CN116631397A - Voice recognition scene awakening method and device - Google Patents
Voice recognition scene awakening method and device Download PDFInfo
- Publication number
- CN116631397A CN116631397A CN202310675003.4A CN202310675003A CN116631397A CN 116631397 A CN116631397 A CN 116631397A CN 202310675003 A CN202310675003 A CN 202310675003A CN 116631397 A CN116631397 A CN 116631397A
- Authority
- CN
- China
- Prior art keywords
- voice
- wake
- module
- word
- service terminal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 230000008054 signal transmission Effects 0.000 claims description 6
- 230000002618 waking effect Effects 0.000 claims description 6
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L19/00—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
The invention provides a voice recognition scene awakening method and device, and relates to the technical field of voice recognition. The voice recognition scene wake-up method comprises the following steps: s1, dividing boundaries of a field; s2, numbering the voice modules in the field; s3, limiting the number of simultaneous work of the voice modules in the field; s4, the appointed voice module enters a wake-up word in the scene; s5, sending a wake-up word to an external service terminal, and entering a corresponding scene; s6, a contracted voice module quits a wake-up word of a scene; s7, sending a wake-up word to the external service terminal, and exiting the corresponding scene. Before sending a wake-up word to an external service terminal, temporarily storing signals input by a plurality of voice modules, encoding the signals in sequence, and forming the wake-up word; by temporarily storing and encoding in sequence the signals input by the plurality of speech modules. The voice recognition scene wake-up method and device provided by the invention have the advantage of being beneficial to the external service terminal to receive the voice signal.
Description
Technical Field
The present invention relates to the field of speech recognition technologies, and in particular, to a method and apparatus for waking up speech recognition scenes.
Background
Scene wake experiments are established based on exploring new scene applications in commercial spaces, where scenes can occur in any space, whether restaurants, bars, clothing stores, or vegetable markets, where scenes exist.
At present, when scene wake-up is performed through voice recognition, in order to improve interestingness and participation, a plurality of voice wake-up modules are generally provided, and when the voice wake-up modules work simultaneously, a plurality of voice signals are mutually interfered, so that the voice signals are not received by an external service terminal.
Therefore, it is necessary to provide a new voice recognition scene wake-up method and device to solve the above technical problems.
Disclosure of Invention
In order to solve the technical problems, the invention provides a voice recognition scene wake-up method and a device which are beneficial to an external service terminal to receive voice signals.
The invention provides a voice recognition scene wake-up method, which comprises the following steps:
s1, dividing boundaries of a field;
s2, numbering the voice modules in the field;
s3, limiting the number of simultaneous work of the voice modules in the field;
s4, the appointed voice module enters a wake-up word in the scene;
s5, sending a wake-up word to an external service terminal, and entering a corresponding scene;
s6, a contracted voice module quits a wake-up word of a scene;
s7, sending a wake-up word to the external service terminal, and exiting the corresponding scene.
Preferably, before sending the wake-up word to the external service terminal, temporarily storing signals input by a plurality of voice modules, encoding the signals in sequence, and forming the wake-up word; the signals input by the voice modules are temporarily stored and encoded according to the sequence, so that the orderly input of the voice signals is ensured, and the mutual interference of the voice signals is avoided.
Preferably, when the external service terminal receives the wake-up word, the wake-up word is analyzed through a fuzzy recognition module in the external service terminal.
Preferably, the wake-up word is generated by means of external preset, automatic system generation and the like.
Preferably, the user previews the wake-up scenes of different voice modules through the external display module, and selects the voice module which accords with the preference of the user through the serial number of the voice module.
Preferably, the number of simultaneous operations of the voice modules in the site in S3 is adjustable, and is adjusted according to the data processing capability of the external service terminal, and is generally controlled to 2-4.
A speech recognition scene wake-up device comprising:
the external display module, the voice module, the signal transmission module and the voice information temporary storage and encoding module; the external display module is used for previewing wake-up scenes of different voice modules by a user and introducing the whole device; the voice module is used for receiving voice information; the voice information temporary storage and encoding module is used for temporarily storing the information input by the voice module and encoding the information correspondingly, so that the voice information is received by the external service terminal; the signal transmission module is used for sending the coded voice information to an external service terminal or transmitting an instruction of the external service terminal.
Compared with the related art, the voice recognition scene wake-up method and device provided by the invention have the following steps of
The beneficial effects are that:
1. the signals input by the voice modules are temporarily stored and coded according to the sequence, so that the orderly input of the voice signals is ensured, the mutual interference of the voice signals is avoided, and the voice signals are received by an external service terminal; the signals input by the voice modules are temporarily stored and then sequentially released after being stored, so that the collision of the voice modules in the process of coding is avoided, the sufficient coding time is ensured, and the voice signals are received by an external service terminal;
2. the wake-up words are analyzed through the fuzzy recognition module, so that the user can still accurately recognize the wake-up words when the user has accents, and the using difficulty of the device is reduced.
Drawings
FIG. 1 is a schematic diagram of a control structure of a method and a device for waking up a speech recognition scene according to the present invention;
Detailed Description
The invention will be further described with reference to the drawings and embodiments.
Referring to fig. 1 in combination, the voice recognition scene wake method includes:
s1, dividing boundaries of a field;
s2, numbering the voice modules in the field;
s3, limiting the number of simultaneous work of the voice modules in the field;
s4, the appointed voice module enters a wake-up word in the scene;
s5, sending a wake-up word to an external service terminal, and entering a corresponding scene;
s6, a contracted voice module quits a wake-up word of a scene;
s7, sending a wake-up word to the external service terminal, and exiting the corresponding scene.
Before sending a wake-up word to an external service terminal, temporarily storing signals input by a plurality of voice modules, encoding the signals in sequence, and forming the wake-up word; the signals input by the voice modules are temporarily stored and encoded according to the sequence, so that the orderly input of the voice signals is ensured, and the mutual interference of the voice signals is avoided.
It is necessary to explain that: the signals input by the voice modules are temporarily stored and coded according to the sequence, so that the orderly input of the voice signals is ensured, the mutual interference of the voice signals is avoided, and the voice signals are received by an external service terminal;
it also needs to be stated that: the signals input by the voice modules are temporarily stored and then sequentially released after being stored, so that the collision of the voice modules during encoding is avoided, the sufficient encoding time is ensured, and the voice signals are received by the external service terminal.
When the external service terminal receives the wake-up word, the wake-up word is analyzed through a fuzzy recognition module in the external service terminal.
It is necessary to explain that: the wake-up words are analyzed through the fuzzy recognition module, so that the user can still accurately recognize the wake-up words when the user has accents, and the using difficulty of the device is reduced.
The wake-up words are generated in an external preset mode, a system automatic generation mode and the like.
The user previews the awakening scenes of the different voice modules through the external display module, and selects the voice module which accords with the preference of the user through the serial number of the voice module.
It is necessary to explain that: the voice module which accords with the preference of the user is selected through the number of the voice module, so that the participation degree of the user is improved, and the enthusiasm of the user is further improved; and the number of the voice module is used for selecting the voice module which accords with the preference of the user, so that the interest is better.
The number of the voice modules in the site in the S3 is adjustable, and the voice modules are adjusted according to the data processing capacity of the external service terminal and are generally controlled to be 2-4.
A speech recognition scene wake-up device comprising:
the external display module, the voice module, the signal transmission module and the voice information temporary storage and encoding module; the external display module is used for previewing wake-up scenes of different voice modules by a user and introducing the whole device; the voice module is used for receiving voice information; the voice information temporary storage and encoding module is used for temporarily storing the information input by the voice module and encoding the information correspondingly, so that the voice information is received by the external service terminal; the signal transmission module is used for sending the coded voice information to an external service terminal or transmitting an instruction of the external service terminal
The foregoing description is only illustrative of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes or direct or indirect application in other related technical fields are included in the scope of the present invention.
Claims (7)
1. The voice recognition scene wake-up method is characterized by comprising the following steps of:
s1, dividing boundaries of a field;
s2, numbering the voice modules in the field;
s3, limiting the number of simultaneous work of the voice modules in the field;
s4, the appointed voice module enters a wake-up word in the scene;
s5, sending a wake-up word to an external service terminal, and entering a corresponding scene;
s6, a contracted voice module quits a wake-up word of a scene;
s7, sending a wake-up word to the external service terminal, and exiting the corresponding scene.
2. The voice recognition scene wake-up method of claim 1, wherein signals input by a plurality of voice modules are temporarily stored and sequentially encoded before a wake-up word is transmitted to an external service terminal, and the wake-up word is formed; the signals input by the voice modules are temporarily stored and encoded according to the sequence, so that the orderly input of the voice signals is ensured, and the mutual interference of the voice signals is avoided.
3. The method for waking up a speech recognition scene according to claim 2, wherein the external service terminal analyzes the wake-up word through a fuzzy recognition module built in the external service terminal when receiving the wake-up word.
4. The method for waking up a speech recognition scene according to claim 1, wherein the wake-up words are generated by means of external presets, automatic system generation, etc.
5. The method for waking up a speech recognition scene according to claim 1, wherein the user previews the wake-up scenes of different speech modules through an external display module, and selects a speech module according with his own preference through the number of the speech module.
6. The method for waking up a speech recognition scene according to claim 1, wherein the number of simultaneous operation of the speech modules in the site in S3 is adjustable, and is adjusted according to the data processing capability of the external service terminal, and is generally controlled to 2-4.
7. The voice recognition scene wake-up device is characterized by comprising:
the external display module, the voice module, the signal transmission module and the voice information temporary storage and encoding module; the external display module is used for previewing wake-up scenes of different voice modules by a user and introducing the whole device; the voice module is used for receiving voice information; the voice information temporary storage and encoding module is used for temporarily storing the information input by the voice module and encoding the information correspondingly, so that the voice information is received by the external service terminal; the signal transmission module is used for sending the coded voice information to an external service terminal or transmitting an instruction of the external service terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310675003.4A CN116631397A (en) | 2023-06-08 | 2023-06-08 | Voice recognition scene awakening method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310675003.4A CN116631397A (en) | 2023-06-08 | 2023-06-08 | Voice recognition scene awakening method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116631397A true CN116631397A (en) | 2023-08-22 |
Family
ID=87641777
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310675003.4A Pending CN116631397A (en) | 2023-06-08 | 2023-06-08 | Voice recognition scene awakening method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116631397A (en) |
-
2023
- 2023-06-08 CN CN202310675003.4A patent/CN116631397A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1098592C (en) | Method for selecting channel of digital multichannel television | |
| GB2124419A (en) | Radio paging apparatus | |
| CN102036051A (en) | Method and device for prompting in video meeting | |
| RU96118106A (en) | METHOD AND DEVICE FOR SAVING ENERGY IN A COMMUNICATION SYSTEM | |
| CN106888507A (en) | Information transferring method, terminal and base station | |
| CA1313398C (en) | Radio communication system | |
| CN103905636A (en) | Information processing method and electronic device | |
| CN100493112C (en) | Broadcast terminal for searching broadcast content and method thereof | |
| CN116631397A (en) | Voice recognition scene awakening method and device | |
| CN102685307A (en) | Method, device and system for processing command information | |
| EP0583073A1 (en) | Cordless telephone system | |
| CN103686263B (en) | A kind of data processing method, equipment and system | |
| GB1581477A (en) | Apparatus for synthesising verbal announcements | |
| DE69632454T2 (en) | DATA RECEIVER AND DEINTERLEAVER FOR VARIOUS DATA RATES AND MODULATION PROCEDURES | |
| JPH0730523A (en) | Data communication method | |
| JPH0481370B2 (en) | ||
| US6950890B2 (en) | Wireless receiving apparatus and method | |
| CN106874979A (en) | A kind of bar code treatment, display, read method and device | |
| GB2363932A (en) | Improved recognition of a pre-defined region on a transmitted image | |
| JP2626504B2 (en) | Radio selective call receiver and radio frequency channel search method thereof | |
| CN100372358C (en) | Wireless communication system and method using wireless channel | |
| CN1203507A (en) | Mobile station having improved DCCH synchronization | |
| CN111510644B (en) | Video processing method and device, mobile terminal and storage medium | |
| CN101299658B (en) | Synchronization method and device | |
| EP1018227A1 (en) | Method for synchronizing a mobile component of a multiplex-operated mobile radiotelephone system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |