CN106356062A - Machine intelligent recognition and manual service combined voice recognition method and system - Google Patents
Machine intelligent recognition and manual service combined voice recognition method and system Download PDFInfo
- Publication number
- CN106356062A CN106356062A CN201510424792.XA CN201510424792A CN106356062A CN 106356062 A CN106356062 A CN 106356062A CN 201510424792 A CN201510424792 A CN 201510424792A CN 106356062 A CN106356062 A CN 106356062A
- Authority
- CN
- China
- Prior art keywords
- recording device
- voice
- vehicle
- sound recording
- input
- 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
Landscapes
- Mobile Radio Communication Systems (AREA)
Abstract
The invention is applicable to the technical field of voice recognition and provides a machine intelligent recognition and manual service combined voice recognition method. A vehicular recording device is adopted for voice input and recognition. The voice recognition method includes steps: A, waking up a voice control module in a dormant state in the vehicular recording device; B inputting voice instructions through the vehicular recording device; C, recognizing inputted voice by the voice control module in the vehicular recording device; D, allowing a processor of the vehicular recording device to automatically send instructions to connect with background services; E, judging whether background service connection succeeds or not in set time. By combination of machine intelligent recognition and manual recognition, recognition rate is increased; by means of voice recognition, equipment brightness is increased or reduced correspondingly, and volume is increased or reduced correspondingly, so that driving safety is improved.
Description
Technical field
The invention belongs to technical field of voice recognition, audio recognition method and system that more particularly, to a kind of machine intelligence identification is combined with manual service.
Background technology
The Circuits System that can continuously monitor voice command when in standby mode is provided to be known.This avoid to for by this equipment from the overall button of " wake-up " (for example to activate speech identifying function) of standby mode or the demand of other mechanical activators.
A kind of possible mode starting hands-free operation is to make the user of phone say a key phrase, such as " hello for phone (hello phone) ".Then, this equipment is capable of identify that this key phrase is spoken, and wakes up speech identifying function, and is also possible to wake up the remainder of this equipment.In addition, it is special that this hands-free order can be programmed to user, in the case, the user (or multiple user) of only earlier registration can say this key phrase, and this equipment is possible to checking and is exactly that specific user in speech (identification teller) and and then wakes up speech identifying function.
In the process of driving, car owner's hands-on car-mounted electronic device will affect traffic safety, and can be very good to solve this problem using the interactive mode of voice command.
Current car-mounted electronic device adopts pure machine recognition, and discrimination is low, and can not close screen by voice command, closes sound, adjusts screen intensity and sound etc..
Content of the invention
It is an object of the invention to provide the audio recognition method that a kind of machine intelligence identification is combined with manual service is it is intended to solve pure machine recognition, the low problem of discrimination.
The present invention is achieved in that the audio recognition method that a kind of machine intelligence identification is combined with manual service, including vehicle-carrying sound recording device, for phonetic entry and identification；Described audio recognition method comprises the following steps:
A, by the acoustic control data bits of resting state in vehicle-carrying sound recording device；
B, voice command is inputted by vehicle-carrying sound recording device；
Acoustic control module in c, vehicle-carrying sound recording device is identified to the voice of input；As identified successfully, then acoustic control module is according to the corresponding order of the voice execution of input, such as recognition failures, then execution step d；
D, the processor of vehicle-carrying sound recording device automatically send instruction and connect background service；
E, judge whether to connect background service success, such as success in setting time, then passing through customer service provides the manual service needing, and such as fails, then return to step b re-enters new voice command.
The further technical scheme of the present invention is: further comprising the steps of in described step c:
C1, after speech recognition failure, the voice of input is carried out by twice decomposition becomes byte to carry out speech recognition；As success, then the restructuring of acoustic control module byte is according to the corresponding order of the voice execution of input；As identification, then execution step d.
The further technical scheme of the present invention is: further comprising the steps of in described step e:
E1, once connect background service failure after system can handover network agreement carry out secondary connection background service in setting time；As successful connection, provide, by customer service, the manual service needing, such as connection failure, then return to step b re-enter new voice command.
The further technical scheme of the present invention is: further comprising the steps of in described step a:
A1, the mic of vehicle-carrying sound recording device carry out noise reduction process to it in receiving wake-up mechanism.
The further technical scheme of the present invention is: described setting time is 10s.
Another object of the present invention is to providing the speech recognition system that a kind of machine intelligence identification is combined with manual service, including vehicle-carrying sound recording device, for phonetic entry and identification；Described speech recognition system includes:
Wake module, for by the acoustic control data bits of resting state in vehicle-carrying sound recording device；
Input module, for inputting voice command by vehicle-carrying sound recording device；
Sound identification module, is identified to the voice of input for the acoustic control module in vehicle-carrying sound recording device；As identified successfully, then acoustic control module according to the corresponding order of the voice execution of input, such as recognition failures, then executes link block；
Link block, the processor of user's vehicle-carrying sound recording device automatically sends instruction and connects background service；
Judge module, user judges whether to connect background service success, such as success in setting time, then provide the manual service needing, such as failure by customer service, then return input module and re-enter new voice command.
The further technical scheme of the present invention is: also includes in described sound identification module:
Secondary recognition unit, user carries out twice decomposition to the voice of input after speech recognition failure and becomes byte to carry out speech recognition；As success, then the restructuring of acoustic control module byte is according to the corresponding order of the voice execution of input；As identification, then execute link block.
The further technical scheme of the present invention is: also includes in described link block:
Secondary connection unit, handover network agreement can carry out secondary connection background service for system after once connecting background service failure in setting time；As successful connection, provide the manual service needing, such as connection failure by customer service, then return input module and re-enter new voice command.
The further technical scheme of the present invention is: described wake module also includes:
Noise reduction unit, the mic for vehicle-carrying sound recording device carries out noise reduction process to it in reception wake-up mechanism.
The further technical scheme of the present invention is: described setting time is 10s.
The invention has the beneficial effects as follows: by the way of machine intelligence identification is combined with artificial cognition, lifting discrimination, using the corresponding increase or the reduction that identify the brightness to equipment of voice, increase corresponding to volume or reduction carry out voice adjustment, improve the safety of driving.
Brief description
Fig. 1 is the flow chart of the audio recognition method that machine intelligence identification provided in an embodiment of the present invention is combined with manual service；
Fig. 2 is the structured flowchart of the speech recognition system that machine intelligence identification provided in an embodiment of the present invention is combined with manual service.
Specific embodiment
The flow chart that Fig. 1 shows the audio recognition method that the machine intelligence identification that the present invention provides is combined with manual service；The audio recognition method that machine intelligence identification is combined with manual service, including vehicle-carrying sound recording device, for phonetic entry and identification；Details are as follows for it:
Step s1, by the acoustic control data bits of resting state in vehicle-carrying sound recording device；User is during driving，Electronic equipment to be operated is very inconvenient，Will be very convenient using speech recognition controlled，And during vehicle travels，The acoustic control module of vehicle-mounted recording device is at resting state，So can save resources，User needs using during speech recognition，User carries out to vehicle-carrying sound recording device inputting wake-up mechanism by it from resting state wake-up，Noise can be accompanied by wake-up mechanism input process，Asking under money with the presence of noise again，The wake-up mechanism inefficacy easily causing input can not wake up acoustic control module，The wake-up mechanism that mic inputs to it during receiving wake-up mechanism in inputting wake-up mechanism carries out noise reduction process，By it with the noise remove in wake-up mechanism，Retain five noise-induceds of the wake-up mechanism of input，The wake-up mechanism sound of noise reduction is inputed to vehicle-carrying sound recording device，Its internal acoustic control data bits is used for subsequent treatment audio-frequency information；Wherein wake-up mechanism includes the similar operations possessing wake-up property operation of key word wake-up, gesture wake-up, key wakeup etc..
Step s2, inputs voice command by vehicle-carrying sound recording device；After waking up equipment, user carries out voice command input by mic to the acoustic control module of vehicle-carrying sound recording device, and the same process along with noise reduction during input voice command is so as to minimum in voice.Wherein voice command includes adjusting volume, screen intensity, bolt down procedure, condition of road surface inquiry etc..By calling speech recognition program, equipment is sent with phonetic order " close screen, improve brightness, reduce brightness ", after equipment identifies corresponding order, brightness of display screen accordingly increases or reduces；By calling speech recognition program, equipment is sent with phonetic order " close sound, increase volume, reduce volume ", after equipment identifies corresponding order, volume accordingly increases or reduces；By calling speech recognition program, equipment is sent with phonetic order, and " xx road blocks up？/ xx road conditions are how ", after equipment identifies corresponding order, the road conditions of the corresponding road of big data background query, and road conditions figure and corresponding word road conditions are returned to equipment, the real-time road of equipment this road of voice broadcast；Carry out after bluetooth connection with mobile phone, hud can obtain the contacts list in mobile phone, by calling speech recognition program, equipment is sent with phonetic order " phoning so-and-so ", equipment can complete active call function.
Step s3, the acoustic control module in vehicle-carrying sound recording device is identified to the voice of input；As identified successfully, then acoustic control module is according to the corresponding order of the voice execution of input, such as recognition failures, then execution step s4.Carrying out twice decomposition to the voice of input after speech recognition failure becomes byte to carry out speech recognition；As success, then the restructuring of acoustic control module byte is according to the corresponding order of the voice execution of input；As identification, then execution step s4.
Step s4, the processor of vehicle-carrying sound recording device automatically sends instruction and connects background service；After speech recognition identification, the processor of vehicle-carrying sound recording device can for the voice of identification, voluntarily output order, from the background service that is dynamically connected, realizes the process being voluntarily converted to manual service from voice of system according to phonetic entry.
Step s5, judges whether to connect background service success, such as success in setting time, then provides the manual service needing, such as failure by customer service, then return to step s2 re-enters new voice command.After once connecting background service failure, system handover network agreement can carry out secondary connection background service in setting time；As successful connection, provide, by customer service, the manual service needing, such as connection failure, then return to step s2 re-enter new voice command.
User speech input wakes up word, after the noise reduction mic of equipment receives wake-up word, wakes up voice-controlled software；User speech input order, machine is identified, after identification success, application program execution is corresponding operates, if recognition failures, machine talk feeds back to user, user inputs order again, machine carries out second identification, identifies that successfully application program execution is corresponding for second and operates, if second identification still fails, by artificial for turn on automatically backstage, background service personnel provide professional service to user by way of voip to equipment.
Fig. 2 shows another object of the present invention is to providing the speech recognition system that a kind of machine intelligence identification is combined with manual service, including vehicle-carrying sound recording device, for phonetic entry and identification；Described speech recognition system includes:
Wake module, for by the acoustic control data bits of resting state in vehicle-carrying sound recording device；
Input module, for inputting voice command by vehicle-carrying sound recording device；
Sound identification module, is identified to the voice of input for the acoustic control module in vehicle-carrying sound recording device；As identified successfully, then acoustic control module according to the corresponding order of the voice execution of input, such as recognition failures, then executes link block；
Link block, the processor of user's vehicle-carrying sound recording device automatically sends instruction and connects background service；
Judge module, user judges whether to connect background service success, such as success in setting time, then provide the manual service needing, such as failure by customer service, then return input module and re-enter new voice command.
Also include in described sound identification module:
Secondary recognition unit, user carries out twice decomposition to the voice of input after speech recognition failure and becomes byte to carry out speech recognition；As success, then the restructuring of acoustic control module byte is according to the corresponding order of the voice execution of input；As identification, then execute link block.
Also include in described link block:
Secondary connection unit, handover network agreement can carry out secondary connection background service for system after once connecting background service failure in setting time；As successful connection, provide the manual service needing, such as connection failure by customer service, then return input module and re-enter new voice command.
Described wake module also includes:
Noise reduction unit, the mic for vehicle-carrying sound recording device carries out noise reduction process to it in reception wake-up mechanism.
Described setting time is 10s.
By the way of machine intelligence identification is combined with artificial cognition, lift discrimination, using the corresponding increase or the reduction that identify the brightness to equipment of voice, increase corresponding to volume or reduction carry out voice adjustment, improve the safety of driving.
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all any modification, equivalent and improvement made within the spirit and principles in the present invention etc., should be included within the scope of the present invention.
Claims (10)
1. the audio recognition method that a kind of machine intelligence identification is combined with manual service, including vehicle-carrying sound recording device, for phonetic entry and identification；It is characterized in that, described audio recognition method comprises the following steps:
A, by the acoustic control data bits of resting state in vehicle-carrying sound recording device；
B, voice command is inputted by vehicle-carrying sound recording device；
Acoustic control module in c, vehicle-carrying sound recording device is identified to the voice of input；As identified successfully, then acoustic control module is according to the corresponding order of the voice execution of input, such as recognition failures, then execution step d；
D, the processor of vehicle-carrying sound recording device automatically send instruction and connect background service；
E, judge whether to connect background service success, such as success in setting time, then passing through customer service provides the manual service needing, and such as fails, then return to step b re-enters new voice command.
2. audio recognition method according to claim 1 is it is characterised in that further comprising the steps of in described step c:
C1, after speech recognition failure, the voice of input is carried out by twice decomposition becomes byte to carry out speech recognition；As success, then the restructuring of acoustic control module byte is according to the corresponding order of the voice execution of input；As identification, then execution step d.
3. audio recognition method according to claim 2 is it is characterised in that further comprising the steps of in described step e:
E1, once connect background service failure after system can handover network agreement carry out secondary connection background service in setting time；As successful connection, provide, by customer service, the manual service needing, such as connection failure, then return to step b re-enter new voice command.
4. audio recognition method according to claim 3 is it is characterised in that further comprising the steps of in described step a:
A1, the mic of vehicle-carrying sound recording device carry out noise reduction process to it in receiving wake-up mechanism.
5. audio recognition method according to claim 4 is it is characterised in that described setting time is 10s.
6. the speech recognition system that a kind of machine intelligence identification is combined with manual service, including vehicle-carrying sound recording device, for phonetic entry and identification；It is characterized in that, described speech recognition system includes:
Wake module, for by the acoustic control data bits of resting state in vehicle-carrying sound recording device；
Input module, for inputting voice command by vehicle-carrying sound recording device；
Sound identification module, is identified to the voice of input for the acoustic control module in vehicle-carrying sound recording device；As identified successfully, then acoustic control module according to the corresponding order of the voice execution of input, such as recognition failures, then executes link block；
Link block, the processor of user's vehicle-carrying sound recording device automatically sends instruction and connects background service；
Judge module, user judges whether to connect background service success, such as success in setting time, then provide the manual service needing, such as failure by customer service, then return input module and re-enter new voice command.
7. speech recognition system according to claim 6 is it is characterised in that also include in described sound identification module:
Secondary recognition unit, user carries out twice decomposition to the voice of input after speech recognition failure and becomes byte to carry out speech recognition；As success, then the restructuring of acoustic control module byte is according to the corresponding order of the voice execution of input；As identification, then execute link block.
8. speech recognition system according to claim 7 is it is characterised in that also include in described link block:
Secondary connection unit, handover network agreement can carry out secondary connection background service for system after once connecting background service failure in setting time；As successful connection, provide the manual service needing, such as connection failure by customer service, then return input module and re-enter new voice command.
9. speech recognition system according to claim 8 is it is characterised in that described wake module also includes:
Noise reduction unit, the mic for vehicle-carrying sound recording device carries out noise reduction process to it in reception wake-up mechanism.
10. speech recognition system according to claim 9 is it is characterised in that described setting time is 10s.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510424792.XA CN106356062A (en) | 2015-07-17 | 2015-07-17 | Machine intelligent recognition and manual service combined voice recognition method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510424792.XA CN106356062A (en) | 2015-07-17 | 2015-07-17 | Machine intelligent recognition and manual service combined voice recognition method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106356062A true CN106356062A (en) | 2017-01-25 |
Family
ID=57842622
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510424792.XA Pending CN106356062A (en) | 2015-07-17 | 2015-07-17 | Machine intelligent recognition and manual service combined voice recognition method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106356062A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106950698A (en) * | 2017-05-02 | 2017-07-14 | 深圳市可可卓科科技有限公司 | Support the automobile HUD methods and terminal of brightness self adapting and study |
| CN107168677A (en) * | 2017-03-30 | 2017-09-15 | 联想(北京)有限公司 | Audio-frequency processing method and device, electronic equipment, storage medium |
| CN108881377A (en) * | 2018-04-28 | 2018-11-23 | 上海车音智能科技有限公司 | A kind of application service invocation method, terminal device and server |
| CN111899722A (en) * | 2020-08-11 | 2020-11-06 | Oppo广东移动通信有限公司 | Voice processing method and device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000112497A (en) * | 1998-10-02 | 2000-04-21 | Canon Inc | Speech recognizing method, device therefor, and communication device, and control method therefor |
| US6353809B2 (en) * | 1997-06-06 | 2002-03-05 | Olympus Optical, Ltd. | Speech recognition with text generation from portions of voice data preselected by manual-input commands |
| CN103188408A (en) * | 2011-12-29 | 2013-07-03 | 上海博泰悦臻电子设备制造有限公司 | Voice auto-answer cloud server, voice auto-answer system and voice auto-answer method |
| CN104318924A (en) * | 2014-11-12 | 2015-01-28 | 沈阳美行科技有限公司 | Method for realizing voice recognition function |
| CN104751843A (en) * | 2013-12-25 | 2015-07-01 | 上海博泰悦臻网络技术服务有限公司 | Voice service switching method and voice service switching system |
-
2015
- 2015-07-17 CN CN201510424792.XA patent/CN106356062A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6353809B2 (en) * | 1997-06-06 | 2002-03-05 | Olympus Optical, Ltd. | Speech recognition with text generation from portions of voice data preselected by manual-input commands |
| JP2000112497A (en) * | 1998-10-02 | 2000-04-21 | Canon Inc | Speech recognizing method, device therefor, and communication device, and control method therefor |
| CN103188408A (en) * | 2011-12-29 | 2013-07-03 | 上海博泰悦臻电子设备制造有限公司 | Voice auto-answer cloud server, voice auto-answer system and voice auto-answer method |
| CN104751843A (en) * | 2013-12-25 | 2015-07-01 | 上海博泰悦臻网络技术服务有限公司 | Voice service switching method and voice service switching system |
| CN104318924A (en) * | 2014-11-12 | 2015-01-28 | 沈阳美行科技有限公司 | Method for realizing voice recognition function |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107168677A (en) * | 2017-03-30 | 2017-09-15 | 联想(北京)有限公司 | Audio-frequency processing method and device, electronic equipment, storage medium |
| CN106950698A (en) * | 2017-05-02 | 2017-07-14 | 深圳市可可卓科科技有限公司 | Support the automobile HUD methods and terminal of brightness self adapting and study |
| CN108881377A (en) * | 2018-04-28 | 2018-11-23 | 上海车音智能科技有限公司 | A kind of application service invocation method, terminal device and server |
| CN108881377B (en) * | 2018-04-28 | 2021-12-03 | 上海车音智能科技有限公司 | Application service calling method, terminal equipment and server |
| CN111899722A (en) * | 2020-08-11 | 2020-11-06 | Oppo广东移动通信有限公司 | Voice processing method and device and storage medium |
| CN111899722B (en) * | 2020-08-11 | 2024-02-06 | Oppo广东移动通信有限公司 | Voice processing method and device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106992009B (en) | Vehicle-mounted voice interaction method and system and computer readable storage medium | |
| WO2018149285A1 (en) | Voice wake-up method and apparatus, electronic device, and storage medium | |
| TWI489372B (en) | Voice control method and mobile terminal apparatus | |
| CN111724775A (en) | Voice interaction method and electronic equipment | |
| US20060074658A1 (en) | Systems and methods for hands-free voice-activated devices | |
| CN106356062A (en) | Machine intelligent recognition and manual service combined voice recognition method and system | |
| CN107919138B (en) | Emotion processing method in voice and mobile terminal | |
| CN107257420A (en) | System and method for signaling upcoming input | |
| JP2002534716A (en) | Voice input device with attention period | |
| CN104348953A (en) | System for automatically matching vehicle-borne device and mobile phone terminal based on Bluetooth and method thereof | |
| CN112040442B (en) | Interaction method, mobile terminal, vehicle-mounted terminal and computer-readable storage medium | |
| CN112230877A (en) | Voice operation method and device, storage medium and electronic equipment | |
| CN105244025A (en) | Voice identification method and system based on intelligent wearable device | |
| WO2023273321A1 (en) | Voice control method and electronic device | |
| CN109151637A (en) | Wireless headset, intelligent sound control system and method for wireless headset | |
| CN101266791A (en) | Method for cooperative voice command recognition and related system | |
| US20070281748A1 (en) | Method & apparatus for unlocking a mobile phone keypad | |
| CN103971683A (en) | Voice control method and system and handheld device | |
| KR20140067687A (en) | Car system for interactive voice recognition | |
| CN106028102A (en) | Television voice control method and control system | |
| CN118197323A (en) | Voice interaction method and related electronic equipment | |
| CN113220373B (en) | Processing method, apparatus and storage medium | |
| WO2020029503A1 (en) | Voice control device and method | |
| CN113223527A (en) | Voice control method for intelligent instrument of electric vehicle and electric vehicle | |
| CN103187062A (en) | Vehicle-mounted data processing device and preservation service data processing system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170125 |
|
| RJ01 | Rejection of invention patent application after publication |