CN109410952B - Voice awakening method, device and system - Google Patents
Voice awakening method, device and system Download PDFInfo
- Publication number
- CN109410952B CN109410952B CN201811482267.3A CN201811482267A CN109410952B CN 109410952 B CN109410952 B CN 109410952B CN 201811482267 A CN201811482267 A CN 201811482267A CN 109410952 B CN109410952 B CN 109410952B
- Authority
- CN
- China
- Prior art keywords
- voice
- control logic
- voice control
- user
- wake
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G10L15/26—Speech to text systems
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
Abstract
The embodiment of the invention discloses a voice awakening method, which comprises the following steps: step 101, judging whether a preset condition is met, if so, executing step 103, otherwise, executing step 105; 103, activating the operation of the wake-up-free word wake-up voice control logic; and 105, not activating the operation of the wake-up-free word wake-up voice control logic. By the voice awakening method, the voice interaction process between the user and the voice control logic can be simplified, the voice interaction is more convenient, humanized and intelligent, the voice interaction efficiency is improved, and the user experience is improved.
Description
Technical Field
The embodiment of the invention relates to the field of artificial intelligence, in particular to a voice awakening method, device and system.
Background
With the continuous development of artificial intelligence technology, users increasingly obtain various services from terminals and various APP applications in a voice interaction mode in daily life.
At present, people usually speak a fixed awakening keyword for a user when performing voice interaction, and a terminal awakens corresponding services such as a voice assistant and the like after acquiring the keyword, starts a voice interaction process, and then acquires the voice of the user to perform man-machine interaction. Or the fixed awakening key words and the user commands are collected at the same time, and after the terminal judges that the awakening key words are collected, the terminal performs a human-computer interaction process with the intelligent terminal according to the subsequent user commands.
In the voice interaction process, a user needs to use a fixed awakening keyword, the interaction process is complicated and not simple, the interaction cost is high, and particularly, when the user forgets to awaken the keyword in an emergency or the time of the user is short and the voice interaction process needs to be started as soon as possible, the voice interaction mode is too rigid, the time for the user to wait for obtaining a required voice interaction result is too long, and the user experience is reduced.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a voice awakening method, a device and a system.
The embodiment of the invention provides a voice awakening method, which comprises the following steps:
a voice wake-up method, the voice wake-up method comprising the steps of:
step 101, judging whether a preset condition is met, if so, executing step 103, otherwise, executing step 105;
103, activating the operation of the wake-up-free word wake-up voice control logic;
and 105, not activating the operation of the wake-up-free word wake-up voice control logic.
The judging whether the preset condition is met comprises the following steps:
judging whether only one person exists in a preset range of the voice control logic, and meeting a preset condition when only one person exists;
and/or the presence of a gas in the gas,
judging whether the user sends an emergency help, if so, meeting a preset condition;
and/or the presence of a gas in the gas,
detecting the speaking volume of a driver in the automobile, and determining whether a preset condition is met according to the speaking volume;
and/or the presence of a gas in the gas,
and judging whether the voice control logic is located in a specific area, if so, meeting a preset condition.
When the voice control logic is in the room, the preset range is in the room;
when the voice control logic is outdoors, the preset range is a circle with the position of the voice control logic as the center of the circle and R as the radius, and R is a number greater than 0;
when the voice control logic is in the vehicle or installed in the vehicle, the preset range is in the vehicle.
Preferably, the determining whether there is only one person within the preset range of the voice control logic includes, when there is only one person, meeting the preset condition:
judging whether only one person exists in a preset range of the voice control logic, if so, determining a user of the artificial voice control logic, and if the voice control logic acquires the voice sent by the user, meeting a preset condition;
alternatively, the first and second electrodes may be,
after the voice sent by the user is obtained, whether only one person exists in the preset range of the voice control logic is judged, and if yes, the preset condition is met.
Judging whether the user sends an emergency help, if so, meeting the preset conditions comprises:
the voice uttered by the user is acquired,
and judging whether the voice includes emergency help, if so, meeting a preset condition.
Preferably, the determination of whether there is only one person within the preset range of voice control logic is performed, and when there is only one person, further,
and acquiring sound information, and judging whether the acquired sound information is the voice sent by the personnel in the preset range, wherein if the acquired sound information is the voice sent by the personnel in the preset range, the preset condition is met.
Preferably, detecting the speaking volume of the driver in the vehicle, and determining whether the preset condition is met according to the speaking volume comprises
Acquiring voice sent by a driver, judging whether only one person exists in the vehicle, and if so, meeting a preset condition when the voice volume is greater than or equal to a first preset value; if more than one person is in the vehicle, when the voice volume is greater than or equal to a second preset value, a preset condition is met; or when the voice volume of the driver is greater than or equal to a third preset value, the preset condition is met;
the first preset value is lower than the second preset value.
Preferably, when the preset range is in the vehicle,
and further judging whether the only one person is the driver or not, and if so, meeting the preset condition.
Preferably, the determining whether the voice control logic is located in the specific area, if so, the meeting the preset condition includes:
and acquiring the voice of the user, judging whether the voice of the user is associated with the specific area, and if so, meeting a preset condition.
Preferably, the pre-establishing of the association relationship between the user voice and the specific area and the determining of whether the association exists between the user voice and the specific area includes
And acquiring a position area where the voice and the voice control logic of the user are located, judging whether the acquired voice and the position area are matched with the pre-established association relation, and if so, meeting the preset condition.
Preferably, whether the user is performing voice related services is judged, and if yes, the operation of waking up the voice control logic by the wake-up-free word is not activated.
Preferably, it is determined whether the user turns on the function of the wake-up free word wake-up voice control logic, and if so, the user turns on the function to execute step 101.
Preferably, it is determined whether the acquired voice uttered by the user includes a fixed wake-up keyword, and if not, step 101 is executed.
And if the acquired voice sent by the user contains the fixed awakening keyword, awakening the voice control logic based on the fixed awakening keyword.
The operation of activating the wake-free word wake-up voice control logic comprises:
and the voice control logic executes corresponding actions according to the acquired voice.
The operation of not activating the wake-free word wake-up voice control logic comprises:
and the voice control logic wakes up the voice control logic according to other wake-up modes.
An embodiment of the present invention further provides a voice wake-up apparatus, including:
the judging module is used for judging whether preset conditions are met or not; if the preset condition is met, triggering an activation module to activate the wake-up-free word wake-up operation; otherwise, triggering the activation module not to execute the wake-up-free word wake-up operation;
and the activation module is used for activating the wake-up-free word wake-up voice control logic or not activating the wake-up-free word wake-up voice control logic according to the trigger signal of the judgment module.
Judging whether the preset condition is met comprises the following steps:
judging whether only one person exists in a preset range of the voice control logic, and meeting a preset condition when only one person exists;
and/or the presence of a gas in the gas,
judging whether the user sends an emergency help, if so, meeting a preset condition;
and/or the presence of a gas in the gas,
detecting the speaking volume of a driver in the automobile, and determining whether a preset condition is met according to the speaking volume;
and/or the presence of a gas in the gas,
judging whether the voice control logic is located in a specific area, if so, meeting a preset condition;
preferably, when the voice control logic is indoors, the preset range is in a room;
when the voice control logic is outdoors, the preset range is a circle with the position of the voice control logic as the center of the circle and R as the radius, and R is a number greater than 0;
when the voice control logic is in the vehicle or installed in the vehicle, the preset range is in the vehicle.
Preferably, the determining whether there is only one person within the preset range of the voice control logic includes, when there is only one person, meeting the preset condition:
judging whether only one person exists in a preset range of the voice control logic, if so, determining a user of the artificial voice control logic, and if the voice control logic acquires the voice sent by the user, meeting a preset condition;
alternatively, the first and second electrodes may be,
after the voice sent by the user is obtained, whether only one person exists in the preset range of the voice control logic is judged, and if yes, the preset condition is met.
Preferably, the judging whether the user sends an emergency help, if so, the meeting of the preset condition includes:
and judging whether the acquired voice sent by the user includes emergency help, if so, meeting a preset condition.
Preferably, the determining whether there is only one person within the preset range of the voice control logic includes, when there is only one person, satisfying the preset condition
And judging whether the acquired sound information is the voice sent by the personnel in the preset range, if so, meeting the preset condition.
Preferably, detecting the speaking volume of the driver in the vehicle, and determining whether the preset condition is met according to the speaking volume comprises
Acquiring voice sent by a driver, judging whether only one person exists in the vehicle, and if so, meeting a preset condition when the voice volume is greater than or equal to a first preset value; if more than one person is in the vehicle, when the voice volume is greater than or equal to a second preset value, a preset condition is met; or when the voice volume of the driver is greater than or equal to a third preset value, the preset condition is met;
the first preset value is lower than the second preset value.
Preferably, when the preset range is in a vehicle, whether only one person is a driver is further judged, and if the only one person is the driver, the preset condition is met.
Preferably, the determining whether the terminal is located in the specific area, if so, meeting the preset condition includes:
and judging whether the voice of the user is associated with the specific area or not, and if so, meeting a preset condition.
Preferably, the pre-establishing of the association relationship between the user voice and the specific area and the determining of whether the association exists between the user voice and the specific area includes
And judging whether the acquired voice and the position area are matched with the pre-established association relation or not according to the acquired voice of the user and the position area where the voice control logic is located, and if so, meeting the preset condition.
Preferably, the determining module is further configured to determine whether the user is performing a voice-related service, and if so, determine that the predetermined condition is not satisfied.
Preferably, the device further comprises a switch module for the user to select to turn on or turn off the wake-up free word wake-up function; when the user selects to turn on, the function of the voice control logic awakened by the awakening-free word is turned on.
Preferably, the device further comprises a voice detection module, configured to determine whether the acquired voice sent by the user includes a fixed wake-up keyword, and if not, trigger the determination module to execute its function; if yes, the activation module is triggered to not activate the operation of the wake-up-free word wake-up voice control logic.
The operation of triggering the activation module to not activate the wake-up exempt word to wake up the voice control logic includes waking up the voice control logic based on the fixed wake-up keyword.
The device also comprises
And the acquisition module is used for acquiring the voice sent by the user.
The embodiment of the invention also provides a voice control logic, which comprises the device.
An embodiment of the present invention provides a computer device, which includes a processor and a memory, where the memory stores computer instructions executable by the processor, and when the processor executes the computer instructions, the method as described above is implemented.
An embodiment of the present invention provides a computer-readable storage medium, which is characterized by storing computer instructions for implementing the method described above.
By the voice awakening method and the voice awakening device, when a user performs voice interaction with the voice control logic, the user does not need to speak the awakening word every time, and the awakening mode of the user is judged according to the preset condition voice control logic, so that the awakening voice control logic efficiency is improved, and the voice interaction between the user and the voice control logic is more natural, humanized and intelligent. Particularly, the voice awakening method provided by the invention executes different judgment processes according to different environments, and can awaken the voice control logic more accurately and efficiently. In addition, the invention determines whether to execute the operation of the wake-up-free voice control logic by judging whether to carry out the voice service, so that the false wake-up rate of the voice control logic is reduced.
Drawings
Fig. 1 is a method for voice wake-up in an embodiment of the present invention.
Fig. 2 is a device for voice wake-up in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
Fig. 1 is a method for wake-up free word according to an embodiment of the present invention.
The method may be applied to voice control logic comprising software, hardware, firmware, etc. capable of performing voice interaction functions, either uni-directionally or bi-directionally, which may be performed by one or more devices.
Referring to fig. 1, the voice wake-up method includes the following steps:
step 101, judging whether a preset condition is met, if so, executing step 103, otherwise, executing step 105;
103, activating a wake-up free word wake-up operation;
and 105, not activating the wake-up-free word wake-up operation.
Specifically, in step 101, determining whether the preset condition is met includes:
and judging whether only one person exists in the preset range of the voice control logic, and activating the wake-up-free word wake-up operation if the preset condition is met when only one person exists. When only one person in the preset range is judged, the voice control logic acquires the voice sent by the user, and then awakens the voice control logic to execute corresponding actions according to the voice. If only one person in the preset range of the voice control logic is judged, and the voice of the user is obtained, namely the person is rainy in the sea, the voice control logic is awakened, the voice of the user is recognized, other services or programs are called, the weather in the sea is inquired locally or through a cloud server, the inquiry result is fed back to the user, and if the voice of the user is obtained as 'i want to chat with you', the voice control logic is awakened, and the user chats.
Alternatively, the first and second electrodes may be,
when the voice control logic acquires the voice sent by the user, whether only one person exists in the preset range of the voice control logic is judged, if only one person exists, the wake-up-free word wake-up operation is started, the voice control logic is woken up, and corresponding operation is executed according to the voice of the user. If the voice of 'the Shanghai has rained' sent by the user is acquired, the number of people in the environment within the preset range is detected, if the judgment is that only one person exists, the wake-up-free word wake-up operation is started, the voice sent by the user is identified, other services or programs are called, the operation of inquiring weather is executed, if the voice of the user is chat and the like, and the voice control logic is only woken up and is communicated with the voice according to the voice of the user when other programs or services are not called.
In the invention, two modes of judging whether only one person exists in the preset range of the voice control logic, then acquiring the voice sent by the user or firstly acquiring the voice sent by the user, and then judging whether only one person exists in the preset range can be replaced mutually, and the method is not limited to only adopting one mode.
And/or the presence of a gas in the gas,
and acquiring the voice of the user, judging whether the user sends an emergency help, and if so, meeting a preset condition. If the user says 'dial 120', the voice control logic judges that the voice is an emergency call after acquiring the voice spoken by the user, and directly wakes up the voice control logic without using a fixed wake-up keyword, executes a command in the voice, calls a call function and dials 120 calls. When judging whether the voice belongs to the emergency help seeking, the acquired voice is identified through semantic analysis, for example, and if the voice belongs to the emergency help seeking situation, such as emergency call, emergency rescue and the like, the user is determined to send out the emergency help seeking.
And/or the presence of a gas in the gas,
and judging whether the voice control logic is located in a specific area, if so, meeting a preset condition. When the voice control logic is located in a specific area, the voice of the user is acquired, the voice control logic is awakened directly, corresponding operation is executed according to the voice, or after the voice of the user is acquired, whether the voice control logic is located in the specific area is judged, if yes, the voice control logic is awakened directly, and a fixed awakening keyword is not needed. For example, the specific area is an area with specific functions such as a shopping mall, a supermarket, a gas station, a home, etc., when the voice control logic is in the area, the specific operation is usually executed, and in the area, the voice control logic is directly awakened by the awakening-free word tone, so that the user operation can be simplified, and the convenience is improved. In the present invention, the execution sequence of detecting the position of the voice control logic and acquiring the voice is not limited, and any one of the steps may be executed first.
Further, whether the voice command is associated with the area or not is judged for different specific areas, if yes, a preset condition is met, and a wake-up-free word wake-up mode is executed, for example, when the user is located in a hospital, after the voice of the user is obtained, whether the voice of the user is related to hospitalization or not is identified, such as registration, payment, laboratory test reports and the like, if yes, a wake-up-free keyword wake-up voice control logic mode is executed, other programs or services are called through the voice control logic, and if the APP of the hospital, the command indicated by the voice is executed. When a user is located in a shopping mall or a supermarket and the voice of the user for price inquiry or payment or restaurant inquiry is acquired, whether the voice of the user is related to the area where the user is located is judged, if yes, the voice control logic is awakened according to the voice, and corresponding operation is executed. By the limitation, the voice control logic can be prevented from being awakened by mistake to a certain degree.
Preferably, the voice of the user is acquired, the position area of the voice control logic is acquired, the voice is identified, the relevance between the voice of the user and the position area of the voice control logic is judged, if the relevance is relevant, the preset condition is met, and if the relevance is not relevant, the preset condition is not met.
The judgment of the relevance between the user voice and the position area can be executed by the voice control logic, or the voice and the position area are sent to the server through the network and executed by the server, or the judgment can be executed by the voice control logic firstly, when the relevance between the user voice and the position area cannot be judged, the server is sent through the network, the judgment is executed by the server, and the judgment result is fed back to the voice control logic.
Preferably, the relevance relationship between the user voice and the specific area can be established in advance, the relevance relationship can be subjected to model training through big data, and when the recognized voice is judged to have relevance with the position area, the preset condition is met; or training the voice of the user interacting with the voice control logic in the area and/or the operation of the user executing in the area, establishing an operation executed by the user in a specific area and/or an association relation model of the user voice and the position area through deep learning of historical data of the user, continuously updating the model according to the operation executed by the user in the specific area and the sent voice, updating the model according to a voice command awakened by mistake, when the voice command awakened by mistake meets a certain condition, updating the model according to the voice command, eliminating the association between the voice command and the position area, and when judging that the association exists between the voice of the user and the position area, directly awakening the voice control logic according to the voice and executing the operation corresponding to the recognized voice.
Further, the association relationship may also be defined by a user, or the user modifies the association relationship in the model by himself, for example, the user may set an association relationship table between the voice and the location area in the voice control logic or the server, where the list includes the location area and the wake-up-free word wake-up instruction, where the location area and the instruction have a corresponding relationship, and after obtaining the voice of the user, determine whether the voice of the user and the location area belong to an entry having a corresponding relationship in the list according to the recognized voice, if so, a preset condition is satisfied, otherwise, the entry does not satisfy. Or the user wants to delete or add the wake-free voice command in the model, and can directly delete the voice command or add the corresponding wake-free voice command.
Preferably, after the position area where the user voice and the voice control logic are located is obtained, whether the user voice and the voice control logic are matched with the user-defined incidence relation or the model trained according to the historical data of the user is judged, if yes, the preset condition is met, otherwise, the judgment is further carried out according to the model trained by the big data, and if yes, the preset condition is met. By means of the method, on one hand, the judgment result is more in line with the use habit of the user, the judgment speed is increased, and on the other hand, the user experience can be improved according to the big data model.
And/or the presence of a gas in the gas,
the method comprises the steps of obtaining voice sent by a user, identifying the voice, judging whether the voice is associated with functions of a foreground APP and/or a background APP, and if so, meeting preset conditions. If foreground APP or background APP is the music player, the obtained user voice is 'next', and the voice is judged to be associated with the APP, so that the preset condition is met.
Preferably, when the judging operation is executed, whether the voice is associated with the foreground APP is judged firstly, if so, the preset condition is met, if not, whether the voice is associated with the background APP is further judged, if so, the preset condition is met, and otherwise, the preset condition is not met. Through the above-mentioned mode of judging in proper order, can satisfy when same pronunciation is correlated with a plurality of APPs simultaneously, the user expects to control proscenium APP, and not to the situation of backstage APP control.
And/or the presence of a gas in the gas,
and learning the voice interacted between the user and the voice control logic, counting the command with higher utilization rate, and taking the high-frequency command as a wake-up-free word wake-up command. For example, the voice of the user is acquired, the voice is identified, whether the identified voice belongs to a high-frequency command or not is judged, if yes, a preset condition is met, and otherwise, the preset condition is not met. By continuously learning the voice of the user and analyzing and counting the high-frequency command, the voice control logic can be more flexibly communicated with the user. And similarly, for the command of mistaken awakening, the rejection is updated in time.
And/or the presence of a gas in the gas,
when the voice control logic is in the vehicle or the voice control logic is arranged on the vehicle, the speaking volume of a driver is detected, and whether the preset condition is met or not is determined according to the speaking volume. If the voice sent by the driver is acquired, judging whether the driver is alone in the vehicle, if so, when the voice volume is more than or equal to a first preset value, meeting a preset condition; if more than one person is in the vehicle, when the voice volume is greater than or equal to a second preset value, a preset condition is met; the first preset value is lower than the second preset value. When only one person exists in the vehicle, the environment is relatively quiet, the driver can meet the preset condition with lower volume, and when more than one person exists in the vehicle, in order to prevent the interference caused by the speaking sound of other people, the sound volume of the driver is higher than the second preset value, the preset condition is met.
For the environment in the vehicle, the number of people in the vehicle does not need to be judged, and when the voice volume of the driver is greater than or equal to a third preset value, the preset condition is determined to be met;
the first preset value, the second preset value and the third preset value may be preset by a user, or the voice control logic may adaptively adjust the volume according to historical data when waking up according to the volume, such as the volume when waking up correctly and the volume when waking up incorrectly, or may be set by a factory when leaving a factory.
When the volume of the voice is determined, the voice signal may be denoised first and then compared, for example, the decibel of the voice is compared with a preset decibel value.
The specific embodiments of determining whether the preset condition is met may be combined arbitrarily, including one or more of the specific conditions.
By the method, the operation of awakening the voice control logic can be simplified, the user does not need to frequently and repeatedly speak the awakening keyword to the voice control logic, the voice interaction process between the user and the voice control logic is simpler, more humanized and intelligent, and the efficiency of man-machine voice interaction is improved.
For the above embodiments, the preset range may be indoor, outdoor, or in-vehicle.
1) When the voice control logic is located indoors
The preset range is a room where the voice control logic is located.
And judging whether the room where the voice control logic is located has only one person, if so, activating a wake-up-free word wake-up operation to wake up the voice control logic when the speaking voice is acquired. Preferably, in order to prevent interference caused by external sounds, the acquired sounds are further judged, whether the sounds are sounds generated by speaking of the people in the room is judged, and if yes, a preset condition is met; otherwise, the preset condition is not met. If a sound source positioning technology is adopted, whether the sound source is the same as the position of a person in a room or not is determined, if the sound source is the same as the position of the person in the room, the obtained sound is judged to be sent by the person in the room, a voice control logic is awakened, the voice of a user is recognized, and corresponding operation is executed according to the recognized voice.
2) When the voice control logic is located outdoors,
the preset range is an outdoor environment.
The detection range of the voice control logic may be set, for example, the position where the voice control logic is located is taken as the center of a circle, R is the detection range within the circle with the radius, R is a number greater than zero, and the value of R may be preset by the user. If only one person exists in the detection range, the preset condition is met, and if more than one person exists in the detection range, the preset condition is not met. Also, the judgment operation as described above when the terminal is in the room may be further performed on the acquired sound.
3) When the preset range is in the vehicle
When the number of the persons in the vehicle is one person, the preset condition is met. The awakening condition of the awakening-free word in the environment in the vehicle can be further limited, when the person is a driver, the preset condition is met, otherwise, when the person is not the driver, the preset condition is not met. Or judging whether the personnel is an authorized user, if so, meeting the preset conditions, otherwise, not meeting the preset conditions. Whether the judgment personnel is a driver or not can be judged by detecting whether the user sits at the driving position or not, in addition, whether the judgment personnel is the driver or the authorized user or not can also be judged by inputting information of the driver or the authorized user in advance, such as fingerprint information, head portrait information, voice information or other information related to biological characteristics or other related information capable of determining the identity of the personnel, detecting the personnel in the vehicle, judging whether the acquired personnel information is matched with the information input in advance or not, and if the acquired personnel information is matched with the information input in advance, judging that the personnel is the driver or the authorized user. If the voice information of a driver or an authorized user is recorded in advance, when a person in the vehicle speaks, the voice information is acquired and compared with the voice information recorded in advance, whether the person belongs to the person who records the voice is judged, if so, the driver or the authorized user is judged, the preset condition is met, the operation of the wake-up-free word wake-up voice control logic can be started, and the voice control logic executes corresponding actions according to the acquired voice.
Furthermore, different awakening-free word awakening conditions are set for different people, the function of awakening the voice control logic by the awakening-free word can be realized for a driver by all voices, and the awakening-free word awakening voice control logic is disabled for other people for voice commands related to driving safety. Therefore, after the voice of the user is acquired, whether the user is a driver or not is judged, if yes, the wake-up-free word wake-up function is executed, otherwise, whether the voice of the user is related to driving safety or not is further judged, if yes, the wake-up-free word wake-up function cannot be realized, and otherwise, the voice control logic is directly woken up.
In step 103, when it is determined that the preset condition is met according to any of the above manners, the voice control logic may be directly awakened, and corresponding action is executed according to the acquired voice of the user.
As described above, after the preset condition is satisfied, the voice control logic is awakened to recognize the user voice, when the user voice command needs to be executed by calling another program or function, the other program or function is called, and the execution result is fed back to the user, and when the user voice command does not need to be executed by calling another program or function, the user performs voice communication with the user according to the recognized voice.
In step 105, when it is determined that the preset condition is not satisfied, the operation of the wake-up-free word wake-up voice control logic is not activated.
When the preset condition is judged not to be met according to the judging step, the operation of the wake-up-free word wake-up voice control logic is not activated, and the fixed wake-up keyword wake-up voice control logic or other common wake-up voice control logic mode is needed to wake up.
According to the method for awakening the voice control logic by voice, whether the voice control logic meets the preset condition or not is judged, and when the preset condition is met, the mode that the voice control logic is awakened by the awakening-free word is activated, so that the flow of man-machine voice interaction is simplified, the user experience is improved, and the voice control logic can serve the user more conveniently.
In another embodiment, in order to prevent the method for waking up the voice control logic by using the wake-up-free word from erroneously waking up the voice control logic, when the voice control logic acquires the voice uttered by the user, it is further detected whether the user is performing a voice communication service, if the user is performing the voice communication service, the wake-up-free word wake-up operation is not activated when the user speaks at the opening, otherwise, the method of the present invention is further performed. For example, if the user has a call incoming or outgoing call, or is making a call, or is performing a video communication service or a voice communication service with another person, the wakeup exempt word wakeup operation is not activated. In this case, if the user needs to wake up the voice control logic, the voice control logic may be woken up by using a wake-up method known in the art, such as waking up the voice control logic by using a fixed wake-up word. For example, if the user is calling with a friend to ask the friend "Shanghai Yuwu", and in this case, the voice control logic acquires and recognizes the voice of the user, and if the voice control logic is awoken by mistake to inquire about weather conditions, which affects the user to call, according to the embodiment of the present invention, the voice control logic detects that the user is calling, and only when the user uses the existing awaking method, such as speaking a voice including a fixed awaking keyword, such as "how do you have slept in Shanghai" or "how do you have slept in Shanghai, who have slept in Shanghai", and the voice control logic recognizes the fixed awaking keyword "little you", the voice control logic wakes up the voice control logic by using the fixed awaking keyword, recognizes the voice associated with "little you" and performs corresponding actions according to the voice, such as collecting the voice within a certain time range before and after the user utters "little you have slept",in "little you" when the user, analyzing the voice, judging which contents are related to voice interaction of the voice control logic and which contents are contents of a call made between the user and the opposite side, and executing corresponding actions according to the related contents after identifying the related contents of the voice interaction of the voice control logic, such as inquiring weather in Shanghai. If the user is not performing the voice communication service, step 101 is executed to further determine whether the preset condition is met, and the method is executed according to the present invention.
By the method, the problem that when the voice control logic starts the wake-up-free word wake-up operation, the voice control logic is mistakenly awakened due to voice-related services carried out by a user is effectively avoided, and the effect of reducing the probability of mistaken wake-up is achieved.
In another embodiment, an option of whether to enable the wake-up free word wake-up function may be set in the voice control logic, and if the user turns on the function, the method is performed, and if the user turns off the function, a wake-up manner commonly used in the prior art, such as a fixed wake-up keyword, is used to wake up the voice control logic. Through the setting, the user can select the voice awakening mode more flexibly according to the needs of the user.
In another embodiment, when the voice control logic obtains the voice uttered by the user, the voice is recognized first, and whether the voice includes the fixed wake-up keyword is determined, if yes, the voice control logic and the voice control logic are voice-interacted in a manner of waking up the voice control logic by using the fixed wake-up word in the prior art, and the interaction manner may be as described above. If the fixed wake-up key is not included, step 101 is executed according to the voice wake-up method of the present invention.
For example, a user says that the user does not rain at sea, the voice control logic collects the voice of the user and recognizes that the user includes a fixed awakening keyword which is a key word of the user, the user awakens the voice control logic according to the method in the prior art and executes the action of voice indication. Or the user says that the user rains in the sea and the user rains once every so, although the awakening keyword is positioned behind the action indicated by the user voice, the voice control logic takes the sentence as a whole, recognizes the fixed awakening keyword 'the user watches once every so' included in the sentence, awakens the voice control logic in a mode of awakening the voice control logic by the fixed awakening keyword, executes the action indicated in the voice, inquires weather in the sea, determines whether the user rains or not, and feeds back a result to the user.
When the user says "it is rainy in the sea," because the voice does not include the fixed wake-up keyword, the voice control logic is woken up according to the method for waking up the voice control logic of the present invention, that is, the above step 101 is executed.
Preferably, in the voice wake-up method of the present invention, the method step of preventing the voice control logic from being woken up by mistake and the step of determining whether the obtained voice contains a fixed wake-up keyword may be both performed, or either performed. Wherein the steps are not sequential when all steps are performed.
The method for voice wake-up of voice control logic according to the present invention is described in detail above.
Fig. 2 is a schematic structural diagram of a voice wake-up apparatus provided in the present invention, configured to execute the above method, as shown in fig. 2, the voice wake-up apparatus provided in this embodiment includes:
the judging module is used for judging whether preset conditions are met or not; if the preset condition is met, triggering an activation module to activate the wake-up-free word wake-up operation; otherwise, triggering the activation module not to execute the wake-up-free word wake-up operation;
the activation module is used for activating the wake-up-free word wake-up voice control logic or not activating the wake-up-free word wake-up voice control logic according to the trigger signal of the judgment module;
preferably, the judging whether the preset condition is satisfied includes:
judging whether only one person exists in a preset range of the voice control logic, and meeting a preset condition when only one person exists;
and/or the presence of a gas in the gas,
judging whether the user sends an emergency help, if so, meeting a preset condition;
and/or the presence of a gas in the gas,
detecting the speaking volume of a driver in the automobile, and determining whether a preset condition is met according to the speaking volume;
and/or the presence of a gas in the gas,
judging whether the voice control logic is located in a specific area, if so, meeting a preset condition;
and/or the presence of a gas in the gas,
judging whether the acquired voice of the user is associated with the functions of the foreground APP and/or the background APP, if so, meeting a preset condition;
and/or the presence of a gas in the gas,
and judging whether the acquired voice of the user belongs to a high-frequency command or not, and if so, meeting a preset condition.
Further, in the above-mentioned case,
when the voice control logic is in the room, the preset range is in the room;
when the voice control logic is outdoors, the preset range is a circle with the position of the voice control logic as the center of the circle and R as the radius, and R is a number greater than 0;
when the voice control logic is in the vehicle or installed in the vehicle, the preset range is in the vehicle.
Further, it is judged whether only one person exists in the preset range of the voice control logic, and when only one person exists, the meeting of the preset condition includes:
judging whether only one person exists in a preset range of the voice control logic, if so, determining a user of the artificial voice control logic, and if the voice sent by the user is acquired, meeting a preset condition;
alternatively, the first and second electrodes may be,
after the voice sent by the user is obtained, whether only one person exists in the preset range of the voice control logic is judged, and if yes, the preset condition is met.
Judging whether the user sends an emergency help, if so, meeting the preset conditions comprises:
and judging whether the acquired voice sent by the user includes emergency help, if so, meeting a preset condition.
Preferably, the determining whether there is only one person within the preset range of the voice control logic includes, when there is only one person, satisfying the preset condition
And judging whether the acquired sound information is the voice sent by the personnel in the preset range, if so, meeting the preset condition.
Preferably, detecting the speaking volume of the driver in the vehicle, and determining whether the preset condition is met according to the speaking volume comprises
After the voice sent by a driver is acquired, judging whether only one person exists in the vehicle, if so, when the voice volume is greater than or equal to a first preset value, meeting a preset condition; if more than one person is in the vehicle, when the voice volume is greater than or equal to a second preset value, a preset condition is met; or when the voice volume of the driver is greater than or equal to a third preset value, the preset condition is met;
the first preset value is lower than the second preset value.
When the preset range is in the vehicle, whether only one person is a driver or not is further judged, and if the driver is the driver, the preset condition is met.
Preferably, the determining module is further configured to determine whether the user is performing a voice-related service, and if so, determine that the predetermined condition is not satisfied.
Preferably, the device further comprises a switch module for the user to select to turn on or turn off the wake-up free word wake-up function; when the user selects to turn on, the function of the voice control logic awakened by the awakening-free word is turned on to execute the method of the invention, otherwise, the function is turned off, and the voice control logic is awakened by using the awakening mode commonly used in the prior art, such as a fixed awakening keyword.
Preferably, the device further comprises a voice detection module, configured to determine whether the acquired voice sent by the user includes a fixed wake-up keyword, and if not, trigger the determination module to execute its function; if yes, the activation module is triggered to not activate the operation of the wake-up free word wake-up voice control logic, and a wake-up mode commonly used in the prior art, such as a fixed wake-up keyword wake-up voice control logic, is adopted.
Optionally, the apparatus further comprises:
the acquisition module is used for acquiring voice sent by a user;
the acquisition module may be a microphone, or an array of microphones.
Activating the wake-up-free word to wake up the voice control logic comprises the steps that the voice control logic executes corresponding actions according to acquired voice, if other programs or services need to be called, the other programs or services are called, execution results are fed back to a user, and if the voice of the other programs or services does not need to be called, only the voice control logic is woken up, and communication is carried out with the voice control logic according to the voice of the user.
Not activating the wake-exempt word to wake up the voice control logic includes waking up the voice control logic according to other wake-up manners.
The manner in which each module specifically executes each step is the same as the method.
The invention also provides a voice control logic, which comprises the voice awakening device.
The invention also provides a computer device comprising a processor and a memory storing computer instructions executable by the processor, which when executed by the processor, implement a method as described above.
The present invention also provides a computer readable storage medium storing computer instructions for implementing the method as described above.
Any combination of one or more computer-readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. The computer-readable storage medium may include: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), a flash memory, an erasable programmable read-only memory (EPROM), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
Computer program code for carrying out operations of the present invention may be written in one or more programming languages, or a combination thereof.
The above description is only an example for the convenience of understanding the present invention, and is not intended to limit the scope of the present invention. In the specific implementation, a person skilled in the art may change, add, or reduce the components of the apparatus according to the actual situation, and may change, add, reduce, or change the order of the steps of the method according to the actual situation without affecting the functions implemented by the method.
While embodiments of the invention have been shown and described, it will be understood by those skilled in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents, and all changes that come within the meaning and range of equivalency of the claims are to be embraced within their scope.
Claims (29)
1. A voice wake-up method, comprising:
acquiring voice sent by a driver;
judging whether only one driver exists in the vehicle or not;
if so, activating the operation of the wake-up-free word wake-up voice control logic when the voice volume of the driver is greater than or equal to a first preset value;
if not, when the voice volume of the driver is larger than or equal to a second preset value, activating the operation of awakening the voice control logic by the awakening-free word;
wherein the first preset value is lower than the second preset value; the first preset value and the second preset value are preset by a user, or the first preset value and the second preset value are historical data of the voice control logic when activating the wake-up-free word wake-up function according to the volume, and the historical data comprise the volume when the voice control logic is correctly awakened and the volume when the voice control logic is mistakenly awakened, and are self-adaptively adjusted.
2. The method of claim 1,
the preset conditions for activating the wake-up-free word to wake up the voice control logic further include:
judging whether only one person exists in a preset range of the voice control logic, and meeting a preset condition when only one person exists; and/or the presence of a gas in the gas,
judging whether the user sends an emergency help, if so, meeting a preset condition;
and/or the presence of a gas in the gas,
and judging whether the voice control logic is located in a specific area, if so, meeting a preset condition.
3. The method of claim 2,
when the voice control logic is in the room, the preset range is in the room;
when the voice control logic is outdoors, the preset range is a circle with the position of the voice control logic as the center of the circle and R as the radius, and R is a number greater than 0;
when the voice control logic is in the vehicle or installed in the vehicle, the preset range is in the vehicle.
4. The method of claim 2,
whether only one person exists in the voice control logic preset range is judged, and when only one person exists, the preset conditions are met and comprise:
judging whether only one person exists in a preset range of the voice control logic, if so, determining a user of the artificial voice control logic, and if the voice control logic acquires the voice sent by the user, meeting a preset condition;
alternatively, the first and second electrodes may be,
after the voice sent by the user is obtained, whether only one person exists in the preset range of the voice control logic is judged, and if yes, the preset condition is met.
5. The method of claim 2,
judging whether the user sends an emergency help, if so, meeting the preset conditions comprises:
the voice uttered by the user is acquired,
and judging whether the voice includes emergency help, if so, meeting a preset condition.
6. The method of claim 2, further comprising
And judging whether only one person exists in the preset range of the voice control logic, and when only one person exists, further acquiring voice information, judging whether the acquired voice information is the voice sent by the person in the preset range, and if so, meeting the preset condition.
7. The method of claim 3,
when the preset range is within the vehicle,
and further judging whether the only one person is the driver or not, and if so, meeting the preset condition.
8. The method of claim 2,
judging whether the voice control logic is located in a specific area, if so, meeting the preset conditions comprises the following steps:
and acquiring the voice of the user, judging whether the voice of the user is associated with the specific area, and if so, meeting a preset condition.
9. The method of claim 8,
the pre-establishing of the relevance relationship between the user voice and the specific area and the judging whether the relevance exists between the user voice and the specific area comprises the following steps:
and acquiring a position area where the voice and the voice control logic of the user are located, judging whether the acquired voice and the position area are matched with the pre-established association relation, and if so, meeting the preset condition.
10. The method of claim 1, further comprising
And judging whether the user carries out voice related services, if so, not activating the operation of awakening the voice control logic by the awakening-free word.
11. The method of claim 1, further comprising, prior to obtaining the driver uttered speech, obtaining a voice signal from the driver
And determining whether the user starts the function of the wake-up-free word wake-up voice control logic, and if so, starting the function by the user.
12. The method of claim 1,
and judging whether the acquired voice sent by the user contains a fixed awakening keyword or not, and if not, executing the step of judging whether only one driver exists in the vehicle or not.
13. The method of claim 1,
and if the acquired voice sent by the user contains the fixed awakening keyword, awakening the voice control logic based on the fixed awakening keyword.
14. The method of claim 1,
the operation of activating the wake-free word wake-up voice control logic comprises:
and the voice control logic executes corresponding actions according to the acquired voice.
15. A voice wake-up apparatus, the apparatus comprising:
the acquisition module is used for acquiring the voice sent by the driver;
the judging module is used for judging whether only one driver exists in the vehicle, and if so, the activating module is triggered to activate the wake-up-free word wake-up operation when the voice volume of the driver is greater than or equal to a first preset value; if not, when the voice volume of the driver is larger than or equal to a second preset value, triggering an activation module to activate the wake-up-free word wake-up operation;
the activation module is used for activating the wake-up-free word wake-up voice control logic or not activating the wake-up-free word wake-up voice control logic according to the trigger signal of the judgment module;
the first preset value, the second preset value and the third preset value are preset by a user or are adaptively adjusted according to historical data including volume when the voice control logic wakes up according to the volume, wherein the historical data includes volume when the voice control logic wakes up correctly and volume when the voice control logic wakes up mistakenly.
16. The apparatus of claim 15,
the preset condition for triggering the activation module to activate the wake-up free word wake-up operation further comprises:
judging whether only one person exists in a preset range of the voice control logic, and meeting a preset condition when only one person exists;
and/or the presence of a gas in the gas,
judging whether the user sends an emergency help, if so, meeting a preset condition;
and/or the presence of a gas in the gas,
and judging whether the voice control logic is located in a specific area, if so, meeting a preset condition.
17. The apparatus of claim 16,
when the voice control logic is in the room, the preset range is in the room;
when the voice control logic is outdoors, the preset range is a circle with the position of the voice control logic as the center of the circle and R as the radius, and R is a number greater than 0;
when the voice control logic is in the vehicle or installed in the vehicle, the preset range is in the vehicle.
18. The apparatus of claim 16,
whether only one person exists in the voice control logic preset range is judged, and when only one person exists, the preset conditions are met and comprise:
judging whether only one person exists in a preset range of the voice control logic, if so, determining a user of the artificial voice control logic, and if the voice control logic acquires the voice sent by the user, meeting a preset condition;
alternatively, the first and second electrodes may be,
after the voice sent by the user is obtained, whether only one person exists in the preset range of the voice control logic is judged, and if yes, the preset condition is met.
19. The apparatus of claim 16,
judging whether the user sends an emergency help, if so, meeting the preset conditions comprises:
and judging whether the acquired voice sent by the user includes emergency help, if so, meeting a preset condition.
20. The apparatus of claim 16,
whether only one person exists in the voice control logic preset range is judged, and when only one person exists, the preset conditions are met and comprise:
and judging whether the acquired sound information is the voice sent by the personnel in the preset range, if so, meeting the preset condition.
21. The apparatus of claim 16,
when the preset range is in the vehicle, whether only one person is a driver or not is further judged, and if the driver is the driver, the preset condition is met.
22. The apparatus of claim 16,
judging whether the terminal is located in a specific area, if so, meeting the preset conditions comprises:
and judging whether the voice of the user is associated with the specific area or not, and if so, meeting a preset condition.
23. The apparatus of claim 22,
the method comprises the steps of pre-establishing the relevance relationship between the user voice and the specific area, and judging whether the relevance exists between the user voice and the specific area or not
And judging whether the acquired voice and the position area are matched with the pre-established association relation or not according to the acquired voice of the user and the position area where the voice control logic is located, and if so, meeting the preset condition.
24. The apparatus of claim 15,
the judging module is further used for judging whether the user carries out voice related services, and if yes, the preset condition for triggering the activating module to activate the wake-up-free word wake-up operation is not met.
25. The apparatus of claim 15,
the device also comprises a switch module which is used for the user to select to turn on or turn off the wake-up function of the wake-up-free word; when the user selects to turn on, the function of the voice control logic awakened by the awakening-free word is turned on.
26. The apparatus of claim 15,
the device also comprises a voice detection module which is used for judging whether the acquired voice sent by the user contains a fixed awakening keyword or not, and if not, triggering the judgment module to execute the function of the voice; if yes, the activation module is triggered to not activate the operation of the wake-up-free word wake-up voice control logic.
27. The apparatus of claim 26,
the operation of triggering the activation module to not activate the wake-up exempt word to wake up the voice control logic includes waking up the voice control logic based on the fixed wake-up keyword.
28. A computer device comprising a processor and a memory, the memory storing computer instructions executable by the processor, the computer instructions when executed by the processor implementing the method of any one of claims 1 to 14.
29. A computer-readable storage medium storing computer instructions for implementing the method of any one of claims 1-14.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811261773X | 2018-10-26 | ||
| CN201811261773 | 2018-10-26 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109410952A CN109410952A (en) | 2019-03-01 |
| CN109410952B true CN109410952B (en) | 2020-02-28 |
Family
ID=65457390
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811482267.3A Active CN109410952B (en) | 2018-10-26 | 2018-12-05 | Voice awakening method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109410952B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112017651A (en) * | 2019-05-31 | 2020-12-01 | 百度在线网络技术（北京）有限公司 | Voice control method and device of electronic equipment, computer equipment and storage medium |
| CN110047487B (en) * | 2019-06-05 | 2022-03-18 | 广州小鹏汽车科技有限公司 | Wake-up method and device for vehicle-mounted voice equipment, vehicle and machine-readable medium |
| CN110727821A (en) * | 2019-10-12 | 2020-01-24 | 深圳海翼智新科技有限公司 | Method, apparatus, system and computer storage medium for preventing device from being awoken by mistake |
| CN111145739A (en) * | 2019-12-12 | 2020-05-12 | 珠海格力电器股份有限公司 | Vision-based awakening-free voice recognition method, computer-readable storage medium and air conditioner |
| CN111028846B (en) * | 2019-12-25 | 2022-08-16 | 北京梧桐车联科技有限责任公司 | Method and device for registration of wake-up-free words |
| CN111145749B (en) * | 2019-12-31 | 2023-05-02 | 联想(北京)有限公司 | Control method and control device |
| JP7442331B2 (en) * | 2020-02-05 | 2024-03-04 | キヤノン株式会社 | Voice input device and its control method and program |
| CN111354360A (en) * | 2020-03-17 | 2020-06-30 | 北京百度网讯科技有限公司 | Voice interaction processing method and device and electronic equipment |
| CN111816192A (en) * | 2020-07-07 | 2020-10-23 | 云知声智能科技股份有限公司 | Voice equipment and control method, device and equipment thereof |
| CN112037786A (en) * | 2020-08-31 | 2020-12-04 | 百度在线网络技术（北京）有限公司 | Voice interaction method, device, equipment and storage medium |
| CN113593544A (en) * | 2021-06-11 | 2021-11-02 | 青岛海尔科技有限公司 | Device control method and apparatus, storage medium, and electronic apparatus |
| CN113823062A (en) * | 2021-09-13 | 2021-12-21 | 百度在线网络技术（北京）有限公司 | Emergency rescue method, device, electronic equipment and storage medium |
| CN117275471A (en) * | 2022-06-13 | 2023-12-22 | 华为技术有限公司 | Method for processing voice data and terminal equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103561175A (en) * | 2013-11-05 | 2014-02-05 | 广东欧珀移动通信有限公司 | Method using mobile terminal to carry out voice awakening and device thereof |
| CN103813003A (en) * | 2012-11-15 | 2014-05-21 | 三星电子（中国）研发中心 | Data sharing method of mobile terminal in communication and mobile terminal |
| CN106143452A (en) * | 2016-09-24 | 2016-11-23 | 华北理工大学 | Selectivity acoustic control brake system and method |
| CN106297777A (en) * | 2016-08-11 | 2017-01-04 | 广州视源电子科技股份有限公司 | A kind of method and apparatus waking up voice service up |
| CN107949880A (en) * | 2015-09-09 | 2018-04-20 | 三菱电机株式会社 | Vehicle-mounted speech recognition equipment and mobile unit |
| CN108337362A (en) * | 2017-12-26 | 2018-07-27 | 百度在线网络技术（北京）有限公司 | Voice interactive method, device, equipment and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101441869A (en) * | 2007-11-21 | 2009-05-27 | 联想(北京)有限公司 | Method and terminal for speech recognition of terminal user identification |
| US20160196823A1 (en) * | 2015-01-02 | 2016-07-07 | Atieva, Inc. | Voice Command Activated Vehicle Camera System |
| CN105183081A (en) * | 2015-09-07 | 2015-12-23 | 北京君正集成电路股份有限公司 | Voice control method of intelligent glasses and intelligent glasses |
| CN106775569B (en) * | 2017-01-12 | 2020-02-11 | 环旭电子股份有限公司 | Device position prompting system and method |
-
2018
- 2018-12-05 CN CN201811482267.3A patent/CN109410952B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103813003A (en) * | 2012-11-15 | 2014-05-21 | 三星电子（中国）研发中心 | Data sharing method of mobile terminal in communication and mobile terminal |
| CN103561175A (en) * | 2013-11-05 | 2014-02-05 | 广东欧珀移动通信有限公司 | Method using mobile terminal to carry out voice awakening and device thereof |
| CN107949880A (en) * | 2015-09-09 | 2018-04-20 | 三菱电机株式会社 | Vehicle-mounted speech recognition equipment and mobile unit |
| CN106297777A (en) * | 2016-08-11 | 2017-01-04 | 广州视源电子科技股份有限公司 | A kind of method and apparatus waking up voice service up |
| CN106143452A (en) * | 2016-09-24 | 2016-11-23 | 华北理工大学 | Selectivity acoustic control brake system and method |
| CN108337362A (en) * | 2017-12-26 | 2018-07-27 | 百度在线网络技术（北京）有限公司 | Voice interactive method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109410952A (en) | 2019-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109410952B (en) | Voice awakening method, device and system | |
| CN111512365B (en) | Method and system for controlling multiple home devices | |
| US20230352022A1 (en) | Voice activated device for use with a voice-based digital assistant | |
| US10755706B2 (en) | Voice-based user interface with dynamically switchable endpoints | |
| US10438595B2 (en) | Speaker identification and unsupervised speaker adaptation techniques | |
| CN110310623B (en) | Sample generation method, model training method, device, medium, and electronic apparatus | |
| KR101726945B1 (en) | Reducing the need for manual start/end-pointing and trigger phrases | |
| JP4558074B2 (en) | Telephone communication terminal | |
| CN112074900B (en) | Audio analysis for natural language processing | |
| US11551684B1 (en) | State detection and responses for electronic devices | |
| US9697822B1 (en) | System and method for updating an adaptive speech recognition model | |
| US6584439B1 (en) | Method and apparatus for controlling voice controlled devices | |
| CN111357048A (en) | Method and system for controlling home assistant device | |
| JP2019117623A (en) | Voice dialogue method, apparatus, device and storage medium | |
| CN112313741A (en) | Selective registration with an automated assistant | |
| EP1054389A2 (en) | Method and apparatus for machine to machine communication using speech recognition | |
| US20060074658A1 (en) | Systems and methods for hands-free voice-activated devices | |
| US20140122087A1 (en) | Method and apparatus for activating a particular wireless communication device to accept speech and/or voice commands | |
| US20020193989A1 (en) | Method and apparatus for identifying voice controlled devices | |
| KR102343084B1 (en) | Electronic device and method for executing function of electronic device | |
| EP1054387A2 (en) | Method and apparatus for activating voice controlled devices | |
| JP7250900B2 (en) | Hot word recognition and passive assistance | |
| EP1063636A2 (en) | Method and apparatus for standard voice user interface and voice controlled devices | |
| US20240071408A1 (en) | Acoustic event detection | |
| US20200310523A1 (en) | User Request Detection and Execution |
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 |