CN112740321A - Method and device for waking up equipment, storage medium and electronic equipment - Google Patents
Method and device for waking up equipment, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN112740321A CN112740321A CN201880097795.9A CN201880097795A CN112740321A CN 112740321 A CN112740321 A CN 112740321A CN 201880097795 A CN201880097795 A CN 201880097795A CN 112740321 A CN112740321 A CN 112740321A
- Authority
- CN
- China
- Prior art keywords
- recognition
- voice
- electronic device
- voice information
- digital signal
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000002618 waking effect Effects 0.000 title claims abstract description 42
- 230000000694 effects Effects 0.000 claims description 49
- 238000001514 detection method Methods 0.000 claims description 47
- 230000005236 sound signal Effects 0.000 claims description 38
- 238000004590 computer program Methods 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 239000000203 mixture Substances 0.000 claims description 6
- 239000002699 waste material Substances 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000012795 verification Methods 0.000 description 6
- 239000000306 component Substances 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 239000008358 core component Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Telephone Function (AREA)
Abstract
The embodiment provides a method for waking up a device. The method comprises the following steps: acquiring voice information; performing first awakening word recognition and first voiceprint recognition on voice information through a digital signal processor; if the first awakening word recognition and the first voiceprint recognition are verified, performing second awakening word recognition and second voiceprint recognition on the voice information through the application processor; and if the second awakening word recognition and the second voiceprint recognition are verified to be passed, awakening the electronic equipment.
Description
The present application belongs to the technical field of electronic devices, and in particular, to a method and an apparatus for waking up a device, a storage medium, and an electronic device.
With the increasing degree of intelligence of the electronic device, the electronic device may be awakened by using awakening word recognition and voiceprint recognition technologies in the related art, where the awakening word recognition is to detect whether the user speech includes a preset vocabulary for awakening the electronic device. For example, after the wake-up word recognition and the voiceprint recognition performed on the user voice are both verified, the electronic device may light up the display screen and unlock the display screen. However, the related art is apt to waste power consumption of the electronic device when the electronic device is woken up using the wake word recognition and the voiceprint recognition.
Disclosure of Invention
The embodiment of the application provides a method and a device for waking up equipment, a storage medium and electronic equipment, which can reduce the power consumption waste of the electronic equipment.
In a first aspect, this embodiment provides a method for waking up a device, including:
acquiring voice information;
performing first awakening word recognition and first voiceprint recognition on the voice information through a digital signal processor of the electronic equipment;
if the first awakening word recognition and the first voiceprint recognition are verified, performing second awakening word recognition and second voiceprint recognition on the voice information through an application processor of the electronic equipment;
and if the second awakening word recognition and the second voiceprint recognition are verified to be passed, awakening the electronic equipment.
In a second aspect, this embodiment provides an apparatus for waking up a device, including:
the acquisition module is used for acquiring voice information;
the first recognition module is used for performing first awakening word recognition and first voiceprint recognition on the voice information through a digital signal processor of the electronic equipment;
the second recognition module is used for performing second awakening word recognition and second voiceprint recognition on the voice information through an application processor of the electronic equipment if the first awakening word recognition and the first voiceprint recognition are verified;
and the awakening module is used for awakening the electronic equipment if the second awakening word identification and the second voiceprint identification are verified to be passed.
In a third aspect, the present embodiment provides a storage medium having a computer program stored thereon, where the computer program is executed on a computer, so as to make the computer execute the method for waking up a device provided in the present embodiment.
In a fourth aspect, this embodiment provides an electronic device, including a memory, and a processor, where the processor is configured to execute, by calling a computer program stored in the memory:
acquiring voice information;
performing first awakening word recognition and first voiceprint recognition on the voice information through a digital signal processor of the electronic equipment;
if the first awakening word recognition and the first voiceprint recognition are verified, performing second awakening word recognition and second voiceprint recognition on the voice information through an application processor of the electronic equipment;
and if the second awakening word recognition and the second voiceprint recognition are verified to be passed, awakening the electronic equipment.
In this embodiment, the electronic device may perform first voice print recognition on the obtained voice information of the user while performing first wake-up word recognition on the voice information. And only when the first awakening word recognition and the first voiceprint recognition are verified, triggering the electronic equipment to perform awakening word recognition and voiceprint recognition again, and executing awakening operation when the second awakening word recognition and the voiceprint recognition are verified. If the first voiceprint recognition is failed, the electronic equipment cannot perform the second awakening word recognition and voiceprint recognition, so that power consumption waste caused by the fact that a non-owner user in the related art speaks an awakening word and triggers the electronic equipment to perform the second awakening word recognition and voiceprint recognition when the non-owner user performs the first awakening word recognition is effectively avoided.
The technical solutions and advantages of the present application will become apparent from the following detailed description of specific embodiments of the present application when taken in conjunction with the accompanying drawings.
Fig. 1 is a flowchart illustrating a method for waking up a device according to an embodiment of the present application.
Fig. 2 is another schematic flowchart of a method for waking up a device according to an embodiment of the present application.
Fig. 3 to fig. 6 are schematic scene diagrams of a method for waking up a device according to an embodiment of the present application.
Fig. 7 is a schematic structural diagram of an apparatus for waking up a device according to an embodiment of the present application.
Fig. 8 is a schematic structural diagram of an electronic device provided in an embodiment of the present application.
Fig. 9 is another schematic structural diagram of an electronic device according to an embodiment of the present application.
Referring to the drawings, wherein like reference numbers refer to like elements, the principles of the present application are illustrated as being implemented in a suitable computing environment. The following description is based on illustrated embodiments of the application and should not be taken as limiting the application with respect to other embodiments that are not detailed herein.
It is understood that the execution subject of the embodiment of the present application may be an electronic device such as a smart phone or a tablet computer.
Referring to fig. 1, fig. 1 is a schematic flowchart of a method for waking up a device according to an embodiment of the present application, where the flowchart may include:
in 101, voice information is acquired.
With the increasing degree of intelligence of the electronic device, the electronic device may be awakened by using awakening word recognition and voiceprint recognition technologies in the related art, where the awakening word recognition is to detect whether the user speech includes a preset vocabulary for awakening the electronic device. For example, after the wake-up word recognition and the voiceprint recognition performed on the user voice are both verified, the electronic device may light up the display screen and unlock the display screen. However, the related art is apt to waste power consumption of the electronic device when the electronic device is woken up using the wake word recognition and the voiceprint recognition.
For example, when waking up the electronic device, the related art may first perform wake-up word recognition on the obtained voice to detect whether the voice includes a wake-up word preset by the owner. If the voice contains the preset awakening word, the electronic equipment can perform awakening word recognition again and perform voiceprint recognition. If the current user is detected to be the owner through voiceprint recognition, and the voice is determined to contain the preset awakening words again through second awakening word recognition, the electronic equipment is awakened, namely the electronic equipment is turned on and unlocked. However, if the non-owner user knows the preset wake word and speaks the wake word to the electronic device, the electronic device also performs voiceprint recognition and second wake word recognition. But since the current user is an inactive user, the electronic device will not be woken up. That is, the fact that the electronic device performs voiceprint recognition and second wake-up word recognition is redundant, which wastes power consumption of the electronic device.
In 101 of the embodiment of the present application, for example, the electronic device may first acquire the speech information a spoken by the current user.
At 102, a first wake-up word recognition and a first voice print recognition are performed on the voice information by a digital signal processor of the electronic device.
For example, after acquiring the voice information a of the current user, the electronic device may perform first wake-up word recognition and first voiceprint recognition on the voice information a through a Digital Signal Processor (DSP) of the electronic device.
It should be noted that the digital signal processor is a microprocessor for processing signals, and is a core component of the voice encoder and the modem. The digital signal processor has the advantages of small volume, low power consumption and high operation speed.
The awakening word recognition means that the electronic equipment detects whether a certain section of voice contains preset vocabulary content for awakening the electronic equipment. For example, the wake-up word preset by the owner for waking up the electronic device is "wake-up on a small ohm". Then, after obtaining the user voice, the electronic device may convert the user voice into a text, and detect whether the text obtained after conversion includes a wakeup word "wake up on a small ohm", that is, the electronic device may detect whether the user voice includes a wakeup word "wake up on a small ohm". If the user voice contains the awakening word of 'small wake up', the electronic equipment can determine that the awakening word recognition verification is passed. If the user voice does not contain the awakening word of 'small wake up', the electronic equipment can determine that the awakening word recognition verification is not passed.
Voiceprint recognition is a biometric technique that discriminates the identity of a speaker through voice. For example, the voiceprint feature information of the owner is prestored in the electronic device, and then after the voice information of the current user is obtained, the electronic device can extract the voiceprint feature information of the current user from the voiceprint feature information. And then, the electronic equipment can match the voiceprint characteristic information of the current user with the prestored voiceprint characteristic information of the owner. If the two are matched successfully, the electronic device can determine that the current user is the owner, namely the voiceprint identification passes. If the two are not matched, the electronic device may determine that the current user is not the owner, that is, the voiceprint identification verification fails.
After performing the first wake-up word recognition and the first voiceprint recognition on the voice information a acquired in 101, the electronic device may detect whether the first wake-up word recognition and the first voiceprint recognition are both verified.
And if the first awakening word recognition and the first voiceprint recognition are verified to be passed, entering 103. For example, the electronic device detects that the voice spoken by the current user includes a preset wake-up word "small wake-up", and the electronic device determines that the current user is the main user through the first voiceprint recognition, in which case, the step may be performed in 103.
If the first wake word recognition and the first voiceprint recognition are not all verified, the electronic device may perform other operations. For example, when the first voiceprint recognition is not verified, the electronic device can perform other operations without triggering the operations of performing the second wake word recognition and the second voiceprint recognition.
In 103, if the first time awakening word recognition and the first time voiceprint recognition are both verified, performing, by an application processor of the electronic device, a second time awakening word recognition and a second time voiceprint recognition on the voice information.
For example, if the first wake-up word recognition and the first voiceprint recognition performed on the voice information a of the current user by the electronic device are verified through the digital signal Processor, the electronic device may be triggered to perform the second wake-up word recognition and the second voiceprint recognition on the voice information a of the current user by using an Application Processor (AP) of the electronic device.
It should be noted that the second time of the awakening word recognition is also to detect whether the voice information a of the current user includes a preset awakening word. For example, the second wake word recognition also detects whether the voice information a of the current user includes a wake word "wake up small" preset by the owner. The second voiceprint recognition is also to detect whether the current user is the owner. In addition, since the resources and operations that can be obtained by the application processor can be stronger than those of the digital signal processor, the identification result of the application processor can be more accurate. The power consumption of the application processor is also greater than that of the digital signal processor.
After performing the second wake-up word recognition and the second voiceprint recognition on the voice information a acquired in 101, the electronic device may detect whether both the second wake-up word recognition and the second voiceprint recognition are verified.
And entering 104 if the second awakening word recognition and the second voiceprint recognition are verified. For example, the electronic device detects that the voice spoken by the current user does indeed include a preset wake word "wake up small", and the electronic device determines that the current user is indeed the owner through a second voiceprint recognition, in which case 104 may be entered.
If the second wake word recognition and the second voiceprint recognition are not all verified, the electronic device may perform other operations.
At 104, if the second time awakening word recognition and the second time voiceprint recognition are verified, the electronic device is awakened.
For example, the electronic device may perform the wake-up operation if the second wake-up word recognition and the second voiceprint recognition performed by the electronic device on the speech information a of the current user are both verified by the application processor. For example, the electronic device may illuminate the display screen and unlock the display screen, and so on.
It can be understood that, in this embodiment, the electronic device may perform first voice print recognition on the obtained voice information of the user while performing first wake-up word recognition on the voice information. And only when the first awakening word recognition and the first voiceprint recognition are verified, triggering the electronic equipment to perform awakening word recognition and voiceprint recognition again, and executing awakening operation when the second awakening word recognition and the voiceprint recognition are verified. If the first voiceprint recognition is failed, the electronic equipment cannot perform the second awakening word recognition and voiceprint recognition, so that power consumption waste caused by the fact that a non-owner user in the related art speaks an awakening word and triggers the electronic equipment to perform the second awakening word recognition and voiceprint recognition when the non-owner user performs the first awakening word recognition is effectively avoided.
Referring to fig. 2, fig. 2 is another schematic flow chart of a method for waking up a device according to an embodiment of the present application, where the flow chart may include:
in 201, the electronic device acquires a sound signal of the surrounding environment.
For example, the electronic device may collect sound signals of the surrounding environment through its microphone.
At 202, the electronic device performs voice activity detection on the sound signal through a digital signal processor, wherein the digital signal processor is in a preset low frequency mode when performing voice activity detection.
For example, after acquiring a sound signal of the surrounding environment, the electronic device may perform Voice Activity Detection (VAD) on the sound signal through a digital signal processor DSP of the electronic device. When voice activity detection is performed, the digital signal processor of the electronic device can be in a preset low-frequency mode.
It should be noted that the voice activity detection is to distinguish a voice signal from a background noise signal from a voice signal. That is, in the present embodiment, the voice activity detection is mainly to detect whether the voice (voice) of the user exists in the voice signal.
In this embodiment, the digital signal processor of the electronic device has two operating modes, which are a preset low-frequency mode and a preset high-frequency mode. When the digital signal processor is in the low-frequency mode, the clock frequency of the digital signal processor is low, the number of instructions executed by the digital signal processor per second is small, the processing capacity is low, and correspondingly, the power consumption is low. When the digital signal processor is in the high-frequency mode, the clock frequency of the digital signal processor is higher, the number of instructions executed by the digital signal processor per second is larger, the processing capacity is stronger, and the corresponding power consumption is higher.
In this embodiment, the electronic device may control the digital signal processor to perform voice activity detection in a preset low frequency mode.
In one embodiment, the electronic device may use an energy-plus-model algorithm to perform voice activity detection on the captured acoustic signals of the surrounding environment.
At 203, based on the voice activity detection, the electronic device determines whether a user voice is present in the voice signal.
For example, in the process of performing voice activity detection on the collected sound signal, the electronic device may determine whether the user sound exists in the collected sound signal according to the voice activity detection.
If the presence of the user's voice in the captured voice signal is determined by voice activity detection, then 204 is entered.
If it is determined through voice activity detection that the user voice is not present in the captured voice signal, but only background noise is present, the electronic device may perform other operations.
At 204, if the user voice is present, the electronic device obtains voice information of the user.
For example, the electronic device determines, through voice activity detection, that there is a user voice in the surrounding sound signal, and at this time, the electronic device may obtain corresponding voice information from the user voice. For example, the electronic device acquires voice information a of the user.
In 205, the electronic device performs a first wake-up word recognition and a first voiceprint recognition on the voice message through a digital signal processor, wherein the digital signal processor is in a preset high frequency mode when the first wake-up word recognition and the first voiceprint recognition are performed.
For example, after obtaining the voice information a of the user, the electronic device may control the digital signal processor to enter a preset high-frequency mode, and when the electronic device is in the high-frequency mode, the digital signal processor performs wakeup word recognition and voiceprint recognition on the voice information a. Namely, the electronic equipment performs the first awakening word recognition and the first voiceprint recognition on the voice information A.
It should be noted that, for example, the wake-up word preset by the owner for waking up the electronic device is "wake-up on a small ohm". Then, after obtaining the user voice information a, the electronic device may convert the user voice information a into a text, and detect whether the text obtained after conversion includes a wakeup word "wake up on a small ohm", that is, the electronic device may detect whether the user voice includes a wakeup word "wake up on a small ohm". If the user voice contains the awakening word of 'small wake up', the electronic equipment can determine that the awakening word recognition verification is passed. If the user voice does not contain the awakening word of 'small wake up', the electronic equipment can determine that the awakening word recognition verification is not passed.
Voiceprint recognition is used to determine whether the current user is the owner. When voiceprint recognition is carried out, the electronic equipment can match voiceprint characteristic information of a current user with voiceprint characteristic information of a pre-stored owner. If the two are matched successfully, the electronic device may determine that the current user is the owner. If the two are not matched, the electronic device may determine that the current user is not the owner.
And if the first awakening word recognition and the first voiceprint recognition are verified, entering 206. For example, the electronic device detects that the voice spoken by the current user includes a preset wake-up word "small wake-up", and the electronic device determines that the current user is the main user through the first voiceprint recognition, in which case it may enter 206.
If the first wake word recognition and the first voiceprint recognition are not all verified, the electronic device may perform other operations. For example, when the first voiceprint recognition is not verified, that is, the electronic device detects that the current user is not the owner through the voiceprint recognition, the electronic device may perform other operations without triggering the operations of performing the second wake word recognition and the second voiceprint recognition.
In 206, if the first wake word recognition and the first voiceprint recognition are verified, the electronic device performs a second wake word recognition and a second voiceprint recognition on the voice information through the application processor.
For example, if the electronic device verifies that both the wakeup word recognition and the voiceprint recognition performed on the voice information a of the current user are passed through the digital signal Processor, the electronic device may be triggered to perform the wakeup word recognition and the voiceprint recognition on the voice information a of the current user again by using an Application Processor (AP), that is, the electronic device may perform the second wakeup word recognition and the second voiceprint recognition on the voice information a of the current user.
It should be noted that the second time of the awakening word recognition is also to detect whether the voice information a of the current user includes a preset awakening word. For example, the second wake word recognition also detects whether the voice information a of the current user includes a wake word "wake up small" preset by the owner. The second voiceprint recognition is also to detect whether the current user is the owner. Because the operational capability of the application processor is stronger than that of the digital signal processor, the results of the awakening word recognition and the voiceprint recognition of the voice information A of the current user through the application processor are more accurate than the results of the awakening word recognition and the voiceprint recognition of the digital signal processor, so that the effects of further confirming whether the voice information A of the current user contains the preset awakening word and further confirming whether the current user is the owner are achieved. In addition, the resources and operations available to the application processor can be stronger relative to the digital signal processor, and the power consumption of the application processor is also greater than that of the digital signal processor.
After performing the second wake-up word recognition and the second voiceprint recognition on the voice information a acquired in 204, the electronic device may detect whether both the second wake-up word recognition and the second voiceprint recognition are verified.
And if the second awakening word recognition and the second voiceprint recognition are verified to be passed, entering 207. For example, the electronic device detects that the voice spoken by the current user does indeed include a preset wake-up word of "wake up small", and the electronic device determines that the current user is indeed the owner through a second voice print recognition, in which case it may proceed to 207.
If the second wake word recognition and the second voiceprint recognition are not all verified, the electronic device may perform other operations.
In 207, if the second time awakening word recognition and the second time voiceprint recognition are both verified, the electronic device executes an awakening operation.
For example, the electronic device may wake up the electronic device by verifying that the second wake-up word recognition and the second voiceprint recognition performed on the voice information a of the current user by the application processor are both passed, that is, the electronic device may perform a wake-up operation. For example, the electronic device may illuminate the display screen and unlock the display screen, and so on.
In an implementation manner, the electronic device in the process 205 of this embodiment performs a first wake word recognition and a first voiceprint recognition on voice information through a digital signal processor, and may include:
through the digital signal processor, the electronic equipment performs first awakening word recognition and first voiceprint recognition on the voice information, wherein the digital signal processor performs the first awakening word recognition and the first voiceprint recognition by using the first model.
The step 206 of performing, by the electronic device, a second wake word recognition and a second voiceprint recognition on the voice information through the application processor may include: and through the application processor, the electronic equipment performs the second awakening word recognition and the second voiceprint recognition on the voice information, wherein the application processor performs the second awakening word recognition and the second voiceprint recognition by using the second model.
And the number of the parameters used by the first model is smaller than that used by the second model, so that the running power consumption of the first model is smaller than that of the second model.
For example, in the present embodiment, the first model and the second model may be used to perform the wakeup word recognition and the voiceprint recognition on the speech information a of the current user. The number of the parameters used by the first model is smaller than that used by the second model, so that the running power consumption of the first model is smaller than that of the second model. For example, the first model uses A, B, C parameters for the wake word recognition and the voiceprint recognition of the speech information a of the current user. The second model uses A, B, C, D, E, F parameters for the wake word recognition and the voiceprint recognition of the speech information a of the current user. It can be understood that, in this embodiment, both the first model and the second model can perform the wakeup word recognition and the voiceprint recognition on the speech information a of the current user. However, the second model uses more parameters, so the recognition results of the second model for identifying the awakening words and the voiceprint are more accurate compared with the recognition results of the first model.
In this embodiment, since the resources that can be used by the digital signal processor are limited, when performing the first wake-up word recognition and the first voiceprint recognition on the speech information a of the current user, the electronic device may use the first model to perform the first wake-up word recognition and the first voiceprint recognition. Since the application processor can use more resources, when performing the second wake-up word recognition and the second voiceprint recognition on the speech information a of the current user, the electronic device can use the second model to perform the second wake-up word recognition and the second voiceprint recognition, thereby further determining whether the speech information a of the current user contains a preset wake-up word or not and further determining whether the current user is the owner or not according to the recognition result of the second model.
In an implementation manner, in the process 205 of this embodiment, the performing, by the digital signal processor, first wake word recognition and first voiceprint recognition on the voice information by the electronic device may include:
through the digital signal processor, the electronic device performs first wake word recognition and first voiceprint recognition on the voice information using a Gaussian mixture model.
For example, when performing wake word recognition and voiceprint recognition on the voice information a of the current user through the digital signal processor, the electronic device may perform wake word recognition and voiceprint recognition on the voice information a using a gaussian mixture model.
Of course, in other embodiments, the electronic device may also use other algorithm models to perform the first wake-up word recognition and the first voiceprint recognition on the speech information a of the current user, which is not specifically limited in this embodiment.
In an implementation manner, in the process 206 of this embodiment, the performing, by the application processor, the second wake word recognition and the second voiceprint recognition on the voice information by the electronic device may include:
and through the application processor, the electronic equipment performs second awakening word recognition and second voiceprint recognition on the voice information by using the deep neural network algorithm model.
For example, when performing wake word recognition and voiceprint recognition on the voice information a of the current user through the application processor, the electronic device may perform wake word recognition and voiceprint recognition on the voice information a using a Deep Neural Network (DNN) algorithm model.
Of course, in other embodiments, the electronic device may also use other algorithm models to perform the second wake-up word recognition and the second voiceprint recognition on the speech information a of the current user, which is not specifically limited in this embodiment.
It can be understood that, in this embodiment, the electronic device may first perform voice activity detection on the collected sound signal of the surrounding environment to detect whether the sound signal includes the user sound. Wherein the voice activity detection is performed when the digital signal processor is in a low frequency mode. Thus, the present embodiment can perform voice activity detection with extremely low power consumption.
If the voice activity detection judges that the sound signal of the surrounding environment contains the user sound, the electronic equipment can control the digital signal processor to enter a high-frequency mode and perform first awakening word recognition and first voiceprint recognition on the user sound. Only when the first awakening word recognition and the first voiceprint recognition are verified, the electronic device can trigger the application processor to perform the second awakening word recognition and the second voiceprint recognition, and because the power consumption of the application processor is generally 50 times to 100 times that of the digital signal processor, the embodiment triggers the application processor to perform voice recognition and voiceprint recognition when the digital signal processor determines that the current user is the owner and speaks the awakening word, so that the power consumption waste caused by the fact that only the voiceprint recognition is performed on the application processor side in the related technology can be effectively avoided.
In addition, because the awakening word recognition and the voiceprint recognition are both subjected to secondary verification, the condition that the electronic equipment is awakened by mistake can be reduced, and the experience that the user awakens the electronic equipment is improved.
Referring to fig. 3 to 6, fig. 3 to 6 are schematic views illustrating a scenario of a method for waking up a device according to an embodiment of the present application.
For example, the owner of the electronic device is first. As shown in fig. 3, the electronic device prompts the owner to speak a voice that is used as a wake-up word. For example, the main user A speaks a "small wake up" voice, which the electronic device may capture through its microphone. Then, the electronic device can perform voice recognition and voiceprint recognition on the voice, so as to obtain a wake word "small wake up" for waking up the electronic device and a voiceprint feature of the main user nail.
In the screen-off and screen-locked state, the electronic device may collect sound signals of the surrounding environment through its microphone. After the sound signal is collected, the electronic device can control the digital signal processor to enter a preset low-frequency mode, and voice activity detection is performed on the collected sound signal through the digital signal processor in the low-frequency mode so as to detect whether the sound signal contains user sound.
For example, as shown in FIG. 4, the current user speaks a speech "Small wake Up" (Speech B) to the electronic device. After the microphone of the electronic device collects the section of voice B, the digital signal processor in the low-frequency mode detects the voice activity of the voice B and detects that the voice B contains the user voice.
If the voice activity detection judges that the collected voice signal contains the voice of the user, the electronic equipment can acquire the voice information of the current user from the voice signal. And then, the electronic equipment can control the digital signal processor to enter a preset high-frequency mode, and performs awakening word recognition and voiceprint recognition on the acquired voice information of the current user in the high-frequency mode. Namely, the electronic equipment performs first awakening word recognition and first voiceprint recognition on the voice information of the current user.
For example, the electronic device may perform first wake word recognition on the voice B of the current user through the digital signal processor in the high frequency mode to detect whether the voice B is a preset wake word "small wake up". And the electronic equipment can extract the voiceprint feature of the current user from the voice B of the current user, and match the voiceprint feature of the current user with the preset voiceprint feature of the owner user A so as to detect whether the current user is the owner user A.
If the first awakening word recognition and the first voiceprint recognition are verified, the electronic equipment can perform awakening word recognition and voiceprint recognition on the voice information of the current user again through the application processor of the electronic equipment. Namely, the electronic equipment performs the second awakening word recognition and the second voiceprint recognition on the voice information of the current user. And the second awakening word recognition is also used for detecting whether the voice information of the current user contains the preset awakening word. The second voiceprint recognition is also used for detecting whether the current user is the owner user A.
If the second wake-up word recognition and the second voiceprint recognition are both verified, the electronic device may perform a wake-up operation, for example, the electronic device may light up a screen display and unlock the screen display.
For example, the electronic device detects that the current user is the owner user a through first voiceprint recognition, and detects that the voice B is a preset wake word "waken up a small ohm" through first wake word recognition. And the electronic equipment further confirms that the current user is the owner user A through the second voiceprint recognition, and further confirms that the voice B is really the preset awakening word 'Xiaoouxing' through the second awakening word recognition. In this case, the electronic device may illuminate the display screen and unlock the display screen.
A schematic diagram of the above process can be seen in fig. 5.
If the first time of awakening word recognition and the first time of voiceprint recognition are not verified, the electronic equipment can execute other operations without performing the second time of voiceprint recognition and the second time of awakening word recognition.
For example, as shown in FIG. 6, the non-individual user B speaks a voice C "Small Wake Up" containing a wake word to the electronic device. However, when the first voiceprint recognition is performed on the voice C spoken by the user b, the first voiceprint recognition cannot be verified because the user b is not the owner user a. Then, the electronic device does not perform the second wake word recognition and the second voiceprint recognition on the voice C.
In the related art, the electronic device performs voiceprint recognition only when performing the second wake-up word recognition, but does not perform voiceprint recognition when performing the first wake-up word recognition. Therefore, although the voice C is spoken by the user b, since the electronic device does not perform voiceprint recognition when performing the first wake-up word recognition, the electronic device triggers the second wake-up word recognition and voiceprint recognition on the voice C after detecting that the wake-up word "wake up a little" is included in the voice C. When voiceprint recognition is carried out, the electronic equipment detects that the current user is not the owner user A, and therefore the electronic equipment cannot execute awakening operation. Therefore, in the related art, the second wake-up word recognition and the voiceprint recognition performed by the electronic device actually cause waste of power consumption of the electronic device.
Referring to fig. 7, fig. 7 is a schematic structural diagram of an apparatus for waking up a device according to an embodiment of the present application. The apparatus 300 for waking up a device may include: the system comprises an acquisition module 301, a first identification module 302, a second identification module 303 and a wake-up module 304.
An obtaining module 301, configured to obtain voice information.
The first recognition module 302 is configured to perform first wake-up word recognition and first voiceprint recognition on the voice message through a digital signal processor of the electronic device.
A second identification module 303, configured to perform, by the application processor of the electronic device, second wake-up word identification and second voiceprint identification on the voice information if both the first wake-up word identification and the first voiceprint identification are verified.
And the waking module 304 is configured to wake up the electronic device if the second wake-up word recognition and the second voiceprint recognition are both verified.
In one embodiment, the obtaining module 301 may be configured to:
acquiring a sound signal of the surrounding environment, and carrying out voice activity detection on the sound signal;
judging whether user voice exists in the voice signal or not according to the voice activity detection;
and if the user voice exists, acquiring voice information.
In one embodiment, the obtaining module 301 may be configured to:
performing, by a digital signal processor of the electronic device, voice activity detection on the sound signal.
In one embodiment, the obtaining module 301 may be configured to:
and carrying out voice activity detection on the sound signal through a digital signal processor of the electronic equipment, wherein when the voice activity detection is carried out, the digital signal processor is in a preset low-frequency mode.
In one embodiment, the first identification module 302 may be configured to:
and performing first awakening word recognition and first voiceprint recognition on the voice information through a digital signal processor of the electronic equipment, wherein the digital signal processor is in a preset high-frequency mode when the first awakening word recognition and the first voiceprint recognition are performed.
In one embodiment, the first identification module 302 may be configured to: performing first awakening word recognition and first voiceprint recognition on the voice information through a digital signal processor of the electronic equipment, wherein the digital signal processor performs the first awakening word recognition and the first voiceprint recognition by using a first model;
the second identification module 303 may be configured to: and performing second awakening word recognition and second voiceprint recognition on the voice information through an application processor of the electronic equipment, wherein the application processor performs the second awakening word recognition and the second voiceprint recognition by using a second model.
Wherein the number of parameters used by the first model is less than the number of parameters used by the second model, such that the operating power consumption of the first model is less than the operating power consumption of the second model.
In one embodiment, the first identification module 302 may be configured to: and performing first awakening word recognition and first voiceprint recognition on the voice information by using a Gaussian mixture model through a digital signal processor of the electronic equipment.
In one embodiment, the second identification module 303 may be configured to: and performing second awakening word recognition and second voiceprint recognition on the voice information by using a deep neural network algorithm model through an application processor of the electronic equipment.
The present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed on a computer, the computer is caused to execute the procedures in the method for waking up a device as provided in this embodiment.
The embodiment of the present application further provides an electronic device, which includes a memory and a processor, where the processor is configured to execute the procedure in the method for waking up a device provided in this embodiment by calling the computer program stored in the memory.
For example, the electronic device may be a mobile terminal such as a tablet computer or a smart phone. Referring to fig. 8, fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.
The electronic device 400 may include components such as a display 401, memory 402, processor 403, microphone 404, and the like. Those skilled in the art will appreciate that the electronic device configuration shown in fig. 8 does not constitute a limitation of the electronic device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
The display 401 may be used to display information such as images, text, and the like.
The memory 402 may be used to store applications and data. The memory 402 stores applications containing executable code. The application programs may constitute various functional modules. The processor 403 executes various functional applications and data processing by running an application program stored in the memory 402.
The processor 403 is a control center of the electronic device, connects various parts of the whole electronic device by using various interfaces and lines, and performs various functions of the electronic device and processes data by running or executing an application program stored in the memory 402 and calling data stored in the memory 402, thereby performing overall monitoring of the electronic device.
In this embodiment, the processor 403 in the electronic device loads the executable code corresponding to the processes of one or more application programs into the memory 402 according to the following instructions, and the processor 403 runs the application programs stored in the memory 402, so as to execute:
acquiring voice information; performing first awakening word recognition and first voiceprint recognition on the voice information through a digital signal processor of the electronic equipment; if the first awakening word recognition and the first voiceprint recognition are verified, performing second awakening word recognition and second voiceprint recognition on the voice information through an application processor of the electronic equipment; and if the second awakening word recognition and the second voiceprint recognition are verified to be passed, awakening the electronic equipment.
Referring to fig. 9, the electronic device 500 may include a display 501, a memory 502, a processor 503, a microphone 504, a speaker 505, a battery 506, and the like.
The display 501 may be used to display information such as images, text, and the like.
The memory 502 may be used to store applications and data. Memory 502 stores applications containing executable code. The application programs may constitute various functional modules. The processor 503 executes various functional applications and data processing by running an application program stored in the memory 502.
The processor 503 is a control center of the electronic device, connects various parts of the whole electronic device by using various interfaces and lines, and performs various functions of the electronic device and processes data by running or executing an application program stored in the memory 502 and calling the data stored in the memory 502, thereby performing overall monitoring of the electronic device.
The input unit 504 may be used to receive input numbers, character information, or user characteristic information (such as a fingerprint), and to generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control.
The output unit 505 may be used to display information input by or provided to a user and various graphical user interfaces of the electronic device, which may be made up of graphics, text, icons, video, and any combination thereof. The output unit may include a display panel.
In this embodiment, the processor 503 in the electronic device loads the executable code corresponding to the processes of one or more application programs into the memory 502 according to the following instructions, and the processor 503 runs the application programs stored in the memory 502, so as to execute:
acquiring voice information; performing first awakening word recognition and first voiceprint recognition on the voice information through a digital signal processor of the electronic equipment; if the first awakening word recognition and the first voiceprint recognition are verified, performing second awakening word recognition and second voiceprint recognition on the voice information through an application processor of the electronic equipment; and if the second awakening word recognition and the second voiceprint recognition are verified to be passed, awakening the electronic equipment.
In one embodiment, before the acquiring the voice information, the processor 503 may further perform: acquiring a sound signal of the surrounding environment, and carrying out voice activity detection on the sound signal; and judging whether the voice of the user exists in the voice signal or not according to the voice activity detection.
Then, the processor 503, when executing the acquiring of the voice information, may perform: and if the user voice exists, acquiring voice information.
In one embodiment, the processor 503, when performing the voice activity detection on the sound signal, may perform: performing, by a digital signal processor of the electronic device, voice activity detection on the sound signal.
In one embodiment, the processor 503, when executing the voice activity detection on the sound signal by the digital signal processor of the electronic device, may execute: and carrying out voice activity detection on the sound signal through a digital signal processor of the electronic equipment, wherein when the voice activity detection is carried out, the digital signal processor is in a preset low-frequency mode.
In one embodiment, the processor 503, when executing the first wake-up word recognition and the first voiceprint recognition on the voice information by the digital signal processor of the electronic device, may perform: and performing first awakening word recognition and first voiceprint recognition on the voice information through a digital signal processor of the electronic equipment, wherein the digital signal processor is in a preset high-frequency mode when the first awakening word recognition and the first voiceprint recognition are performed.
In one embodiment, the processor 503, when executing the first wake-up word recognition and the first voiceprint recognition on the voice information by the digital signal processor of the electronic device, may perform: and performing first awakening word recognition and first voiceprint recognition on the voice information through a digital signal processor of the electronic equipment, wherein the digital signal processor performs the first awakening word recognition and the first voiceprint recognition by using a first model.
Then, the processor 503, when executing the second wake word recognition and the second voiceprint recognition on the voice information by the application processor of the electronic device, may perform: and performing second awakening word recognition and second voiceprint recognition on the voice information through an application processor of the electronic equipment, wherein the application processor performs the second awakening word recognition and the second voiceprint recognition by using a second model. Wherein the number of parameters used by the first model is less than the number of parameters used by the second model, such that the operating power consumption of the first model is less than the operating power consumption of the second model.
In one embodiment, the processor 503, when executing the first wake-up word recognition and the first voiceprint recognition on the voice information by the digital signal processor of the electronic device, may perform: and performing first awakening word recognition and first voiceprint recognition on the voice information by using a Gaussian mixture model through a digital signal processor of the electronic equipment.
In one embodiment, the processor 503, when executing the application processor of the electronic device to perform the second wake word recognition and the second voiceprint recognition on the voice information, may perform: and performing second awakening word recognition and second voiceprint recognition on the voice information by using a deep neural network algorithm model through an application processor of the electronic equipment.
In the above embodiments, the descriptions of the embodiments have respective emphasis, and a part which is not described in detail in a certain embodiment may refer to the above detailed description of the method for waking up the device, and is not described herein again.
The apparatus for waking up a device provided in the embodiment of the present application and the method for waking up a device in the above embodiments belong to the same concept, and any method provided in the method for waking up a device may be run on the apparatus for waking up a device, and a specific implementation process thereof is described in the method embodiment for waking up a device in detail, and is not described herein again.
It should be noted that, for the method for waking up a device according to the embodiment of the present application, it can be understood by those skilled in the art that all or part of the process of implementing the method for waking up a device according to the embodiment of the present application may be implemented by controlling related hardware through a computer program, where the computer program may be stored in a computer-readable storage medium, such as a memory, and executed by at least one processor, and during the execution, the process of the embodiment of the method for waking up a device may be included. The storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a Random Access Memory (RAM), or the like.
For the apparatus of the wake-up device in the embodiment of the present application, each functional module may be integrated in one processing chip, or each module may exist alone physically, or two or more modules are integrated in one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium, such as a read-only memory, a magnetic or optical disk, or the like.
The method, the apparatus, the storage medium, and the electronic device for waking up a device provided in the embodiments of the present application are described in detail above, and a specific example is applied in the present application to explain the principle and the implementation of the present application, and the description of the above embodiments is only used to help understand the method and the core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (20)
- A method of waking a device, comprising:acquiring voice information;performing first awakening word recognition and first voiceprint recognition on the voice information through a digital signal processor of the electronic equipment;if the first awakening word recognition and the first voiceprint recognition are verified, performing second awakening word recognition and second voiceprint recognition on the voice information through an application processor of the electronic equipment;and if the second awakening word recognition and the second voiceprint recognition are verified to be passed, awakening the electronic equipment.
- The method of waking up a device as recited in claim 1, wherein prior to the obtaining voice information, further comprising:acquiring a sound signal of the surrounding environment, and carrying out voice activity detection on the sound signal;judging whether user voice exists in the voice signal or not according to the voice activity detection;the acquiring of the voice information comprises: and if the user voice exists, acquiring voice information.
- A method of waking up a device as claimed in claim 2, wherein said voice activity detection of the sound signal comprises:performing, by a digital signal processor of the electronic device, voice activity detection on the sound signal.
- A method of waking up a device as claimed in claim 3, wherein said performing, by a digital signal processor of the electronic device, voice activity detection on the sound signal comprises:and carrying out voice activity detection on the sound signal through a digital signal processor of the electronic equipment, wherein when the voice activity detection is carried out, the digital signal processor is in a preset low-frequency mode.
- The method of waking up a device of claim 4, wherein the performing, by a digital signal processor of an electronic device, a first wake-up word recognition and a first voiceprint recognition on the voice information comprises:and performing first awakening word recognition and first voiceprint recognition on the voice information through a digital signal processor of the electronic equipment, wherein the digital signal processor is in a preset high-frequency mode when the first awakening word recognition and the first voiceprint recognition are performed.
- The method of waking up a device as claimed in claim 1, wherein the performing, by a digital signal processor of an electronic device, a first wake-up word recognition and a first voiceprint recognition on the voice information comprises:performing first awakening word recognition and first voiceprint recognition on the voice information through a digital signal processor of the electronic equipment, wherein the digital signal processor performs the first awakening word recognition and the first voiceprint recognition by using a first model;the performing, by the application processor of the electronic device, a second wake-up word recognition and a second voiceprint recognition on the voice message includes: performing, by an application processor of the electronic device, a second wake-up word recognition and a second voiceprint recognition on the voice information, wherein the application processor performs the second wake-up word recognition and the second voiceprint recognition using a second model;wherein the number of parameters used by the first model is less than the number of parameters used by the second model, such that the operating power consumption of the first model is less than the operating power consumption of the second model.
- The method of waking up a device as claimed in claim 1, wherein the performing, by a digital signal processor of an electronic device, a first wake-up word recognition and a first voiceprint recognition on the voice information comprises:and performing first awakening word recognition and first voiceprint recognition on the voice information by using a Gaussian mixture model through a digital signal processor of the electronic equipment.
- The method of waking up a device as claimed in claim 1, wherein the performing, by an application processor of the electronic device, a second wake-up word recognition and a second voiceprint recognition on the voice information comprises:and performing second awakening word recognition and second voiceprint recognition on the voice information by using a deep neural network algorithm model through an application processor of the electronic equipment.
- An apparatus to wake up a device, comprising:the acquisition module is used for acquiring voice information;the first recognition module is used for performing first awakening word recognition and first voiceprint recognition on the voice information through a digital signal processor of the electronic equipment;the second recognition module is used for performing second awakening word recognition and second voiceprint recognition on the voice information through an application processor of the electronic equipment if the first awakening word recognition and the first voiceprint recognition are verified;and the awakening module is used for awakening the electronic equipment if the second awakening word identification and the second voiceprint identification are verified to be passed.
- The apparatus of claim 9, wherein the means for obtaining is further configured to:acquiring a sound signal of the surrounding environment, and carrying out voice activity detection on the sound signal;judging whether user voice exists in the voice signal or not according to the voice activity detection;and if the user voice exists, acquiring voice information.
- The apparatus of claim 10, wherein the means for obtaining is configured to:performing, by a digital signal processor of the electronic device, voice activity detection on the sound signal.
- A storage medium having stored thereon a computer program, wherein the computer program, when executed on a computer, causes the computer to perform the method of any one of claims 1 to 8.
- An electronic device comprising a memory, a processor, wherein the processor is operable to execute, by invoking a computer program stored in the memory:acquiring voice information;performing first awakening word recognition and first voiceprint recognition on the voice information through a digital signal processor of the electronic equipment;if the first awakening word recognition and the first voiceprint recognition are verified, performing second awakening word recognition and second voiceprint recognition on the voice information through an application processor of the electronic equipment;and if the second awakening word recognition and the second voiceprint recognition are verified to be passed, awakening the electronic equipment.
- The electronic device of claim 13, wherein the processor is configured to perform:acquiring a sound signal of the surrounding environment, and carrying out voice activity detection on the sound signal;judging whether user voice exists in the voice signal or not according to the voice activity detection;and if the user voice exists, acquiring voice information.
- The electronic device of claim 14, wherein the processor is configured to perform:performing, by a digital signal processor of the electronic device, voice activity detection on the sound signal.
- The electronic device of claim 15, wherein the processor is configured to perform:and carrying out voice activity detection on the sound signal through a digital signal processor of the electronic equipment, wherein when the voice activity detection is carried out, the digital signal processor is in a preset low-frequency mode.
- The electronic device of claim 16, wherein the processor is configured to perform:and performing first awakening word recognition and first voiceprint recognition on the voice information through a digital signal processor of the electronic equipment, wherein the digital signal processor is in a preset high-frequency mode when the first awakening word recognition and the first voiceprint recognition are performed.
- The electronic device of claim 13, wherein the processor is configured to perform:performing first awakening word recognition and first voiceprint recognition on the voice information through a digital signal processor of the electronic equipment, wherein the digital signal processor performs the first awakening word recognition and the first voiceprint recognition by using a first model;performing, by an application processor of the electronic device, a second wake-up word recognition and a second voiceprint recognition on the voice information, wherein the application processor performs the second wake-up word recognition and the second voiceprint recognition using a second model;wherein the number of parameters used by the first model is less than the number of parameters used by the second model, such that the operating power consumption of the first model is less than the operating power consumption of the second model.
- The electronic device of claim 13, wherein the processor is configured to perform:and performing first awakening word recognition and first voiceprint recognition on the voice information by using a Gaussian mixture model through a digital signal processor of the electronic equipment.
- The electronic device of claim 13, wherein the processor is configured to perform:and performing second awakening word recognition and second voiceprint recognition on the voice information by using a deep neural network algorithm model through an application processor of the electronic equipment.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2018/116493 WO2020102991A1 (en) | 2018-11-20 | 2018-11-20 | Method and apparatus for waking up device, storage medium and electronic device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112740321A true CN112740321A (en) | 2021-04-30 |
Family
ID=70773736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201880097795.9A Pending CN112740321A (en) | 2018-11-20 | 2018-11-20 | Method and device for waking up equipment, storage medium and electronic equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112740321A (en) |
| WO (1) | WO2020102991A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117524228A (en) * | 2024-01-08 | 2024-02-06 | 腾讯科技（深圳）有限公司 | Voice data processing method, device, equipment and medium |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111951793B (en) * | 2020-08-13 | 2021-08-24 | 北京声智科技有限公司 | Method, device and storage medium for awakening word recognition |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105869655A (en) * | 2015-02-06 | 2016-08-17 | 美商富迪科技股份有限公司 | Audio device and method for voice detection |
| CN106448663A (en) * | 2016-10-17 | 2017-02-22 | 海信集团有限公司 | Voice wakeup method and voice interaction device |
| CN106815507A (en) * | 2015-11-30 | 2017-06-09 | 中兴通讯股份有限公司 | Voice wakes up implementation method, device and terminal |
| CN107767863A (en) * | 2016-08-22 | 2018-03-06 | 科大讯飞股份有限公司 | voice awakening method, system and intelligent terminal |
| US20180330727A1 (en) * | 2017-05-10 | 2018-11-15 | Ecobee Inc. | Computerized device with voice command input capability |
| CN108831477A (en) * | 2018-06-14 | 2018-11-16 | 出门问问信息科技有限公司 | A kind of audio recognition method, device, equipment and storage medium |
| CN110520927A (en) * | 2016-12-21 | 2019-11-29 | 爱浮诺亚股份有限公司 | Low-power, the voice command monitored always detection and capture |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2509291B1 (en) * | 2011-04-06 | 2015-06-03 | BlackBerry Limited | System and method for locating a misplaced mobile device |
| CN107886957A (en) * | 2017-11-17 | 2018-04-06 | 广州势必可赢网络科技有限公司 | The voice awakening method and device of a kind of combination Application on Voiceprint Recognition |
-
2018
- 2018-11-20 CN CN201880097795.9A patent/CN112740321A/en active Pending
- 2018-11-20 WO PCT/CN2018/116493 patent/WO2020102991A1/en active Application Filing
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105869655A (en) * | 2015-02-06 | 2016-08-17 | 美商富迪科技股份有限公司 | Audio device and method for voice detection |
| CN106815507A (en) * | 2015-11-30 | 2017-06-09 | 中兴通讯股份有限公司 | Voice wakes up implementation method, device and terminal |
| CN107767863A (en) * | 2016-08-22 | 2018-03-06 | 科大讯飞股份有限公司 | voice awakening method, system and intelligent terminal |
| CN106448663A (en) * | 2016-10-17 | 2017-02-22 | 海信集团有限公司 | Voice wakeup method and voice interaction device |
| CN110520927A (en) * | 2016-12-21 | 2019-11-29 | 爱浮诺亚股份有限公司 | Low-power, the voice command monitored always detection and capture |
| US20180330727A1 (en) * | 2017-05-10 | 2018-11-15 | Ecobee Inc. | Computerized device with voice command input capability |
| CN108831477A (en) * | 2018-06-14 | 2018-11-16 | 出门问问信息科技有限公司 | A kind of audio recognition method, device, equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117524228A (en) * | 2024-01-08 | 2024-02-06 | 腾讯科技（深圳）有限公司 | Voice data processing method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020102991A1 (en) | 2020-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106782554B (en) | Voice awakening method and device based on artificial intelligence | |
| US20170256270A1 (en) | Voice Recognition Accuracy in High Noise Conditions | |
| CN108831477B (en) | Voice recognition method, device, equipment and storage medium | |
| CN110825446B (en) | Parameter configuration method and device, storage medium and electronic equipment | |
| CN110544468B (en) | Application awakening method and device, storage medium and electronic equipment | |
| CN109272991B (en) | Voice interaction method, device, equipment and computer-readable storage medium | |
| US9633655B1 (en) | Voice sensing and keyword analysis | |
| CN106250747B (en) | Information processing method and electronic equipment | |
| CN111508493B (en) | Voice wake-up method and device, electronic equipment and storage medium | |
| CN108052818B (en) | Application starting method and device, storage medium and electronic equipment | |
| CN112669822B (en) | Audio processing method and device, electronic equipment and storage medium | |
| CN108847243B (en) | Voiceprint feature updating method and device, storage medium and electronic equipment | |
| CN112084478A (en) | Multi-user account switching method and device, electronic equipment and storage medium | |
| CN113963695A (en) | Awakening method, awakening device, equipment and storage medium of intelligent equipment | |
| CN112700782A (en) | Voice processing method and electronic equipment | |
| CN112740321A (en) | Method and device for waking up equipment, storage medium and electronic equipment | |
| CN110858479B (en) | Voice recognition model updating method and device, storage medium and electronic equipment | |
| CN108600559B (en) | Control method and device of mute mode, storage medium and electronic equipment | |
| CN111599352B (en) | Voice wake-up method and device, computer equipment and storage medium | |
| CN111641751B (en) | Screen unlocking method and device of terminal equipment, terminal equipment and storage medium | |
| CN110706691B (en) | Voice verification method and device, electronic equipment and computer readable storage medium | |
| CN111369992A (en) | Instruction execution method and device, storage medium and electronic equipment | |
| CN108989551B (en) | Position prompting method and device, storage medium and electronic equipment | |
| US10803870B2 (en) | Electronic device performing operation using voice command and method of operating electronic device | |
| CN111599360B (en) | Wake-up control method and device, storage medium and electronic equipment |
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 |