CN106128458A - A kind of home voice control system based on speech recognition technology and method - Google Patents
A kind of home voice control system based on speech recognition technology and method Download PDFInfo
- Publication number
- CN106128458A CN106128458A CN201610767525.7A CN201610767525A CN106128458A CN 106128458 A CN106128458 A CN 106128458A CN 201610767525 A CN201610767525 A CN 201610767525A CN 106128458 A CN106128458 A CN 106128458A
- Authority
- CN
- China
- Prior art keywords
- signal
- module
- digital
- acoustical
- sound
- 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 51
- 238000005516 engineering process Methods 0.000 title claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 115
- 230000009466 transformation Effects 0.000 claims description 49
- 230000005236 sound signal Effects 0.000 claims description 32
- 238000009432 framing Methods 0.000 claims description 23
- 238000006243 chemical reaction Methods 0.000 claims description 19
- 230000008569 process Effects 0.000 claims description 18
- 230000003321 amplification Effects 0.000 claims description 17
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 17
- 230000005540 biological transmission Effects 0.000 claims description 10
- 238000005070 sampling Methods 0.000 claims description 8
- 238000004088 simulation Methods 0.000 claims description 8
- 206010068319 Oropharyngeal pain Diseases 0.000 claims description 4
- 201000007100 Pharyngitis Diseases 0.000 claims description 4
- 230000000052 comparative effect Effects 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000004378 air conditioning Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/2803—Home automation networks
- H04L12/2816—Controlling appliance services of a home automation network by calling their functionalities
- H04L12/282—Controlling appliance services of a home automation network by calling their functionalities based on user interaction within the home
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention provides a kind of home voice control system based on speech recognition technology and method, relate to data processing field, it is characterised in that described system includes: voice collection device;Described voice collection device, signal is connected to the first modem;Described first modem signal is connected to the first analog-digital converter;Described first analog-digital converter signal is connected to Digital Signal Processing control centre;Described Digital Signal Processing control centre signal respectively is connected to flash memory, harddisk memory, display device, the second digital to analog converter, the 3rd digital to analog converter and the 4th digital to analog converter.The present invention has the advantages such as speech recognition is accurate, distant control, low cost, cost performance are high and intelligent.
Description
Technical field
The present invention relates to Smart Home field, particularly to a kind of home voice control system based on speech recognition technology
And method.
Background technology
Smart Home is the embodiment of Internet of Things under the influence of internet.Smart Home passes through technology of Internet of things by family
Various equipment are (such as audio & video equipment, illuminator, curtain control, airconditioning control, safety-protection system, Digital Theater System, audio-visual clothes
Business device, shadow cabinet system, network home appliance etc.) connect together, it is provided that home wiring control, Lighting control, remote control using telephone, indoor and outdoor
Several functions and the means such as remote control, burglar alarm, environmental monitoring, HVAC control, infrared forwarding and programmable Timer control.With
Common household is compared, and Smart Home not only has traditional inhabitation function, has both building, network service, information household appliances, equipment certainly
Dynamicization, it is provided that omnibearing information interactive function, the most various energy expenditures save fund.
Home automation means and utilizes micro-process electronic technology, comes integrated or controls the electric equipment products in family or be
System, such as: illuminating lamp, coffee stove, computer equipment, security system, heating installation and cold gas system, video signal and sound system etc..Family
Automated system mainly receives auto-correlation electricity with a CPU microprocessor (Central Processor Unit, CPU)
After the message of sub-electric equipment products (change of outside environmental elements, as sun initial rise or west such as fall at the light change etc. caused),
Other electric equipment products is sent appropriate information to again with set program.CPU microprocessor must be transmitted through many interfaces to be come
Controlling the electric equipment products in family, these interfaces can be keyboard, it is also possible to is touch screen, button, computer, telephone set, distant
Control device etc.;Consumer can send a signal to CPU microprocessor, or receives the signal from CPU microprocessor.
Summary of the invention
In consideration of it, the invention provides a kind of home voice control system based on speech recognition technology and method, this
Bright have the advantages such as speech recognition is accurate, distant control, low cost, cost performance are high and intelligent.
The technical solution used in the present invention is as follows:
A kind of home voice control system based on speech recognition technology, it is characterised in that described system includes: sound collection fills
Put;Described voice collection device, is used for gathering original sound signal, and signal is connected to for being modulated original sound signal
The first modem with demodulation;Described first modem signal is connected to for the original sound signal of simulation being turned
It is changed to the first analog-digital converter of digital audio signal;Described first analog-digital converter signal is connected to for entering acoustical signal
The Digital Signal Processing control centre that row identifies;Described Digital Signal Processing control centre signal respectively is connected to flash memory, hard disk
Memorizer, display device, the second digital to analog converter, the 3rd digital to analog converter and the 4th digital to analog converter;Described second digital-to-analogue turns
Parallel operation, for the digital signal that Digital Signal Processing control centre sends over is converted to analogue signal, signal is connected to use
In the second modem converting analog signals into infrared signal;Described 3rd digital to analog converter, for by digital signal
The digital signal that processing controls center sends over is converted to analogue signal, and signal is connected to convert analog signals into WIFI letter
Number the 3rd modem;Described 4th digital to analog converter, for number Digital Signal Processing control centre sended over
Word signal is converted to analogue signal, and signal is connected to convert analog signals into the 4th modem of Bluetooth signal;Described
Second modem signal is connected to the Infrared Projector for launching infrared signal;Described 3rd modem letter
Number it is connected to the WIFI signal emitter for launching WIFI signal;Described 4th modem signal is connected to for launching
The Bluetooth signal emitter of Bluetooth signal.
Described Digital Signal Processing control centre includes: sub-frame processing module, judge module, Fourier transformation module and ratio
Relatively module;Described sub-frame processing module signal respectively is connected to the first analog-digital converter, comparison module and judge module;Described sentence
Disconnected module signal respectively is connected to Fourier transformation module, flash memory and harddisk memory;Described Fourier transformation module by signal is even
It is connected to comparison module;Described comparison module signal respectively is connected to the second digital to analog converter, the 3rd digital to analog converter, the 4th digital-to-analogue
Transducer, display device and sub-frame processing module.
Described voice collection device includes: audio sensor, comparison module, amplification module and power supply;Described audio frequency senses
Device signal is connected to compare, and is used for obtaining acoustical signal, sends acoustical signal to comparing;Described comparison module signal respectively is even
It is connected to amplification module and the first modem, for the intensity of sound is identified, by the intensity of sound of identification with default
Intensity threshold compare, if the intensity of this sound less than preset intensity threshold, then by acoustical signal send to amplifying mould
Block;If the intensity of this sound is higher than the intensity threshold preset, then acoustical signal is sent directly to the first modem;Described
Amplification module signal is connected to the first modem, and the acoustical signal for being sended over by comparison module is amplified place
Reason, is sent directly to the first modem by the acoustical signal after processing and amplifying;Described power supply signal respectively is connected to audio frequency
Sensor, comparison module and amplification module, provide power supply for each functional module for voice collection device.
Described sub-frame processing module, for carrying out framing to the acoustical signal collected;Described judge module, is used for judging
Whether the sample audio in acoustical signal after sub-frame processing and flash memory or harddisk memory mates;Described Fourier transformation mould
Block, the signal after processing judge module carries out Fourier transformation;Described comparison module, after to Fourier transformation
Acoustical signal carries out the comparison of frequency domain.
Described sub-frame processing module includes: framing module and judge module;Described framing module signal respectively is connected to sound
Sound harvester and judge module, for carrying out sub-frame processing by acoustical signal;Described judge module signal is connected to framing mould
Block, for judging the acoustical signal after framing, it is judged that whether it is positioned at the last frame of acoustical signal;Described Fourier
Conversion module includes: conversion module and amplitude ask for module;Described conversion module signal respectively is connected to judge module and amplitude
Asking for module, the signal after processing judge module carries out Fourier transformation process;Described amplitude is asked for module and is believed respectively
Number it is connected to conversion module and comparison module, for the signal after Fourier transformation is processed, asks for this signal in short-term
Average amplitude;Described comparison module, for judging according to the short-time average magnitude of signal, it is judged that whether the amplitude of its frequency domain
Match with the sample audio signal in flash memory or harddisk memory.
The control method of a kind of home voice control system based on speech recognition technology, it is characterised in that described method
Comprise the following steps:
Step 1: system start-up, system initialization;
Step 2: the voice collection device of system starts collected sound signal;The original sound signal collected is modulated through first
After the modulation of demodulator, sending to analog-digital converter, the original sound signal of simulation is converted to the sound of numeral by analog-digital converter
Tone signal, is sent to Digital Signal Processing control centre;
Step 3: after Digital Signal Processing control centre receives the acoustical signal collected, acoustical signal is processed, so
After will process after acoustical signal be stored in flash memory;First from harddisk memory, obtain sample sound;And to the sound collected
Comparing with sample sound after tone signal processes, the result transmission after comparing shows to display device, and
Result after comparing sends to the second digital to analog converter, the 3rd digital to analog converter and the 4th digital to analog converter;
Step 4: after the signal received is processed by each digital to analog converter, sends to corresponding modem;Adjust
Modulator-demodulator sends to corresponding signal projector after processing these signals;
Step 5: signal projector sends a signal to the household electrical appliances of correspondence, controls the operation of household electrical appliances.
The method that the acoustical signal collected is processed by described Digital Signal Processing control centre comprises the following steps:
Step 1: after Digital Signal Processing control centre receives the acoustical signal that voice collection device collects, sub-frame processing mould
Block carries out sub-frame processing to acoustical signal;Each frame acoustical signal after sub-frame processing is sent to judge module;
Step 2: the coordinating property of acoustical signal after each frame is processed by judge module judges;After will determine that result preserves
Send to Fourier transformation module;
Step 3: Fourier transformation module starts acoustical signal is carried out Fourier transformation, sends the acoustical signal after conversion extremely
Comparison module;
Step 4: comparison module carries out frequency domain to the acoustical signal after Fourier transformation and compares, sends comparative result to flash memory
Keep in;
Step 5: sub-frame processing module, can whether real-time judge processes be last of acoustical signal when processing acoustical signal
Frame, if it is transfers the transmission of the storage result in flash memory and shows to display device;If not then continuing executing with step
1。
The method that described judge module carries out Sound Match to the acoustical signal after sub-frame processing comprises the following steps:
Step 1: ask for the short-time energy of the signal after sub-frame processing, the acquiring method employing equation below of described short-time energy:
, whereinIt it is the acoustical signal sampling in certain point
Signal;
Step 2: distinguish sore throat relieving or Voiced signal according to the short-time energy sought out;
Step 3: if telling is Voiced signal, then obtain sample from harddisk memory, and the same acoustical signal that extracts is at this point
Sampling, seek out short-time energy;
Step 4: the Voiced signal short-time energy in this shop and sample are contrasted in the short-time energy of this point, it is judged that both
Difference, and then judge whether the acoustical signal collected mates.
Use above technical scheme, present invention produces following beneficial effect:
1, remotely control: present invention employs modem and the signal needing transmission is processed, ensure to the full extent
The distance of signal transmission, it is achieved that remote control domestic electrical equipment equipment, also ensure that in home environment, subregion cannot simultaneously
Cover and cause the defect of dtr signal.
2, the suitability is wide: the control system of the present invention can be launched three kinds of different signals and is controlled household electrical appliances, substantially
Cover the wireless signal control mode of main flow, extend its suitability.
3, low cost: the simple in construction of the present invention, annexation and structure between unit are the most clear, it is adaptable to
Industrialized production and manufacture, considerably reduce cost, improves popularity rate.
Use above technical scheme, present invention produces following beneficial effect:
1, speech recognition is accurate: except signal being asked for energy in time domain, judge for this energy beyond, also at frequency domain pin
The amplitude of signal is asked for and judges.Judged result according to both carries out Comprehensive Evaluation, will be greatly improved acoustical signal
Identify accuracy and the accuracy of evaluation.Avoiding existing speech control system, the not accurate enough situation of speech recognition goes out
Existing, improve Consumer's Experience.
2, remotely control: present invention employs modem and the signal needing transmission is processed, to the full extent
Ensure that the distance that signal transmits, it is achieved that remote control domestic electrical equipment equipment, also ensure that in home environment, subregion simultaneously
Cannot cover and cause the defect of dtr signal.
3, the suitability is wide: the control system of the present invention can be launched three kinds of different signals and is controlled household electrical appliances, substantially
Cover the wireless signal control mode of main flow, extend its suitability.
4, low cost: the simple in construction of the present invention, annexation and structure between unit are the most clear, it is adaptable to
Industrialized production and manufacture, considerably reduce cost, improves popularity rate.
Accompanying drawing explanation
Fig. 1 is a kind of based on speech recognition technology the home voice control system of the present invention and the system structure of method is shown
It is intended to.
Detailed description of the invention
All features disclosed in this specification, or disclosed all methods or during step, except mutually exclusive
Feature and/or step beyond, all can combine by any way.
Any feature disclosed in this specification (including any accessory claim, summary), unless specifically stated otherwise,
By other equivalences or there is the alternative features of similar purpose replaced.I.e., unless specifically stated otherwise, each feature is a series of
An example in equivalence or similar characteristics.
The embodiment of the present invention 1 provides a kind of home voice control system based on speech recognition technology, system structure
As shown in Figure 1:
A kind of home voice control system based on speech recognition technology, it is characterised in that described system includes: sound collection fills
Put;Described voice collection device, is used for gathering original sound signal, and signal is connected to for being modulated original sound signal
The first modem with demodulation;Described first modem signal is connected to for the original sound signal of simulation being turned
It is changed to the first analog-digital converter of digital audio signal;Described first analog-digital converter signal is connected to for entering acoustical signal
The Digital Signal Processing control centre that row identifies;Described Digital Signal Processing control centre signal respectively is connected to flash memory, hard disk
Memorizer, display device, the second digital to analog converter, the 3rd digital to analog converter and the 4th digital to analog converter;Described second digital-to-analogue turns
Parallel operation, for the digital signal that Digital Signal Processing control centre sends over is converted to analogue signal, signal is connected to use
In the second modem converting analog signals into infrared signal;Described 3rd digital to analog converter, for by digital signal
The digital signal that processing controls center sends over is converted to analogue signal, and signal is connected to convert analog signals into WIFI letter
Number the 3rd modem;Described 4th digital to analog converter, for number Digital Signal Processing control centre sended over
Word signal is converted to analogue signal, and signal is connected to convert analog signals into the 4th modem of Bluetooth signal;Described
Second modem signal is connected to the Infrared Projector for launching infrared signal;Described 3rd modem letter
Number it is connected to the WIFI signal emitter for WIFI signal;Described 4th modem signal is connected to for launching bluetooth
The Bluetooth signal emitter of signal.
Described Digital Signal Processing control centre includes: sub-frame processing module, judge module, Fourier transformation module and ratio
Relatively module;Described sub-frame processing module signal respectively is connected to the first analog-digital converter, comparison module and judge module;Described sentence
Disconnected module signal respectively is connected to Fourier transformation module, flash memory and harddisk memory;Described Fourier transformation module by signal is even
It is connected to comparison module;Described comparison module signal respectively is connected to the second digital to analog converter, the 3rd digital to analog converter, the 4th digital-to-analogue
Transducer, display device and sub-frame processing module.
Described voice collection device includes: audio sensor, comparison module, amplification module and power supply;Described audio frequency senses
Device signal is connected to compare, and is used for obtaining acoustical signal, sends acoustical signal to comparing;Described comparison module signal respectively is even
It is connected to amplification module and the first modem, for the intensity of sound is identified, by the intensity of sound of identification with default
Intensity threshold compare, if the intensity of this sound less than preset intensity threshold, then by acoustical signal send to amplifying mould
Block;If the intensity of this sound is higher than the intensity threshold preset, then acoustical signal is sent directly to the first modem;Described
Amplification module signal is connected to the first modem, and the acoustical signal for being sended over by comparison module is amplified place
Reason, is sent directly to the first modem by the acoustical signal after processing and amplifying;Described power supply signal respectively is connected to audio frequency
Sensor, comparison module and amplification module, provide power supply for each functional module for voice collection device.
Described sub-frame processing module, for carrying out framing to the acoustical signal collected;Described judge module, is used for judging
Whether the sample audio in acoustical signal after sub-frame processing and flash memory or harddisk memory mates;Described Fourier transformation mould
Block, the signal after processing judge module carries out Fourier transformation;Described comparison module, after to Fourier transformation
Acoustical signal carries out the comparison of frequency domain.
Described sub-frame processing module includes: framing module and judge module;Described framing module signal respectively is connected to sound
Sound harvester and judge module, for carrying out sub-frame processing by acoustical signal;Described judge module signal is connected to framing mould
Block, for judging the acoustical signal after framing, it is judged that whether it is positioned at the last frame of acoustical signal;Described Fourier
Conversion module includes: conversion module and amplitude ask for module;Described conversion module signal respectively is connected to judge module and amplitude
Asking for module, the signal after processing judge module carries out Fourier transformation process;Described amplitude is asked for module and is believed respectively
Number it is connected to conversion module and comparison module, for the signal after Fourier transformation is processed, asks for this signal in short-term
Average amplitude;Described comparison module, for judging according to the short-time average magnitude of signal, it is judged that whether the amplitude of its frequency domain
Match with the sample audio signal in flash memory or harddisk memory..
The embodiment of the present invention 2 provides a kind of home voice control method based on speech recognition technology:
The control method of a kind of home voice control system based on speech recognition technology, it is characterised in that described method includes
Following steps:
Step 1: system start-up, system initialization;
Step 2: the voice collection device of system starts collected sound signal;The original sound signal collected is modulated through first
After the modulation of demodulator, sending to analog-digital converter, the original sound signal of simulation is converted to the sound of numeral by analog-digital converter
Tone signal, is sent to Digital Signal Processing control centre;
Step 3: after Digital Signal Processing control centre receives the acoustical signal collected, acoustical signal is processed, so
After will process after acoustical signal be stored in flash memory;First from harddisk memory, obtain sample sound;And to the sound collected
Comparing with sample sound after tone signal processes, the result transmission after comparing shows to display device, and
Result after comparing sends to the second digital to analog converter, the 3rd digital to analog converter and the 4th digital to analog converter;
Step 4: after the signal received is processed by each digital to analog converter, sends to corresponding modem;Adjust
Modulator-demodulator sends to corresponding signal projector after processing these signals;
Step 5: signal projector sends a signal to the household electrical appliances of correspondence, controls the operation of household electrical appliances.
The method that the acoustical signal collected is processed by described Digital Signal Processing control centre comprises the following steps:
Step 1: after Digital Signal Processing control centre receives the acoustical signal that voice collection device collects, sub-frame processing mould
Block carries out sub-frame processing to acoustical signal;Each frame acoustical signal after sub-frame processing is sent to judge module;
Step 2: the coordinating property of acoustical signal after each frame is processed by judge module judges;After will determine that result preserves
Send to Fourier transformation module;
Step 3: Fourier transformation module starts acoustical signal is carried out Fourier transformation, sends the acoustical signal after conversion extremely
Comparison module;
Step 4: comparison module carries out frequency domain to the acoustical signal after Fourier transformation and compares, sends comparative result to flash memory
Keep in;
Step 5: sub-frame processing module, can whether real-time judge processes be last of acoustical signal when processing acoustical signal
Frame, if it is transfers the transmission of the storage result in flash memory and shows to display device;If not then continuing executing with step
1。
The method that described judge module carries out Sound Match to the acoustical signal after sub-frame processing comprises the following steps:
Step 1: ask for the short-time energy of the signal after sub-frame processing, the acquiring method employing equation below of described short-time energy:
, whereinIt it is the acoustical signal sampling in certain point
Signal;
Step 2: distinguish sore throat relieving or Voiced signal according to the short-time energy sought out;
Step 3: if telling is Voiced signal, then obtain sample from harddisk memory, and the same acoustical signal that extracts is at this point
Sampling, seek out short-time energy;
Step 4: the Voiced signal short-time energy in this shop and sample are contrasted in the short-time energy of this point, it is judged that both
Difference, and then judge whether the acoustical signal collected mates.
The embodiment of the present invention 3 provides a kind of home voice control system based on speech recognition technology and method, is
Unite structure chart as shown in Figure 1:
A kind of home voice control system based on speech recognition technology, it is characterised in that described system includes: sound collection fills
Put;Described voice collection device, is used for gathering original sound signal, and signal is connected to for being modulated original sound signal
The first modem with demodulation;Described first modem signal is connected to for the original sound signal of simulation being turned
It is changed to the first analog-digital converter of digital audio signal;Described first analog-digital converter signal is connected to for entering acoustical signal
The Digital Signal Processing control centre that row identifies;Described Digital Signal Processing control centre signal respectively is connected to flash memory, hard disk
Memorizer, display device, the second digital to analog converter, the 3rd digital to analog converter and the 4th digital to analog converter;Described second digital-to-analogue turns
Parallel operation, for the digital signal that Digital Signal Processing control centre sends over is converted to analogue signal, signal is connected to use
In the second modem converting analog signals into infrared signal;Described 3rd digital to analog converter, for by digital signal
The digital signal that processing controls center sends over is converted to analogue signal, and signal is connected to convert analog signals into WIFI letter
Number the 3rd modem;Described 4th digital to analog converter, for number Digital Signal Processing control centre sended over
Word signal is converted to analogue signal, and signal is connected to convert analog signals into the 4th modem of Bluetooth signal;Described
Second modem signal is connected to the Infrared Projector for launching infrared signal;Described 3rd modem letter
Number it is connected to the WIFI signal emitter for WIFI signal;Described 4th modem signal is connected to for launching bluetooth
The Bluetooth signal emitter of signal.
Described Digital Signal Processing control centre includes: sub-frame processing module, judge module, Fourier transformation module and ratio
Relatively module;Described sub-frame processing module signal respectively is connected to the first analog-digital converter, comparison module and judge module;Described sentence
Disconnected module signal respectively is connected to Fourier transformation module, flash memory and harddisk memory;Described Fourier transformation module by signal is even
It is connected to comparison module;Described comparison module signal respectively is connected to the second digital to analog converter, the 3rd digital to analog converter, the 4th digital-to-analogue
Transducer, display device and sub-frame processing module.
Described voice collection device includes: audio sensor, comparison module, amplification module and power supply;Described audio frequency senses
Device signal is connected to compare, and is used for obtaining acoustical signal, sends acoustical signal to comparing;Described comparison module signal respectively is even
It is connected to amplification module and the first modem, for the intensity of sound is identified, by the intensity of sound of identification with default
Intensity threshold compare, if the intensity of this sound less than preset intensity threshold, then by acoustical signal send to amplifying mould
Block;If the intensity of this sound is higher than the intensity threshold preset, then acoustical signal is sent directly to the first modem;Described
Amplification module signal is connected to the first modem, and the acoustical signal for being sended over by comparison module is amplified place
Reason, is sent directly to the first modem by the acoustical signal after processing and amplifying;Described power supply signal respectively is connected to audio frequency
Sensor, comparison module and amplification module, provide power supply for each functional module for voice collection device.
Described sub-frame processing module, for carrying out framing to the acoustical signal collected;Described judge module, is used for judging
Whether the sample audio in acoustical signal after sub-frame processing and flash memory or harddisk memory mates;Described Fourier transformation mould
Block, the signal after processing judge module carries out Fourier transformation;Described comparison module, after to Fourier transformation
Acoustical signal carries out the comparison of frequency domain.
Described sub-frame processing module includes: framing module and judge module;Described framing module signal respectively is connected to sound
Sound harvester and judge module, for carrying out sub-frame processing by acoustical signal;Described judge module signal is connected to framing mould
Block, for judging the acoustical signal after framing, it is judged that whether it is positioned at the last frame of acoustical signal;Described Fourier
Conversion module includes: conversion module and amplitude ask for module;Described conversion module signal respectively is connected to judge module and amplitude
Asking for module, the signal after processing judge module carries out Fourier transformation process;Described amplitude is asked for module and is believed respectively
Number it is connected to conversion module and comparison module, for the signal after Fourier transformation is processed, asks for this signal in short-term
Average amplitude;Described comparison module, for judging according to the short-time average magnitude of signal, it is judged that whether the amplitude of its frequency domain
Match with the sample audio signal in flash memory or harddisk memory.
The control method of a kind of home voice control system based on speech recognition technology, it is characterised in that described method
Comprise the following steps:
Step 1: system start-up, system initialization;
Step 2: the voice collection device of system starts collected sound signal;The original sound signal collected is modulated through first
After the modulation of demodulator, sending to analog-digital converter, the original sound signal of simulation is converted to the sound of numeral by analog-digital converter
Tone signal, is sent to Digital Signal Processing control centre;
Step 3: after Digital Signal Processing control centre receives the acoustical signal collected, acoustical signal is processed, so
After will process after acoustical signal be stored in flash memory;First from harddisk memory, obtain sample sound;And to the sound collected
Comparing with sample sound after tone signal processes, the result transmission after comparing shows to display device, and
Result after comparing sends to the second digital to analog converter, the 3rd digital to analog converter and the 4th digital to analog converter;
Step 4: after the signal received is processed by each digital to analog converter, sends to corresponding modem;Adjust
Modulator-demodulator sends to corresponding signal projector after processing these signals;
Step 5: signal projector sends a signal to the household electrical appliances of correspondence, controls the operation of household electrical appliances.
The method that the acoustical signal collected is processed by described Digital Signal Processing control centre comprises the following steps:
Step 1: after Digital Signal Processing control centre receives the acoustical signal that voice collection device collects, sub-frame processing mould
Block carries out sub-frame processing to acoustical signal;Each frame acoustical signal after sub-frame processing is sent to judge module;
Step 2: the coordinating property of acoustical signal after each frame is processed by judge module judges;After will determine that result preserves
Send to Fourier transformation module;
Step 3: Fourier transformation module starts acoustical signal is carried out Fourier transformation, sends the acoustical signal after conversion extremely
Comparison module;
Step 4: comparison module carries out frequency domain to the acoustical signal after Fourier transformation and compares, sends comparative result to flash memory
Keep in;
Step 5: sub-frame processing module, can whether real-time judge processes be last of acoustical signal when processing acoustical signal
Frame, if it is transfers the transmission of the storage result in flash memory and shows to display device;If not then continuing executing with step
1。
The method that described judge module carries out Sound Match to the acoustical signal after sub-frame processing comprises the following steps:
Step 1: ask for the short-time energy of the signal after sub-frame processing, the acquiring method employing equation below of described short-time energy:
, whereinIt is that acoustical signal is believed in the sampling of certain point
Number;
Step 2: distinguish sore throat relieving or Voiced signal according to the short-time energy sought out;
Step 3: if telling is Voiced signal, then obtain sample from harddisk memory, and the same acoustical signal that extracts is at this point
Sampling, seek out short-time energy;
Step 4: the Voiced signal short-time energy in this shop and sample are contrasted in the short-time energy of this point, it is judged that both
Difference, and then judge whether the acoustical signal collected mates.
The invention is not limited in aforesaid detailed description of the invention.The present invention expands to any disclose in this manual
New feature or any new combination, and the arbitrary new method that discloses or the step of process or any new combination.
Claims (8)
1. a home voice control system based on speech recognition technology, it is characterised in that described system includes: sound collection
Device;Described voice collection device, is used for gathering original sound signal, and signal is connected to for adjusting original sound signal
System and the first modem of demodulation;Described first modem signal is connected to for the original sound signal by simulation
Be converted to the first analog-digital converter of digital audio signal;Described first analog-digital converter signal is connected to for acoustical signal
The Digital Signal Processing control centre being identified;Described Digital Signal Processing control centre signal respectively is connected to flash memory, hard
Disk storage, display device, the second digital to analog converter, the 3rd digital to analog converter and the 4th digital to analog converter;Described second digital-to-analogue
Transducer, for the digital signal that Digital Signal Processing control centre sends over is converted to analogue signal, signal is connected to
For converting analog signals into the second modem of infrared signal;Described 3rd digital to analog converter, for believing numeral
Number digital signal that processing controls center sends over is converted to analogue signal, and signal is connected to convert analog signals into WIFI
3rd modem of signal;Described 4th digital to analog converter, for send over Digital Signal Processing control centre
Digital signal is converted to analogue signal, and signal is connected to convert analog signals into the 4th modem of Bluetooth signal;Institute
State second modem signal and be connected to the Infrared Projector for launching infrared signal;Described 3rd modem
Signal is connected to the WIFI signal emitter for launching WIFI signal;Described 4th modem signal is connected to for sending out
Penetrate the Bluetooth signal emitter of Bluetooth signal.
2. home voice control system based on speech recognition technology as claimed in claim 1, it is characterised in that described numeral
Signal processing control centre includes: sub-frame processing module, judge module, Fourier transformation module and comparison module;Described framing
Processing module signal respectively is connected to the first analog-digital converter, comparison module and judge module;Described judge module signal respectively
It is connected to Fourier transformation module, flash memory and harddisk memory;Described Fourier transformation module by signal is connected to comparison module;Institute
State comparison module signal respectively and be connected to the second digital to analog converter, the 3rd digital to analog converter, the 4th digital to analog converter, display device
With sub-frame processing module.
3. home voice control system based on speech recognition technology as claimed in claim 2, it is characterised in that described sound
Harvester includes: audio sensor, comparison module, amplification module and power supply;Described audio sensor signal is connected to compare,
For obtaining acoustical signal, acoustical signal is sent to comparing;Described comparison module signal respectively is connected to amplification module and
One modem, for being identified the intensity of sound, compares the intensity of sound of identification and the intensity threshold preset
Relatively, if the intensity of this sound is less than the intensity threshold preset, then acoustical signal is sent to amplification module;If the intensity of this sound
Higher than the intensity threshold preset, then acoustical signal is sent directly to the first modem;Described amplification module signal connects
In the first modem, the acoustical signal for being sended over by comparison module is amplified processing, after processing and amplifying
Acoustical signal is sent directly to the first modem;Described power supply signal respectively be connected to audio sensor, comparison module and
Amplification module, provides power supply for each functional module for voice collection device.
4. home voice control system based on speech recognition technology as claimed in claim 2, it is characterised in that described framing
Processing module, for carrying out framing to the acoustical signal collected;Described judge module, the sound after judging sub-frame processing
Whether the sample audio in signal and flash memory or harddisk memory mates;Described Fourier transformation module, for judge module
Signal after process carries out Fourier transformation;Described comparison module, for carrying out frequency domain to the acoustical signal after Fourier transformation
Comparison.
5. home voice control system based on speech recognition technology as claimed in claim 3, it is characterised in that described framing
Processing module includes: framing module and judge module;Described framing module signal respectively is connected to voice collection device and judgement
Module, for carrying out sub-frame processing by acoustical signal;Described judge module signal is connected to framing module, after to framing
Acoustical signal judges, it is judged that whether it is positioned at the last frame of acoustical signal;Described Fourier transformation module includes: conversion
Module and amplitude ask for module;Described conversion module signal respectively is connected to judge module and amplitude asks for module, for sentencing
Signal after disconnected resume module carries out Fourier transformation process;Described amplitude ask for module signal respectively be connected to conversion module and
Comparison module, for processing the signal after Fourier transformation, asks for the short-time average magnitude of this signal;Described compare mould
Block, for judging according to the short-time average magnitude of signal, it is judged that the amplitude of its frequency domain whether with flash memory or harddisk memory
In sample audio signal match.
6. a control based on the home voice control system based on speech recognition technology one of claim 1 to 5 Suo Shu
Method, it is characterised in that said method comprising the steps of:
Step 1: system start-up, system initialization;
Step 2: the voice collection device of system starts collected sound signal;The original sound signal collected is modulated through first
After the modulation of demodulator, sending to analog-digital converter, the original sound signal of simulation is converted to the sound of numeral by analog-digital converter
Tone signal, is sent to Digital Signal Processing control centre;
Step 3: after Digital Signal Processing control centre receives the acoustical signal collected, acoustical signal is processed, so
After will process after acoustical signal be stored in flash memory;First from harddisk memory, obtain sample sound;And to the sound collected
Comparing with sample sound after tone signal processes, the result transmission after comparing shows to display device, and
Result after comparing sends to the second digital to analog converter, the 3rd digital to analog converter and the 4th digital to analog converter;
Step 4: after the signal received is processed by each digital to analog converter, sends to corresponding modem;Adjust
Modulator-demodulator sends to corresponding signal projector after processing these signals;
Step 5: signal projector sends a signal to the household electrical appliances of correspondence, controls the operation of household electrical appliances.
7. home voice control method based on speech recognition technology as claimed in claim 6, it is characterised in that described numeral
The method that the acoustical signal collected is processed by signal processing control centre comprises the following steps:
Step 1: after Digital Signal Processing control centre receives the acoustical signal that voice collection device collects, sub-frame processing mould
Block carries out sub-frame processing to acoustical signal;Each frame acoustical signal after sub-frame processing is sent to judge module;
Step 2: the coordinating property of acoustical signal after each frame is processed by judge module judges;After will determine that result preserves
Send to Fourier transformation module;
Step 3: Fourier transformation module starts acoustical signal is carried out Fourier transformation, sends the acoustical signal after conversion extremely
Comparison module;
Step 4: comparison module carries out frequency domain to the acoustical signal after Fourier transformation and compares, sends comparative result to flash memory
Keep in;
Step 5: sub-frame processing module, can whether real-time judge processes be last of acoustical signal when processing acoustical signal
Frame, if it is transfers the transmission of the storage result in flash memory and shows to display device;If not then continuing executing with step
1。
8. home voice control method based on speech recognition technology as claimed in claim 7, it is characterised in that described judgement
The method that module carries out Sound Match to the acoustical signal after sub-frame processing comprises the following steps:
Step 1: ask for the short-time energy of the signal after sub-frame processing, the acquiring method employing equation below of described short-time energy:
, whereinIt is that acoustical signal is believed in the sampling of certain point
Number;
Step 2: distinguish sore throat relieving or Voiced signal according to the short-time energy sought out;
Step 3: if telling is Voiced signal, then obtain sample from harddisk memory, and the same acoustical signal that extracts is at this point
Sampling, seek out short-time energy;
Step 4: the Voiced signal short-time energy in this shop and sample are contrasted in the short-time energy of this point, it is judged that both
Difference, and then judge whether the acoustical signal collected mates.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610767525.7A CN106128458A (en) | 2016-08-31 | 2016-08-31 | A kind of home voice control system based on speech recognition technology and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610767525.7A CN106128458A (en) | 2016-08-31 | 2016-08-31 | A kind of home voice control system based on speech recognition technology and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106128458A true CN106128458A (en) | 2016-11-16 |
Family
ID=57272280
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610767525.7A Pending CN106128458A (en) | 2016-08-31 | 2016-08-31 | A kind of home voice control system based on speech recognition technology and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106128458A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106691382A (en) * | 2016-12-26 | 2017-05-24 | 赛博龙科技(北京)有限公司 | Snore detection method and device based on time frequency similarity |
CN108881168A (en) * | 2018-05-17 | 2018-11-23 | 东莞市华睿电子科技有限公司 | A kind of method for verifying login of household appliance |
CN109059199A (en) * | 2018-06-28 | 2018-12-21 | 珠海格力电器股份有限公司 | Voice wake-up device and method and voice control air conditioning system |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20020008629A (en) * | 2000-07-24 | 2002-01-31 | 배천수 | power control method using voice identificotion |
CN101567933A (en) * | 2008-04-25 | 2009-10-28 | 乐金电子(中国)研究开发中心有限公司 | Kara OK mobile phone and data processing method for Kara OK function of mobile phone |
CN102815279A (en) * | 2011-06-10 | 2012-12-12 | 沈阳君天科技股份有限公司 | Method and device for directly starting automobile by voice and preventing thievery on basis of embedded system |
CN103312827A (en) * | 2013-07-15 | 2013-09-18 | 孟凡忠 | Home cloud control method and system on basis of mobile network |
CN103943104A (en) * | 2014-04-15 | 2014-07-23 | 海信集团有限公司 | Voice information recognition method and terminal equipment |
CN105139866A (en) * | 2015-08-10 | 2015-12-09 | 泉州师范学院 | Nanyin music recognition method and device |
CN105451110A (en) * | 2014-09-24 | 2016-03-30 | 广东工业大学 | Household appliance control voice earphone based on WiFi |
-
2016
- 2016-08-31 CN CN201610767525.7A patent/CN106128458A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20020008629A (en) * | 2000-07-24 | 2002-01-31 | 배천수 | power control method using voice identificotion |
CN101567933A (en) * | 2008-04-25 | 2009-10-28 | 乐金电子(中国)研究开发中心有限公司 | Kara OK mobile phone and data processing method for Kara OK function of mobile phone |
CN102815279A (en) * | 2011-06-10 | 2012-12-12 | 沈阳君天科技股份有限公司 | Method and device for directly starting automobile by voice and preventing thievery on basis of embedded system |
CN103312827A (en) * | 2013-07-15 | 2013-09-18 | 孟凡忠 | Home cloud control method and system on basis of mobile network |
CN103943104A (en) * | 2014-04-15 | 2014-07-23 | 海信集团有限公司 | Voice information recognition method and terminal equipment |
CN105451110A (en) * | 2014-09-24 | 2016-03-30 | 广东工业大学 | Household appliance control voice earphone based on WiFi |
CN105139866A (en) * | 2015-08-10 | 2015-12-09 | 泉州师范学院 | Nanyin music recognition method and device |
Non-Patent Citations (1)
Title |
---|
杨毅明;陈东华;: "一种实时说话人身份识别***的设计", 华侨大学学报(自然科学版), no. 05 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106691382A (en) * | 2016-12-26 | 2017-05-24 | 赛博龙科技(北京)有限公司 | Snore detection method and device based on time frequency similarity |
CN106691382B (en) * | 2016-12-26 | 2020-12-15 | 赛博龙科技(北京)有限公司 | Snore detection method and device based on time-frequency similarity |
CN108881168A (en) * | 2018-05-17 | 2018-11-23 | 东莞市华睿电子科技有限公司 | A kind of method for verifying login of household appliance |
CN109059199A (en) * | 2018-06-28 | 2018-12-21 | 珠海格力电器股份有限公司 | Voice wake-up device and method and voice control air conditioning system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP7425349B2 (en) | equipment control system | |
CN107622767B (en) | Voice control method of household appliance system and household appliance control system | |
CN107622652B (en) | Voice control method of household appliance system and household appliance control system | |
TWI665584B (en) | A voice controlling system and method | |
CN112789561B (en) | System and method for customizing a portable natural language processing interface for an appliance | |
CN106842968B (en) | Control method, device and system | |
WO2016180163A1 (en) | Household control and adjustment method and system | |
JP6355939B2 (en) | Voice server, control method therefor, and voice system | |
CN110308660A (en) | Smart machine control method and device | |
CN108989162B (en) | Household intelligent robot management system | |
JP2016206851A (en) | Control apparatus, control method thereof, control system, environment control device, and control program | |
JP6045982B2 (en) | Operation support device, operation support system, and program | |
CN111754997B (en) | Control device and operation method thereof, and voice interaction device and operation method thereof | |
CN111936981A (en) | Device control system and device control method | |
CN106128458A (en) | A kind of home voice control system based on speech recognition technology and method | |
KR20130045545A (en) | Method for controlling electric-device and apparatus having the same | |
CN107566230A (en) | A kind of intelligent home control system and method based on mobile radio communication | |
JP2016063415A (en) | Network system, audio output method, server, device and audio output program | |
CN110632854A (en) | Voice control method and device, voice control node and system and storage medium | |
CN106094555A (en) | A kind of Smart Home voice activated control and home equipment control method | |
CN113009838A (en) | Intelligent home control method, terminal equipment and intelligent home control system | |
US20200258376A1 (en) | Control system, installation equipment, remote controller, control method, and program | |
CN115793481A (en) | Device control method, device, electronic device and storage medium | |
CN106710595A (en) | Intelligent household electrical appliance speech control system and method | |
CN111183478B (en) | Household electrical appliance system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20240621 |
|
AD01 | Patent right deemed abandoned |