CN113808584A - Voice wake-up method and device, electronic equipment and storage medium - Google Patents

Voice wake-up method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN113808584A
CN113808584A CN202110864374.8A CN202110864374A CN113808584A CN 113808584 A CN113808584 A CN 113808584A CN 202110864374 A CN202110864374 A CN 202110864374A CN 113808584 A CN113808584 A CN 113808584A
Authority
CN
China
Prior art keywords
state
screen
voice
electronic device
preset
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
CN202110864374.8A
Other languages
Chinese (zh)
Inventor
马浩
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 Douku Software Technology Co Ltd
Original Assignee
Hangzhou Douku Software 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 Douku Software Technology Co Ltd filed Critical Hangzhou Douku Software Technology Co Ltd
Priority to CN202110864374.8A priority Critical patent/CN113808584A/en
Publication of CN113808584A publication Critical patent/CN113808584A/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
    • G10L15/20—Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech
    • 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
    • G10L17/22—Interactive procedures; Man-machine interfaces
    • 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
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
    • G10L21/0208—Noise filtering
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M1/00—Substation equipment, e.g. for use by subscribers
    • H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
    • H04M1/724—User interfaces specially adapted for cordless or mobile telephones
    • H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
    • H04M1/7243—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality with interactive means for internal management of messages
    • H04M1/72433—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality with interactive means for internal management of messages for voice messaging, e.g. dictaphones
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M1/00—Substation equipment, e.g. for use by subscribers
    • H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
    • H04M1/724—User interfaces specially adapted for cordless or mobile telephones
    • H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
    • H04M1/72454—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions according to context-related or environment-related conditions
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W52/00—Power management, e.g. TPC [Transmission Power Control], power saving or power classes
    • H04W52/02—Power saving arrangements
    • H04W52/0209—Power saving arrangements in terminal devices
    • H04W52/0225—Power saving arrangements in terminal devices using monitoring of external events, e.g. the presence of a signal
    • 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
    • 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
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
    • G10L21/0208—Noise filtering
    • G10L2021/02082—Noise filtering the noise being echo, reverberation of the speech
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M2250/00—Details of telephonic subscriber devices
    • H04M2250/12—Details of telephonic subscriber devices including a sensor for measuring a physical value, e.g. temperature or motion
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M2250/00—Details of telephonic subscriber devices
    • H04M2250/74—Details of telephonic subscriber devices with voice recognition means
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computational Linguistics (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Environmental & Geological Engineering (AREA)
  • Business, Economics & Management (AREA)
  • General Business, Economics & Management (AREA)
  • Quality & Reliability (AREA)
  • Telephone Function (AREA)

Abstract

The application discloses a voice awakening method, a device, an electronic device and a storage medium, wherein the voice awakening method is applied to the electronic device, and can comprise the following steps: acquiring a screen state of the electronic equipment; if the screen state is changed from the screen-off state to the screen-on state, acquiring a voice signal in the environment where the electronic equipment is located; and if the text corresponding to the voice signal comprises the content matched with the preset awakening word, awakening the electronic equipment. The method can be convenient for users to wake up the electronic equipment and reduce the power consumption of the electronic equipment.

Description

Voice wake-up method and device, electronic equipment and storage medium
Technical Field
The present application relates to the field of electronic device technologies, and in particular, to a voice wake-up method and apparatus, an electronic device, and a storage medium.
Background
With the rapid progress of the technology level and the living standard, electronic devices (such as smart phones, tablet computers, and the like) become an indispensable part of the life of people. When the electronic device is used, the electronic device can be woken up by voice wake-up. In the related art, waking up the electronic device by voice requires that the electronic device continuously record and run a wake-up program in an un-woken state, which brings large power consumption to the electronic device.
Disclosure of Invention
In view of the foregoing problems, the present application provides a voice wake-up method, an apparatus, an electronic device, and a storage medium.
In a first aspect, an embodiment of the present application provides a voice wake-up method, which is applied to an electronic device, and the method includes: acquiring a screen state of the electronic equipment; if the screen state is changed from the screen-off state to the screen-on state, acquiring a voice signal in the environment where the electronic equipment is located; and if the text corresponding to the voice signal comprises the content matched with the preset awakening word, awakening the electronic equipment.
In a second aspect, an embodiment of the present application provides a voice wake-up apparatus, which is applied to an electronic device, and the apparatus includes: the device comprises a state acquisition module, a voice acquisition module and a device awakening module, wherein the state acquisition module is used for acquiring the screen state of the electronic device; the voice acquisition module is used for acquiring a voice signal in the environment where the electronic equipment is located if the screen state is changed from the screen-off state to the screen-on state; the equipment awakening module is used for awakening the electronic equipment if the text corresponding to the voice signal comprises content matched with a preset awakening word.
In a third aspect, an embodiment of the present application provides an electronic device, including: one or more processors; a memory; one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the voice wake-up method provided by the first aspect above.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where a program code is stored in the computer-readable storage medium, and the program code may be called by a processor to execute the voice wake-up method provided in the first aspect.
According to the scheme, through obtaining the screen state of the electronic equipment, when the screen state of the electronic equipment is changed from the screen off state to the screen on state, the voice signals in the environment where the electronic equipment is located are collected, and if the text corresponding to the voice signals comprises the content matched with the preset awakening words, the electronic equipment is awakened. The electronic equipment is triggered to execute voice awakening recording and voice recognition when the screen state is changed from off to on, and awakens the electronic equipment when the recognized text comprises the preset awakening words, so that the power consumption of the electronic equipment is reduced.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 shows a flow chart of a voice wake-up method according to an embodiment of the present application.
Fig. 2 shows a schematic diagram of an application scenario of a voice wakeup method provided in an embodiment of the present application.
Fig. 3 shows another schematic diagram of an application scenario of the voice wakeup method provided in the embodiment of the present application.
Fig. 4 shows a flowchart of a voice wake-up method according to another embodiment of the present application.
Fig. 5 shows a flowchart of a voice wake-up method according to another embodiment of the present application.
Fig. 6 shows a flowchart of a voice wake-up method according to yet another embodiment of the present application.
FIG. 7 shows a flowchart of a voice wake-up method according to yet another embodiment of the present application.
Fig. 8 shows a block diagram of a voice wake-up unit according to an embodiment of the present application.
Fig. 9 is a block diagram of an electronic device according to an embodiment of the present application, configured to perform a voice wake-up method according to an embodiment of the present application.
Fig. 10 is a storage unit for storing or carrying program codes for implementing a voice wake-up method according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
With the development of electronic devices, more and more functions can be realized by the electronic devices, and at present, most of the electronic devices can support the function of voice wake-up. In the technology of waking up the electronic device by voice, the electronic device can perform recording, voice recognition and a processing procedure of determining whether to wake up the electronic device according to a recognition result under the condition of dormancy so as to realize the waking up of the electronic device by voice.
Of course, most electronic devices support voice assistants, and the voice assistants have functions of realizing voice control, information query and the like through voice interaction modes such as intelligent conversation, instant question answering and the like. Voice wake-up may also be used for wake-up of a voice assistant, which usually requires the user to wake up, typically by inputting a specific voice wake-up word, such as: the voice helps hand small A voice wake-up word is "he, small A". In the wake-up scheme of the voice assistant, the electronic device is also required to perform recording, voice recognition and a processing procedure of determining whether to wake up the electronic device according to a recognition result, so as to wake up the voice assistant. Therefore, in the voice wakeup schemes of the device and the voice assistant, the electronic device needs to be in a dormant state or the voice assistant needs to be in a dormant state, and the processes of collecting voice, performing voice recognition and determining whether to wake up are performed continuously for a long time, so that large power consumption is brought to the electronic device. In the related art, some electronic devices are additionally provided with chips with low power consumption, so that a voice wake-up processing flow is operated when the electronic devices are in a sleep state or a voice assistant is in the sleep state, so that the power consumption of the electronic devices is reduced, but the cost problem is also caused, and part of the electronic devices can only use a scheme with high power consumption due to the cost problem, and still have high power consumption.
In view of the above problems, the inventor provides a voice wake-up method, a voice wake-up apparatus, an electronic device, and a storage medium, which can trigger execution of voice wake-up recording and voice recognition when a screen of the electronic device is changed from off to on, and wake up the electronic device when a recognized text includes a preset wake-up word, so as to reduce power consumption of the electronic device. The specific voice wake-up method is described in detail in the following embodiments.
Referring to fig. 1, fig. 1 is a flowchart illustrating a voice wake-up method according to an embodiment of the present application. In a specific embodiment, the voice wake-up method is applied to the voice wake-up apparatus 400 shown in fig. 8 and the electronic device 100 (fig. 9) configured with the voice wake-up apparatus 400. The following will describe a specific process of this embodiment by taking an electronic device as an example, and it is understood that the electronic device applied in this embodiment may be a smart phone, a tablet computer, a smart watch, smart glasses, a notebook computer, and the like, which is not limited herein. As will be described in detail with respect to the flow shown in fig. 1, the voice wake-up method may specifically include the following steps:
step S110: and acquiring the screen state of the electronic equipment.
In the embodiment of the application, the electronic device may monitor the screen state thereof to determine whether to trigger the processing flow of voice wakeup according to the screen state. The screen state refers to the working state of a screen of the electronic equipment; the screen state may include a screen-on state and a screen-off state, the screen-on state refers to an operating state when a screen of the electronic device is lit, and the screen-off state refers to an operating state when the screen of the electronic device is extinguished.
In some implementations, the electronic device can obtain the screen state in a variety of ways. Optionally, the operating system reads the corresponding parameter value to determine the screen state of the electronic device according to the read parameter value.
As an implementation manner, when the system installed in the electronic device is an Android (Android) system, the screen state may be obtained by an issscreen on method of PowerManager, that is, by obtaining a value of issscreen on, if the value of issscreen on is true, the screen of the electronic device is in a bright screen state, and if the value of issscreen on is false, the screen of the electronic device is in a screen-off state.
As another embodiment, the electronic device may also determine the screen state of the electronic device by acquiring the brightness value of the screen and according to the brightness value of the screen. For example, if the brightness value of the screen is 0, it indicates that the screen is in the off-screen state, and if the brightness value of the screen is greater than 0, the screen is in the on-screen state.
Of course, the manner of specifically detecting the screen status of the electronic device may not be limiting.
It is understood that the screen state of the electronic device indicates to some extent whether the user uses the electronic device, and therefore, the processing flow of whether to trigger the voice wakeup can be determined based on the screen state of the electronic device.
Step S120: and if the screen state is changed from the screen-off state to the screen-on state, acquiring the voice signal in the environment where the electronic equipment is located.
In the embodiment of the application, after the electronic device obtains the screen state, whether the screen state changes or not can be determined, and if the screen state of the electronic device changes, whether a voice wake-up processing flow is triggered or not can be determined based on the change of the screen state. The electronic equipment can determine whether the screen state is changed from the screen off state to the screen bright state or not based on the screen state; if the screen state of the electronic device changes from the screen-off state to the screen-on state, it indicates that the user may use the electronic device, and there is a possibility of waking up the electronic device. If the screen state of the electronic device is the screen-off state, the processing flow of voice wake-up may not be executed.
In some embodiments, in a case that the screen state changes from the screen-off state to the screen-on state, the electronic device may start to collect a voice signal in an environment where the electronic device is located, and then determine whether to wake up the electronic device according to the collected voice signal. That is to say, before the screen state of the electronic device changes from the screen-off state to the screen-on state, the screen state is the screen-off state, and at this time, the electronic device does not collect the voice signal, so that the voice signal is collected and whether to wake up the electronic device is determined according to the voice signal under the condition that the screen state changes to the screen-on state, and the power consumption of the electronic device is saved. Optionally, after the electronic device starts to collect the voice signal in the environment, the electronic device may continuously collect the voice signal in the environment when the screen is in the bright screen state, so that the user can input voice to wake up the electronic device when the screen of the electronic device is in the bright screen state.
In some embodiments, after the electronic device starts to acquire the voice signal in the environment, the electronic device may continuously acquire the screen state, and after it is determined that the screen state changes from the screen-off state to the screen-on state, the electronic device may also stop acquiring the voice signal in the environment where the electronic device is located when the screen state changes from the screen-on state to the screen-off state, that is, end the processing flow of voice wakeup, so as to reduce the power consumption of the electronic device.
In some embodiments, the change of the screen state of the electronic device from the off-screen state to the bright-screen state may be a user operating the electronic device, so as to trigger the change of the screen state of the electronic device from the off-screen state to the bright-screen state. For example, when the electronic device is in a screen-off state, and a user clicks a power key, the screen state of the electronic device may be triggered to change into a screen-on state; for another example, when the electronic device is in a screen-off state, the user holds the electronic device to lift the electronic device, so that the electronic device detects a lift event and triggers the screen state of the electronic device to change into a screen-on state; for another example, when the electronic device is in the screen-off state, the user inputs a screen-off gesture operation on the screen, and accordingly, the electronic device detects the screen-off gesture operation and controls the screen to be in the screen-on state. Of course, the manner in which the user triggers the screen of the electronic device to change from the off-screen state to the on-screen state may not be limited.
In other embodiments, the screen state of the electronic device changes from the off-screen state to the on-screen state, or the electronic device automatically triggers to change to the on-screen state. Optionally, the electronic device may control the screen to be in a bright screen state when detecting that a reminding event is generated, where the reminding event may be a generated incoming call reminding event, a short message reminding event, or the like, and is not limited herein. Of course, the specific manner of triggering the electronic device to change from the off-screen state to the on-screen state may not be limited.
In some embodiments, the electronic device may be provided with an audio capture device, for example, the electronic device may be provided with a microphone. Under the condition that the electronic equipment determines that the screen state is changed from the screen-off state to the screen-on state, the audio acquisition device can be controlled to acquire the voice signals in the environment where the electronic equipment is located, so that whether the electronic equipment is awakened or not is determined according to the acquired voice signals.
Step S130: and if the text corresponding to the voice signal comprises the content matched with the preset awakening word, awakening the electronic equipment.
In the embodiment of the application, if the electronic device acquires the voice signal, the acquired voice signal can be subjected to voice recognition to obtain the text corresponding to the voice signal. After the text corresponding to the voice signal is obtained, whether the text corresponding to the voice signal includes the content matched with the preset awakening word can be judged, and whether the electronic equipment is awakened or not is determined according to the judgment result. The preset awakening words are awakening words set for awakening the electronic equipment. If the text corresponding to the voice signal is judged to comprise the content matched with the preset awakening word, awakening the electronic equipment; if the text corresponding to the voice signal does not include the content matched with the preset awakening word, the electronic equipment is not awakened.
In some embodiments, the electronic device performs speech recognition on the collected speech signal in a variety of ways. Alternatively, the electronic device may perform speech recognition on the acquired speech signal by using a speech recognition algorithm such as a Dynamic Time Warping (Dynamic Time Warping) based algorithm, a Hidden Markov Model (HMM) based method based on a parametric model, a Vector Quantization (VQ) based on a non-parametric model, and the like. Optionally, the electronic device may also use a pre-trained neural network model to perform speech recognition on the acquired speech signal, where the neural network model may be a convolutional neural network, a deep learning neural network, or the like, and is not limited herein.
In some embodiments, the electronic device may wake up itself when determining that the text corresponding to the voice signal includes content matching a preset wake-up word. Optionally, the electronic device may be awakened when the electronic device is in a sleep state, wherein the electronic device may enter the sleep state when the electronic device is in a screen-saving state, and in some scenarios, the electronic device may also be in the sleep state in a screen-lighting state. For example, when the electronic device is in a bright screen power saving mode and the screen is changed from an off screen state to a bright screen state, the system of the electronic device may not be directly awakened but enters a bright screen sleep mode, and the system time may be updated and displayed on the screen; then the system goes through the same flow as the screen-off dormancy to close various functional devices, and when the screen and the backlight are closed, the screen is normally powered off on a screen driving layer, but the backlight is not closed, the driving returns the false state that the backlight is turned off to the system, the system is still bright actually, and the screen displays the current system time.
Optionally, when the electronic device changes from the screen-off state to the screen-on state, the electronic device may be in the screen-locking state, and at this time, the electronic device is awakened, or the electronic device is unlocked. When the electronic device is in the screen-off state, the electronic device usually enters the screen-locking state, and after the screen-off state is changed into the screen-lighting state, the electronic device still can be in the screen-locking state, and under the condition of being in the screen-locking state, the electronic device can be used after being unlocked.
In a possible implementation manner, if the electronic device is awakened, the electronic device is unlocked, the electronic device can also extract voiceprint features according to the collected voice signals, and if the extracted voiceprint features are matched with preset voiceprint features for unlocking the screen, the screen can be unlocked; and if the extracted voiceprint features are not matched with the preset voiceprint features for unlocking the screen, not unlocking the screen.
In a possible implementation manner, if the electronic device is awakened, the electronic device is unlocked, and in consideration of the security of unlocking the electronic device, when the electronic device determines that the text corresponding to the voice signal includes the content matched with the preset awakening word, user authentication information required for unlocking, such as a face image, may be collected, so as to determine whether to unlock the screen according to the collected user authentication information.
In some embodiments, when the electronic device determines that the text corresponding to the voice signal includes content matching a preset wake-up word, the electronic device is woken up, or a voice assistant of the electronic device is woken up. The voice assistant is an application installed in a system of the mobile terminal, and can realize intelligent interaction through intelligent conversation and instant question and answer, and help a user to solve problems, for example, functions of voice control, information query and the like are realized through voice interaction modes such as intelligent conversation, instant question and answer and the like.
Exemplarily, referring to fig. 2 and fig. 3 simultaneously, fig. 2 and fig. 3 show schematic views of application scenarios of the voice wake-up method provided by the embodiment of the present application, an electronic device may be a smartphone 101, a user may place the smartphone 101 on a desktop, and the smartphone 101 is in a screen-off state after being not operated for a long time and a voice assistant of the smartphone 101 is in a sleep state; after a user touches the screen of the smart phone 101, when the screen of the smart phone 101 is in a bright screen state, the smart phone 101 may collect a voice signal sent by the user, recognize a text corresponding to the voice signal, and wake up a voice assistant of the smart phone 101 when the text includes a preset wake-up word, so as to complete functions of voice control, information query and the like required by the user. Therefore, under the condition that the electronic equipment is changed from the screen-off state to the screen-on state, the voice assistant of the electronic equipment can be awakened by voice, and under the condition that the screen-off state is changed to the screen-on state, the processing flow of voice awakening is executed, so that the power consumption of the electronic equipment can be reduced.
According to the voice awakening method provided by the embodiment of the application, when the screen state of the electronic equipment is changed from off to on, the electronic equipment triggers and executes voice awakening recording and voice recognition, and when the recognized text comprises the preset awakening words, the electronic equipment is awakened, so that the voice awakening processing flow cannot be triggered under other conditions, and the power consumption of the electronic equipment is reduced. Moreover, under the condition of not increasing hardware cost, the power consumption of the electronic equipment is reduced while voice awakening is realized.
Referring to fig. 4, fig. 4 is a flowchart illustrating a voice wake-up method according to another embodiment of the present application. The voice wake-up method is applied to the electronic device, and will be described in detail with respect to the flow shown in fig. 4, where the voice wake-up method specifically includes the following steps:
step S210: and acquiring the screen state of the electronic equipment.
Step S220: and if the screen state is changed from the screen-off state to the screen-on state, acquiring the voice signal in the environment where the electronic equipment is located.
In the embodiment of the present application, step S210 and step S220 may refer to the contents of the foregoing embodiments, and are not described herein again.
Step S230: and if the screen state is the screen off state, detecting the equipment state of the preset type of the electronic equipment, wherein the equipment state at least comprises pose information and a generated real-time reminding event.
In the embodiment of the application, after the electronic device obtains the screen state, if the screen state is the screen off state, the device state of the preset type of the electronic device may be detected, so as to determine whether to trigger the voice wake-up processing flow under the condition that the screen of the electronic device is off according to the detected device state. The preset type of device state may include pose information and generated real-time reminder events, wherein the pose information may include electronic device position and pose; the real-time reminding event can comprise a call reminding event, a short message reminding event, an application notice, an alarm clock reminding and other reminding events. It can be understood that, under the condition that the screen of the electronic device is in the screen-off state, if the pose information of the electronic device meets the corresponding pose condition or generates the corresponding real-time reminding event, the possibility that the user uses the electronic device is also high at this time, so that when the screen state is in the screen-off state, the above device states of the electronic device can be detected to determine whether to trigger the processing flow of voice wakeup.
In some embodiments, a sensor for detecting pose information may be provided in the electronic device, so that the electronic device may detect the pose information through the above sensor in a case where it is determined that the screen state is the screen-off state. The sensor for detecting pose information may be an accelerometer, a gyroscope, or the like, which is not limited herein.
In some embodiments, the generated real-time reminder event obtained by the electronic device may be a real-time reminder event generated within a first time period from the current time, for example, a real-time reminder event generated within five minutes from the current time. Therefore, whether the voice awakening process is triggered or not can be determined according to the real-time reminding event in a short time, the habit that a user uses voice awakening based on the real-time reminding event is more met, and the phenomenon that the power consumption of the electronic equipment is increased due to the fact that the long real-time reminding event triggers the voice awakening process is avoided.
In a possible implementation manner, the real-time reminding event acquired by the electronic device may be a reminding event that is not viewed by the user within a first time length from the current time. It can be understood that if the user has checked the generated real-time reminding event, the possibility that the user uses voice wakeup based on the real-time reminding event is low, so that the real-time reminding event that the user has checked can be eliminated, the accuracy of triggering voice wakeup is improved, and the power consumption of the electronic device is reduced.
Step S240: and if at least one state in the equipment states meets the corresponding preset state condition, acquiring the voice signal in the environment where the electronic equipment is located.
In this embodiment of the application, the preset state condition may be a condition that is set for each device state and can trigger a processing procedure of voice wakeup in a preset screen-off state. If any one of the device states of the electronic device meets the preset state condition corresponding to the state, it can indicate that the user has a high possibility of using the electronic device at the moment, and therefore, a voice wake-up process can be triggered, that is, voice signals of the environment where the user is located are collected, and whether to wake up the electronic device is determined according to the collected voice signals. That is to say, the above device states include a plurality of states such as pose information and real-time reminding events, and when any one of the plurality of states satisfies a corresponding preset state condition, a voice wake-up processing flow can be triggered. If any one of the device states of the electronic device does not satisfy the corresponding preset state condition, it indicates that the user has a low possibility of waking up the electronic device currently, and therefore the voice wake-up process may not be triggered.
In some embodiments, the preset state condition corresponding to the pose information may include: the pose information meets the preset pose condition. The preset pose condition can trigger pose information corresponding to the behavior event of the voice awakening processing flow.
Optionally, the preset pose condition may include: the preset pose condition may also be defined by the user, and is not limited herein, such as pose information when the electronic device is lifted, pose information when the portable electronic device is in a walking state, and pose information when the portable electronic device is in a running state.
It can be understood that if the pose information of the electronic device matches the pose information when lifted, it indicates that the user has a high possibility of waking up the electronic device using voice currently, and therefore may trigger a processing procedure of voice wake-up. If the pose information of the electronic equipment is matched with the pose information of the portable electronic equipment in a walking state or matched with the pose information of the portable electronic equipment in a running state, the user is inconvenient to operate the electronic equipment at the moment, so the possibility of waking up the electronic equipment by using voice is high, a voice waking processing flow can be triggered, for example, when the user runs by carrying an intelligent watch, the user is inconvenient to directly operate the intelligent watch by hand, and therefore, a voice assistant of the electronic equipment can be waken up in a voice waking mode to operate the electronic equipment required by the user.
In some embodiments, the preset state condition corresponding to the real-time reminding event may include: the generated real-time reminding event is matched with a preset reminding event. The preset reminding event can be a preset reminding event for triggering a voice awakening processing flow.
Optionally, the preset reminding event may include: the preset reminding event can also be defined by the user, and is not limited herein. It can be understood that when a reminding event such as an incoming call reminding event, a short message reminding event, an application notification, etc. is generated, a user may operate the electronic device at a high probability and check the reminding event, so that the possibility of waking up the electronic device by using a voice wake-up mode is high, and a voice wake-up processing flow can be triggered. For example, when the electronic device generates a short message reminding event, the electronic device may turn on the screen and perform prompt, but the user may not have time to view the short message reminding event, so that after the screen is turned off, the voice wake-up process may be continuously triggered according to the short message reminding event, so as to meet the requirement that the user needs to wake up the electronic device through voice to obtain information corresponding to the short message reminding event.
Step S250: and if the text corresponding to the voice signal comprises the content matched with the preset awakening word, awakening the electronic equipment.
In the embodiment of the present application, the step S250 may refer to the contents of the foregoing embodiments, and is not described herein again.
According to the voice awakening method provided by the embodiment of the application, when the screen state of the electronic equipment is changed from the screen-off state to the screen-on state, the electronic equipment can be triggered to execute voice awakening recording and voice recognition, when the recognized text comprises the preset awakening words, the electronic equipment is awakened, and under the condition that the screen state is the screen-off state, if the acquired equipment state of the preset type meets the preset state condition, the processing flow of voice awakening is also triggered to execute, so that the requirement that a user needs to awaken the electronic equipment in a voice awakening mode is met, and the power consumption of the electronic equipment is also reduced.
Referring to fig. 5, fig. 5 is a flowchart illustrating a voice wake-up method according to another embodiment of the present application. The voice wake-up method is applied to the electronic device, and will be described in detail with respect to the flow shown in fig. 5, where the voice wake-up method specifically includes the following steps:
step S310: and acquiring the screen state of the electronic equipment.
In the embodiment of the present application, the step S310 may refer to the contents of the foregoing embodiments, and is not described herein again.
Step S320: and if the screen state is changed from the screen-off state to the screen-on state, acquiring the voice signal in the environment where the electronic equipment is located.
In the embodiment of the application, after the electronic device determines that the screen state is changed from the screen off state to the screen on state, and starts to collect the voice signal in the environment where the electronic device is located, the electronic device may collect the voice signal in the environment where the electronic device is located within the second time period, and determine whether to wake up the electronic device according to the collected voice signal. It can be understood that, when the screen state of the electronic device changes from the off-screen state to the on-screen state, the user usually performs voice wakeup by triggering the screen to be on-screen, and when the screen state of the electronic device is in the on-screen state, if the processing flow of voice wakeup is performed all the time, a larger power consumption is brought, so that the electronic device can execute the processing flow of voice wakeup within the second duration when determining that the screen state changes from the off-screen state to the on-screen state, thereby reducing the power consumption of the electronic device.
In some embodiments, the second duration may be determined according to a recorded duration from each detection of the bright screen to each triggering of the voice wakeup by the user. The electronic equipment records the time when the screen extinguishing state is changed into the screen lightening state every time and the time between the time when the distance is awakened to the electronic equipment through voice, and the electronic equipment can determine the use habits of the user in different time periods according to the recorded time at every time so as to set different second time periods in different time periods. Optionally, the electronic device may learn through a deep learning neural network according to the recorded time length each time and the time period to which the voice wakeup is triggered each time, so as to obtain a second time length which is not set corresponding to the time period. Optionally, the electronic device may also count the average duration corresponding to different time periods according to the duration recorded each time in a statistical manner, so as to obtain a second duration corresponding to a habit of the user to perform voice wakeup on the electronic device.
In some embodiments, before determining that the screen state changes from the off-screen state to the on-screen state and starting to collect the voice signals in the environment where the electronic device is located, the electronic device may further determine whether the current user is presentAt the position ofTime period capable of voice awakening；If the user is in the time period capable of voice awakening, the user can start to collect the voice signals in the environment where the user is located, and if the user is not in the time period capable of voice awakening, the voice awakening processing flow is not required, namely the voice signals are not collected and whether the electronic equipment is awakened or not is determined according to the collected voice signals, so that whether the voice awakening processing flow is triggered or not can be controlled more accurately, and the power consumption of the electronic equipment is further reduced. Optionally, schedule information of the user may be acquired, and according to the schedule information, it is determined whether the user performs a target behavior in a time period to which the current time belongs, if the target behavior is being performed, it indicates that the current time belongs to a time period in which voice wakeup is not possible, and if the user does not perform the target behavior in the time period to which the previous time belongs, it indicates that the current time belongs to a time period in which voice wakeup is possible. The target behavior can be that the user inconveniently wakes up the electronic equipment by voice in meeting, classroom teaching, work and the likeActs, are not limited herein.
In some embodiments, after determining that the screen state changes from the screen-off state to the screen-on state and starting to collect the voice signals in the environment where the electronic device is located, the electronic device may further determine the volume of the environmental sound according to the start of collecting the voice signals within the specified time duration; if the volume of the environmental sound is larger than the volume threshold, the electronic equipment is not suitable for being awakened by voice currently, at the moment, the electronic equipment can not execute the subsequent flow of determining whether to awaken the electronic equipment or not according to the acquired voice signal, and prompt information is displayed on a screen to prompt that the current voice awakening mode is not started; if the volume of the environmental sound is not greater than the volume threshold, the electronic equipment is suitable to be awakened by voice currently, so that voice signals can be collected continuously, and whether the electronic equipment is awakened or not is determined according to the collected voice signals.
In a possible implementation manner, the electronic device may also determine the number of sound sources in the environmental sound according to the start of collecting the voice signals within the specified duration, and when the number of sound sources is greater than the number threshold, it indicates that it is currently not suitable to wake up the electronic device by using voice, and at this time, the electronic device may not perform a subsequent process of determining whether to wake up the electronic device according to the collected voice signals, and display a prompt message on a screen to prompt that the current voice wake-up mode is not started; if the number of the sound sources is not larger than the number threshold, the electronic equipment is suitable to be awakened by voice currently, so that voice signals can be collected continuously, and whether the electronic equipment is awakened or not is determined according to the collected voice signals.
Step S330: and if the screen state is the screen off state, detecting the equipment state of the preset type of the electronic equipment, wherein the equipment state at least comprises pose information and a generated real-time reminding event.
In the embodiment of the present application, step S330 may refer to the contents of the foregoing embodiments, and is not described herein again.
Step S340: and if the equipment state meets the preset state condition, acquiring the voice signal in the environment where the electronic equipment is located within a preset time.
In the embodiment of the application, when the electronic device determines that the preset type of device state of the electronic device meets the preset state condition when the screen state is the off-screen state, a processing flow of voice wakeup can be executed within the preset duration, that is, a voice signal in an environment where the electronic device is located is collected within the preset duration, and if a text corresponding to the voice signal includes content matched with the preset wakeup word, the electronic device is awakened. Therefore, the processing flow of voice awakening can be executed within the preset duration, and the power consumption of the electronic equipment is reduced.
In some embodiments, the preset durations may be different for different pose information satisfying the preset pose condition and different real-time reminding events matching the preset reminding event. For example, if the pose information matches the pose information of the walking state, the voice signal in the environment where the electronic device is located may be collected during the whole walking state, and if the text corresponding to the voice signal includes the content matching the preset wake-up word, the electronic device may be woken up. For another example, if the pose information matches the pose information of the wrist lifting event, it is determined that the wrist lifting event is detected, a voice signal in an environment where the electronic device is located may be collected within one minute after the wrist lifting event is detected, and the electronic device is awakened if a text corresponding to the voice signal includes content matching a preset awakening word. For another example, if the real-time reminding event matched with the preset reminding event is an incoming call reminding event, a voice signal in the environment where the electronic device is located can be collected within 5 minutes after the incoming call reminding event is generated, and if the text corresponding to the voice signal includes content matched with the preset awakening word, the electronic device is awakened, so that the incoming call event can be generated, but the user does not get ready to answer, and the screen becomes an off state, at this time, the user can be awakened by voice within 5 minutes, so that a contact-free incoming call reply can be realized.
In some embodiments, the electronic device may record a distance between a time when the user triggers voice wakeup each time and a time when the state of the device is detected to meet a preset state condition, so as to determine, according to the recorded time each time, different pose information meeting the preset pose condition and different real-time reminding events matched with the preset reminding events, corresponding to the preset time. Optionally, the electronic device may learn through a deep learning neural network according to the time length recorded each time, and the pose information and the real-time reminding event that satisfy the device state condition each time, so as to obtain preset time lengths corresponding to different pose information that satisfy the preset pose condition and different real-time reminding events that match the preset reminding event. Optionally, the electronic device may also count different pose information meeting the preset pose condition and different real-time reminding events matched with the preset reminding events according to the recorded duration each time in a statistical manner, and the corresponding average duration is taken as the preset duration.
In some embodiments, if the device state of the electronic device meets the preset state condition, in order to match the generated real-time reminding event with the preset reminding event, the electronic device may further obtain schedule information of the user to determine the current state of the user, and then determine the preset duration according to the state of the user. The determined preset duration may correspond to a state of the user. For example, if the user is in a conference state, the user cannot respond to the real-time reminding event for a long time, and therefore the voice wake-up processing flow can be executed in a relatively short time, so as to save power consumption. For another example, if the state of the user is a driving state, the preset duration may be relatively long, so that the user can wake up the electronic device quickly in a voice wake-up manner when stopping driving, and view the generated real-time reminding event.
Step S350: and if the text corresponding to the voice signal comprises the content matched with the preset awakening word, awakening the electronic equipment.
In the embodiment of the present application, step S550 may refer to the contents of other embodiments, which are not described herein again.
The voice awakening method provided by the embodiment of the application is different from the previous embodiment in that when the electronic device is in a screen-off state and the state of the preset type device meets the preset state condition, the collection of the voice signal of the environment is executed within the preset time length, and whether the electronic device is awakened or not is determined according to the collected voice signal, so that the processing flow of executing the voice awakening within the preset time length can be realized, and the power consumption of the electronic device is reduced.
Referring to fig. 6, fig. 6 is a flowchart illustrating a voice wake-up method according to still another embodiment of the present application. The voice wake-up method is applied to the electronic device, and will be described in detail with respect to the flow shown in fig. 6, where the voice wake-up method specifically includes the following steps:
step S410: and acquiring the screen state of the electronic equipment.
Step S420: and if the screen state is changed from the screen-off state to the screen-on state, acquiring the voice signal in the environment where the electronic equipment is located.
In the embodiment of the present application, step S410 and step S420 may refer to the contents of the foregoing embodiments, and are not described herein again.
Step S430: and if the text corresponding to the voice signal comprises the content matched with the preset awakening word, awakening the voice assistant of the electronic equipment.
In the embodiment of the application, the electronic equipment can be awakened by a voice assistant of the electronic equipment, so that the user can realize the functions of voice control, information query and the like through voice interaction modes such as intelligent conversation, instant question and answer and the like.
Step S440: and collecting the input control voice.
In the embodiment of the application, after the voice assistant of the electronic device is awakened, the control voice input by the user can be further collected, so that the voice assistant can execute corresponding control according to the control voice input by the user.
Step S450: and if the control voice is used for a control scene behind the screen to be unlocked, acquiring input unlocking information.
In the embodiment of the application, the electronic device is usually in the screen locking state when being in the screen extinguishing state, and after the screen of the electronic device is changed from the screen extinguishing state to the screen lightening state, if the voice assistant is awakened, the electronic device is still in the screen locking state at the moment. If the voice assistant is in the awakening state, the current control voice is recognized to be used for a control scene behind the screen to be unlocked according to the input control voice, namely, the scene which can be controlled after the screen is unlocked, the operation of the user can be detected, the unlocking information input by the user is obtained, and the electronic equipment is unlocked according to the unlocking information. The unlocking information may be password information, face image, fingerprint information, and the like, which is not limited herein.
In some embodiments, the control scenario for the unlocked state may include: the scenario of running the target application, the scenario of using a function that the electronic device can use in the unlocked state, querying a file stored in the electronic device, and the like are not limited herein, and may also be other scenarios that can be realized only when the electronic device needs to be in the unlocked state.
In some embodiments, if the control voice is used for the control executable in the lock screen state, the corresponding control may be executed in response to the control voice. For example, if the control voice is used for inquiring and broadcasting the system time, inquiring and broadcasting the weather, inquiring and broadcasting the electric quantity and other scenes, and the control which can be executed only after the screen is unlocked is not needed, therefore, the corresponding control can be directly executed according to the control voice.
Step S460: and if the unlocking information is matched with preset verification information, controlling the electronic equipment to unlock, and then executing control corresponding to the control voice.
In the embodiment of the application, if the acquired unlocking information is matched with the preset verification information, the electronic equipment can be controlled to unlock. The preset verification information is preset verification information used for unlocking a screen, the preset verification information is matched with the type of the unlocking information, for example, the unlocking information is password information, the preset verification information is a preset unlocking password, for example, the unlocking information is a face image, the preset verification information is a face image which is input in advance, for example, the unlocking information is fingerprint information, and the preset verification information is fingerprint data which is input in advance.
After the electronic device is controlled to be unlocked, the control corresponding to the control voice can be executed in response to the control voice. For example, when the above control scenario is a scenario in which a music application is executed and music is played, the music application may be executed and a corresponding song may be played after the electronic device is controlled to be unlocked.
In some embodiments, multiple voice assistants may be installed in an electronic device. The plurality of voice assistants may include: a system voice assistant, a voice assistant for a third party application, etc. When the electronic equipment wakes up the voice assistant, the electronic equipment can wake up the system voice assistant; when recognizing the input control voice, the system voice assistant may first recognize a keyword that includes an application program in the control voice, and when recognizing that the control voice input by the user includes a keyword of a target application, the system voice assistant indicates that the control voice is controlling the target application, wherein the target application is an application having a corresponding voice assistant; in this case, the system voice assistant may not recognize what kind of control is for the target application, so the control voice may be handed over to the voice assistant of the target application for processing to achieve the control for the target application; if the control voice input by the user is recognized not to contain the keywords of the target application, the system voice assistant can further recognize specific control operation to complete the control required by the user. Through the implementation mode, the system voice assistant can be awakened under the condition that the electronic equipment is provided with the plurality of voice assistants, but not all the voice assistants, so that the power consumption of the electronic equipment is saved, and the cruising ability of the electronic equipment is improved.
The voice awakening method provided by the embodiment of the application is different from the embodiment in that after the voice assistant is awakened, if the collected control voice is used for a control scene behind a screen to be unlocked, unlocking information needs to be input by a user, and after the electronic equipment is unlocked, corresponding control can be realized, so that the control which can be performed in an unlocking state by using the voice assistant after the voice assistant of the electronic equipment is awakened is effectively avoided, and the safety is ensured.
Referring to fig. 7, fig. 7 is a flowchart illustrating a voice wake-up method according to yet another embodiment of the present application. The voice wake-up method is applied to the electronic device, and will be described in detail with respect to the flow shown in fig. 7, where the voice wake-up method specifically includes the following steps:
step S510: and acquiring the screen state of the electronic equipment.
Step S520: and if the screen state is changed from the screen-off state to the screen-on state, acquiring the voice signal in the environment where the electronic equipment is located.
In the embodiment of the present application, step S510 and step S520 may refer to the contents of the foregoing embodiments, and are not described herein again.
Step S530: and if the electronic equipment is in the state of playing the audio, carrying out echo cancellation on the voice signal based on the audio played by the electronic equipment.
In the embodiment of the application, after the electronic device collects the voice signal in the environment, if the electronic device is in a state of playing the audio, the audio played by the electronic device may affect waking up the electronic device by the voice, that is, interfere with waking up the electronic device by the voice. Therefore, the electronic equipment can also acquire the audio played by the electronic equipment so as to perform echo cancellation on the collected voice signal according to the audio played by the electronic equipment.
In some embodiments, the electronic device may obtain the audio played by each speaker, then generate an echo portion by simulation according to the audio played by each speaker, and then cancel the echo in the collected voice signal by using the echo portion generated by simulation. The electronic equipment can be additionally provided with a return channel, and the data of the return channel is matched with the number of the speakers, so that the audio played by each speaker can be acquired.
Step S540: and matching the text corresponding to the voice signal with which the echo is eliminated with the preset awakening word.
Step S550: and if the text corresponding to the voice signal comprises the content matched with the preset awakening word, acquiring the voiceprint characteristic corresponding to the voice signal as a target voiceprint characteristic.
In the embodiment of the application, if the text corresponding to the voice signal includes content matched with the preset wake-up word, the electronic device may further perform verification to prevent a non-user from waking up the electronic device. The electronic equipment can perform voiceprint recognition on the voice signals, obtain voiceprint characteristics corresponding to the voice signals and use the voiceprint characteristics as target voiceprint characteristics, and conduct identity verification according to the target voiceprint characteristics.
Step S560: and if the target voiceprint characteristics are matched with the preset voiceprint characteristics, awakening the electronic equipment.
In this embodiment of the application, the preset voiceprint feature is a preset voiceprint feature of a user that can wake up the electronic device. After the electronic device obtains the target voiceprint feature, the target voiceprint feature can be matched with a preset voiceprint feature, and if the target voiceprint feature is matched with the preset voiceprint feature, the user currently inputting the voice signal is a user capable of waking up the electronic device, so that the electronic device can be woken up; if the target voiceprint feature is not matched with the preset voiceprint feature, the user who inputs the voice signal currently is not the user who can wake up the electronic device, so that the voice signal collected at this time can be ignored, and the electronic device is not woken up.
In some embodiments, the electronic device may be provided with a play status monitoring module, a recording module (including a reference tone), an Acoustic Echo Cancellation (AEC) module, a wake-up word detection module, a depth check module (voiceprint check, etc.), and a trigger module. When the play state monitoring module determines that self-play audio exists, the recording module can start recording with reference sound, a return module of the reference sound (played by a loudspeaker) is added in audio drive, the number of return channels is equal to that of the loudspeaker, and microphone channel sound and loudspeaker channel sound are sent to the AEC module; then the AEC module performs echo cancellation according to the acquired audio, and after the echo is cancelled, the audio can be input to the awakening word detection module; the awakening word detection module detects awakening words according to the audio frequency; and under the condition that the awakening word is detected, the voiceprint detection module further performs voiceprint verification, and after the voiceprint verification is performed, if the voiceprint verification passes, the module is triggered to control to awaken the electronic equipment.
The voice awakening method provided by the embodiment of the application is different from the embodiment in that under the condition that the voice signals in the environment are collected, if the electronic equipment is in an audio playing state, echo cancellation is performed on the collected voice signals, and after echo cancellation, whether the preset awakening words are included or not is identified, so that the accuracy of voice awakening of the electronic equipment is effectively improved. In addition, under the condition that the preset awakening words are identified, voiceprint verification is further performed according to the collected voice signals, so that the electronic equipment is prevented from being awakened illegally, and the safety of the electronic equipment is guaranteed.
Referring to fig. 8, a block diagram of a voice wake-up apparatus 400 according to an embodiment of the present application is shown. The voice wake-up apparatus 400 is applied to the electronic device, and the voice wake-up apparatus 400 includes: a status acquisition module 410, a voice acquisition module 420, and a device wake-up module 430. The state acquiring module 410 is configured to acquire a screen state of the electronic device; the voice collecting module 420 is configured to collect a voice signal in an environment where the electronic device is located if the screen status changes from a screen-off status to a screen-on status; the device wake-up module 430 is configured to wake up the electronic device if the text corresponding to the voice signal includes content matched with a preset wake-up word.
In some embodiments, the state obtaining module 410 may be further configured to, after obtaining the screen state of the electronic device, detect a preset type of device state of the electronic device if the screen state is an off-screen state, where the device state at least includes pose information and a generated real-time reminding event. If at least one of the device states satisfies a corresponding preset state condition, the voice acquisition module 420 may acquire a voice signal in an environment where the electronic device is located; if the text corresponding to the voice signal includes content matched with a preset wake-up word, the device wake-up module 430 wakes up the electronic device.
In a possible implementation manner, the preset state condition corresponding to the pose information includes:
the pose information meets a preset pose condition;
the preset state conditions corresponding to the real-time reminding events comprise:
and the real-time reminding event is matched with a preset reminding event.
In a possible implementation manner, the device state satisfies a preset state condition, and the voice collecting module 420 may collect a voice signal in an environment where the electronic device is located; if the text corresponding to the voice signal includes content matched with a preset wake-up word, the device wake-up module 430 wakes up the electronic device, which may include: and if the equipment state meets the preset state condition, executing the acquisition of the voice signal in the environment where the electronic equipment is located within a preset time length, and if the text corresponding to the voice signal comprises the content matched with a preset awakening word, awakening the electronic equipment.
In some embodiments, the voice wake-up apparatus 400 may further include a collection termination module. The acquisition termination module is used for stopping acquiring the voice signals in the environment where the electronic equipment is located when the screen state is changed from the bright screen state to the off screen state.
In some embodiments, the device wake-up module 430 may be configured to: waking a voice assistant of the electronic device.
In a possible implementation, the device wake-up apparatus 400 may further include an unlocking information obtaining module and a screen unlocking module. The voice collecting module 420 can also be used for collecting the input control voice after the voice assistant awakening the electronic equipment; the unlocking information acquisition module is used for acquiring input unlocking information if the control voice is used for a control scene behind a screen to be unlocked; and the screen unlocking module is used for controlling the electronic equipment to unlock and then executing control corresponding to the control voice if the unlocking information is matched with preset verification information.
In some embodiments, the device wake-up module 430 may be configured to: if the text corresponding to the voice signal comprises content matched with a preset awakening word, acquiring voiceprint features corresponding to the voice signal as target voiceprint features; and if the target voiceprint characteristics are matched with the preset voiceprint characteristics, awakening the electronic equipment.
In some embodiments, the voice wake-up apparatus 400 may further include an echo cancellation module and a matching module. The echo cancellation module is used for performing echo cancellation on the voice signal based on the audio played by the electronic equipment if the electronic equipment is in the audio playing state before the electronic equipment is awakened if the text corresponding to the voice signal comprises the content matched with the preset awakening word; and the matching module is used for matching the text corresponding to the voice signal after the echo is eliminated with the preset awakening word.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and modules may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, the coupling between the modules may be electrical, mechanical or other type of coupling.
In addition, functional modules in the embodiments of the present application may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.
To sum up, according to the scheme provided by the application, when the screen state of the electronic device is changed from the screen-off state to the screen-on state by acquiring the screen state of the electronic device, the voice signal in the environment where the electronic device is located is acquired, and if the text corresponding to the voice signal includes the content matched with the preset awakening word, the electronic device is awakened. Because the electronic equipment triggers and executes voice awakening recording and voice recognition when the screen state is changed from off to on, and awakens the electronic equipment when the recognized text comprises the preset awakening words, the power consumption of the electronic equipment is reduced.
Referring to fig. 9, a block diagram of an electronic device according to an embodiment of the present application is shown. The electronic device 100 may be an electronic device capable of running an application, such as a smart phone, a tablet computer, a smart watch, smart glasses, and a notebook computer. The electronic device 100 in the present application may include one or more of the following components: a processor 110, a memory 120, and one or more applications, wherein the one or more applications may be stored in the memory 120 and configured to be executed by the one or more processors 110, the one or more programs configured to perform a method as described in the aforementioned method embodiments.
Processor 110 may include one or more processing cores. The processor 110 connects various parts within the overall electronic device 100 using various interfaces and lines, and performs various functions of the electronic device 100 and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 120 and calling data stored in the memory 120. Alternatively, the processor 110 may be implemented in hardware using at least one of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 110 may integrate one or more of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a modem, and the like. Wherein, the CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing display content; the modem is used to handle wireless communications. It is understood that the modem may not be integrated into the processor 110, but may be implemented by a communication chip.
The Memory 120 may include a Random Access Memory (RAM) or a Read-Only Memory (Read-Only Memory). The memory 120 may be used to store instructions, programs, code sets, or instruction sets. The memory 120 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing various method embodiments described below, and the like. The data storage area may also store data created by the electronic device 100 during use (e.g., phone book, audio-video data, chat log data), and the like.
Referring to fig. 10, a block diagram of a computer-readable storage medium according to an embodiment of the present application is shown. The computer-readable medium 800 has stored therein a program code that can be called by a processor to execute the method described in the above-described method embodiments.
The computer-readable storage medium 800 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. Alternatively, the computer-readable storage medium 800 includes a non-volatile computer-readable storage medium. The computer readable storage medium 800 has storage space for program code 810 to perform any of the method steps of the method described above. The program code can be read from or written to one or more computer program products. The program code 810 may be compressed, for example, in a suitable form.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not necessarily depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.

Claims (12)

1. A voice wake-up method is applied to an electronic device, and comprises the following steps:
acquiring a screen state of the electronic equipment;
if the screen state is changed from the screen-off state to the screen-on state, acquiring a voice signal in the environment where the electronic equipment is located;
and if the text corresponding to the voice signal comprises the content matched with the preset awakening word, awakening the electronic equipment.
2. The method of claim 1, wherein after the obtaining the screen state of the electronic device, the method further comprises:
if the screen state is the screen-off state, detecting a preset type of equipment state of the electronic equipment, wherein the equipment state at least comprises pose information and a generated real-time reminding event;
and if at least one state in the equipment states meets the corresponding preset state condition, executing the acquisition of the voice signal in the environment where the electronic equipment is located, and if the text corresponding to the voice signal comprises the content matched with a preset awakening word, awakening the electronic equipment.
3. The method according to claim 2, wherein the preset state condition corresponding to the pose information comprises:
the pose information meets a preset pose condition;
the preset state conditions corresponding to the real-time reminding events comprise:
and the real-time reminding event is matched with a preset reminding event.
4. The method according to claim 2, wherein the acquiring a voice signal in an environment where the electronic device is located if the device status satisfies the preset status condition, and the waking up the electronic device if the text corresponding to the voice signal includes content matching a preset wake-up word comprises:
and if the equipment state meets the preset state condition, executing the acquisition of the voice signal in the environment where the electronic equipment is located within a preset time length, and if the text corresponding to the voice signal comprises the content matched with a preset awakening word, awakening the electronic equipment.
5. The method according to claim 1, wherein after the collecting the voice signal in the environment where the electronic device is located if the screen state changes from the screen-off state to the screen-on state, the method further comprises:
and when the screen state is changed from the bright screen state to the screen-off state, stopping collecting the voice signals in the environment where the electronic equipment is located.
6. The method of claim 1, wherein waking up the electronic device comprises:
waking a voice assistant of the electronic device.
7. The method of claim 6, wherein after the waking of the voice assistant of the electronic device, the method further comprises:
collecting input control voice;
if the control voice is used for a control scene behind a screen to be unlocked, acquiring input unlocking information;
and if the unlocking information is matched with preset verification information, controlling the electronic equipment to unlock, and then executing control corresponding to the control voice.
8. The method according to any one of claims 1 to 7, wherein the waking up the electronic device if the text corresponding to the voice signal includes content matched with a preset wake-up word comprises:
if the text corresponding to the voice signal comprises content matched with a preset awakening word, acquiring voiceprint features corresponding to the voice signal as target voiceprint features;
and if the target voiceprint characteristics are matched with the preset voiceprint characteristics, awakening the electronic equipment.
9. The method according to any one of claims 1 to 7, wherein before the waking up the electronic device if the text corresponding to the voice signal includes content matching a preset wake-up word, the method further comprises:
if the electronic equipment is in a state of playing audio, echo cancellation is carried out on the voice signal based on the audio played by the electronic equipment;
and matching the text corresponding to the voice signal with which the echo is eliminated with the preset awakening word.
10. A voice wake-up device applied to an electronic device, the device comprising: a state acquisition module, a voice acquisition module and an equipment awakening module, wherein,
the state acquisition module is used for acquiring the screen state of the electronic equipment;
the voice acquisition module is used for acquiring a voice signal in the environment where the electronic equipment is located if the screen state is changed from the screen-off state to the screen-on state;
the equipment awakening module is used for awakening the electronic equipment if the text corresponding to the voice signal comprises content matched with a preset awakening word.
11. An electronic device, comprising:
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the method of any of claims 1-9.
12. A computer-readable storage medium, having stored thereon program code that can be invoked by a processor to perform the method according to any one of claims 1 to 9.
CN202110864374.8A 2021-07-29 2021-07-29 Voice wake-up method and device, electronic equipment and storage medium Pending CN113808584A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110864374.8A CN113808584A (en) 2021-07-29 2021-07-29 Voice wake-up method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110864374.8A CN113808584A (en) 2021-07-29 2021-07-29 Voice wake-up method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN113808584A true CN113808584A (en) 2021-12-17

Family

ID=78942607

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110864374.8A Pending CN113808584A (en) 2021-07-29 2021-07-29 Voice wake-up method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113808584A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114786080A (en) * 2022-04-21 2022-07-22 维沃移动通信有限公司 Microphone control method and device, electronic equipment and readable storage medium

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130080178A1 (en) * 2011-09-26 2013-03-28 Donghyun KANG User interface method and device
CN103596252A (en) * 2013-11-28 2014-02-19 贝壳网际（北京）安全技术有限公司 Method and device for controlling mobile terminal and mobile terminal
CN104715754A (en) * 2015-03-05 2015-06-17 北京华丰亨通科贸有限公司 Method and device for rapidly responding to voice commands
CN107817891A (en) * 2017-11-13 2018-03-20 广东欧珀移动通信有限公司 Screen control method, device, equipment and storage medium
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
CN109036426A (en) * 2018-09-20 2018-12-18 广东小天才科技有限公司 A kind of awakening method and wearable device of wearable device
CN110362290A (en) * 2019-06-29 2019-10-22 华为技术有限公司 A kind of sound control method and relevant apparatus
CN113055524A (en) * 2021-03-09 2021-06-29 北京有竹居网络技术有限公司 Terminal control method and device, terminal and storage medium

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130080178A1 (en) * 2011-09-26 2013-03-28 Donghyun KANG User interface method and device
CN103596252A (en) * 2013-11-28 2014-02-19 贝壳网际（北京）安全技术有限公司 Method and device for controlling mobile terminal and mobile terminal
CN104715754A (en) * 2015-03-05 2015-06-17 北京华丰亨通科贸有限公司 Method and device for rapidly responding to voice commands
CN107817891A (en) * 2017-11-13 2018-03-20 广东欧珀移动通信有限公司 Screen control method, device, equipment and storage medium
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
CN109036426A (en) * 2018-09-20 2018-12-18 广东小天才科技有限公司 A kind of awakening method and wearable device of wearable device
CN110362290A (en) * 2019-06-29 2019-10-22 华为技术有限公司 A kind of sound control method and relevant apparatus
CN113055524A (en) * 2021-03-09 2021-06-29 北京有竹居网络技术有限公司 Terminal control method and device, terminal and storage medium

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114786080A (en) * 2022-04-21 2022-07-22 维沃移动通信有限公司 Microphone control method and device, electronic equipment and readable storage medium

Similar Documents

Publication Publication Date Title
CN108735209B (en) Wake-up word binding method, intelligent device and storage medium
CN107360327B (en) Speech recognition method, apparatus and storage medium
CN109712621B (en) Voice interaction control method and terminal
CN105575395A (en) Voice wake-up method and apparatus, terminal, and processing method thereof
CN108831477B (en) Voice recognition method, device, equipment and storage medium
CN110574355B (en) Alarm clock reminding method and device, storage medium and electronic equipment
CN110544468B (en) Application awakening method and device, storage medium and electronic equipment
CN108848264A (en) Control method, device, storage medium and the electronic equipment of microphone
CN112700782A (en) Voice processing method and electronic equipment
WO2022048319A1 (en) Switching method and apparatus for multiple user accounts, electronic device, and storage medium
CN109032554B (en) Audio processing method and electronic equipment
CN108628644A (en) A kind of the startup method, apparatus and mobile terminal of application
CN112233676A (en) Intelligent device awakening method and device, electronic device and storage medium
CN113808584A (en) Voice wake-up method and device, electronic equipment and storage medium
WO2022042485A1 (en) Control method and apparatus for near-field communication module, and electronic device
CN113160815B (en) Intelligent control method, device, equipment and storage medium for voice wakeup
CN110543333A (en) Dormancy processing method and device for processor, mobile terminal and storage medium
CN107368175A (en) Reduce processing method, device and the terminal of power consumption of terminal
CN111526244A (en) Alarm clock processing method and electronic equipment
CN108833688B (en) Position reminding method and device, storage medium and electronic equipment
CN111580911A (en) Operation prompting method and device for terminal, storage medium and terminal
CN112435441B (en) Sleep detection method and wearable electronic device
CN112740321A (en) Method and device for waking up equipment, storage medium and electronic equipment
CN114121042A (en) Voice detection method and device under wake-up-free scene and electronic equipment
WO2019061123A1 (en) Information display method, terminal device, and computer readable storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination