CN215680107U - Intelligent instrument with off-line voice function - Google Patents

Intelligent instrument with off-line voice function Download PDF

Info

Publication number
CN215680107U
CN215680107U CN202122141423.3U CN202122141423U CN215680107U CN 215680107 U CN215680107 U CN 215680107U CN 202122141423 U CN202122141423 U CN 202122141423U CN 215680107 U CN215680107 U CN 215680107U
Authority
CN
China
Prior art keywords
voice
neural network
signal input
sound
information
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
Application number
CN202122141423.3U
Other languages
Chinese (zh)
Inventor
马光
李召勤
余升
吕豆
徐文庆
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu Jinpeng Group Co Ltd
Original Assignee
Jiangsu Jinpeng Group Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jiangsu Jinpeng Group Co Ltd filed Critical Jiangsu Jinpeng Group Co Ltd
Priority to CN202122141423.3U priority Critical patent/CN215680107U/en
Application granted granted Critical
Publication of CN215680107U publication Critical patent/CN215680107U/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Fittings On The Vehicle Exterior For Carrying Loads, And Devices For Holding Or Mounting Articles (AREA)
  • Instrument Panels (AREA)

Abstract

The utility model relates to an intelligent instrument with offline voice, and belongs to the technical field of electric vehicle instruments. The voice recognition device comprises a voice neural network processor, a sound pickup part, an audio amplification part, a control output part, an LCD display part, a power supply part and a signal input part; the voice neural network processor is a processor of the whole instrument, carries out digital signal processing on the sound information output by the sound pickup part, decodes the sound information output by the sound pickup part through an acoustic model, a language model and a pronunciation dictionary in the processor, broadcasts voice prompt tones through the audio amplification part, controls and controls the lamp electric appliance of the vehicle through the control output part, detects the combination switch information, the battery information and the power system information which are input into the voice neural network processor by the signal input part to be processed, and controls the lamp electric appliance of the vehicle and drives the LCD part to display through the control output part.

Description

Intelligent instrument with off-line voice function
Technical Field
The utility model relates to an intelligent instrument with offline voice, and belongs to the technical field of electric vehicle instruments.
Background
At present, intelligentization is more and more popular, especially, smart homes are rapidly developed, smart voice control devices such as a Tianmao demon and a Xiaodu are very popular, however, the smart voice control in the field of electric vehicles is more limited, for example, environmental noise is large, WIFI does not exist in the vehicle, the mobile network flow consumption is large, and mobile signals are unstable. Therefore, the meter with the off-line voice function can meet the requirement of controlling the vehicle by voice and solve the problem of dependence of voice recognition on a network.
Disclosure of Invention
In order to overcome the defects of the prior art, the utility model provides the intelligent instrument with the off-line voice, and solves the problems of dependence of voice recognition on a network, misrecognition of noise in a vehicle on the voice recognition, and fusion of the voice recognition and the vehicle.
The utility model is realized by the following technical scheme: an intelligent instrument with off-line voice, characterized in that: the voice recognition device comprises a voice neural network processor, a sound pickup part, an audio amplification part, a control output part, an LCD display part, a power supply part and a signal input part;
the voice neural network processor is a processor of the whole instrument, carries out digital signal processing on the sound information output by the sound pickup part, decodes the sound information output by the sound pickup part through an acoustic model, a language model and a pronunciation dictionary in the processor, broadcasts voice prompt tones through the audio amplification part, controls and controls the lamp electric appliance of the vehicle through the control output part, detects the combination switch information, the battery information and the power system information which are input into the voice neural network processor by the signal input part to be processed, and controls the lamp electric appliance of the vehicle and drives the LCD part to display through the control output part.
The sound pickup part picks up sound by adopting two microphones.
The voice neural network processor adopts a CI1103 neural network intelligent voice chip.
The audio amplification section comprises: the audio amplifier circuit adopts a 5W and D type power amplifier to drive a 4 omega 3W loudspeaker.
The control output part comprises: switching value output and 485 communication output.
The LCD display part is used for displaying the vehicle speed, the battery electric quantity, the gear information, the light state and the running state of a vehicle power system.
The power supply part converts the voltage of the battery pack into 12V, 5V, 3.3V and 1.2V required by the instrument to provide a working power supply for the instrument.
The signal input part comprises: the signal input of the combination switch, the signal input of the battery state and the signal input of the power system.
The utility model has the beneficial effects that: the method solves the problems of dependence of voice recognition on a network, misrecognition of noise in a vehicle to the voice recognition, and fusion of the voice recognition and the vehicle.
Drawings
The utility model is further illustrated below with reference to the figures and examples.
FIG. 1 is a system block diagram of the present invention;
FIG. 2 is a schematic diagram of the operation of the present invention;
fig. 3 is a schematic circuit diagram of a sound pickup portion of the present invention;
FIG. 4 is a schematic diagram of the circuit of the audio amplification portion of the present invention;
FIG. 5 is a schematic circuit diagram of the power supply portion of the power supply of the present invention;
FIG. 6 is a schematic circuit diagram of the signal input portion of the present invention;
FIG. 7 is a schematic circuit diagram of the control output section of the present invention;
FIG. 8 is a schematic diagram of the CI1103 speech neural network processor circuit of the present invention.
Detailed Description
The intelligent instrument with the off-line voice shown in fig. 1 to 8 has the functions of off-line voice, controlling vehicle-mounted electric appliances and lamps, detecting a combination switch, detecting a power system and detecting battery pack information besides the functions of ordinary instruments of an electric vehicle. The method is characterized in that: the voice recognition device comprises a voice neural network processor, a sound pickup part, an audio amplification part, a control output part, an LCD display part, a power supply part and a signal input part;
the voice neural network processor is a processor of the whole instrument, carries out digital signal processing on the sound information output by the sound pickup part, decodes the sound information output by the sound pickup part through an acoustic model, a language model and a pronunciation dictionary in the processor, broadcasts voice prompt tones through the audio amplification part, controls and controls the lamp electric appliance of the vehicle through the control output part, detects the combination switch information, the battery information and the power system information which are input into the voice neural network processor by the signal input part to be processed, and controls the lamp electric appliance of the vehicle and drives the LCD part to display through the control output part.
The sound pickup part picks up sound by adopting two microphones.
The voice neural network processor adopts a CI1103 neural network intelligent voice chip. CI1103 pronunciation neural network processor is responsible for handling the information of the part of picking up the sound, audio signal's output, the signal output of on-vehicle electrical apparatus and lamps and lanterns, the output of LCD demonstration content, a MCU controller is saved like this, improve the integration level, save the cost, let the off-line pronunciation chip can handle the speech instruction and can also drive the LCD demonstration, CI1103 pronunciation neural network processor inside noise reduction algorithm is used for reducing the noise that exists in the environment, improve the SNR, further promote the recognition effect, can be fine discernment speech instruction in the electric motor car driving process, the part of picking up the sound, adopt two microphone arrays, realize sound localization, microphone array confirms speaker position, prepare for the beam forming processing of discernment stage. The CI1103 voice neural network processor outputs an audio signal which drives the loudspeaker to broadcast voice command feedback sound through the amplification of the audio amplifying part. Telling the user that the voice command has been executed.
The audio amplification section comprises: the audio amplifier circuit adopts a 5W and D type power amplifier to drive a 4 omega 3W loudspeaker.
The control output part comprises: switching value output and 485 communication output.
The LCD display part is used for displaying the vehicle speed, the battery electric quantity, the gear information, the light state and the running state of a vehicle power system.
The power supply part converts the voltage of the battery pack into 12V, 5V, 3.3V and 1.2V required by the instrument to provide a working power supply for the instrument.
The signal input part comprises: the signal input of the combination switch, the signal input of the battery state and the signal input of the power system.

Claims (8)

1. An intelligent instrument with off-line voice, characterized in that: the voice recognition device comprises a voice neural network processor, a sound pickup part, an audio amplification part, a control output part, an LCD display part, a power supply part and a signal input part;
the voice neural network processor is a processor of the whole instrument, carries out digital signal processing on the sound information output by the sound pickup part, decodes the sound information output by the sound pickup part through an acoustic model, a language model and a pronunciation dictionary in the processor, broadcasts voice prompt tones through the audio amplification part, controls and controls the lamp electric appliance of the vehicle through the control output part, detects the combination switch information, the battery information and the power system information which are input into the voice neural network processor by the signal input part to be processed, and controls the lamp electric appliance of the vehicle and drives the LCD part to display through the control output part.
2. The intelligent meter with off-line voice according to claim 1, characterized in that: the sound pickup part picks up sound by adopting two microphones.
3. The intelligent meter with off-line voice according to claim 1, characterized in that: the voice neural network processor adopts a CI1103 neural network intelligent voice chip.
4. The intelligent meter with off-line voice according to claim 1, characterized in that: the audio amplification section comprises: the audio amplifier circuit adopts a 5W and D type power amplifier to drive a 4 omega 3W loudspeaker.
5. The intelligent meter with off-line voice according to claim 1, characterized in that: the control output part comprises: switching value output and 485 communication output.
6. The intelligent meter with off-line voice according to claim 1, characterized in that: the LCD display part is used for displaying the vehicle speed, the battery electric quantity, the gear information, the light state and the running state of a vehicle power system.
7. The intelligent meter with off-line voice according to claim 1, characterized in that: the power supply part converts the voltage of the battery pack into 12V, 5V, 3.3V and 1.2V required by the instrument to provide a working power supply for the instrument.
8. The intelligent meter with off-line voice according to claim 1, characterized in that: the signal input part comprises: the signal input of the combination switch, the signal input of the battery state and the signal input of the power system.
CN202122141423.3U 2021-09-07 2021-09-07 Intelligent instrument with off-line voice function Active CN215680107U (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202122141423.3U CN215680107U (en) 2021-09-07 2021-09-07 Intelligent instrument with off-line voice function

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202122141423.3U CN215680107U (en) 2021-09-07 2021-09-07 Intelligent instrument with off-line voice function

Publications (1)

Publication Number Publication Date
CN215680107U true CN215680107U (en) 2022-01-28

Family

ID=79960013

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202122141423.3U Active CN215680107U (en) 2021-09-07 2021-09-07 Intelligent instrument with off-line voice function

Country Status (1)

Country Link
CN (1) CN215680107U (en)

Similar Documents

Publication Publication Date Title
CN106782591B (en) Device and method for improving speech recognition rate under background noise
CN201489315U (en) On-board voice recognition control system
CN109040905A (en) A kind of low-power consumption speaker and its working method
CN107945799A (en) A kind of multifunction speech interactive intelligence machine
CN215680107U (en) Intelligent instrument with off-line voice function
CN104980823A (en) Multifunctional warning speaker for vehicle
CN101645716B (en) Vehicle-borne communication system having voice recognition function and recognition method thereof
CN107566945A (en) A kind of Multifunctional mobile pull bar audio amplifier
CN202480977U (en) Vehicle-mounted equipment capable of realizing voice prompt outside vehicle
CN207802262U (en) A kind of disappear echo circuit and speech recognition equipment based on microphone array
CN201550108U (en) Vehicle-mounted Bluetooth telephone device
CN215341939U (en) System for realizing vehicle control based on sound source positioning
CN102802101A (en) Device for reducing noise pollution of automobile horn and application of device
CN215815170U (en) Sound card equipment system with voice recognition function
CN210265228U (en) Fan controller based on AI pronunciation chip
CN209861140U (en) Emotion expression part of intelligent sound box
CN209980228U (en) External sound card control system based on bluetooth
CN111327994A (en) Low-power-consumption microphone, voice control device and voice control method
CN207266251U (en) A kind of car audio system
CN202957962U (en) Novel vehicle-mounted multimedia player
CN221651188U (en) Universal off-line voice central control system
CN214846339U (en) Manual control device of row is inserted to pronunciation
CN213109306U (en) Sound control system of battery car
CN113346916B (en) Vehicle-mounted frequency modulation transmitting equipment
CN211481464U (en) Low-power consumption microphone and voice control device

Legal Events

Date Code Title Description
GR01 Patent grant
GR01 Patent grant