CN104078041B - Audio recognition method and system - Google Patents
Audio recognition method and system Download PDFInfo
- Publication number
- CN104078041B CN104078041B CN201410301039.7A CN201410301039A CN104078041B CN 104078041 B CN104078041 B CN 104078041B CN 201410301039 A CN201410301039 A CN 201410301039A CN 104078041 B CN104078041 B CN 104078041B
- Authority
- CN
- China
- Prior art keywords
- index
- discrimination index
- comprehensive
- speech recognition
- distance parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- User Interface Of Digital Computer (AREA)
- Alarm Systems (AREA)
Abstract
The present invention discloses a kind of audio recognition method, and this method includes：Acoustic information is picked up from environment, analyzes the acoustic information picked up, searches noise recognition strategy table, obtains speech recognition index corresponding to Context awareness rate；The distance between controlled plant and sound source are measured, obtains corresponding distance parameter, searches functional expression corresponding to distance parameter table or substitution, acquisition distance parameter is corresponding apart from discrimination index；According to speech recognition index and apart from discrimination index, calculated according to default mathematical algorithm rule and obtain comprehensive discrimination index corresponding to Context awareness rate；According to comprehensive discrimination index, prompt message corresponding to display, corresponding operating is performed according to prompt message for user；Invention additionally discloses a kind of speech recognition system；Ambient noise that speech recognition system identifies itself and sound source position situation are shown in time, improve the intelligent and man-machine interaction of speech recognition system.
Description
Technical field
The present invention relates to speech recognition technology, more particularly to a kind of audio recognition method and system.
Background technology
With the progress of speech recognition technology, increasing equipment (such as the household electric such as television set, air conditioner
Device) corresponding function can be performed by Voice command；, can basis for example controlled plant is when detecting phonetic control command
The phonetic control command detected performs corresponding operation.And speech recognition technology be highly susceptible to noisy voice and its
The influence of his environmental noise, and the accuracy rate of speech recognition is directly related to environmental noise, such as when environmental noise is smaller, language
Sound discrimination is higher, but when environmental noise is very big or during surrounding group's declamation, speech recognition effect will become
It is very poor, or even controlled plant can not recognize corresponding phonetic order.And environment is made an uproar in view of the adaptability of human ear, human ear
Sound is but and insensitive, and human ear can not accurately perceive influence of the environmental noise to speech recognition, and therefore, human ear can not accurately known
The problem of phonetic order sent when other ambient conditions will cause controlled plant to identify or can not accurately identify,
Influence the operation of controlled plant.In addition, when sound is propagated in atmosphere, acoustic energy is fixed, and with the increase of distance, acoustic pressure
It is gradually reduced；Therefore, closer to sound source, acoustic pressure is bigger, stronger to speech recognition；Therefore, user send phonetic order with by
The distance between control equipment also influences whether the effect of speech recognition to a certain extent.
The above is only used for auxiliary and understands technical scheme, does not represent and recognizes that the above is existing skill
Art.
The content of the invention
The main object of the present invention is intended to：The ambient conditions for enabling controlled plant to prompt itself to be identified.
To achieve the above object, the embodiment of the present invention provides a kind of audio recognition method, comprises the following steps：
Acoustic information is picked up from environment, analyzes the acoustic information picked up, and according to the acoustic information
Analysis result, search noise recognition strategy table, obtain Context awareness rate corresponding to speech recognition index；
Measurement pick up the controlled plant of the acoustic information with send phonetic order control the controlled plant sound source it
Between distance, obtain corresponding distance parameter, according to the distance parameter, search distance parameter table or function corresponding to substituting into
Formula, obtain corresponding to the distance parameter apart from discrimination index；
According to the speech recognition index of acquisition and apart from discrimination index, calculate and obtain according to default mathematical algorithm rule
Take comprehensive discrimination index corresponding to Context awareness rate；
According to the comprehensive discrimination index of acquisition, the prompt message of the display comprehensive discrimination index mapping, for user
Corresponding operating is performed according to the prompt message.
Preferably, the distance parameter that the basis is measured, obtain distance identification corresponding to the distance parameter and refer to
Several steps include：
According to the distance parameter measured, distance parameter table is searched；
From the distance parameter table, the described apart from discrimination index of the distance parameter mapping is obtained.
Preferably, the comprehensive discrimination index according to acquisition, the prompting of the display comprehensive discrimination index mapping
The step of information, includes：
According to the comprehensive discrimination index of acquisition, indicator light colors corresponding to the comprehensive discrimination index are searched；
According to the indicator light colors found, corresponding indicator lamp is lighted.
Preferably, the comprehensive discrimination index according to acquisition, the prompting of the display comprehensive discrimination index mapping
The step of information, includes：
According to the comprehensive discrimination index of acquisition, indicator lamp pillar height degree corresponding to the comprehensive discrimination index is searched；
According to the indicator lamp pillar height degree found, the instruction lamppost of respective heights is lighted.
Preferably, the comprehensive discrimination index according to acquisition, the prompting of the display comprehensive discrimination index mapping
The step of information, includes：
According to the comprehensive discrimination index of acquisition, tristimulus values corresponding to the comprehensive discrimination index are searched；
According to the tristimulus values found out, corresponding indicator lamp is set to be carried out gradually according to color corresponding to the tristimulus values
Become display.
In addition, to achieve the above object, the embodiment of the present invention also provides a kind of speech recognition system, including：
Voice index acquisition module, for picking up acoustic information from environment, the acoustic information picked up is analyzed,
And according to the analysis result to the acoustic information, noise recognition strategy table is searched, voice corresponding to Context awareness rate is obtained and knows
Other index；
Range index acquisition module, the controlled plant of the acoustic information is picked up for measuring with sending phonetic order control
The distance between sound source of the controlled plant, corresponding distance parameter is obtained, according to the distance parameter, search distance parameter
Functional expression corresponding to table or substitution, is obtained corresponding to the distance parameter apart from discrimination index；
Composite index acquisition module, for the speech recognition index according to acquisition and apart from discrimination index, according to pre-
If mathematical algorithm rule calculate and obtain comprehensive discrimination index corresponding to Context awareness rate；
Information display module, for the comprehensive discrimination index according to acquisition, the display comprehensive discrimination index mapping
Prompt message, for user according to the prompt message perform corresponding operating.
Preferably, the range index acquisition module is additionally operable to：
According to the distance parameter measured, distance parameter table is searched；
From the distance parameter table, the described apart from discrimination index of the distance parameter mapping is obtained.
Preferably, described information display module is additionally operable to：
According to the comprehensive discrimination index of acquisition, indicator light colors corresponding to the comprehensive discrimination index are searched；
According to the indicator light colors found, corresponding indicator lamp is lighted.
Preferably, described information display module is additionally operable to：
According to the comprehensive discrimination index of acquisition, indicator lamp pillar height degree corresponding to the comprehensive discrimination index is searched；
According to the indicator lamp pillar height degree found, the instruction lamppost of respective heights is lighted.
Preferably, described information display module is additionally operable to：
According to the comprehensive discrimination index of acquisition, tristimulus values corresponding to the comprehensive discrimination index are searched；
According to the tristimulus values found out, corresponding indicator lamp is set to be carried out gradually according to color corresponding to the tristimulus values
Become display.
Speech recognition system of the embodiment of the present invention picks up acoustic information from environment, analyzes the sound letter picked up
Breath, and according to the analysis result to the acoustic information, obtain speech recognition index corresponding to Context awareness rate；Measurement pickup institute
The distance between the sound source of the controlled plant of acoustic information with sending the phonetic order control controlled plant is stated, is obtained corresponding
Distance parameter, according to the distance parameter, obtain corresponding to the distance parameter apart from discrimination index；According to institute's predicate of acquisition
Sound discrimination index and apart from discrimination index, calculates according to preset rules and obtains comprehensive discrimination index corresponding to Context awareness rate；Root
According to the comprehensive discrimination index of acquisition, the prompt message of the display comprehensive discrimination index mapping, carried for user according to described
Show that information performs corresponding operating；The ambient conditions that the speech recognition system is identified itself is shown in time
Come, prompt the above-mentioned ambient conditions of user, be easy to ambient noise and sound source position that user prompts according to the speech recognition system
Situation is put, takes corresponding measure；Improve the intelligent and man-machine interaction of speech recognition system；Further, by
Corresponding phonetic order can pointedly be sent according to the ambient noise and sound source position situation prompted in user, therefore,
Improve recognition accuracy of the speech recognition system to phonetic order.
Brief description of the drawings
Fig. 1 is the hardware structure schematic diagram for the controlled plant preferred embodiment that the present invention realizes speech recognition；
Fig. 2 is the high-level schematic functional block diagram of speech recognition system preferred embodiment of the present invention；
Fig. 3 is the schematic flow sheet of audio recognition method preferred embodiment of the present invention.
Realization, functional characteristics and the advantage of purpose of the embodiment of the present invention will be done furtherly referring to the drawings in conjunction with the embodiments
It is bright.
Embodiment
Technical scheme is further illustrated below in conjunction with Figure of description and specific embodiment.It should be appreciated that this
The specific embodiment of place description is not intended to limit the present invention only to explain the present invention.
Originally Fig. 1 is refer to, Fig. 1 is the hardware structure signal for the controlled plant preferred embodiment that the present invention realizes speech recognition
Figure.As shown in figure 1, the controlled plant 100 includes processing unit 11, memory cell 12, voice receiving unit 13, speech recognition
System 14 and distance measuring unit 15.Wherein, the controlled plant 100 includes but is not limited to：Household electrical appliance (such as air conditioner
Deng), mobile terminal (such as mobile phone, tablet personal computer etc.), remote control or other any suitable electronic equipment (preferably air-conditionings
Device).
The memory cell 12, for storing：The speech recognition system 14 and its service data, the speech recognition system
The acoustic information of the pickup of system 14, the discrimination index with the Context awareness rate of the acoustic information mapping of pickup, the voice are known
The distance between the user for the transmission phonetic order that other system 14 measures and the controlled plant 100 parameter, with measure it is described
Apart from discrimination index etc. corresponding to distance parameter.It is emphasized that the memory cell 12 both can be an individually storage
The general designation of device or multiple different storage devices, therefore not to repeat here.
The voice receiving unit 13, under the control of the processing unit 11, whether detection user to send voice
Instruction, and after detecting that user sends out phonetic order, pick up the acoustic information in environment；Or in the processing unit
Under 11 control, the acoustic information in environment is picked up in real time or according to predetermined period.
The distance measuring unit 15, under the control of the processing unit 11, measure the controlled plant 100 with
Send phonetic order and control the distance between sound source of the controlled plant 100, obtain corresponding distance parameter, and according to measurement
The obtained distance parameter, obtain corresponding to the distance parameter apart from discrimination index.Wherein, the distance measuring unit 15
The side such as infrared technique, Distance-sensing technology, NFC (Near Field Communication, near-field communication) technology can be passed through
Formula measures the distance between the user and the controlled plant 100, and the present embodiment adjusts the distance what measuring unit 15 was taken
Specific e measurement technology does not limit.Sound source described in the present embodiment includes but is not limited to：User, loudspeaker or other types
Audible device；The preferable sound source of the present embodiment is user, i.e., corresponding phonetic order is sent by user's sounding.
The processing unit 11, for calling and performing the speech recognition system 14, to pick up sound from environment
Information；After acoustic information corresponding to picking up, the acoustic information picked up is analyzed, and according to the acoustic information
Analysis result, obtain discrimination index corresponding to Context awareness rate；Meanwhile the controlled plant 100 is measured with sending phonetic order
Control the distance between user of the controlled plant 100, obtain corresponding distance parameter, and according to obtaining measurement away from
From parameter, obtain corresponding to the distance parameter apart from discrimination index；According to the speech recognition index of acquisition and apart from knowledge
Other index, calculated according to preset rules and obtain comprehensive discrimination index corresponding to Context awareness rate；So as to according to the described comprehensive of acquisition
Discrimination index is closed, the prompt message of the display comprehensive discrimination index mapping, is performed accordingly according to the prompt message for user
Operation, so as to realize the controlled plant 100 can according to the ambient noise conditions that identify and send phonetic order user and
These integrate discrimination indexs to prompt user to the distance between controlled plant 100, the ring prompted for user according to controlled plant 100
Border situation is tactful to take corresponding processing.The processing unit 11 and memory cell 12 both can be single unit respectively,
It can integrate, form a controller, therefore not to repeat here.
In the present embodiment, the acoustic information, which can be understood as the sound that user is sent corresponding to phonetic control command, to be believed
Breath, wherein, other acoustic informations corresponding to other non-effective phonetic orders may also be included in the acoustic information；The distance ginseng
Number can be understood as：The distance between the controlled plant 100 of the user of phonetic order with picking up the acoustic information is sent, should be away from
Horizontal displacement that can be between the user and the controlled plant 100 from parameter, or the points of articulation of the user with
Distance parameter under other definition such as horizontal displacement between the controlled plant 100；The prompt message can be understood as：Root
According to the difference of the synthesis discrimination index of Context awareness rate corresponding to the acoustic information and distance parameter, the different letters mapped
Breath；For example the comprehensive discrimination index is higher corresponding to the Context awareness rate, represent environment in noise decibel and it is described away from
Interference of the composite factor of dissociation index to speech recognition is lower, then the prompt message for corresponding to display is also different；Such as comprehensive identification
When index is advanced, the indicator lamp of green is shown；When comprehensive discrimination index is intermediate, the indicator lamp of yellow is shown；Comprehensive identification
When index is rudimentary, the indicator lamp of red is shown, the required corresponding plan taken when corresponding to phonetic order so as to prompt user to send
Slightly.Certainly, the prompt message can also be according to the difference of particular hardware equipment, production cost, use environment etc., its specific table
Existing form can also be different, herein without repeating one by one.
Fig. 2 is refer to, Fig. 2 is the high-level schematic functional block diagram of speech recognition system preferred embodiment of the present invention.
It is emphasized that it will be apparent to those skilled in the art that functional block diagram shown in Fig. 2 is only one preferably real
The exemplary plot of example is applied, those skilled in the art, can be easily around the functional module of the speech recognition system 14 shown in Fig. 2
Carry out the supplement of new functional module；The title of each functional module is self-defined title, is only used for auxiliary and understands that the voice is known
Each program function block of other system 14, restriction technical scheme is not used in, the core of technical solution of the present invention is, respectively
The function to be reached of the functional module of self-defined title.
The speech recognition system 14 that the present embodiment proposes is run in controlled plant 100 described in Fig. 1, and the voice is known
Other system 14 includes：Voice index acquisition module 141, range index acquisition module 142, composite index acquisition module 143 and
Information display module 144, the function of modules are as follows：
Voice index acquisition module 141, for picking up acoustic information from environment, analyze the sound letter picked up
Breath, and according to the analysis result to the acoustic information, obtain speech recognition index corresponding to Context awareness rate；
In the present embodiment, the acoustic information that voice index acquisition module 141 picks up from current environment includes current environment
Noise.In order to prompt the noise situations of user's current environment in time, it is easy to user to be prompted according to the speech recognition system 14
Ambient noise present situation, send corresponding phonetic order, improve the discrimination for the phonetic order that user sends, work as language
During sound identifying system 14 is run, voice index acquisition module 141 picks up corresponding sound from current environment in real time
Information.For the power consumption saved the operating cost of speech recognition system 14, reduce speech recognition system 14, voice index obtains mould
Block 141 can also pick up corresponding acoustic information according to predetermined period from current environment.The predetermined period can be by voice
Identifying system 14 is self-defined, and such as to set the predetermined period be 10ms, can also be set by user according to self-demand, or
When the controlled plant 100 for running the speech recognition system 14 is dispatching from the factory, by technical staff according to the speech recognition system
14 running environment is configured；The present embodiment is to the specific duration of the predetermined period without concrete restriction.Certainly, this is pre-
If the cycle can also be updated or reset according to specific needs.
When picking up corresponding acoustic information from environment, voice index acquisition module 141 analyzes picked up sound
Message ceases, such as, obtain sound decibel corresponding to the noise included in the acoustic information, or the sound that analysis is picked up
Whether the phonetic order of user transmission is included in message breath.According to the analysis result to tut information, the voice refers to
Number acquisition module 141 obtains the speech recognition index corresponding to current environment discrimination.
Speech recognition index corresponding to the Context awareness rate can be understood as：The speech recognition system 14 can recognize
The recognition capability for the effective phonetic order that user sends；The speech recognition index is higher, represents the speech recognition system
14 noises being presently in environment are smaller, and the discrimination for the phonetic order that the speech recognition system 14 is sent to user is higher.
Range index acquisition module 142, the controlled plant of the acoustic information is picked up for measuring with sending phonetic order
The distance between sound source of the controlled plant is controlled, obtains corresponding distance parameter, according to the distance parameter, described in acquisition
Apart from discrimination index corresponding to distance parameter；
Range index acquisition module 142 measures：Pick up the controlled plant described in controlled plant i.e. Fig. 1 of the acoustic information
100, the distance between described sound source with sending phonetic order, obtain corresponding distance parameter.Obtaining corresponding distance ginseng
After number, the range index acquisition module 142 is obtained and identified with the distance of distance parameter mapping according to above-mentioned distance parameter
Index；It is described to can be understood as apart from discrimination index：Represent to send efficient voice instruction sound source and the controlled plant 100 it
Between distance, i.e., described sound source and the distance of the controlled plant 100 are nearer, then described higher apart from discrimination index；Institute
State sound source and the distance of the controlled plant 100 is more remote, then it is described lower apart from discrimination index.And it is higher apart from discrimination index,
Then represent that the controlled plant 100 is higher to the discrimination of the phonetic order.
Wherein, the range index acquisition module 142 measures the distance between the user and the controlled plant 100
When, the measurement to above-mentioned distance, the embodiment of the present invention can be realized by infrared technique, range sensor or NFC technique etc.
The concrete mode that the distance parameter is taken is obtained to the range index acquisition module 142 not limit.In addition, it is described away from
The distance between the user and described controlled plant 100 that dissociation index acquisition module 142 measures can be understood as：The user
Horizontal range between central point and the controlled plant 100；Under normal circumstances, the range index acquisition module can be set
Horizontal range of 142 distance parameters obtained between the sound source and the controlled plant 100 of transmission phonetic order；It is described
Sound source can be regarded as sending user, loudspeaker or the other equipment of efficient voice instruction.In the embodiment of the present invention, preferable sound
Source is user.
Composite index acquisition module 143, for the speech recognition index according to acquisition and apart from discrimination index, according to
Preset rules, which calculate, obtains comprehensive discrimination index corresponding to Context awareness rate；
The speech recognition index that composite index acquisition module 143 obtains according to voice index acquisition module 141, and distance
Index acquisition module 142 obtain apart from discrimination index, calculate to obtain according to preset rules and comprehensive corresponding to Context awareness rate know
Other index.The preset rules can be understood as：Controlled plant 100 acquiescence use computation rule, or technical staff according to
Specifically used scene setting is the computation rule that the controlled plant 100 is set；Under default situations, the comprehensive discrimination index is
Speech recognition index with apart from discrimination index sum.Such as under current environment, speech recognition index corresponding to the ambient noise
For 52, it is corresponding apart from discrimination index be -5, then speech recognition index with apart from discrimination index sum be 47, i.e., it is described comprehensive to know
Other index is 47.
Information display module 144, for the comprehensive discrimination index according to acquisition, show that the comprehensive discrimination index reflects
The prompt message penetrated, corresponding operating is performed according to the prompt message for user.
After the composite index acquisition module 143 gets comprehensive discrimination index corresponding to Context awareness rate, the letter
The comprehensive discrimination index that breath display module 144 obtains according to the composite index acquisition module 143, show the comprehensive knowledge
The prompt message of other index mapping, the prompt message shown for user according to described information display module 144 perform corresponding
Operation.
For example the comprehensive of current environment is known according to corresponding to the prompt message that described information display module 144 is shown
Other index is advanced, then user chooses whether to send corresponding phonetic order, or whether user needs height according to above-mentioned prompting
Sound sends corresponding phonetic order, or whether user needs to reduce the noise in current environment so as to take normal sound point
Shellfish sends corresponding phonetic order etc.；For another example, according to corresponding to the prompt message that described information display module 144 is shown
The synthesis discrimination index of current environment is rudimentary, then it represents that under current environment, ambient noise and sound source distance are known to the voice
Other system 14 identifies that the influence of phonetic order can almost be ignored, i.e., user can send corresponding voice according to common mode
Instruction, then user sends corresponding phonetic order according to the prompt message of described information display module 144 according to common mode.
It will be understood by those skilled in the art that described information display module 144 can also by above-mentioned speech recognition index and
It is described individually to be shown apart from discrimination index, it is as described above to be particularly shown form；Herein without repeating one by one.
Speech recognition system of the embodiment of the present invention picks up acoustic information from environment, analyzes the sound letter picked up
Breath, and according to the analysis result to the acoustic information, obtain speech recognition index corresponding to Context awareness rate；Measurement pickup institute
The distance between the sound source of the controlled plant of acoustic information with sending the phonetic order control controlled plant is stated, is obtained corresponding
Distance parameter, according to the distance parameter, obtain corresponding to the distance parameter apart from discrimination index；According to institute's predicate of acquisition
Sound discrimination index and apart from discrimination index, calculates according to preset rules and obtains comprehensive discrimination index corresponding to Context awareness rate；Root
According to the comprehensive discrimination index of acquisition, the prompt message of the display comprehensive discrimination index mapping, carried for user according to described
Show that information performs corresponding operating；Enable the ambient noise and sound source position feelings that the speech recognition system identifies itself
Condition is shown in time, prompts the above-mentioned ambient conditions of user, the environment for being easy to user to be prompted according to the speech recognition system
Noise and sound source position situation, take corresponding measure；Improve the intelligent and man-machine interaction of speech recognition system；
Further, because user can pointedly send corresponding phonetic order according to the ambient conditions prompted, therefore, improve
Recognition accuracy of the speech recognition system to phonetic order.
Further, Fig. 1 and Fig. 2 are continued referring to, in speech recognition system 14 of the present invention, the voice index obtains mould
According to the analysis result of the acoustic information to pickup, discrimination index corresponding to acquisition Context awareness rate can use as follows block 141
Mode：
When voice index acquisition module 141 analyzes the noise decibel corresponding to the acoustic information of pickup, search noise and know
Other Policy Table, from the Noise Identification Policy Table, obtain the discrimination index of the noise decibel mapping.
Further, the range index acquisition module 142 measures the controlled plant and hair for picking up the acoustic information
Sending voice instruction controls the distance between sound source of the controlled plant, after obtaining corresponding distance parameter, according to the distance
Parameter, distance parameter table is searched, from the distance parameter table, the distance identification for obtaining the distance parameter mapping refers to
Number.For example the distance parameter above-mentioned distance parameter table corresponding with the mapping relations apart from discrimination index is：
| Distance parameter | Apart from discrimination index |
| 1 meter | -5 |
| 2 meters | -2 |
| 3 meters | 0 |
| 4 meters | 2 |
| 5 meters | 3.5 |
| …… | …… |
When the range index acquisition module 142 measures the distance parameter, by searching the distance parameter table,
Can obtain the distance parameter mapped it is described apart from discrimination index.Certainly, in the embodiment of the present invention, the distance identification
Index can also be a certain function corresponding to distance parameter, such as linear function or quadratic function etc.；When the distance refers to
When number acquisition module 142 measures the distance parameter, functional expression corresponding to distance parameter substitution can also be calculated
To described apart from discrimination index corresponding to the distance parameter.
Further, in speech recognition system embodiment of the present invention, the composite index acquisition module 143 is according to acquisition
The speech recognition index and described apart from discrimination index, when the comprehensive discrimination index is calculated, can be used any suitable
The mathematical algorithm of conjunction or other algorithms draw above-mentioned comprehensive discrimination index, and the present embodiment is without exhaustive one by one；The present embodiment
In, it is preferred to use following algorithm：Using the speech recognition index and the vector apart from discrimination index as the synthesis
Discrimination index.
Further, in speech recognition system embodiment of the present invention, described information display module 144 is according to acquisition
Comprehensive discrimination index, the prompt message of the display comprehensive discrimination index mapping can be in the following way：
Mode one：
Described information display module 144 shows the comprehensive discrimination index of different numerical value using the color of indicator lamp,
For example the comprehensive discrimination index that the composite index acquisition module 143 obtains is less than 50, then described information display module
144 display green lights；The comprehensive discrimination index that the composite index acquisition module 143 obtains (includes 50, not wrapped for 50~70
Between 70), then described information display module 144 shows amber light；The synthesis that the composite index acquisition module 143 obtains
Discrimination index was more than 70 (containing 70), then described information display module 144 shows red light.For example if the composite index obtains
The comprehensive discrimination index that module 143 obtains is 45, then described information display module 144 shows green light.
Mode two：
Described information display module 144 shows that the comprehensive identification of different numerical value refers to using the height for indicating lamppost
Number, wherein, the instruction lamppost can horizontally or vertically be arranged by several display units, and according to different noise decibel meters
The number for the display unit for needing to show is calculated, so as to which corresponding display indicates the height of lamppost.For example 10 display units are formed
Instruction lamppost vertical arrangement, when the composite index acquisition module 143 obtain the comprehensive discrimination index be 40 when, it is described
Information display module 144 lights a display unit of composition instruction lamppost bottom；When the composite index acquisition module 143
Obtain the comprehensive discrimination index be 70 when, described information display module 144 light from composition instruction lamppost most under to most
All 10 display units of top, the height of lamppost is correspondingly indicated by the number of display unit to remind the noise of user environment
It is horizontal.For another example, when the comprehensive discrimination index that the composite index acquisition module 143 obtains is 65, then described information shows
Showing that module 144 lights 8 display units, the lamppost that now user sees is higher, then knowing needs with bigger sound, with
It is easy to the speech recognition system 14 to accurately identify corresponding phonetic order.
Mode three：
Described information display module 144 shows that the comprehensive identification of different numerical value refers to using the tristimulus values of indicator lamp
Number, the size variation of noise decibel value in environment is converted into the trichromatic compositions of corresponding RGB, by according to noise decibel value
To adjust the brightness value of each primary components in three primary colors, so as to match out gradient color, the size with noise decibel value is shown
Show the gradual change of color.For example ambient noise is when becoming big, the synthesis that correspondingly the composite index acquisition module 143 obtains
Discrimination index can also become big, then described information display module 144 is according to the comprehensive redeployed color value of discrimination index
From light color system gradually toward the conversion of dark color system, so as to prompt user that noise is increasing.
Mode four：
Described information display module 144 shows that the comprehensive identification of different numerical value refers to using the flicker frequency of indicator lamp
Number, such as when the comprehensive discrimination index that the composite index acquisition module 143 obtains is below the first default decibel value,
The indicator lamp that then described information display module 144 is shown is Chang Liang, that is to say, that the indicator lamp seen by person is without dodging
It is bright；As the comprehensive discrimination index is increasing, then described information display module 144 show indicator lamp flicker frequency
More and more higher, so as to prompt user that noise is increasing.It is also understood that the instruction that described information display module 144 is shown
The flicker frequency of lamp is directly proportional to the size of the comprehensive discrimination index.
What the four kinds of display modes listed above enumerated were merely exemplary, those skilled in the art utilize skill of the invention
Art thought, other display modes proposed according to its real needs are within the scope of the present invention, herein without one
One is exhaustive.
Speech recognition system of the present invention is shown by the distance of noise corresponding to the environment by identification and sound source and controlled plant
Show to prompt user's present circumstances, to improve the intelligent of the speech recognition system；Further, due to being capable of root
Corresponding phonetic order is pointedly sent according to the ambient conditions prompted, voice is referred to this improves speech recognition system
The recognition accuracy of order.
It refer to Fig. 3, Fig. 3 is the schematic flow sheet of audio recognition method preferred embodiment of the present invention, the embodiment of the present invention
Provide a kind of embodiment of audio recognition method one.
As shown in figure 3, audio recognition method of the present invention comprises the following steps：
Step S01, acoustic information is picked up from environment, analyzes the acoustic information picked up, and according to described
The analysis result of acoustic information, obtain speech recognition index corresponding to Context awareness rate.
In the present embodiment, the acoustic information that controlled plant picks up from current environment includes the noise of current environment.In order to
The noise situations of prompting user's current environment in time, the ambient noise present feelings for being easy to user to be prompted according to the controlled plant
Condition, corresponding phonetic order is sent, improve the discrimination for the phonetic order that user sends, when the process of controlled plant operation
In, controlled plant picks up corresponding acoustic information from current environment in real time.In order to save the operating cost of controlled plant, drop
The power consumption of low controlled plant, controlled plant can also pick up corresponding acoustic information according to predetermined period from current environment.
The predetermined period can by controlled plant it is self-defined such as to set the predetermined period be 10ms, can also be by user according to itself
Demand is set, or when controlled plant is dispatching from the factory, is configured by technical staff according to the running environment of the controlled plant；
The present embodiment is to the specific duration of the predetermined period without concrete restriction.Certainly, the predetermined period can also be according to specific
Need to be updated or reset.
When picking up corresponding acoustic information from environment, controlled plant analyzes picked up acoustic information, such as,
Obtain sound decibel corresponding to the noise included in the acoustic information, or in the picked up acoustic information of analysis whether
Include the phonetic order of user's transmission.According to the analysis result to tut information, the controlled plant, which obtains, works as front ring
Speech recognition index corresponding to the discrimination of border.
Speech recognition index corresponding to the Context awareness rate can be understood as：The controlled plant being capable of discriminating user hair
The recognition capability of the effective phonetic order sent；The speech recognition index is higher, represents that the controlled plant is presently in ring
Noise in border is smaller, and the discrimination for the phonetic order that the controlled plant is sent to user is higher.
Step S02, measurement picks up the controlled plant of the acoustic information with sending the phonetic order control controlled plant
The distance between sound source, obtain corresponding distance parameter, according to the distance parameter, obtain corresponding to the distance parameter away from
From discrimination index；
Controlled plant measures the distance between the described sound source of the controlled plant itself with sending phonetic order, obtains pair
The distance parameter answered.After distance parameter corresponding to obtaining, controlled plant is obtained and joined with the distance according to above-mentioned distance parameter
Number mapping apart from discrimination index；It is described to can be understood as apart from discrimination index：Represent send efficient voice instruction sound source with
The distance between controlled plant distance, i.e., described sound source and the distance of the controlled plant are nearer, then the distance identification
Index is higher；The sound source and the distance of the controlled plant are more remote, then described lower apart from discrimination index.And refer to apart from identification
Number is higher, then it represents that the controlled plant is higher to the discrimination of the phonetic order.
Wherein, can be by infrared during controlled plant measurement the distance between the user and the controlled plant
Technology, range sensor or NFC technique etc. realize the measurement to above-mentioned distance, and the embodiment of the present invention obtains to the controlled plant
The concrete mode for taking the distance parameter to be taken does not limit.In addition, the user of controlled plant measurement with it is described
The distance between controlled plant can be understood as：Horizontal range between the customer center point and the controlled plant；Generally
In the case of, the distance parameter that the controlled plant obtains can be set and controlled set with described to send the sound source of phonetic order
Horizontal range between standby；The sound source can be regarded as sending user, loudspeaker or the other equipment of efficient voice instruction.This
In inventive embodiments, preferable sound source is user.
In addition, first obtaining the speech recognition index for controlled plant, still first obtain apart from discrimination index, be not
The present embodiment relation, as long as controlled plant gets above-mentioned speech recognition index and apart from discrimination index, therefore,
The present embodiment is not limited the step S01 and step S02 sequencings performed.
Step S03, according to the speech recognition index of acquisition and apart from discrimination index, calculate and obtain according to preset rules
Comprehensive discrimination index corresponding to Context awareness rate；
Controlled plant calculates according to preset rules according to the speech recognition index of acquisition and apart from discrimination index and obtains ring
Comprehensive discrimination index corresponding to the discrimination of border.The preset rules can be understood as：The computation rule that controlled plant acquiescence uses,
Or technical staff is according to the computation rule that specifically used scene setting is that the controlled plant is set；It is described under default situations
Comprehensive discrimination index is for speech recognition index and apart from discrimination index sum.For example under current environment, the ambient noise is corresponding
Speech recognition index be 52, it is corresponding apart from discrimination index be -5, then speech recognition index with being apart from discrimination index sum
47, i.e., described comprehensive discrimination index is 47.
Step S04, according to the comprehensive discrimination index of acquisition, the prompting letter of the display comprehensive discrimination index mapping
Breath, corresponding operating is performed according to the prompt message for user.
After controlled plant gets comprehensive discrimination index corresponding to Context awareness rate, according to the comprehensive identification of acquisition
Index, the prompt message of the display comprehensive discrimination index mapping, the prompting shown for user according to the controlled plant
Information performs corresponding operating.
For example the synthesis discrimination index of current environment according to corresponding to the prompt message that controlled plant is shown is height
Grade, then user chooses whether to send corresponding phonetic order, or whether user needs to send loudly accordingly according to above-mentioned prompting
Phonetic order, or whether user need to reduce the noise in current environment so as to taking normal sound decibel to send accordingly
Phonetic order etc.；For another example, the synthesis identification of current environment refers to according to corresponding to the prompt message that controlled plant is shown
Number is rudimentary, then it represents that under current environment, ambient noise and sound source distance identify phonetic order to the speech recognition system 14
Influence can almost ignore, i.e., user can send corresponding phonetic order according to common mode, then user is according to described
The prompt message of information display module 144, corresponding phonetic order is sent according to common mode.
It will be understood by those skilled in the art that the controlled plant can also be by above-mentioned speech recognition index and the distance
Discrimination index is individually shown, it is as described above to be particularly shown form；Herein without repeating one by one.
Speech recognition system of the embodiment of the present invention picks up acoustic information from environment, analyzes the sound letter picked up
Breath, and according to the analysis result to the acoustic information, obtain speech recognition index corresponding to Context awareness rate；Measurement pickup institute
The distance between the sound source of the controlled plant of acoustic information with sending the phonetic order control controlled plant is stated, is obtained corresponding
Distance parameter, according to the distance parameter, obtain corresponding to the distance parameter apart from discrimination index；According to institute's predicate of acquisition
Sound discrimination index and apart from discrimination index, calculates according to preset rules and obtains comprehensive discrimination index corresponding to Context awareness rate；Root
According to the comprehensive discrimination index of acquisition, the prompt message of the display comprehensive discrimination index mapping, carried for user according to described
Show that information performs corresponding operating；The ambient conditions that the speech recognition system is identified itself is shown in time
Come, prompt the above-mentioned ambient conditions of user, be easy to ambient noise and sound source position that user prompts according to the speech recognition system
Situation is put, takes corresponding measure；Improve the intelligent and man-machine interaction of speech recognition system；Further, by
Corresponding phonetic order can pointedly be sent according to the ambient noise and sound source position situation prompted in user, therefore,
Improve recognition accuracy of the speech recognition system to phonetic order.
Further, Fig. 3 is continued referring to, in audio recognition method of the embodiment of the present invention, controlled plant is according to described
The analysis result of acoustic information, discrimination index corresponding to acquisition Context awareness rate can be in the following way：
When controlled plant analyzes the noise decibel corresponding to the acoustic information of pickup, Noise Identification Policy Table is searched, from
In the Noise Identification Policy Table, the discrimination index of the noise decibel mapping is obtained.And then according to the knowledge of acquisition
Other index, controlled plant show corresponding to prompt message.
Further, controlled plant obtains distance corresponding to the distance parameter according to the distance parameter measured
Discrimination index can be in the following way：
Controlled plant searches distance parameter table according to the distance parameter measured；From the distance parameter table, obtain
Take the described apart from discrimination index of the distance parameter mapping.
Controlled plant measure the controlled plant itself with send phonetic order control the controlled plant sound source it
Between distance, obtain corresponding to after distance parameter, controlled plant searches distance parameter table according to the distance parameter, from described
In distance parameter table, the described apart from discrimination index of the distance parameter mapping is obtained.Such as the distance parameter with it is described away from
Mapping relations from discrimination index correspond to above-mentioned distance parameter table and are：
| Distance parameter | Apart from discrimination index |
| 1 meter | -5 |
| 2 meters | -2 |
| 3 meters | 0 |
| 4 meters | 2 |
| 5 meters | 3.5 |
| …… | …… |
When the controlled plant measures the distance parameter, by searching the distance parameter table, you can obtain institute
State distance parameter mapped it is described apart from discrimination index.Certainly, in the embodiment of the present invention, it is described can also apart from discrimination index
For a certain function corresponding to distance parameter, such as linear function or quadratic function etc.；When controlled plant measure it is described away from
During from parameter, functional expression corresponding to distance parameter substitution can also be calculated described corresponding to the distance parameter
Apart from discrimination index.
Further, in speech recognition system embodiment of the present invention, the controlled plant is known according to the voice of acquisition
Other index and described apart from discrimination index, when the comprehensive discrimination index is calculated, can use arbitrarily suitable mathematics to calculate
Method or other algorithms draw above-mentioned comprehensive discrimination index, and the present embodiment is without exhaustive one by one；In the present embodiment, it is preferred to use
Following algorithm：Using the speech recognition index and the vector apart from discrimination index as the comprehensive discrimination index.
Further, in speech recognition system embodiment of the present invention, controlled plant refers to according to the comprehensive identification of acquisition
Number, the prompt message of the display comprehensive discrimination index mapping can be in the following way：
Mode one：
Controlled plant shows the comprehensive discrimination index of different numerical value using the color of indicator lamp, such as, it is described by
It is less than 50 to control the comprehensive discrimination index that equipment obtains, then the controlled plant shows green light；The controlled plant obtains
The comprehensive discrimination index (include 50, between 70), then the controlled plant shows amber light for 50~70；It is described by
It was more than 70 (containing 70) to control the comprehensive discrimination index that equipment obtains, then the controlled plant shows red light.It is such as if described
The comprehensive discrimination index that controlled plant obtains is 45, then the controlled plant shows green light.
Mode two：
Controlled plant shows the comprehensive discrimination index of different numerical value using the height for indicating lamppost, wherein, it is described
Instruction lamppost can horizontally or vertically be arranged by several display units, and calculate what needs were shown according to different noise decibels
The number of display unit, so as to which corresponding display indicates the height of lamppost.For example the instruction lamppost of 10 display unit compositions is hung down
In line row, when the comprehensive discrimination index that the controlled plant obtains is 40, the controlled plant lights composition indicator lamp
One display unit of post bottom；It is described controlled to set when the comprehensive discrimination index that the controlled plant obtains is 70
It is standby light from composition instruction lamppost most under to the top all 10 display units, indicated by the number of display unit is corresponding
The height of lamppost reminds the noise level of user environment.For another example, the comprehensive discrimination index that the controlled plant obtains
For 65 when, then the controlled plant lights 8 display units, and the lamppost that now user sees is higher, then know needs with than
Larger sound, in order to which the speech recognition system 14 can accurately identify corresponding phonetic order.
Mode three：
Controlled plant shows the comprehensive discrimination index of different numerical value using the tristimulus values of indicator lamp, by environment
The size variation of noise decibel value is converted into the trichromatic compositions of corresponding RGB, former by adjusting three according to noise decibel value
The brightness value of each primary components in color, so as to match out gradient color, display color is carried out gradually with the size of noise decibel value
Become.For example ambient noise, when becoming big, the comprehensive discrimination index that correspondingly controlled plant obtains can also become big, then institute
Controlled plant is stated according to the comprehensive redeployed color value of discrimination index also from light color system gradually toward the conversion of dark color system, so that
Prompt user's noise increasing.
Mode four：
Controlled plant shows the comprehensive discrimination index of different numerical value using the flicker frequency of indicator lamp, for example works as institute
The comprehensive discrimination index of controlled plant acquisition is stated when first presets below decibel value, then the finger that the controlled plant is shown
It is Chang Liang to show lamp, that is to say, that the indicator lamp seen by person is without flicker；With the comprehensive discrimination index increasingly
Greatly, then the flicker frequency for the indicator lamp that the controlled plant is shown also more and more higher, so as to prompt user that noise is increasing.
It is to be understood that the flicker frequency for the indicator lamp that the controlled plant is shown is directly proportional to the size of the comprehensive discrimination index.
What the four kinds of display modes listed above enumerated were merely exemplary, those skilled in the art utilize skill of the invention
Art thought, other display modes proposed according to its real needs are within the scope of the present invention, herein without one
One is exhaustive.
Speech recognition system of the present invention is shown by the distance of noise corresponding to the environment by identification and sound source and controlled plant
Show to prompt user's ambient noise present and sound source position situation, to improve the intelligent of the speech recognition system；Enter one
Step ground, due to can pointedly send corresponding phonetic order according to the ambient noise and sound source position situation prompted, because
This, improves recognition accuracy of the speech recognition system to phonetic order.
It should be noted that herein, term " comprising ", "comprising" or its any other variant are intended to non-row
His property includes, so that process, method, article or system including a series of elements not only include those key elements, and
And also include the other element being not expressly set out, or also include for this process, method, article or system institute inherently
Key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that including this
Other identical element also be present in the process of key element, method, article or system.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on such understanding, technical scheme is substantially done to prior art in other words
Going out the part of contribution can be embodied in the form of software product, and the computer software product is stored in a storage medium
In (such as ROM/RAM, magnetic disc, CD), including some instructions to cause a station terminal equipment (can be mobile phone, computer, clothes
Be engaged in device, air conditioner, or network equipment etc.) perform method described in each embodiment of the present invention.
The preferred embodiments of the present invention are the foregoing is only, not thereby limit its scope of the claims, it is every to utilize the present invention
The equivalent structure or equivalent flow conversion that specification and accompanying drawing content are made, directly or indirectly it is used in other related technology necks
Domain, it is included within the scope of the present invention.
Claims (10)
1. a kind of audio recognition method, it is characterised in that comprise the following steps：
Acoustic information is picked up from environment, analyzes the acoustic information picked up, and divide according to the acoustic information
Result is analysed, searches noise recognition strategy table, obtains speech recognition index corresponding to Context awareness rate, the Context awareness rate is corresponding
Speech recognition index be interpreted as：Controlled plant is capable of the recognition capability of the effective phonetic order of discriminating user transmission；
Measurement is picked up between the controlled plant of the acoustic information and the sound source of the transmission phonetic order control controlled plant
Distance, corresponding distance parameter is obtained, according to the distance parameter, searches functional expression corresponding to distance parameter table or substitution,
Obtain and send efficient voice instruction apart from discrimination index, described be understood to mean that apart from discrimination index corresponding to the distance parameter
Sound source and the distance between controlled plant distance；
According to the speech recognition index of acquisition and apart from discrimination index, calculated according to default mathematical algorithm rule and obtain ring
Comprehensive discrimination index corresponding to the discrimination of border, the comprehensive discrimination index be the speech recognition index and apart from discrimination index it
With；
According to the comprehensive discrimination index of acquisition, the prompt message of the display comprehensive discrimination index mapping, for user according to
The prompt message performs corresponding operating.
2. audio recognition method as claimed in claim 1, it is characterised in that the distance parameter that the basis is measured, obtain
Take includes corresponding to the distance parameter apart from the step of discrimination index：
According to the distance parameter measured, distance parameter table is searched；
From the distance parameter table, the described apart from discrimination index of the distance parameter mapping is obtained.
3. audio recognition method as claimed in claim 1 or 2, it is characterised in that the comprehensive identification according to acquisition
Index, include the step of the prompt message of the display comprehensive discrimination index mapping：
According to the comprehensive discrimination index of acquisition, indicator light colors corresponding to the comprehensive discrimination index are searched；
According to the indicator light colors found, corresponding indicator lamp is lighted.
4. audio recognition method as claimed in claim 1 or 2, it is characterised in that the comprehensive identification according to acquisition
Index, include the step of the prompt message of the display comprehensive discrimination index mapping：
According to the comprehensive discrimination index of acquisition, indicator lamp pillar height degree corresponding to the comprehensive discrimination index is searched；
According to the indicator lamp pillar height degree found, the instruction lamppost of respective heights is lighted.
5. audio recognition method as claimed in claim 1 or 2, it is characterised in that the comprehensive identification according to acquisition
Index, include the step of the prompt message of the display comprehensive discrimination index mapping：
According to the comprehensive discrimination index of acquisition, tristimulus values corresponding to the comprehensive discrimination index are searched；
According to the tristimulus values found out, corresponding indicator lamp is carried out gradual change according to color corresponding to the tristimulus values and show
Show.
A kind of 6. speech recognition system, it is characterised in that including：
Voice index acquisition module, for picking up acoustic information from environment, analyze the acoustic information picked up, and root
According to the analysis result to the acoustic information, noise recognition strategy table is searched, speech recognition corresponding to acquisition Context awareness rate refers to
Number, speech recognition index corresponding to the Context awareness rate are interpreted as：Controlled plant is capable of the effective language of discriminating user transmission
The recognition capability of sound instruction；
Range index acquisition module, the controlled plant of the acoustic information is picked up for measuring with sending described in phonetic order control
The distance between sound source of controlled plant, obtain corresponding distance parameter, according to the distance parameter, search distance parameter table or
Functional expression corresponding to person's substitution, is obtained corresponding to the distance parameter apart from discrimination index, described to be interpreted as apart from discrimination index
Represent to send the distance between the sound source of efficient voice instruction and controlled plant distance；
Composite index acquisition module, for the speech recognition index according to acquisition and apart from discrimination index, according to default
Mathematical algorithm rule, which calculates, obtains comprehensive discrimination index corresponding to Context awareness rate, and the comprehensive discrimination index is voice knowledge
Other index and apart from discrimination index sum；
Information display module, for the comprehensive discrimination index according to acquisition, the display comprehensive discrimination index mapping carries
Show information, corresponding operating is performed according to the prompt message for user.
7. speech recognition system as claimed in claim 6, it is characterised in that the range index acquisition module is additionally operable to：
According to the distance parameter measured, distance parameter table is searched；
From the distance parameter table, the described apart from discrimination index of the distance parameter mapping is obtained.
8. speech recognition system as claimed in claims 6 or 7, it is characterised in that described information display module is additionally operable to：
According to the comprehensive discrimination index of acquisition, indicator light colors corresponding to the comprehensive discrimination index are searched；
According to the indicator light colors found, corresponding indicator lamp is lighted.
9. speech recognition system as claimed in claims 6 or 7, it is characterised in that described information display module is additionally operable to：
According to the comprehensive discrimination index of acquisition, indicator lamp pillar height degree corresponding to the comprehensive discrimination index is searched；
According to the indicator lamp pillar height degree found, the instruction lamppost of respective heights is lighted.
10. speech recognition system as claimed in claims 6 or 7, it is characterised in that described information display module is additionally operable to：
According to the comprehensive discrimination index of acquisition, tristimulus values corresponding to the comprehensive discrimination index are searched；
According to the tristimulus values found out, corresponding indicator lamp is carried out gradual change according to color corresponding to the tristimulus values and show
Show.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410301039.7A CN104078041B (en) | 2014-06-26 | 2014-06-26 | Audio recognition method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410301039.7A CN104078041B (en) | 2014-06-26 | 2014-06-26 | Audio recognition method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104078041A CN104078041A (en) | 2014-10-01 |
| CN104078041B true CN104078041B (en) | 2018-03-13 |
Family
ID=51599264
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410301039.7A Active CN104078041B (en) | 2014-06-26 | 2014-06-26 | Audio recognition method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104078041B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104078040A (en) * | 2014-06-26 | 2014-10-01 | 美的集团股份有限公司 | Voice recognition method and system |
| CN104697119B (en) * | 2015-03-24 | 2017-07-04 | 广东美的制冷设备有限公司 | A kind of air-conditioning self adaptation air supply method and controller |
| CN104848478B (en) * | 2015-04-28 | 2017-11-10 | 广东美的制冷设备有限公司 | The method of adjustment and system of phonetic order recognition threshold in air conditioner |
| CN104820556A (en) * | 2015-05-06 | 2015-08-05 | 广州视源电子科技股份有限公司 | Method and device for waking up voice assistant |
| CN105845131A (en) * | 2016-04-11 | 2016-08-10 | 乐视控股（北京）有限公司 | Far-talking voice recognition method and device |
| CN108962252A (en) * | 2017-05-17 | 2018-12-07 | 武汉默联股份有限公司 | Data processing method, device and medical terminal |
| CN108320742B (en) * | 2018-01-31 | 2021-09-14 | 广东美的制冷设备有限公司 | Voice interaction method, intelligent device and storage medium |
| CN110186171B (en) * | 2019-05-30 | 2021-09-10 | 广东美的制冷设备有限公司 | Air conditioner, method of controlling the same, and computer-readable storage medium |
| CN111508473B (en) * | 2020-06-12 | 2023-03-14 | 佛山科学技术学院 | Speech recognition rate analysis device, method and storage medium |
| CN112259128B (en) * | 2020-10-21 | 2023-07-28 | 恒玄科技(上海)股份有限公司 | Audio device and voice recognition method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102907019A (en) * | 2010-07-29 | 2013-01-30 | 英派尔科技开发有限公司 | Acoustic noise management through control of electrical device operations |
| CN103065631A (en) * | 2013-01-24 | 2013-04-24 | 华为终端有限公司 | Voice identification method and device |
| CN103677234A (en) * | 2012-09-17 | 2014-03-26 | 联想(北京)有限公司 | Information processing method and electronic equipment |
-
2014
- 2014-06-26 CN CN201410301039.7A patent/CN104078041B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102907019A (en) * | 2010-07-29 | 2013-01-30 | 英派尔科技开发有限公司 | Acoustic noise management through control of electrical device operations |
| CN103677234A (en) * | 2012-09-17 | 2014-03-26 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN103065631A (en) * | 2013-01-24 | 2013-04-24 | 华为终端有限公司 | Voice identification method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104078041A (en) | 2014-10-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104078041B (en) | Audio recognition method and system | |
| CN104078040A (en) | Voice recognition method and system | |
| CN112863547B (en) | Virtual resource transfer processing method, device, storage medium and computer equipment | |
| US20150112678A1 (en) | Sound capturing and identifying devices | |
| CN103167151A (en) | Automatic screen-locking system and method for mobile phone placed in pocket | |
| CN105118257A (en) | Intelligent control system and method | |
| CN108196469A (en) | A kind of AI control pieces, intelligent home control system and control method | |
| CN103982977A (en) | Sleep temperature control method and device | |
| CN104165438A (en) | Air conditioner controlling method and system | |
| CN103919531A (en) | Health monitoring device and children learning equipment provided with same | |
| CN108073856A (en) | The recognition methods of noise signal and device | |
| CN107195304A (en) | Voice control circuit and method for electrical equipment | |
| CN106996619A (en) | A kind of Detection of Air Quality method and terminal | |
| CN104978955A (en) | Voice control method and system | |
| CN107395873B (en) | Volume adjusting method, device, storage medium and terminal | |
| CN103982983A (en) | Method and system for adjusting running parameters of air conditioner | |
| CN107643967A (en) | A kind of automatic speech wakes up test device, system and method | |
| CN110553449A (en) | Intelligent refrigerator, system and control method of intelligent refrigerator | |
| CN107843287A (en) | Integrated sensor device and the environment event recognition methods based on it | |
| CN104049869B (en) | A kind of data processing method and device | |
| CN104202694B (en) | The orientation method and system of voice pick device | |
| CN107743083A (en) | A kind of intelligent domestic system | |
| CN111669681B (en) | Control method and device of intelligent sound equipment and storage medium | |
| CN106162475A (en) | Identification of sound source system based on mike and intelligent appliance equipment | |
| CN106648244A (en) | Method and system for preventing crushing of mobile terminal screen |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |