CN212809774U - Intelligent wearable device with characteristic voice recognition function - Google Patents
Intelligent wearable device with characteristic voice recognition function Download PDFInfo
- Publication number
- CN212809774U CN212809774U CN201920479299.1U CN201920479299U CN212809774U CN 212809774 U CN212809774 U CN 212809774U CN 201920479299 U CN201920479299 U CN 201920479299U CN 212809774 U CN212809774 U CN 212809774U
- Authority
- CN
- China
- Prior art keywords
- voiceprint
- processing unit
- voice recognition
- output
- casing
- 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
Images
Abstract
The utility model discloses an intelligence wearing equipment with characteristic voice recognition relates to the relevant field of wearing equipment, and for the voiceprint recognition speed who solves among the prior art is slow, and is not high enough to characteristic voice recognition's precision, and to the not enough problem of the safeguard measure of storage data. The upper and lower both ends of casing all are provided with the watchband connecting piece, the one end of watchband connecting piece is provided with fixed chamber, the one end in fixed chamber is provided with the watchband, one side of watchband connecting piece upper end is provided with the dead lever, the centre of casing is provided with the dial plate, the edge of casing is provided with the anticollision angle, one side of terminal surface is provided with loudspeaker before the casing, the upper end of terminal surface is provided with vice digital MIC before the casing, the lower extreme of terminal surface is provided with main digital MIC before the casing.
Description
Technical Field
The utility model relates to a wearing equipment correlation field specifically is an intelligence wearing equipment with characteristic voice recognition.
Background
Voiceprint recognition, one of the biometric identification technologies, also called speaker recognition, is a technology for discriminating the identity of a speaker by voice. Voiceprint recognition techniques are classified into two categories, namely speaker recognition and speaker verification, and different voiceprint recognition techniques are used for different tasks and applications, for example, recognition techniques may be required when the criminal investigation range is narrowed, and verification techniques are required when bank transactions are conducted.
The existing voice recognition needs to read and compare in the existing voiceprint, so the recognition speed is low, the safety of important data stored in intelligent equipment is not enough only by the voiceprint recognition, and the voiceprint recognition has high requirements on recorded voice, so that the voiceprint recognition cannot be realized even if the voiceprint is a characteristic voiceprint; therefore, the market urgently needs to develop an intelligent wearable device with characteristic voice recognition to help people solve the existing problems.
SUMMERY OF THE UTILITY MODEL
An object of the utility model is to provide an intelligence wearing equipment with characteristic voice recognition to the voiceprint recognition rate who proposes in solving above-mentioned background is slow, and is not high enough to characteristic voice recognition's precision, and to the not enough problem of the safeguard of storage data.
In order to achieve the above object, the utility model provides a following technical scheme: the utility model provides an intelligence wearing equipment with characteristic voice recognition, includes the casing, the upper and lower both ends of casing all are provided with the watchband connecting piece, the one end of watchband connecting piece is provided with fixed chamber, the one end in fixed chamber is provided with the watchband, one side of watchband connecting piece upper end is provided with the dead lever, the centre of casing is provided with the dial plate, the edge of casing is provided with the crashproof angle, one side of terminal surface is provided with loudspeaker before the casing, the upper end of terminal surface is provided with vice digital MIC before the casing, the lower extreme of terminal surface is provided with main digital MIC before the casing.
Preferably, the input of loudspeaker is connected with microprocessor's output, microprocessor respectively with data storage module, voiceprint storage module and developments pronunciation storage module both way junction, microprocessor respectively with 4G communication module and bluetooth communication module both way junction, microprocessor compares unit both way junction with the voiceprint, the input that the unit was compared to the voiceprint is connected with the output of voiceprint decoder, the input of voiceprint decoder and the output of voiceprint processing unitConnected, the input of the voiceprint processing unit being connected to I2The output end of the S bus is connected, I2The input of S bus is connected with digital MIC 'S output, digital MIC' S output is connected with speech recognition unit 'S input, speech recognition unit' S output is connected with the input of speech comparison unit, the speech comparison unit is connected with microprocessor both way junction.
Preferably, the digital MIC comprises a secondary digital MIC and a primary digital MIC, and the output ends of the secondary digital MIC and the primary digital MIC are connected with I2The input end of the S bus is connected, the voiceprint processing unit comprises a main sound processing unit, an auxiliary sound processing unit and a combined voiceprint processing unit, and I2The output end of the S bus is connected with the input ends of the main sound processing unit and the auxiliary sound processing unit respectively, and the output ends of the main sound processing unit and the auxiliary sound processing unit are connected with the input end of the combined voiceprint processing unit.
Preferably, the watchband passes through fixed chamber with the watchband connecting piece and is connected, the watchband connecting piece is connected with casing hot melt, the casing is connected with crashproof angle hot melt, crashproof angle sets up to toughness, loudspeaker, vice digital MIC and main digital MIC all run through the casing, dead lever and watchband connecting piece threaded connection.
Preferably, the I2The S bus includes a bidirectional data transmission line, a command selection line, and a clock line.
Preferably, the type of the microprocessor is CY8C6347BZI-BLD 53.
Preferably, the voiceprint storage module is provided with two partitions, and the data storage module is a 256G data storage module.
Preferably, the model of the Bluetooth communication module is set to be psoc BLE 5.0.
Preferably, the type of the secondary digital MIC is the same as that of the primary digital MIC, and the primary sound processing unit and the secondary sound processing unit both include AGC and DTS noise reduction signal micro-processing circuits.
Compared with the prior art, the beneficial effects of the utility model are that:
1. the utility model has the advantages that through the arrangement of the voiceprint storage module, the voiceprint storage module stores the voiceprint independently, the response is faster when the voiceprint information is read, the recognition speed is fast, the user experience is better, and the character sequence which strengthens the person needing to be recognized can be stored in the voiceprint storage module independently, so that the voiceprint can be recognized one to one or more than one;
2. the utility model discloses a through the setting of vice digital MIC, main sound processing unit and vice sound processing unit, the two MIC's of vice digital MIC and main digital MIC setting is to the sound that needs to read carry out two noise reduction and is handled, because of vice digital MIC and main digital MIC set up the difference in position, there is slight difference in the human sound size that vice digital MIC and main digital MIC were included when carrying out speech control, but noise source decibel size is basically the same, through the joint processing of main sound processing unit and vice sound processing unit, fall the noise to the same noise source, the sound source of variation in size concentrates the enhancement, reduced the requirement to the recorded voice, the discernment rate to characteristic human sound improves greatly;
3. the utility model discloses a through the setting of voiceprint processing unit, voiceprint decoder and voiceprint comparison unit, voiceprint processing unit will concentrate the sound processing of strengthening into corresponding ASCII code character, and the voiceprint decoder restores true character sequence, compares the character sequence of recording sound with the character sequence of voiceprint storage module through voiceprint comparison unit to discernment characteristic crowd;
4. the utility model strengthens the safety measures of recognition through the arrangement of the dynamic voice storage module, the voice recognition unit and the voice comparison unit, for some special commands, such as related to data of passwords, money and the like, the feature person needs to use dynamic voice for dialogue, and the voice comparison unit compares the dynamic voice stored in the dynamic voice storage module, thereby further recognizing and improving the safety;
5. the utility model discloses a can dismantle and change the watchband through setting up of fixed chamber and dead lever, and vice digit MIC and main digit MIC set up respectively at the upper and lower both ends of dial plate, make the volume of a voice recognition have the difference, make things convenient for the noise reduction in later stage to handle.
Drawings
Fig. 1 is a schematic flow chart of the intelligent wearable device with characteristic voice recognition according to the present invention;
FIG. 2 is a schematic flow chart of the voiceprint processing unit of the present invention;
fig. 3 is the utility model discloses an intelligence wearing equipment's structural schematic with characteristic voice recognition.
In the figure: 1. a watchband; 2. a watchband connector; 3. a fixed cavity; 4. fixing the rod; 5. a housing; 6. a horn; 7. a secondary number MIC; 8. an anti-collision angle; 9. a dial plate; 10. a master digital MIC; 11. a digital MIC; 12. i is2S bus; 13. a voiceprint processing unit; 14. a voiceprint decoder; 15. a voiceprint comparison unit; 16. a microprocessor; 17. a data storage module; 18. a voiceprint storage module; 19. a dynamic voice storage module; 20. a voice recognition unit; 21. a voice comparison unit; 22. a 4G communication module; 23. a Bluetooth communication module; 24. a main sound processing unit; 25. a sub-sound processing unit; 26. and a combined voiceprint processing unit.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments.
Referring to fig. 1-3, the present invention provides an embodiment: the utility model provides an intelligence wearing equipment with characteristic voice recognition, which comprises a housin 5, the upper and lower both ends of casing 5 all are provided with watchband connecting piece 2, the one end of watchband connecting piece 2 is provided with fixed chamber 3, the one end of fixed chamber 3 is provided with watchband 1, one side of watchband connecting piece 2 upper end is provided with dead lever 4, the setting of fixed chamber 3 and dead lever 4 can be dismantled and change watchband 1, the centre of casing 5 is provided with dial plate 9, the edge of casing 5 is provided with crashproof angle 8, crashproof angle 8 protects this equipment, one side of terminal surface is provided with loudspeaker 6 before casing 5, the upper end of terminal surface is provided with sub-digital MIC7 before casing 5, the lower extreme of terminal surface is provided with main digital MIC10 before casing 5, sub-digital MIC7 and main digital MIC10 set up respectively at the upper and lower both ends of dial plate 9, make the volume of voice recognition.
Further, the input end of the loudspeaker 6 is connected with the output end of the microprocessor 16, the microprocessor 16 is respectively connected with the data storage module 17, the voiceprint storage module 18 and the dynamic voice storage module 19 in a bidirectional way, the microprocessor 16 is respectively connected with the 4G communication module 22 and the Bluetooth communication module 23 in a bidirectional way, the microprocessor 16 is connected with the voiceprint comparison unit 15 in a bidirectional way, the voiceprint comparison unit 15 compares the in-library characteristic voiceprint recording character sequence called by the microprocessor 16 to the voiceprint storage module 18 with the character sequence restored by the voiceprint decoder 14, thereby confirming the identity of the specific person, the input end of the voiceprint comparison unit 15 is connected with the output end of the voiceprint decoder 14, the voiceprint decoder 14 restores the ASCII code characters to a real character sequence, the input end of the voiceprint decoder 14 is connected with the output end of the voiceprint processing unit 13, and the input end of the voiceprint processing unit 13 is connected with I.2Output connection of S bus 12, I2The input end of the S bus 12 is connected with the output end of the digital MIC11, the output end of the digital MIC11 is connected with the input end of the voice recognition unit 20, the output end of the voice recognition unit 20 is connected with the input end of the voice comparison unit 21, for some special commands, such as data related to passwords, money and the like, feature people need to use dynamic voice for conversation, the voice comparison unit 21 compares the dynamic voice stored in the dynamic voice storage module 19, and therefore recognition is further achieved, safety is improved, and the voice comparison unit 21 is connected with the microprocessor 16 in a bidirectional mode.
Further, the digital MIC11 comprises a sub-digital MIC7 and a main digital MIC10, the double MICs of the sub-digital MIC7 and the main digital MIC10 are arranged to perform double noise reduction processing on the sound to be read, and the output ends of the sub-digital MIC7 and the main digital MIC10 are both equal to I2The input end of the S bus 12 is connected, the voiceprint processing unit 13 comprises a main sound processing unit 24, a secondary sound processing unit 25 and a combined voiceprint processing unit 26, and because the secondary digital MIC7 and the main digital MIC10 are arranged at different positions, when voice control is carried out, the sizes of human voices recorded by the secondary digital MIC7 and the main digital MIC10 are slightly different, but the noise sources are basically the same in decibel, and the main sound is basically the same in decibelThe processing unit 24 and the auxiliary sound processing unit 25 perform joint processing to reduce noise of the same noise source and intensively strengthen sound sources with different sizes, I2The output terminal of the S-bus 12 is connected to the input terminals of the main sound processing unit 24 and the sub sound processing unit 25, respectively, the output terminals of the main sound processing unit 24 and the sub sound processing unit 25 are connected to the input terminal of the merged voiceprint processing unit 26, and the merged voiceprint processing unit 26 processes the centrally enhanced sound into corresponding ASCII code characters.
Further, watchband 1 is connected through fixed chamber 3 with watchband connecting piece 2, and watchband connecting piece 2 is connected with 5 hot melts of casing, and casing 5 is connected with 8 hot melts of crashproof angle, and crashproof angle 8 sets up to toughness, and loudspeaker 6, vice digit MIC7 and main digit MIC10 all run through casing 5, and dead lever 4 and watchband connecting piece 2 threaded connection are fixed once more after changing watchband 1.
Further, I2The S-bus 12 includes a bidirectional data transmission line, a command selection line, and a clock line.
Further, the model of the microprocessor 16 is set to CY8C6347BZI-BLD 53.
Further, the voiceprint storage module 18 is internally provided with two partitions which are respectively a characteristic voiceprint storage area and an unspecific voiceprint storage area, and the data storage module 17 is set to be a 256G data storage module 17 and is enough for small intelligent equipment.
Further, the model of the bluetooth communication module 23 is set to psoc BLE 5.0.
Furthermore, the type of the secondary digital MIC7 is the same as that of the primary digital MIC10, and the primary sound processing unit 24 and the secondary sound processing unit 25 both comprise AGC and DTS noise reduction signal microprocessing circuits, so that the system has a certain noise reduction function and has a better effect on a single noise source.
The working principle is as follows: when the device is used, a characteristic person carries out voice on the device, wherein double noise reduction processing is carried out on the voice to be read by setting double MICs of the secondary number MIC7 and the main number MIC10, the watchband 1 can be disassembled and replaced by setting the fixed cavity 3 and the fixed rod 4, the secondary number MIC7 and the main number MIC10 are respectively arranged at the upper end and the lower end of the dial 9, the volume of voice identification is different, the later noise reduction processing is convenient, the sizes of the voices of the secondary number MIC7 and the main number MIC10 are slightly different when voice control is carried out due to the difference of the setting positions of the secondary number MIC7 and the main number MIC10, but the sizes of noise sources are basically the same, the main sound processing unit 24 and the secondary sound processing unit 25 carry out combined processing, noise reduction is carried out on the same noise source, sound sources with different sizes are intensively reinforced, the sound sources with the same size are treated into corresponding code characters by the combined voiceprint processing unit, the voiceprint decoder 14 restores ASCII code characters into a real character sequence, the voiceprint comparison unit 15 compares the in-library characteristic voiceprint recording character sequence called by the voiceprint storage module 18 through the microprocessor 16 with the character sequence restored by the voiceprint decoder 14 to determine the identity of a specific person, for some special commands, such as data related to passwords, money and the like, the characteristic person is required to have a conversation by dynamic voice, the voice comparison unit 21 compares the data by the dynamic voice stored in the dynamic voice storage module 19 to further recognize and improve the safety, wherein the characteristic person can transmit and communicate data through the 4G communication module 22 and the Bluetooth communication module 23, and the use log and the use data are stored in the data storage module 17 through the microprocessor 16.
It is obvious to a person skilled in the art that the invention is not restricted to details of the above-described exemplary embodiments, but that it can be implemented in other specific forms without departing from the spirit or essential characteristics of the invention. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (9)
1. The utility model provides an intelligence wearing equipment with characteristic voice recognition, includes casing (5), its characterized in that: the watch band is characterized in that watchband connecting pieces (2) are arranged at the upper end and the lower end of the shell (5), a fixed cavity (3) is formed in one end of each watchband connecting piece (2), a watchband (1) is arranged at one end of the fixed cavity (3), a fixing rod (4) is arranged on one side of the upper end of each watchband connecting piece (2), a dial plate (9) is arranged in the middle of the shell (5), an anti-collision angle (8) is arranged at the corner of the shell (5), a horn (6) is arranged on one side of the front end face of the shell (5), an auxiliary digital MIC (7) is arranged at the upper end of the front end face of the shell (5), and a main digital MIC.
2. The intelligent wearable device with characteristic human voice recognition of claim 1, characterized in that: the input of loudspeaker (6) is connected with the output of microprocessor (16), microprocessor (16) respectively with data storage module (17), voiceprint storage module (18) and dynamic voice storage module (19) both way junction, microprocessor (16) respectively with 4G communication module (22) and bluetooth communication module (23) both way junction, microprocessor (16) compare unit (15) both way junction with the voiceprint, the input of unit (15) is compared to the voiceprint is connected with the output of voiceprint decoder (14), the input of voiceprint decoder (14) is connected with the output of voiceprint processing unit (13), the input of voiceprint processing unit (13) and I's output are connected2The output of the S bus (12) is connected, I2The input of S bus (12) is connected with the output of digit MIC (11), the output of digit MIC (11) is connected with the input of speech recognition unit (20), the output of speech recognition unit (20) is connected with the input of pronunciation comparison unit (21), pronunciation comparison unit (21) and microprocessor (16) both way junction.
3. The intelligent wearable device with characteristic human voice recognition of claim 2, wherein: the digital MIC (11) comprises a secondary digital MIC (7) and a primary digital MIC (10), and the output ends of the secondary digital MIC (7) and the primary digital MIC (10) are connected with I2The input ends of the S bus (12) are connected, the voiceprint processing unit (13) comprises a main sound processing unit (24), an auxiliary sound processing unit (25) and a combined voiceprint processing unit (26), and the I2The output end of the S bus (12) is respectively connected with the input ends of the main sound processing unit (24) and the auxiliary sound processing unit (25), and the output ends of the main sound processing unit (24) and the auxiliary sound processing unit (25) are respectively connected with the input end of the combined voiceprint processing unit (26).
4. The intelligent wearable device with characteristic human voice recognition of claim 1, characterized in that: watchband (1) is connected through fixed chamber (3) with watchband connecting piece (2), watchband connecting piece (2) and casing (5) hot melt are connected, casing (5) and crashproof angle (8) hot melt are connected, crashproof angle (8) set up to toughness structure, casing (5) are all run through in loudspeaker (6), vice digital MIC (7) and main digital MIC (10), dead lever (4) and watchband connecting piece (2) threaded connection.
5. The intelligent wearable device with characteristic human voice recognition of claim 2, wherein: said I2The S-bus (12) includes a bidirectional data transmission line, a command selection line, and a clock line.
6. The intelligent wearable device with characteristic human voice recognition of claim 2, wherein: the type of the microprocessor (16) is set to CY8C6347BZI-BLD 53.
7. The intelligent wearable device with characteristic human voice recognition of claim 2, wherein: the voiceprint storage module (18) is internally provided with two partitions, and the data storage module (17) is set to be a 256G data storage module (17).
8. The intelligent wearable device with characteristic human voice recognition of claim 2, wherein: the model of the Bluetooth communication module (23) is set to be psoc BLE 5.0.
9. The intelligent wearable device with characteristic human voice recognition of claim 3, wherein: the type of the secondary digital MIC (7) is the same as that of the primary digital MIC (10), and the primary sound processing unit (24) and the secondary sound processing unit (25) both comprise AGC and DTS noise reduction signal micro-processing circuits.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201920479299.1U CN212809774U (en) | 2019-04-10 | 2019-04-10 | Intelligent wearable device with characteristic voice recognition function |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201920479299.1U CN212809774U (en) | 2019-04-10 | 2019-04-10 | Intelligent wearable device with characteristic voice recognition function |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN212809774U true CN212809774U (en) | 2021-03-26 |
Family
ID=75079489
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201920479299.1U Active CN212809774U (en) | 2019-04-10 | 2019-04-10 | Intelligent wearable device with characteristic voice recognition function |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN212809774U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110060689A (en) * | 2019-04-10 | 2019-07-26 | 南京启诺信息技术有限公司 | A kind of intelligent wearable device and its application method with the identification of feature voice |
-
2019
- 2019-04-10 CN CN201920479299.1U patent/CN212809774U/en active Active
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110060689A (en) * | 2019-04-10 | 2019-07-26 | 南京启诺信息技术有限公司 | A kind of intelligent wearable device and its application method with the identification of feature voice |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108564940B (en) | Speech recognition method, server and computer-readable storage medium | |
| Liu et al. | An MFCC‐based text‐independent speaker identification system for access control | |
| WO2021051544A1 (en) | Voice recognition method and device | |
| CN100521708C (en) | Voice recognition and voice tag recoding and regulating method of mobile information terminal | |
| CN111341325A (en) | Voiceprint recognition method and device, storage medium and electronic device | |
| CN101540170B (en) | Voiceprint recognition method based on biomimetic pattern recognition | |
| Arif et al. | Voice spoofing countermeasure for logical access attacks detection | |
| CN109994106B (en) | Voice processing method and equipment | |
| WO2021013255A1 (en) | Voiceprint recognition method and apparatus | |
| CN212809774U (en) | Intelligent wearable device with characteristic voice recognition function | |
| CN105679323B (en) | A kind of number discovery method and system | |
| CN112183105A (en) | Man-machine interaction method and device | |
| CN111862943B (en) | Speech recognition method and device, electronic equipment and storage medium | |
| CN113643707A (en) | Identity verification method and device and electronic equipment | |
| CN109545226B (en) | Voice recognition method, device and computer readable storage medium | |
| WO2023124248A1 (en) | Voiceprint recognition method and apparatus | |
| CN116110370A (en) | Speech synthesis system and related equipment based on man-machine speech interaction | |
| CN111145748A (en) | Audio recognition confidence determining method, device, equipment and storage medium | |
| CN109922397A (en) | Audio intelligent processing method, storage medium, intelligent terminal and smart bluetooth earphone | |
| CN102479512A (en) | Voiceprint identity authentication system based on SOPC (system on programmable chip) and voiceprint identity authentication method based on SOPC | |
| CN115116437A (en) | Speech recognition method, apparatus, computer device, storage medium and product | |
| CN109102810B (en) | Voiceprint recognition method and device | |
| CN110060689A (en) | A kind of intelligent wearable device and its application method with the identification of feature voice | |
| JPH10116093A (en) | Voice recognition device | |
| CN201947339U (en) | Safe mobile phone based on voice analysis, processing and identification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |