CN110853642A - Voice control method and device, household appliance and storage medium - Google Patents
Voice control method and device, household appliance and storage medium Download PDFInfo
- Publication number
- CN110853642A CN110853642A CN201911112968.2A CN201911112968A CN110853642A CN 110853642 A CN110853642 A CN 110853642A CN 201911112968 A CN201911112968 A CN 201911112968A CN 110853642 A CN110853642 A CN 110853642A
- Authority
- CN
- China
- Prior art keywords
- voice
- household appliance
- target
- candidate
- model
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Abstract
The application provides a voice control method, a voice control device, a household appliance and a storage medium, wherein the method comprises the following steps: the method comprises the steps of acquiring voice in the using environment of the household appliance, determining a target population using the household appliance according to the acquired voice, acquiring a personalized voice model suitable for the target population from a server, replacing a pre-stored voice model with the personalized voice model to perform voice recognition to obtain a control instruction, and controlling the household appliance to execute the control instruction. Therefore, when the target population using the household appliance is different, the personalized voice model suitable for the target population is adopted to perform voice recognition to obtain the control instruction, so that the household appliance is controlled, the user requirements of different target populations are met, and the accuracy of voice control of the household appliance is improved.
Description
Technical Field
The present application relates to the field of home appliance technologies, and in particular, to a voice control method and apparatus, a home appliance, and a storage medium.
Background
With the development of the internet of things technology, more and more users control household appliances through intelligent terminals or control the household appliances in a voice control mode. The voice database of different models of household appliances can be different for different consumer groups. For example, children pronounce more severely, pronounces less clearly, etc., making children's voice database different from adult voice database.
Therefore, when the household appliance is actually controlled through voice, different users can control the same household appliance, and the problem of low accuracy of the voice control device can exist, so that the user experience is poor.
Disclosure of Invention
The present application is directed to solving, at least to some extent, one of the technical problems in the related art.
Therefore, the voice control method provided by the application obtains the control instruction by performing voice recognition by adopting the personalized voice model suitable for the target population when the target population using the household appliance is different, so as to control the household appliance to execute the control instruction, thereby meeting the user requirements of different target populations and improving the accuracy of voice control of the household appliance.
An embodiment of a first aspect of the present application provides a voice control method, including:
collecting voice in the use environment of the household appliance;
determining a target group using the household appliance according to the collected voice;
acquiring a personalized voice model suitable for the target crowd from a server;
replacing a pre-stored voice model with the personalized voice model to perform voice recognition to obtain a control instruction;
and controlling the household appliance to execute the control instruction.
As a first possible implementation manner of the embodiment of the present application, determining a target group using the home appliance device according to the collected voice includes:
acquiring a plurality of voices acquired within a set time period;
identifying a candidate group to which each voice belongs;
and determining the target population from the candidate population to which each voice belongs.
As a second possible implementation manner of the embodiment of the present application, the determining the target population from the candidate population to which each piece of speech belongs includes:
counting the number of the voices belonging to the same candidate group in the plurality of voices;
taking the candidate crowd with the highest number ratio as the target crowd; or, the candidate population with the number ratio larger than the ratio threshold is taken as the target population.
As a third possible implementation manner of the embodiment of the present application, the determining the target population from the candidate population to which each piece of speech belongs includes:
counting the number of the voice belonging to the same candidate group;
taking the candidate crowd with the most voice number as the target crowd; or, the candidate crowd with the number of the voice larger than the threshold value is taken as the target crowd.
As a fourth possible implementation manner of the embodiment of the present application, the identifying a candidate group to which each piece of speech belongs includes:
performing feature analysis on the pronunciation of each voice to obtain a first attribute; wherein the first attribute comprises at least one of age, gender, and accent;
performing word formation analysis on each speech expression text to obtain a second attribute; the second attribute comprising at least one of a written expression, a network expression, and a language expression;
and determining a candidate crowd according to the first attribute and the second attribute.
As a fifth possible implementation manner of the embodiment of the present application, the acquiring voice in a usage environment of a home appliance includes:
and periodically acquiring voices in the using environment of the household appliance to determine target groups corresponding to all periods.
As a sixth possible implementation manner of the embodiment of the present application, before replacing the pre-stored speech model with the personalized speech model, the method further includes:
reading a pre-stored general voice model;
and recognizing the voice by adopting the universal voice model.
An embodiment of a second aspect of the present application provides a voice control apparatus, including:
the acquisition module is used for acquiring voice in the using environment of the household appliance;
the determining module is used for determining a target group using the household appliance equipment according to the collected voice;
the acquisition module is used for acquiring the personalized voice model suitable for the target crowd from the server;
the recognition module is used for replacing a pre-stored voice model with the personalized voice model so as to perform voice recognition to obtain a control instruction;
and the control module is used for controlling the household appliance to execute the control instruction.
In an embodiment of a third aspect of the present application, a home appliance is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the voice control method in the foregoing embodiments.
A fourth aspect of the present application is directed to a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program, when executed by a processor, implementing the voice control method as described in the above embodiments.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
on one hand, the voice in the using environment of the household appliance is collected, the target population using the household appliance is determined according to the collected voice, the personalized voice model suitable for the target population is obtained from the server, the pre-stored voice model is replaced by the personalized voice model, so that the voice recognition is carried out to obtain a control instruction, and the household appliance is controlled to execute the control instruction. Therefore, when the target population using the household appliance is different, the personalized voice model suitable for the target population is adopted to perform voice recognition to obtain the control instruction, so that the household appliance is controlled, the user requirements of different target populations are met, and the accuracy of voice control of the household appliance is improved.
On the other hand, a plurality of voices collected in a set time period are obtained, the candidate group to which each voice belongs is identified, and the target group is determined from the candidate group to which each voice belongs. Therefore, the target population using the household appliance is determined according to the multiple voices collected in the set time period, so that the voice models suitable for the target population are obtained from the server according to different target populations, and the requirements of different populations are met.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic flowchart of a voice control method according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a voice control method according to a second embodiment of the present application;
fig. 3 is a schematic flowchart of a voice control method according to a third embodiment of the present application;
fig. 4 is a schematic structural diagram of a voice control apparatus according to a fourth embodiment of the present application.
Detailed Description
In the related technology, in the production process of the household electrical appliance, the voice data stocks are different for different consumer groups, and production merchants can produce various types of household electrical appliances so as to meet the voice control requirements of different groups. When different users control the same household appliance, the problem of low accuracy of the voice control device can exist, and the user experience is poor.
In order to solve the problems, the voice control method includes the steps of collecting voice in a using environment of the household appliance, determining a target group using the household appliance according to the collected voice, obtaining a personalized voice model suitable for the target group from a server, replacing a pre-stored voice model with the personalized voice model to perform voice recognition to obtain a control instruction, and controlling the household appliance to execute the control instruction. Therefore, when the target population using the household appliance is different, the personalized voice model suitable for the target population is adopted to perform voice recognition to obtain the control instruction, so that the household appliance is controlled, the user requirements of different target populations are met, and the accuracy of voice control of the household appliance is improved.
In order to better understand the above technical solutions, exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the application to those skilled in the art.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
Example one
Fig. 1 is a flowchart illustrating a voice control method according to an embodiment of the present application.
As shown in fig. 1, the voice control method includes the steps of:
step 101, collecting voice in the using environment of the household appliance.
The household appliances are intelligent household appliances, and are not limited to air conditioners, refrigerators, washing machines and the like.
In the embodiment of the application, the household appliance can acquire the voice in the use environment of the household appliance through the voiceprint recognition sensor arranged on the household appliance. As a possible implementation manner, voices in the use environment of the household appliance device can be periodically collected through the voiceprint recognition sensor, so that the corresponding target population in each period can be determined.
The voice in the using environment of the household appliance can be collected in a period of one day, one week, one month and the like.
For example, the home device may collect voice of the home device in the use environment within one week through the voiceprint sensor.
In the embodiment of the application, the voice in the service environment of the household appliance is not limited to be collected by using the voiceprint sensor, the voice in the service environment of the household appliance can also be collected by using the voice collection module of the household appliance, and the mode of collecting the voice in the service environment of the household appliance is not limited here.
And step 102, determining a target group using the household appliance according to the collected voice.
In the embodiment of the application, the collected voice in the use environment of the household appliance is not limited to one voice, and can be for children, teenagers, middle-aged people, old people and the like.
In the embodiment of the application, after a plurality of voices in the using environment of the household appliance are collected, the voices are subjected to statistical analysis to determine the target population using the household appliance. Specifically, each piece of voice may be recognized to determine the crowd to which each piece of voice belongs, and further, a target crowd using the home appliance device may be determined according to the crowd to which each piece of voice belongs.
As a possible implementation manner, after a plurality of voices in the use environment of the household appliance are collected, a group of people with the largest population to which the collected voices belong can be determined as a target group.
For example, if 20 voices are collected in one week, each voice is recognized, and it is determined that 15 voices belong to the old, 2 voices belong to the children, and 3 voices belong to the middle-aged women. In this case, it can be determined that the target group using the home appliance is the elderly.
And 103, acquiring the personalized voice model suitable for the target crowd from the server.
The personalized voice model is a voice model which is trained by adopting voice samples of corresponding crowds and is suitable for different crowds, such as a voice model for children, a voice model for old people and the like. And the server stores personalized voice models suitable for different target crowds.
In the embodiment of the application, after the target population using the household appliance is determined according to the collected voice, the household appliance can obtain the personalized voice model used by the target population from the server so as to meet personalized requirements of different target populations.
For example, if the target group is a child, since the pronunciation of the child is different from that of an adult, the home appliance device can acquire the personalized voice model suitable for the child from the server and can be the voice model of the child, so that the child can accurately control the home appliance device in a voice control manner.
And step 104, replacing the pre-stored voice model with a personalized voice model to perform voice recognition to obtain a control instruction.
It should be noted that, when the home appliance is not networked, after the user inputs the voice control instruction to the home appliance in a voice control manner, the home appliance reads the general voice model prestored in the memory, and recognizes the control recognition input by the user by using the general voice model to obtain the control instruction. When the manufacturer of the household electrical appliance adopts the universal voice model to produce the household electrical appliance, the types of the produced household electrical appliance can be reduced, so that the manufacturer can manage the household electrical appliance conveniently.
In the embodiment of the application, after the household appliance obtains the personalized voice model suitable for the target population from the server, the voice model prestored in the memory of the household appliance is replaced by the personalized voice model, so that the personalized voice model is adopted to perform voice recognition on the control instruction input by the user through voice, and the control instruction is obtained.
As an example, the voice model pre-stored by the user is a child voice model, but after the target group of the home appliance device is determined as young males, a personalized voice model suitable for young males may be obtained from the server, and the child voice model stored in the memory may be replaced with the personalized voice model suitable for young males, so as to obtain the control instruction by performing voice recognition on the voice input by the user using the personalized voice model.
And 105, controlling the household appliance to execute the control command.
In the embodiment of the application, the household appliance identifies the voice command input by the target group using the household appliance according to the personalized voice model suitable for the target group, so that after the control command for controlling the household appliance is obtained, the household appliance executes the control command to realize the control of the household appliance.
Taking a household appliance as an air conditioner as an example, after a user of the air conditioner is determined to be a child, a personalized voice model suitable for the child is obtained from a server, and then the voice model prestored in a memory of the air conditioner is replaced by the child voice model. After the children input the 'air conditioner temperature reduction' voice, the children voice model identifies the voice input by the children to obtain a control instruction for reducing the air conditioner temperature, and then controls the air conditioner to execute the control instruction for reducing the temperature so as to realize the voice control of the air conditioner.
The technical scheme in the embodiment of the application at least has the following technical effects or advantages:
in the embodiment of the application, voice in the using environment of the household appliance is collected, a target group using the household appliance is determined according to the collected voice, an individual voice model suitable for the target group is obtained from a server, the pre-stored voice model is replaced by the individual voice model, so that voice recognition is carried out to obtain a control instruction, and the household appliance is controlled to execute the control instruction. According to the method, when the target population using the household appliance is different, the personalized voice model suitable for the target population is adopted for voice recognition to obtain the control instruction, so that the household appliance is controlled, the user requirements of different target populations are met, and the accuracy of voice control of the household appliance is improved.
As a possible implementation manner, when the target group using the home appliance device is determined in step 102, multiple voices collected within a set time period may be acquired, and the candidate group to which each voice belongs may be identified, so as to determine the target group from the candidate group to which each voice belongs. The specific implementation process is shown in the second embodiment.
Example two
Fig. 2 is a flowchart illustrating a voice control method according to a second embodiment of the present application.
As shown in fig. 2, the voice control method may further include the steps of:
In the embodiment of the present application, the set time period may be a day, a week, a month, and the like, which is not limited herein.
In the embodiment of the application, in order to determine the target population using the household appliance, a plurality of voices in the use environment of the household appliance collected in a set time period can be acquired. For example, multiple voices collected by the home appliance within one month may be obtained.
In step 202, candidate groups to which each voice belongs are identified.
The candidate population is not limited to children, adolescents, adults, the elderly, nor men and women.
In the embodiment of the application, after the plurality of voices collected in the set time period are acquired, each voice can be identified so as to determine the candidate group to which each voice belongs.
As a possible implementation manner, the pronunciation characteristics of each voice may be recognized to determine the candidate group to which each voice belongs.
It should be noted that, the pronunciation of people in different age groups is different, for example, the elderly have slow pronunciation and slow speech speed, and the teenagers have fast pronunciation and fast speech speed.
In the embodiment of the application, a plurality of voices collected in a set time period are acquired, each voice is recognized, and after candidate groups to which each voice belongs are determined, target groups used by household appliances can be determined from the candidate groups.
As a first possible implementation manner, after a candidate group to which each piece of speech belongs is identified, the number ratio of the pieces of speech belonging to the same candidate group in a plurality of pieces of speech is counted, and the candidate group with the highest number ratio is taken as a target group. For example, assume that 10 voices collected in a set time period are acquired, 8 voices of middle-aged women are acquired, and the ratio of the number of voices of middle-aged women is 8/10; the number of the children's voices is 1, and the ratio of the children's voices to the number of the children's voices is 1/10; the voice of the old people is 1, and the voice number of the old people is 1/10. Since the voice number of the middle-aged women accounts for the largest ratio, the target group used by the household appliance can be determined to be the middle-aged women.
As a second possible implementation manner, after the candidate group to which each piece of speech belongs is identified, the number ratio of the pieces of speech belonging to the same candidate group in the plurality of pieces of speech is counted, and the candidate group with the number ratio larger than the ratio threshold value can be used as the target group. For example, assume that 10 voices collected in a set time period are acquired, 8 voices of middle-aged women are acquired, and the ratio of the number of voices of middle-aged women is 8/10; the number of the children's voices is 1, and the ratio of the children's voices to the number of the children's voices is 1/10; the voice of the old people is 1, and the voice number of the old people is 1/10. Assuming that the set ratio threshold is 1/2, since the ratio of the number of voices of the middle-aged women is greater than the ratio threshold, it can be determined that the target group used by the home appliance is the middle-aged women.
As a third possible implementation manner, after the candidate group to which each piece of speech belongs is identified, and the number of pieces of speech belonging to the same candidate group is counted, the candidate group with the largest number of pieces of speech can be used as the target group. For example, assume that 10 voices collected in a set time period are acquired, and after each voice is recognized, it is determined that 8 voices of middle-aged women, 1 voice of children, and 1 voice of the elderly are recognized. The number of voices of the middle-aged women is the largest, so that the middle-aged women can be used as target groups for household appliances.
As a fourth possible implementation manner, after the candidate group to which each piece of speech belongs is identified, the number of pieces of speech belonging to the same candidate group is counted, and the candidate group with the number of pieces of speech greater than the threshold number is taken as the target group. For example, assume that 10 voices collected in a set time period are acquired, a threshold of the number of the voices is set to be 6, the 10 voices are recognized, and it is determined that 8 voices of middle-aged women, 1 voice of children and 1 voice of the elderly are recognized. In this case, the candidate population having the number of voices larger than the number threshold is determined to be middle-aged women, and the middle-aged women can be used as the target population for the home appliance.
The technical scheme in the embodiment of the application at least has the following technical effects or advantages:
in the embodiment of the application, a plurality of voices collected in a set time period are obtained, the candidate group to which each voice belongs is identified, and the target group is determined from the candidate group to which each voice belongs. Therefore, the target population using the household appliance is determined according to the multiple voices collected in the set time period, so that the voice models suitable for the target population are obtained from the server according to different target populations, and the requirements of different populations are met.
In the foregoing embodiment, in step 202, when the candidate group to which each speech belongs is identified, the pronunciation of each speech may be analyzed to obtain a first attribute, and the text expressed by each speech is subjected to word formation analysis to obtain a second attribute, and further, the candidate group is determined according to the first attribute and the second attribute. The specific implementation process is shown in the third embodiment.
EXAMPLE III
Fig. 3 is a flowchart illustrating a voice control method according to a third embodiment of the present application.
As shown in fig. 3, the voice control method may further include the steps of:
Wherein the first attribute includes at least one of age, gender, and accent.
In the embodiment of the application, a user performs voice control on the household appliance in a set time period, and after the household appliance acquires a plurality of voices input by the user in the set time period, the household appliance performs feature analysis on the pronunciation of each voice so as to determine at least one of the age, the gender and the accent of a speaker of the voice.
It should be noted that, different age groups of people have different pronunciations, different pronunciations for men and women, and different accents for different people, so that at least one of the age, gender, and accent of the pronunciations of the voices can be determined by performing feature analysis on the pronunciation of each voice.
Wherein the second attribute comprises at least one of a written expression, a network expression, and a language expression.
In the embodiment of the application, a user performs voice control on household electrical appliances within a set time period, and after the household electrical appliances acquire a plurality of voices input by the user within the set time period, the household electrical appliances perform word formation analysis on each voice-expressed text to determine that the voice expression mode belongs to at least one of written expression, network expression and language expression.
In the embodiment of the application, after the first attribute and the second attribute of each voice are determined, the candidate group to which the voice belongs can be determined according to the first attribute and the second attribute.
For example, after the pronunciation of a piece of collected voice is subjected to feature analysis and determined to be an old woman, further, word formation analysis is performed on the text expressed by the piece of voice and determined to be a language expression, and then the candidate group can be determined to be the old woman.
The technical scheme in the embodiment of the application at least has the following technical effects or advantages:
in the embodiment of the application, a first attribute is obtained by performing feature analysis on the pronunciation of each voice; wherein the first attribute comprises at least one of age, gender, and accent; performing word formation analysis on each speech expression text to obtain a second attribute; a second attribute comprising at least one of a written expression, a network expression, and a verbal expression; and determining a candidate crowd according to the first attribute and the second attribute. Therefore, the candidate crowd can be determined more accurately by analyzing the pronunciation and the expression text of each piece of voice.
Based on the same inventive concept, the embodiment of the present application further provides a device corresponding to the voice control method, see embodiment four.
Example four
Fig. 4 is a schematic structural diagram of a voice control apparatus according to a fourth embodiment of the present application.
As shown in fig. 4, the voice control apparatus 400 may include: an acquisition module 410, a determination module 420, an acquisition module 430, an identification module 440, and a control module 450.
The collection module 410 is configured to collect voice in an environment where the home appliance is used.
And the determining module 420 is configured to determine a target group using the home appliance device according to the collected voice.
The obtaining module 430 is configured to obtain, from the server, a personalized speech model suitable for the target group.
And the recognition module 440 is configured to replace the pre-stored voice model with a personalized voice model to perform voice recognition to obtain a control instruction.
And a control module 450, configured to control the home appliance to execute the control instruction.
As a possible implementation manner, the determining module 420 may further include:
the acquisition unit is used for acquiring a plurality of voices collected in a set time period.
And the recognition unit is used for recognizing the candidate group to which each piece of voice belongs.
And the determining unit is used for determining a target crowd from the candidate crowd to which each voice belongs.
As another possible implementation manner, the determining unit may be further configured to:
counting the number of the voices belonging to the same candidate group in the plurality of voices;
taking the candidate crowd with the highest number ratio as the target crowd; or, the candidate population with the number ratio larger than the ratio threshold is taken as the target population.
As another possible implementation manner, the determining unit may be further configured to:
counting the number of the voice belonging to the same candidate group;
taking the candidate crowd with the most voice number as the target crowd; or, the candidate crowd with the number of the voice larger than the threshold value is taken as the target crowd.
As another possible implementation manner, the identification unit may be further configured to:
performing feature analysis on the pronunciation of each voice to obtain a first attribute; wherein the first attribute comprises at least one of age, gender, and accent;
performing word formation analysis on each speech expression text to obtain a second attribute; the second attribute comprising at least one of a written expression, a network expression, and a language expression;
and determining a candidate crowd according to the first attribute and the second attribute.
As another possible implementation, the acquisition module 410 may be further configured to:
and periodically acquiring voices in the using environment of the household appliance to determine target groups corresponding to all periods.
As another possible implementation manner, the voice control apparatus 400 may further include:
and the reading module is used for reading the pre-stored general voice model and recognizing the voice by adopting the general voice model.
It should be noted that the foregoing explanation of the embodiment of the voice control method is also applicable to the voice control apparatus of this embodiment, and is not repeated here.
The technical scheme in the embodiment of the application at least has the following technical effects or advantages:
the voice control device of the embodiment of the application determines a target group using the household appliance by collecting voice in the service environment of the household appliance and according to the collected voice, acquires an individual voice model suitable for the target group from the server, replaces the pre-stored voice model with the individual voice model, performs voice recognition to obtain a control instruction, and controls the household appliance to execute the control instruction. According to the method, when the target population using the household appliance is different, the personalized voice model suitable for the target population is adopted for voice recognition to obtain the control instruction, so that the household appliance is controlled, the user requirements of different target populations are met, and the accuracy of voice control of the household appliance is improved.
Based on the same inventive concept, the embodiment of the application also provides the household appliance corresponding to the voice control execution method, which is shown in the fifth embodiment.
EXAMPLE five
The embodiment of the application provides a household appliance, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the program, the voice control method in the embodiment is realized.
The technical scheme in the embodiment of the application at least has the following technical effects or advantages:
in the embodiment of the application, the voice in the using environment of the household appliance is collected, the target population using the household appliance is determined according to the collected voice, the personalized voice model suitable for the target population is obtained from the server, the pre-stored voice model is replaced by the personalized voice model, the voice recognition is carried out, the control instruction is obtained, and the household appliance is controlled to execute the control instruction. According to the method, when the target population using the household appliance is different, the personalized voice model suitable for the target population is adopted for voice recognition to obtain the control instruction, so that the household appliance is controlled, the user requirements of different target populations are met, and the accuracy of voice control of the household appliance is improved.
Based on the same inventive concept, the embodiment of the present application further provides a non-transitory computer-readable storage medium corresponding to the method for executing voice control, see embodiment six.
EXAMPLE six
The present application also proposes a non-transitory computer-readable storage medium on which a computer program is stored, which when executed by a processor implements the speech control method as described in the above embodiments.
The technical scheme in the embodiment of the application at least has the following technical effects or advantages:
in the embodiment of the application, the voice in the using environment of the household appliance is collected, the target population using the household appliance is determined according to the collected voice, the personalized voice model suitable for the target population is obtained from the server, the pre-stored voice model is replaced by the personalized voice model, the voice recognition is carried out, the control instruction is obtained, and the household appliance is controlled to execute the control instruction. According to the method, when the target population using the household appliance is different, the personalized voice model suitable for the target population is adopted for voice recognition to obtain the control instruction, so that the household appliance is controlled, the user requirements of different target populations are met, and the accuracy of voice control of the household appliance is improved.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. A method for voice control, the method comprising:
collecting voice in the use environment of the household appliance;
determining a target group using the household appliance according to the collected voice;
acquiring a personalized voice model suitable for the target crowd from a server;
replacing a pre-stored voice model with the personalized voice model to perform voice recognition to obtain a control instruction;
and controlling the household appliance to execute the control instruction.
2. The voice control method according to claim 1, wherein the determining a target group using the home device according to the collected voice comprises:
acquiring a plurality of voices acquired within a set time period;
identifying a candidate group to which each voice belongs;
and determining the target population from the candidate population to which each voice belongs.
3. The method according to claim 2, wherein the determining the target group from the candidate group to which each voice belongs comprises:
counting the number of the voices belonging to the same candidate group in the plurality of voices;
taking the candidate crowd with the highest number ratio as the target crowd; or, the candidate population with the number ratio larger than the ratio threshold is taken as the target population.
4. The method according to claim 2, wherein the determining the target group from the candidate group to which each voice belongs comprises:
counting the number of the voice belonging to the same candidate group;
taking the candidate crowd with the most voice number as the target crowd; or, the candidate crowd with the number of the voice larger than the threshold value is taken as the target crowd.
5. The method of claim 2, wherein the identifying the candidate group to which each voice belongs comprises:
performing feature analysis on the pronunciation of each voice to obtain a first attribute; wherein the first attribute comprises at least one of age, gender, and accent;
performing word formation analysis on each speech expression text to obtain a second attribute; the second attribute comprising at least one of a written expression, a network expression, and a language expression;
and determining a candidate crowd according to the first attribute and the second attribute.
6. The voice control method according to any one of claims 1 to 5, wherein the collecting voice in the usage environment of the home appliance comprises:
and periodically acquiring voices in the using environment of the household appliance to determine target groups corresponding to all periods.
7. The speech control method according to any one of claims 1-5, wherein before replacing the pre-stored speech model with the personalized speech model, further comprising:
reading a pre-stored general voice model;
and recognizing the voice by adopting the universal voice model.
8. A voice control apparatus, characterized in that the apparatus comprises:
the acquisition module is used for acquiring voice in the using environment of the household appliance;
the determining module is used for determining a target group using the household appliance equipment according to the collected voice;
the acquisition module is used for acquiring the personalized voice model suitable for the target crowd from the server;
the recognition module is used for replacing a pre-stored voice model with the personalized voice model so as to perform voice recognition to obtain a control instruction;
and the control module is used for controlling the household appliance to execute the control instruction.
9. An appliance comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the voice control method of any one of claims 1 to 7 when executing the program.
10. A non-transitory computer-readable storage medium on which a computer program is stored, the program, when executed by a processor, implementing the speech control method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911112968.2A CN110853642B (en) | 2019-11-14 | 2019-11-14 | Voice control method and device, household appliance and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911112968.2A CN110853642B (en) | 2019-11-14 | 2019-11-14 | Voice control method and device, household appliance and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110853642A true CN110853642A (en) | 2020-02-28 |
| CN110853642B CN110853642B (en) | 2022-03-25 |
Family
ID=69600476
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911112968.2A Active CN110853642B (en) | 2019-11-14 | 2019-11-14 | Voice control method and device, household appliance and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110853642B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111915940A (en) * | 2020-06-29 | 2020-11-10 | 厦门快商通科技股份有限公司 | Method, system, terminal and storage medium for evaluating and teaching spoken language pronunciation |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011111221A1 (en) * | 2010-03-12 | 2011-09-15 | 三菱電機株式会社 | Voice call registration device for elevator |
| CN102314440A (en) * | 2010-06-30 | 2012-01-11 | 百度在线网络技术（北京）有限公司 | Method for maintaining language model base by using network and system |
| CN105895105A (en) * | 2016-06-06 | 2016-08-24 | 北京云知声信息技术有限公司 | Speech processing method and device |
| KR20180070970A (en) * | 2016-12-19 | 2018-06-27 | 삼성전자주식회사 | Method and Apparatus for Voice Recognition |
| US20190019499A1 (en) * | 2017-04-26 | 2019-01-17 | International Business Machines Corporation | Adaptive digital assistant and spoken genome |
-
2019
- 2019-11-14 CN CN201911112968.2A patent/CN110853642B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011111221A1 (en) * | 2010-03-12 | 2011-09-15 | 三菱電機株式会社 | Voice call registration device for elevator |
| CN102314440A (en) * | 2010-06-30 | 2012-01-11 | 百度在线网络技术（北京）有限公司 | Method for maintaining language model base by using network and system |
| CN105895105A (en) * | 2016-06-06 | 2016-08-24 | 北京云知声信息技术有限公司 | Speech processing method and device |
| KR20180070970A (en) * | 2016-12-19 | 2018-06-27 | 삼성전자주식회사 | Method and Apparatus for Voice Recognition |
| US20190019499A1 (en) * | 2017-04-26 | 2019-01-17 | International Business Machines Corporation | Adaptive digital assistant and spoken genome |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111915940A (en) * | 2020-06-29 | 2020-11-10 | 厦门快商通科技股份有限公司 | Method, system, terminal and storage medium for evaluating and teaching spoken language pronunciation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110853642B (en) | 2022-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108320733B (en) | Voice data processing method and device, storage medium and electronic equipment | |
| US10013977B2 (en) | Smart home control method based on emotion recognition and the system thereof | |
| TWI245259B (en) | Sensor based speech recognizer selection, adaptation and combination | |
| CN108197115A (en) | Intelligent interactive method, device, computer equipment and computer readable storage medium | |
| KR100826875B1 (en) | On-line speaker recognition method and apparatus for thereof | |
| CN110085221A (en) | Speech emotional exchange method, computer equipment and computer readable storage medium | |
| CN108874895B (en) | Interactive information pushing method and device, computer equipment and storage medium | |
| JPWO2017187712A1 (en) | Information processing device | |
| CN110277089B (en) | Updating method of offline voice recognition model, household appliance and server | |
| CN109036471B (en) | Voice endpoint detection method and device | |
| CN110085220A (en) | Intelligent interaction device | |
| CN108899033B (en) | Method and device for determining speaker characteristics | |
| CN110085211A (en) | Speech recognition exchange method, device, computer equipment and storage medium | |
| CN108549628A (en) | The punctuate device and method of streaming natural language information | |
| JP7389421B2 (en) | Device for estimating mental and nervous system diseases | |
| JP2020064253A (en) | Learning device, detection device, learning method, learning program, detection method, and detection program | |
| CN111413877A (en) | Method and device for controlling household appliance | |
| CN109166571A (en) | Wake-up word training method, device and the household appliance of household appliance | |
| CN111179935A (en) | Voice quality inspection method and device | |
| CN110853642B (en) | Voice control method and device, household appliance and storage medium | |
| CN108491519A (en) | Man-machine interaction method and device, storage medium, terminal | |
| CN110570838B (en) | Voice stream processing method and device | |
| CN115331670B (en) | Off-line voice remote controller for household appliances | |
| CN108777804B (en) | Media playing method and device | |
| CN113297412A (en) | Music recommendation method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |