02-15 | 南京汇加家居科技有限公司 | Intelligent home system voice control device |
-
2022
- 2022-08-12 CN CN202210969152.7A patent/CN115331677B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108399920A (en) * | 2018-04-24 | 2018-08-14 | 郑州小蝌蚪文化传播有限公司 | A kind of portable intelligent sound identification device |
| CN210199766U (en) * | 2019-09-03 | 2020-03-27 | 北京佳珥医学科技有限公司 | Voice recognition interaction device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115331677A (en) | 2022-11-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115331677B (en) | An end-to-end speech recognizer based on CTC structure | |
| CN112399786B (en) | Electronic information anti-interference device | |
| CN210515189U (en) | A computer case fixing device with good fixing effect | |
| CN113490382A (en) | Intelligent household control device | |
| CN210573149U (en) | Multimedia device with heat dissipation dustproof construction for classroom | |
| CN218829949U (en) | A fiber optic transceiver | |
| CN216026236U (en) | Net twine ejection of compact edulcoration device | |
| CN213302971U (en) | Data acquisition platform based on big data processing | |
| CN211580482U (en) | Mobile communication interference source suppression equipment | |
| CN115361637A (en) | Indoor study is with split type surround sound loudspeaker | |
| CN209448866U (en) | A kind of acoustic control speaker | |
| CN209767707U (en) | Remote screen-viewing monitoring terminal | |
| CN109240442B (en) | Wire arranging groove of server case | |
| CN221664951U (en) | Voice-controlled radiator fan | |
| CN221572881U (en) | Communication engineering optical fiber box with heat dissipation function | |
| CN221933284U (en) | A solid-liquid separation device for sewage treatment | |
| CN222381272U (en) | Waterproof dustproof weak current case | |
| CN219679040U (en) | Four-in-one vertical test cabinet | |
| CN218526406U (en) | Container type sound box | |
| CN222084344U (en) | Efficient light-transmitting energy-saving window | |
| CN220968476U (en) | Environment-friendly efficient welding fume purifier | |
| CN214890003U (en) | Novel monitoring device | |
| CN219997966U (en) | Cable production surface water trap | |
| CN218387650U (en) | Projection equipment | |
| CN220570894U (en) | Artificial intelligence electric control device |
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 |