CN111105791A - Voice control method, device and system - Google Patents

Voice control method, device and system Download PDF

Info

Publication number
CN111105791A
CN111105791A CN201811258280.0A CN201811258280A CN111105791A CN 111105791 A CN111105791 A CN 111105791A CN 201811258280 A CN201811258280 A CN 201811258280A CN 111105791 A CN111105791 A CN 111105791A
Authority
CN
China
Prior art keywords
age information
voice
sound data
illumination
age
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201811258280.0A
Other languages
Chinese (zh)
Inventor
琚炜
陈展
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Hikvision Digital Technology Co Ltd
Original Assignee
Hangzhou Hikvision Digital Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hangzhou Hikvision Digital Technology Co Ltd filed Critical Hangzhou Hikvision Digital Technology Co Ltd
Priority to CN201811258280.0A priority Critical patent/CN111105791A/en
Publication of CN111105791A publication Critical patent/CN111105791A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/06—Decision making techniques; Pattern matching strategies
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/06—Decision making techniques; Pattern matching strategies
    • G10L17/14—Use of phonemic categorisation or speech recognition prior to speaker recognition or verification
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
    • G10L25/24—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being the cepstrum
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223—Execution procedure of a spoken command

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Computational Linguistics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Game Theory and Decision Science (AREA)
  • Business, Economics & Management (AREA)
  • Signal Processing (AREA)
  • Circuit Arrangement For Electric Light Sources In General (AREA)

Abstract

The embodiment of the invention provides a voice control method, a voice control device and a voice control system, wherein the method comprises the following steps: acquiring sound data to be processed; judging whether the sound data comprises awakening words or not; if yes, identifying age information corresponding to the voice data; and controlling the voice control equipment according to the age information. Therefore, in the scheme, on the first hand, different age information corresponds to different control modes, or users are distinguished according to ages, and different requirements of users at different ages are taken care of; for example, for the old, the lighting duration of the lighting device is relatively long, so that the situation that the lighting device is automatically turned off in the moving process of the old user is reduced, and the risk of the user is reduced. In the second aspect, only when the sound data includes the wakeup word, the subsequent steps are executed, that is, the sound in the environment cannot activate the sound control device, so that the waste of resources is reduced.

Description

Voice control method, device and system
Technical Field
The present invention relates to the field of voice recognition technologies, and in particular, to a voice control method, device, and system.
Background
Voice control means controlling a device by sound. For example, in various fields such as lighting systems, access control systems, smart home devices, etc., the devices can be controlled by sound. Taking the lighting system as an example, when the sound intensity in the scene reaches a set threshold, the lighting device may be activated to perform lighting, and after lighting for a period of time, the lighting device is automatically turned off.
However, in this scheme, the users are not distinguished, and different requirements of different users are not taken care of. For example, for the old, the action is inconvenient, the time required for going upstairs and downstairs is long, and if the old goes upstairs and downstairs, the lighting equipment is automatically turned off, so that great risk is brought to the safety of the old.
Disclosure of Invention
The embodiment of the invention aims to provide a voice control method, a voice control device and a voice control system so as to distinguish users.
To achieve the above object, an embodiment of the present invention provides a voice control method, including:
acquiring sound data to be processed;
judging whether the sound data comprises awakening words or not;
if yes, identifying age information corresponding to the sound data;
and controlling the voice control equipment according to the age information.
Optionally, the identifying age information corresponding to the sound data includes:
preprocessing the sound data to obtain processed sound data;
carrying out feature extraction on the processed sound data to obtain sound features;
and inputting the sound characteristics into an age identification model obtained by pre-training to obtain age information output by the age identification model.
Optionally, the voice control device is a lighting device; according to the age information, controlling the voice control equipment comprises the following steps:
determining the illumination brightness and/or illumination duration corresponding to the identified age information;
and controlling the lighting equipment to illuminate according to the illumination brightness and/or the illumination time length.
Optionally, the voice control device is a lighting device; according to the age information, controlling the voice control equipment comprises the following steps:
and if the identified age information is old, increasing the illumination brightness and/or the illumination time of the illumination equipment.
Optionally, the voice control device is an access control device; according to the age information, controlling the voice control equipment comprises the following steps:
judging whether to open the door and/or the door opening duration according to the age information;
and controlling the access control equipment according to the judgment result.
Optionally, the voice control device is a household device; according to the age information, controlling the voice control equipment comprises the following steps:
judging whether the person corresponding to the sound data is an authorized person or not according to the age information;
if yes, controlling the household equipment according to the voice command sent by the authorized person.
Optionally, after the identifying age information corresponding to the sound data, the method further includes:
if the identified age information is old, playing a first prompt voice;
and/or playing a second prompt voice if the identified age information is children.
In order to achieve the above object, an embodiment of the present invention further provides a voice control apparatus, including:
the acquisition module is used for acquiring sound data to be processed;
the judging module is used for judging whether the sound data comprises awakening words or not; if yes, triggering the identification module;
the identification module is used for identifying age information corresponding to the sound data;
and the control module is used for controlling the voice control equipment according to the age information.
Optionally, the identification module is specifically configured to:
preprocessing the sound data to obtain processed sound data;
carrying out feature extraction on the processed sound data to obtain sound features;
and inputting the sound characteristics into an age identification model obtained by pre-training to obtain age information output by the age identification model.
Optionally, the voice control device is a lighting device; the control module is specifically configured to:
determining the illumination brightness and/or illumination duration corresponding to the identified age information;
and controlling the lighting equipment to illuminate according to the illumination brightness and/or the illumination time length.
Optionally, the voice control device is a lighting device; the control module is specifically configured to: and if the identified age information is old, increasing the illumination brightness and/or the illumination time of the illumination equipment.
Optionally, the voice control device is an access control device; the control module is specifically configured to:
judging whether to open the door and/or the door opening duration according to the age information;
and controlling the access control equipment according to the judgment result.
Optionally, the voice control device is a household device; the control module is specifically configured to:
judging whether the person corresponding to the sound data is an authorized person or not according to the age information;
if yes, controlling the household equipment according to the voice command sent by the authorized person.
Optionally, the apparatus further comprises:
the voice prompt module is used for playing a first prompt voice under the condition that the identified age information is old;
and/or playing a second prompt voice under the condition that the identified age information is the child.
In order to achieve the above object, an embodiment of the present invention further provides an electronic device, including a processor and a memory;
a memory for storing a computer program;
and the processor is used for realizing any one of the voice control methods when executing the program stored in the memory.
In order to achieve the above object, an embodiment of the present invention further provides a voice control system, including: a control device and a controlled device, wherein,
the control equipment is used for acquiring sound data to be processed; judging whether the sound data comprises awakening words or not; if yes, identifying age information corresponding to the sound data; generating a control instruction corresponding to the age information, and sending the control instruction to the controlled equipment;
and the controlled equipment is used for executing response operation corresponding to the control instruction.
Optionally, the controlled device includes an illumination device, and the control instruction includes illumination brightness and/or illumination duration.
Optionally, the controlled device includes an access control device, and the control instruction includes information on whether to open the door and/or a door opening duration.
In the embodiment of the present invention, in a first aspect, different age information corresponds to different control modes, or users are distinguished according to ages, and different requirements of users of different ages are taken care of; for example, for the old, the lighting duration of the lighting device is relatively long, so that the situation that the lighting device is automatically turned off in the moving process of the old user is reduced, and the risk of the user is reduced. In the second aspect, only when the sound data includes the wakeup word, the subsequent steps are executed, that is, the sound in the environment cannot activate the sound control device, so that the waste of resources is reduced.
Of course, not all of the advantages described above need to be achieved at the same time in the practice of any one product or method of the invention.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a voice control method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a voice control apparatus according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a first structure of a voice control system according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a second structure of a voice control system according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a third example of a voice control system according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to solve the above technical problems, embodiments of the present invention provide a method, an apparatus, and a system for voice control, where the method and the apparatus can be applied to various voice control devices, such as lighting devices, access control devices, and home devices, and are not limited specifically. Alternatively, the method and apparatus may also be applied to a control device connected to a voice control device, and are not limited specifically. For convenience of description, the execution main body is referred to as an electronic apparatus in the following embodiments. First, a voice control method provided by an embodiment of the present invention is described in detail below.
Fig. 1 is a schematic flow chart of a voice control method according to an embodiment of the present invention, including:
s101: and acquiring sound data to be processed.
The electronic device (execution main body) may be connected to a sound collection device, the sound collection device sends collected sound data to the electronic device in real time, and the electronic device takes the received sound data as sound data to be processed. Alternatively, the electronic device may have a built-in sound collection unit, and the sound data collected by the sound collection unit is used as the sound data to be processed.
S102: and judging whether the sound data comprises a wakeup word or not, and if so, executing S103.
The wake-up word may be preset, for example, if the sound control device is a lighting device, the wake-up word may be set to "turn on a light", and if the sound control device is a door control device, the wake-up word may be set to "turn on a door", and so on, which are not listed one by one. For another example, if the voice-controlled device is a television, the wake-up word may be set to "power on," etc. The voice data may be collected by a microphone or other voice collection device.
For example, a wakeup word model may be obtained by training for a set wakeup word, the sound data obtained in S101 is matched with the wakeup word model, and if the matching is successful, it indicates that the sound data obtained in S101 includes a wakeup word, and in this case, the subsequent steps are continuously performed. If the sound data does not include the wake-up word, the subsequent steps are not performed.
In one case, the wake word model may be stored in the electronic device (execution subject), which may improve the determination efficiency. Alternatively, the wake-up model may be stored in other devices connected to the electronic device, so as to save the storage space of the electronic device.
In some sound control schemes, the user cannot be distinguished from other sounds in the environment, and the sound in the environment can also activate the sound control device, which causes resource waste. In the scheme, only when the sound data comprises the awakening word, the subsequent steps are executed, namely, the sound in the environment can not activate the sound control equipment, so that the resource waste is reduced.
S103: age information corresponding to the sound data is identified.
The age information may be a specific age value, or may be an age group, or may be words such as "old age", "child", "adult" or the like indicating an age group.
For example, an age recognition model may be obtained by training in advance, and age information corresponding to the voice data may be recognized using the age recognition model. For example, the training process may include: acquiring a plurality of sample sound data and real age information corresponding to each sample sound data; inputting the acquired sample voice data into a neural network with a preset structure, training the neural network by taking the acquired real age information as supervision, namely, iteratively adjusting parameters in the neural network until an iteration stop condition is met, namely, finishing the training of the neural network, wherein the trained neural network is an age identification model.
As an embodiment, S103 may include: preprocessing the sound data to obtain processed sound data; carrying out feature extraction on the processed sound data to obtain sound features; and inputting the sound characteristics into an age identification model obtained by pre-training to obtain age information output by the age identification model.
For example, the pre-processing may include any one or more of: filtering, windowing, end point detection, pre-emphasis, etc. The processed sound data is then subjected to feature extraction, for example, the features may be features using a spectrum base, such as MFCC (Mel-frequency cepstral coefficients), PLP (Perceptual Linear prediction coefficient), LPCC (Linear prediction cepstrum coefficient), and the like, without limitation.
In this embodiment, correspondingly, in the process of training the age recognition model, after the sample sound data is acquired, the sample sound data may be preprocessed, the preprocessed sample sound data may be subjected to feature extraction, and the extracted features may be input to a neural network with a preset structure, so as to train the neural network.
In one case, the age recognition model may be stored in an electronic device (execution subject), which may improve recognition efficiency. Alternatively, the age identification model may be stored in another device connected to the electronic device, so as to save the storage space of the electronic device.
S104: and controlling the voice control equipment according to the identified age information.
In the embodiment of the invention, different age information corresponds to different control modes, or users are distinguished according to ages, and different requirements of users of different ages are taken care of.
As an embodiment, the sound control device is a lighting device; s104 comprises the following steps:
determining the illumination brightness and/or illumination duration corresponding to the identified age information;
and controlling the lighting equipment to illuminate according to the illumination brightness and/or the illumination time length.
In the present embodiment, the illumination brightness and/or illumination time length corresponding to each age information may be set in advance. For example, the setting contents may be as shown in table 1:
TABLE 1
Age information Brightness of illumination Duration of illumination
Age 10 and below 500Lx (lux) 3 minutes
11-60 years old 300Lx 1 minute
Age 61 and older 600Lx 5 minutes
Table 1 is merely an example, and does not limit the specific contents set.
Assuming that the age information identified in S103 is 11-60 years old, the lighting device is controlled to illuminate for 1 minute with an illumination brightness of 300 Lx.
For children 10 years old and younger, and old people 61 years old and older, their action speed is slower, especially for old people, the eyesight condition may not be too good, therefore, if the identified age information belongs to these two conditions, the illumination brightness is relatively higher, the illumination duration is relatively longer, the situation that the lighting apparatus is automatically turned off during the user moving process is reduced, and the risk of the user is reduced. For people in the age range of 11-60 years old, the action speed is high, if the identified age information is 11-60 years old, the illumination brightness is relatively low, the illumination time is relatively short, and resources are saved.
Therefore, by applying the embodiment, on one hand, the user risk is reduced, and on the other hand, the resources are saved.
As an embodiment, the sound control device is a lighting device; s104 comprises the following steps: and if the identified age information is old, increasing the illumination brightness and/or the illumination time of the illumination equipment.
In this embodiment, a basic illumination brightness and/or illumination duration may be set, and if the identified age information is an adult or a teenager, the lighting device is controlled to illuminate according to the basic illumination brightness and/or illumination duration; and if the identified age information is old people or children, increasing the illumination brightness and/or the illumination time length above the basic illumination brightness and/or illumination time length.
For example, the set base illumination intensity may be 300Lx, the base illumination duration may be 1 minute, and above that, the increased illumination intensity may be 300Lx, and the increased illumination duration may be 1 minute. The specific numerical value may be set according to actual conditions, and is not limited herein.
Generally speaking, the action speed of old man is slower, and the eyesight condition probably is not too good yet, therefore, if the age information of discerning is old man, then illumination brightness is some relatively high, and length of time is some relatively long for the illumination, has reduced old user in the removal in-process, and the condition that lighting apparatus goes out automatically has reduced old user's risk. For adults, the action speed is high, if the identified age information is adults, the illumination brightness is relatively low, the illumination duration is relatively short, and resources are saved. Therefore, by applying the embodiment, on one hand, the user risk is reduced, and on the other hand, the resources are saved.
As an implementation mode, the voice control device is an access control device; s104 comprises the following steps: judging whether to open the door and/or the door opening duration according to the age information; and controlling the access control equipment according to the judgment result.
In this embodiment, the voice control device is an access control device. For example, the present embodiment can be applied to places such as a children's park, where children are allowed to enter, and places such as an elderly activity center, where elderly people are allowed to enter, and whether to open a door is determined according to the identified age information.
Taking a children' S park as an example, if the age information identified in S103 is a child, the judgment result is to open the door, and the door access device is controlled to open the door; if the age information identified in S103 is not a child, the determination result is that the door is not opened, and the step of opening the door does not need to be performed.
Similarly, for example, taking the center of activities for the elderly as an example, if the age information identified in S103 is the elderly, the determination result is to open the door, and the access control device is controlled to open the door; if the age information identified in S103 is not old, the determination result is that the door is not opened, and the step of opening the door does not need to be performed.
Therefore, by the aid of the method and the system, the access control equipment can be controlled to open the door of a part of users in a targeted mode, and the users are distinguished and processed.
As another example, some building gates are usually voice-operated automatic doors, and in a related scheme, when the sound intensity in a scene reaches a set threshold, the door can be opened by activating the access control device, and after a period of time, the access control device automatically closes the door.
However, in this scheme, the users are not distinguished, and different requirements of different users are not taken care of. For example, for the elderly, the movement is inconvenient, the time spent on entering the door is long, and if the elderly just walk to the door, the door is closed by the access control device, which brings great risk to the safety of the elderly.
As an embodiment, the door opening time corresponding to each age information may be preset. For example, the setting contents may be as shown in table 2:
TABLE 2
Age information Duration of door opening
Age 10 and below 2 minutes
11-60 years old 1 minute
Age 61 and older 3 minutes
Table 2 is merely an example, and does not limit the specific contents set.
Assuming that the age information identified in S103 is 11 to 60 years old, the time period for controlling the door of the access control device to open is 1 minute.
For children aged 10 and below and old people aged 61 and above, the action speed of the children is slow, so that if the identified age information belongs to the two cases, the door opening time is relatively long, the situation that the door is automatically closed in the door entering process of a user is reduced, the risk of the user is reduced, and the user experience is improved. And for the people in the age range of 11-60 years old, the action speed is higher, and if the identified age information is 11-60 years old, the door opening time is relatively shorter, and the experience is better for the people in the door.
As another embodiment, a basic door opening duration may be set, and if the identified age information is old, a duration may be increased above the basic door opening duration. The specific time length value can be set according to the actual situation, and is not limited herein.
Generally speaking, the action speed of old man is slower, and the eyesight condition probably is not too good yet, therefore, if the age information of discerning is old, then it is a little longer for the time of opening the door, has reduced old user's entering in-process, and the condition of door self-closing has reduced old user's risk. For teenagers and adults, the action speed is high, if the identified age information is the teenagers or adults, the door opening time is relatively short, and the experience is good for people in the door.
If the two implementation modes are applied to control the access control equipment, the user risk is reduced, and the user experience is improved.
As an implementation mode, the voice control equipment is household equipment; s104 comprises the following steps:
judging whether the person corresponding to the sound data is an authorized person or not according to the age information;
if yes, controlling the household equipment according to the voice command sent by the authorized person.
It can be understood that some intelligent household devices can be controlled in a voice control mode. However, some smart home devices are dangerous and not suitable for children or the elderly at home to operate. For example, the intelligent kettle can be controlled to heat through sound. However, it is dangerous for children at home to operate the intelligent kettles. Under the condition, by applying the embodiment, if the age information corresponding to the identification sound data is children, the person corresponding to the identification sound data is judged not to be an authorized person, the intelligent kettle can not be heated, and the risk of the user is reduced.
Besides the smart water bottle, the household equipment can be other equipment, such as a smart stove and the like, and is not limited specifically.
Therefore, the home equipment can be controlled to respond to the instructions of part of the users in a targeted manner by applying the embodiment, so that the users are distinguished and processed, and the user risk is reduced.
As an embodiment, after S104, the method may further include:
if the identified age information is old, playing a first prompt voice;
and/or playing a second prompt voice if the identified age information is children.
As described above, the age information may be a specific age value, or may be an age group, or may be words indicating an age group such as "old age", "child", "adult", and the like. If the identified age information is a specific age value or age group, an age value or age group belonging to "old age", "child" may be set in advance.
For example, if the voice-controlled device is a lighting device arranged in a staircase, the first prompt voice may be: the old can go up and down stairs, please pay attention to safety under feet, and walk carefully and slowly; the second prompt voice may be: a child can go up and down the stairs without jumping, and the child can pay attention to safety and carefully slide. The specific prompt voice content is not limited.
As another example, if the sound control device is a home device, the first prompt voice may be: no operation of dangerous electric appliances is required, and safety is paid attention to; the second prompt voice may be: the children do not operate the dangerous electric appliances, and pay attention to safety. The specific prompt voice content is not limited.
By applying the embodiment, warm and safe reminding is performed for different users, and the method is more humanized.
In the embodiment of the present invention, in a first aspect, different age information corresponds to different control modes, or users are distinguished according to ages, and different requirements of users of different ages are taken care of; for example, for the old, the lighting duration of the lighting device is relatively long, so that the situation that the lighting device is automatically turned off in the moving process of the old user is reduced, and the risk of the user is reduced. In the second aspect, only when the sound data includes the wakeup word, the subsequent steps are executed, that is, the sound in the environment cannot activate the sound control device, so that the waste of resources is reduced. In the third aspect, the complexity of the awakening word model and the age identification model is not high, networking is not required, and the awakening word model and the age identification model can be stored in the local electronic equipment so as to improve the execution efficiency of the scheme.
Corresponding to the foregoing method embodiment, an embodiment of the present invention further provides a voice control apparatus, as shown in fig. 2, including:
an obtaining module 201, configured to obtain sound data to be processed;
a judging module 202, configured to judge whether the sound data includes a wakeup word; if yes, triggering the identification module;
the identification module 203 is used for identifying age information corresponding to the sound data;
and the control module 204 is configured to control the voice control device according to the age information.
For example, the obtaining module 201 may be a voice collecting module, and the determining module 202 may be a wakeup word module.
As an embodiment, the identifying module 203 is specifically configured to:
preprocessing the sound data to obtain processed sound data;
carrying out feature extraction on the processed sound data to obtain sound features;
and inputting the sound characteristics into an age identification model obtained by pre-training to obtain age information output by the age identification model.
In one embodiment, the voice-controlled device is a lighting device; the control module 204 is specifically configured to:
determining the illumination brightness and/or illumination duration corresponding to the identified age information;
and controlling the lighting equipment to illuminate according to the illumination brightness and/or the illumination time length.
In one embodiment, the voice-controlled device is a lighting device; the control module 204 is specifically configured to: and if the identified age information is old, increasing the illumination brightness and/or the illumination time of the illumination equipment.
As an implementation manner, the voice control device is an access control device; the control module 204 is specifically configured to:
judging whether to open the door and/or the door opening duration according to the age information;
and controlling the access control equipment according to the judgment result.
As an implementation manner, the voice control device is a household device; the control module 204 is specifically configured to:
judging whether the person corresponding to the sound data is an authorized person or not according to the age information;
if yes, controlling the household equipment according to the voice command sent by the authorized person.
As an embodiment, the apparatus further comprises:
a voice prompt module (not shown in the figure) for playing a first prompt voice if the identified age information is old; and/or playing a second prompt voice under the condition that the identified age information is the child.
In the embodiment of the present invention, in a first aspect, different age information corresponds to different control modes, or users are distinguished according to ages, and different requirements of users of different ages are taken care of; for example, for the old, the lighting duration of the lighting device is relatively long, so that the situation that the lighting device is automatically turned off in the moving process of the old user is reduced, and the risk of the user is reduced. In the second aspect, only when the sound data includes the wakeup word, the subsequent steps are executed, that is, the sound in the environment cannot activate the sound control device, so that the waste of resources is reduced. In the third aspect, the complexity of the awakening word model and the age identification model is not high, networking is not required, and the awakening word model and the age identification model can be stored in the local electronic equipment so as to improve the execution efficiency of the scheme.
An embodiment of the present invention further provides an electronic device, as shown in fig. 3, including a processor 301 and a memory 302,
a memory 302 for storing a computer program;
the processor 301 is configured to implement any of the above-described voice control methods when executing the program stored in the memory xx 3.
The Memory mentioned in the above electronic device may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component.
The embodiment of the invention also provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any one of the voice control methods is realized.
An embodiment of the present invention further provides a voice control system, as shown in fig. 4, including: a control device and a controlled device, wherein,
the control equipment is used for acquiring sound data to be processed; judging whether the sound data comprises awakening words or not; if yes, identifying age information corresponding to the sound data; generating a control instruction corresponding to the age information, and sending the control instruction to the controlled equipment;
and the controlled equipment is used for executing response operation corresponding to the control instruction.
In one embodiment, the controlled device includes an illumination device, and the control instruction includes illumination brightness and/or illumination duration.
As an implementation manner, the controlled device includes an access control device, and the control instruction includes information on whether to open the door and/or a door opening duration.
As an embodiment, as shown in fig. 5, the system may further include a sound collection device configured to collect sound data and send the sound data to the control device. For example, the sound collection device may be a microphone.
As an embodiment, as shown in fig. 6, the system may further include a sound playing device, configured to play the first prompt voice if the age information identified by the control device is old age; and/or playing the second prompt voice under the condition that the age information identified by the control equipment is the children.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, the device embodiment, the computer-readable storage medium embodiment, and the system embodiment, since they are substantially similar to the method embodiment, the description is relatively simple, and the relevant points can be referred to the partial description of the method embodiment.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

Claims (17)

1. A method for voice control, comprising:
acquiring sound data to be processed;
judging whether the sound data comprises awakening words or not;
if yes, identifying age information corresponding to the sound data;
and controlling the voice control equipment according to the age information.
2. The method of claim 1, wherein the identifying age information corresponding to the voice data comprises:
preprocessing the sound data to obtain processed sound data;
carrying out feature extraction on the processed sound data to obtain sound features;
and inputting the sound characteristics into an age identification model obtained by pre-training to obtain age information output by the age identification model.
3. The method of claim 1, wherein the voice-controlled device is a lighting device; according to the age information, controlling the voice control equipment comprises the following steps:
determining the illumination brightness and/or illumination duration corresponding to the identified age information;
and controlling the lighting equipment to illuminate according to the illumination brightness and/or the illumination time length.
4. The method of claim 1, wherein the voice-controlled device is a lighting device; according to the age information, controlling the voice control equipment comprises the following steps:
and if the identified age information is old, increasing the illumination brightness and/or the illumination time of the illumination equipment.
5. The method of claim 1, wherein the voice-activated device is an access control device; according to the age information, controlling the voice control equipment comprises the following steps:
judging whether to open the door and/or the door opening duration according to the age information;
and controlling the access control equipment according to the judgment result.
6. The method according to claim 1, wherein the voice-controlled device is a home device; according to the age information, controlling the voice control equipment comprises the following steps:
judging whether the person corresponding to the sound data is an authorized person or not according to the age information;
if yes, controlling the household equipment according to the voice command sent by the authorized person.
7. The method of claim 1, further comprising, after the identifying age information corresponding to the voice data:
if the identified age information is old, playing a first prompt voice;
and/or playing a second prompt voice if the identified age information is children.
8. An acoustic control apparatus, comprising:
the acquisition module is used for acquiring sound data to be processed;
the judging module is used for judging whether the sound data comprises awakening words or not; if yes, triggering the identification module;
the identification module is used for identifying age information corresponding to the sound data;
and the control module is used for controlling the voice control equipment according to the age information.
9. The apparatus of claim 8, wherein the identification module is specifically configured to:
preprocessing the sound data to obtain processed sound data;
carrying out feature extraction on the processed sound data to obtain sound features;
and inputting the sound characteristics into an age identification model obtained by pre-training to obtain age information output by the age identification model.
10. The apparatus of claim 8, wherein the voice-activated device is a lighting device; the control module is specifically configured to:
determining the illumination brightness and/or illumination duration corresponding to the identified age information;
and controlling the lighting equipment to illuminate according to the illumination brightness and/or the illumination time length.
11. The apparatus of claim 8, wherein the voice-activated device is a lighting device; the control module is specifically configured to: and if the identified age information is old, increasing the illumination brightness and/or the illumination time of the illumination equipment.
12. The apparatus of claim 8, wherein the voice-operated device is an access control device; the control module is specifically configured to:
judging whether to open the door and/or the door opening duration according to the age information;
and controlling the access control equipment according to the judgment result.
13. The apparatus according to claim 8, wherein the voice-controlled device is a household device; the control module is specifically configured to:
judging whether the person corresponding to the sound data is an authorized person or not according to the age information;
if yes, controlling the household equipment according to the voice command sent by the authorized person.
14. The apparatus of claim 8, further comprising:
the voice prompt module is used for playing a first prompt voice under the condition that the identified age information is old;
and/or playing a second prompt voice under the condition that the identified age information is the child.
15. A voice controlled system, comprising: a control device and a controlled device, wherein,
the control equipment is used for acquiring sound data to be processed; judging whether the sound data comprises awakening words or not; if yes, identifying age information corresponding to the sound data; generating a control instruction corresponding to the age information, and sending the control instruction to the controlled equipment;
and the controlled equipment is used for executing response operation corresponding to the control instruction.
16. The system of claim 15, wherein the controlled device comprises an illumination device, and wherein the control instruction comprises illumination brightness and/or illumination duration.
17. The system of claim 15, wherein the controlled device comprises an entrance guard device, and the control instruction comprises information on whether to open the door and/or a door opening duration.
CN201811258280.0A 2018-10-26 2018-10-26 Voice control method, device and system Pending CN111105791A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811258280.0A CN111105791A (en) 2018-10-26 2018-10-26 Voice control method, device and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811258280.0A CN111105791A (en) 2018-10-26 2018-10-26 Voice control method, device and system

Publications (1)

Publication Number Publication Date
CN111105791A true CN111105791A (en) 2020-05-05

Family

ID=70417934

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811258280.0A Pending CN111105791A (en) 2018-10-26 2018-10-26 Voice control method, device and system

Country Status (1)

Country Link
CN (1) CN111105791A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112435377A (en) * 2021-01-28 2021-03-02 江西云本数字科技有限公司 Intelligent building integrated management system

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103475551A (en) * 2013-09-11 2013-12-25 厦门狄耐克电子科技有限公司 Intelligent home system based on voice recognition
CN105282345A (en) * 2015-11-23 2016-01-27 小米科技有限责任公司 Method and device for regulation of conversation volume
CN105444332A (en) * 2014-08-19 2016-03-30 青岛海尔智能家电科技有限公司 Equipment voice control method and device
CN105895096A (en) * 2016-03-30 2016-08-24 乐视控股（北京）有限公司 Identity identification and voice interaction operating method and device
CN105933188A (en) * 2016-03-30 2016-09-07 宁波三博电子科技有限公司 Smart home control method and system based on different control permissions
CN105959806A (en) * 2016-05-25 2016-09-21 乐视控股（北京）有限公司 Program recommendation method and device
CN106297787A (en) * 2016-08-18 2017-01-04 张培 A kind of voice output responding device
CN106653016A (en) * 2016-10-28 2017-05-10 上海智臻智能网络科技股份有限公司 Intelligent interaction method and intelligent interaction device
CN107170456A (en) * 2017-06-28 2017-09-15 北京云知声信息技术有限公司 Method of speech processing and device

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103475551A (en) * 2013-09-11 2013-12-25 厦门狄耐克电子科技有限公司 Intelligent home system based on voice recognition
CN105444332A (en) * 2014-08-19 2016-03-30 青岛海尔智能家电科技有限公司 Equipment voice control method and device
CN105282345A (en) * 2015-11-23 2016-01-27 小米科技有限责任公司 Method and device for regulation of conversation volume
CN105895096A (en) * 2016-03-30 2016-08-24 乐视控股（北京）有限公司 Identity identification and voice interaction operating method and device
CN105933188A (en) * 2016-03-30 2016-09-07 宁波三博电子科技有限公司 Smart home control method and system based on different control permissions
CN105959806A (en) * 2016-05-25 2016-09-21 乐视控股（北京）有限公司 Program recommendation method and device
CN106297787A (en) * 2016-08-18 2017-01-04 张培 A kind of voice output responding device
CN106653016A (en) * 2016-10-28 2017-05-10 上海智臻智能网络科技股份有限公司 Intelligent interaction method and intelligent interaction device
CN107170456A (en) * 2017-06-28 2017-09-15 北京云知声信息技术有限公司 Method of speech processing and device

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112435377A (en) * 2021-01-28 2021-03-02 江西云本数字科技有限公司 Intelligent building integrated management system

Similar Documents

Publication Publication Date Title
JP4166153B2 (en) Apparatus and method for discriminating emotion of dog based on analysis of voice characteristics
US11120790B2 (en) Multi-assistant natural language input processing
CN104575504A (en) Method for personalized television voice wake-up by voiceprint and voice identification
US11594224B2 (en) Voice user interface for intervening in conversation of at least one user by adjusting two different thresholds
Vacher et al. Challenges in the processing of audio channels for ambient assisted living
US11393477B2 (en) Multi-assistant natural language input processing to determine a voice model for synthesized speech
CN103280220A (en) Real-time recognition method for baby cry
US11393473B1 (en) Device arbitration using audio characteristics
CN109887511A (en) A kind of voice wake-up optimization method based on cascade DNN
CN112820291A (en) Intelligent household control method, system and storage medium
US11776550B2 (en) Device operation based on dynamic classifier
CN111354371A (en) Method, device, terminal and storage medium for predicting running state of vehicle
CN106971714A (en) A kind of speech de-noising recognition methods and device applied to robot
CN110930643A (en) Intelligent safety system and method for preventing infants from being left in car
CN111105791A (en) Voice control method, device and system
CN111276156B (en) Real-time voice stream monitoring method
CN116343797A (en) Voice awakening method and corresponding device
CN114863932A (en) Working mode setting method and device
CN114999472A (en) Air conditioner control method and device and air conditioner
US11133020B2 (en) Assistive technology
WO2023107249A1 (en) Acoustic event detection
CN114155882B (en) Method and device for judging emotion of road anger based on voice recognition
CN113314113B (en) Intelligent socket control method, device, equipment and storage medium
CN102682767B (en) Speech recognition method applied to home network
CN111512364B (en) Intelligent sound box, multi-voice assistant control method and intelligent home system

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