CN110853644B - Voice wake-up method, device, equipment and storage medium - Google Patents
Voice wake-up method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN110853644B CN110853644B CN201911143250.XA CN201911143250A CN110853644B CN 110853644 B CN110853644 B CN 110853644B CN 201911143250 A CN201911143250 A CN 201911143250A CN 110853644 B CN110853644 B CN 110853644B
- Authority
- CN
- China
- Prior art keywords
- processor
- power consumption
- voice
- consumption mode
- electronic equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000001514 detection method Methods 0.000 claims abstract description 11
- 238000012544 monitoring process Methods 0.000 claims description 36
- 230000015654 memory Effects 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 4
- 230000003993 interaction Effects 0.000 abstract description 4
- 230000001960 triggered effect Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000002618 waking effect Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Power Sources (AREA)
Abstract
The embodiment of the application discloses a voice awakening method, a voice awakening device, voice awakening equipment and a storage medium, and belongs to the field of human-computer interaction. The method comprises the following steps: detecting the equipment state of electronic equipment, wherein the electronic equipment is provided with a plurality of processors, and the power consumption of the processors is different; determining a power consumption mode of the electronic equipment according to the equipment state of the electronic equipment, and determining a processor matched with the power consumption mode of the electronic equipment from the plurality of processors; and performing voice recognition on the monitored voice data through a processor matched with the power consumption mode of the electronic equipment, and performing voice awakening on the electronic equipment according to a voice recognition result. Therefore, the recognition and detection of voice awakening are carried out by adopting processors with different power consumptions aiming at different power consumption modes, the power consumption and the performance of the equipment are balanced, and the influence on the voice awakening passing rate is avoided.
Description
Technical Field
The embodiment of the application relates to the field of human-computer interaction, in particular to a voice awakening method, a device, equipment and a storage medium.
Background
In the field of human-computer interaction, in order to facilitate the control of a user on equipment and improve the enjoyment of human-computer interaction, the user can wake up the electronic equipment with a voice function by a voice wake-up technology. The voice awakening means that when the electronic equipment is in a dormant state, the electronic equipment is awakened through a specific awakening word, so that the electronic equipment is switched from the dormant state to a working state, and the electronic equipment starts to serve a user.
In the related art, in order to save power consumption of an electronic device, a first processor and a second processor may be configured in the electronic device, and power consumption of the first processor is smaller than power consumption of the second processor. During voice awakening detection, the electronic equipment can start a first processor with low power consumption, voice monitoring is carried out through the first processor, and if voice data are monitored, voice recognition is carried out on the monitored voice data through a first voice awakening algorithm of the first processor; if the monitored voice data is recognized to include the appointed awakening word through the first processor, switching the working state of the first processor into a dormant state, starting the second processor, and further performing voice recognition on the monitored voice data through a second voice awakening algorithm of the second processor; if the voice data is recognized to comprise the designated awakening words through the second processor, awakening the electronic equipment; and if the second processor recognizes that the voice data does not contain the appointed awakening word, switching the second processor from the working state to the dormant state, restarting the first processor, and continuing voice monitoring through the first processor.
By adopting the voice awakening method, although the electronic device can be switched back and forth between the first processor with low power consumption and the second processor with high power consumption in the voice awakening process, so as to reduce the power consumption of the electronic device, the performance of the electronic device can be limited to a certain extent, and the voice awakening passing rate is influenced.
Disclosure of Invention
The embodiment of the application provides a voice awakening method, a voice awakening device, voice awakening equipment and a storage medium. The technical scheme is as follows:
in one aspect, an embodiment of the present application provides a voice wake-up method, where the method includes:
detecting a device state of an electronic device, wherein a plurality of processors are configured in the electronic device, and the power consumption of the processors is different;
determining a power consumption mode of the electronic equipment according to the equipment state of the electronic equipment, and determining a processor matched with the power consumption mode of the electronic equipment from the plurality of processors;
and performing voice recognition on the monitored voice data through a processor matched with the power consumption mode of the electronic equipment, and performing voice awakening on the electronic equipment according to a voice recognition result.
In another aspect, a voice wake-up apparatus is provided, the apparatus comprising:
The device comprises a detection module, a processing module and a control module, wherein the detection module is used for detecting the device state of electronic equipment, a plurality of processors are configured in the electronic equipment, and the power consumption of the processors is different;
the determining module is used for determining the power consumption mode of the electronic equipment according to the equipment state of the electronic equipment and determining a processor matched with the power consumption mode of the electronic equipment from the plurality of processors;
and the recognition module is used for performing voice recognition on the monitored voice data through a processor matched with the power consumption mode of the electronic equipment and performing voice awakening on the electronic equipment according to a voice recognition result.
In another aspect, an electronic device is provided that includes a processor and a memory; the memory stores at least one instruction for execution by the processor to implement the voice wake-up method described above.
In another aspect, a computer-readable storage medium is provided, wherein the storage medium stores at least one instruction for execution by a processor to implement the above voice wakeup method.
In another aspect, a computer program product is provided, which stores at least one instruction for execution by a processor to implement the above voice wake-up method.
The technical scheme provided by the application can bring the following beneficial effects at least:
in the embodiment of the application, the equipment state of the electronic equipment is detected firstly, then the power consumption mode of the electronic equipment is determined according to the equipment state of the electronic equipment, the processor matched with the power consumption mode of the electronic equipment is used for carrying out voice recognition on the monitored voice data, and the electronic equipment is subjected to voice awakening according to the voice recognition result, so that the aim of different power consumption modes is fulfilled, the processors with different power consumption are adopted for carrying out voice awakening recognition and detection, so that the actual use scene of the electronic equipment can be combined, the equipment performance is ensured on the premise that the power consumption is acceptable by switching of multiple voice awakening modes, the power consumption and the performance of the equipment are balanced, and the influence on the voice awakening passing rate is avoided.
Drawings
Fig. 1 is a flowchart of a voice wake-up method according to an embodiment of the present application;
fig. 2 is a flowchart of another voice wake-up method provided in an embodiment of the present application;
fig. 3 is a schematic diagram of a voice wakeup process of power consumption mode conversion according to an embodiment of the present application;
fig. 4 is a flowchart of another voice wake-up method provided in an embodiment of the present application;
FIG. 5 is a schematic diagram of another power consumption mode transition voice wake-up process provided in an embodiment of the present application;
fig. 6 is a block diagram of a voice wake-up apparatus according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the present application more clear, the following detailed description of the embodiments of the present application will be made with reference to the accompanying drawings.
Reference herein to "a plurality" means two or more. "and/or" describes the association relationship of the associated object, indicating that there may be three relationships, for example, a and/or B, which may indicate: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
Before the embodiments of the present application are described in detail, an implementation environment of the embodiments of the present application is described. The voice awakening method is applied to electronic equipment, the electronic equipment can be an intelligent sound box, an intelligent television, intelligent wearable equipment or a terminal and the like, and the terminal can be a mobile phone, a tablet computer or a computer and the like. Taking the electronic device as an example, the terminal may collect external voice data by using the method provided in the embodiment of the present application, identify whether the voice data includes a specific awakening word, and awaken the terminal according to the identification result.
In the related art, only a fixed voice wake-up scheme is generally adopted for voice wake-up in various complex scenes, such as performing voice recognition by a first processor with low power consumption, after the first processor recognizes that the acquired voice data has the appointed awakening words, the second processor with high power consumption is started to perform voice recognition, so that the power consumption of the terminal can be reduced to a certain extent, however, when the electronic device itself is in a high power consumption mode, it is not necessary to consider the limitation of power consumption, more resources should be utilized to improve the performance, because the power consumption caused by the voice wakeup process is very small and almost negligible compared to the power consumption of the electronic device itself, the user experience should be paid attention to in this scenario, if the first processor with low power consumption is first passed through, the wake-up throughput rate is affected due to the limitation of resources and power consumption.
In the embodiment of the present application, in order to solve the problems in the related art, a voice wake-up method capable of balancing power consumption and performance of an electronic device in a complex scene is provided, that is, a voice wake-up method in a multi-scene mixed mode is provided, which is described in detail in the embodiment of fig. 1 below.
Fig. 1 is a flowchart of a voice wake-up method provided in an embodiment of the present application, where the method is applied to an electronic device, and as shown in fig. 1, the method includes the following steps:
step 101: the method comprises the steps of detecting the device state of the electronic device, wherein a plurality of processors are configured in the electronic device, and the power consumption of the processors is different.
The device state of the electronic device may include a screen state and a sound output state, and may also include other device states, such as a memory state and an environmental noise state.
The screen state comprises a screen-off state and a screen-on state. The sound output state includes a state with sound output and a state without sound output. As an example, the sound output status is used to indicate whether a speaker of the electronic device has sound output, i.e. whether the electronic device is playing audio or video-audio.
Among other things, an electronic device may be configured with multiple processors that consume different amounts of power. For example, the electronic device may include two processors with different power consumptions, namely a first processor and a second processor, and the power consumption of the first processor is smaller than the power consumption of the second processor.
Alternatively, the electronic device is also configured with processors of three different power consumptions. For example, the electronic device is configured with a first processor and a second processor, and the second processor includes a first sub-processor and a second sub-processor, the power consumption of the first sub-processor and the power consumption of the second sub-processor are both greater than that of the first processor, and the power consumption of the first sub-processor is less than that of the second sub-processor.
Of course, the electronic device may also include four or more processors with different power consumptions, which is not limited in this embodiment of the application.
Step 102: according to the device state of the electronic device, the power consumption mode of the electronic device is determined, and a processor matched with the power consumption mode of the electronic device is determined from the plurality of processors.
In the embodiment of the application, the electronic device can be divided into multiple different power consumption modes according to the device state of the electronic device, and the different device states correspond to the different power consumption modes. The electronic device is provided with a plurality of processors, different power consumption modes are matched with different processors, and the processors matched with the power consumption modes are sampled in the corresponding power consumption modes to carry out voice wake-up processing.
As an example, if the power consumption mode of the electronic device is divided into two power consumption modes, and the plurality of processors configured in the electronic device include a first processor and a second processor, and the power consumption of the first processor is smaller than the power consumption of the second processor, the power consumption mode of the electronic device is determined according to the device state of the electronic device, and determining a processor from the plurality of processors that matches the power consumption mode of the electronic device may include the following two cases:
In the first case: if the screen state of the electronic equipment is a screen-off state and the sound output state of the electronic equipment is a state without sound output, determining that the power consumption mode of the electronic equipment is a first power consumption mode, and determining the first processor and the second processor as processors matched with the first power consumption mode.
Wherein the first power consumption mode is a low power consumption mode. When the screen state of the electronic device is the screen off state and the electronic device does not output sound, the power consumption mode of the electronic device at the time can be determined as the low power consumption mode, and the first processor and the second processor are determined as processors matched with the low power consumption mode, so that voice recognition is performed through the first processor first, and then voice recognition is performed through the second processor.
As one example, the first processor is a low power processor and the second processor is a high power processor that consumes more power than the first processor. Illustratively, the first Processor is a DSP (Digital Signal Processor), a high-fidelity (high fidelity) chip, a ceva (think) chip, or the like. The second processor may be an ARM (Advanced RISC Machine), an ADSP (Analog Device Instrument DSP, a digital signal processing chip manufactured by american Analog devices corporation), a CM4(Cortex-M4, a processor), or the like.
As an example, the first processor performs voice recognition on the monitored voice data by using a first voice wakeup algorithm to recognize whether a specified wakeup word exists in the voice data; and the second processor performs voice recognition on the monitored voice data by adopting a second voice awakening algorithm so as to recognize whether the designated awakening words exist in the voice data. Moreover, the speech recognition accuracy of the first voice wake-up algorithm is less than the second voice wake-up algorithm.
In the second case: and if the screen state of the electronic equipment is a bright screen state and/or the sound output state of the electronic equipment is a sound output state, determining that the power consumption mode of the electronic equipment is a second power consumption mode, and determining the second processor as a processor matched with the second power consumption mode.
Wherein the power consumption of the second power consumption mode is greater than the power consumption of the first power consumption mode. For example, the first power consumption mode is a low power consumption mode, and the second power consumption mode is a high power consumption mode.
When the screen state of the electronic device is a bright screen state or the electronic device has voice output, the power consumption mode of the electronic device at the moment can be determined as a high power consumption mode, and the second processor is determined as a processor matched with the high power consumption mode, so that voice recognition is directly performed through the high power consumption second processor without passing through the first processor, and the device performance and the awakening passing rate are improved.
In the embodiment of the application, when the electronic device is in the low power consumption mode, the voice monitoring and recognition can be performed by adopting a low power consumption voice awakening scheme matched with the low power consumption mode. If the electronic equipment is switched from the low-power-consumption mode to the high-power-consumption mode, the low-power-consumption voice awakening scheme can be switched to a high-power-consumption voice awakening scheme matched with the high-power-consumption mode for voice monitoring and recognition. If the electronic equipment is switched from the high-power-consumption mode to the low-power-consumption mode, the high-power-consumption voice awakening scheme can be switched to be in voice monitoring and recognition with the low-power-consumption voice awakening scheme. That is, along with the switching of the power consumption mode of the electronic device, the appropriate voice awakening scheme can be switched therewith, so that the electronic device can cope with complex use scenes, and the switching of various voice awakening schemes ensures that the performance of the device is guaranteed and better awakening experience is brought on the premise that the power consumption is acceptable.
As another example, it is also possible to divide the power consumption mode of the electronic device into three power consumption modes, configure three processors having different power consumption in the electronic device, and then determine a processor matching each power consumption mode from among the three processors, respectively.
In one possible implementation manner, the second power consumption mode may include a breaking (barkeln) mode and a high power consumption mode, power consumption of the breaking mode and the high power consumption mode is greater than that of the first power consumption mode, the second processor includes a first sub-processor and a second sub-processor, power consumption of the first sub-processor and power consumption of the second sub-processor are greater than that of the first processor, and power consumption of the first sub-processor is less than that of the second sub-processor, then the power consumption mode of the electronic device is determined according to the device state of the electronic device, and determining, from the plurality of processors, a processor that matches the power consumption mode of the electronic device may include the following three cases:
in the first case: if the screen state of the electronic equipment is a screen-off state and the sound output state of the electronic equipment is a state without sound output, determining that the power consumption mode of the electronic equipment is a first power consumption mode, and determining the first processor and the first sub-processor as processors matched with the first power consumption mode.
Wherein the first power consumption mode is a low power consumption mode. When the screen state of the electronic device is the screen off state and the electronic device does not output sound, the power consumption mode of the electronic device at the moment can be determined as the low power consumption mode, and the first processor and the first sub-processor are determined as the processors matched with the low power consumption mode, so that voice recognition is performed through the first processor first, and then voice recognition is performed through the first sub-processor.
As an example, the first processor performs voice recognition on the monitored voice data by using a first voice wakeup algorithm to recognize whether a specified wakeup word exists in the voice data; the first sub-processor performs voice recognition on the monitored voice data by adopting a second voice wake-up algorithm so as to recognize whether the designated wake-up words exist in the voice data. Moreover, the speech recognition accuracy of the first voice wake-up algorithm is less than that of the second voice wake-up algorithm.
In the second case: if the screen state of the electronic equipment is a screen-on state or a screen-off state, and the sound output state of the electronic equipment is a sound output state, determining that the power consumption mode of the electronic equipment is an interrupt mode, and determining the first sub-processor and the second sub-processor as processors matched with the interrupt mode.
Since the power consumption of each of the first and second sub-processors is greater than that of the first processor and the power consumption of the first sub-processor is less than that of the second sub-processor, the first processor may be referred to as a low power consumption processor, the first sub-processor as a sub-power consumption processor, and the second sub-processor as a high power consumption processor.
When the sound output state of the electronic device is a sound output state, it indicates that the electronic device is playing audio, and at this time, the electronic device can monitor not only the wake-up voice of the user, but also the sound emitted by the electronic device itself, and in this case, the power consumption mode in which the electronic device is located can be determined as an interrupt mode. When the electronic equipment is in the interrupt mode, the first sub-processor and the second sub-processor can be determined as processors matched with the interrupt mode, so that voice recognition is carried out through the first sub-processor firstly, and then voice recognition is carried out through the second sub-processor.
As an example, the first sub-processor performs voice recognition on the monitored voice data by using a third voice wake-up algorithm to recognize whether a designated wake-up word is included in the voice data; the second sub-processor performs voice recognition on the monitored voice data by adopting a second voice wake-up algorithm so as to recognize whether the voice data comprises a designated wake-up word. Moreover, the third voice wake-up algorithm has a voice recognition accuracy less than the second voice wake-up algorithm.
In a third case: and if the screen state of the electronic equipment is a bright screen state and the sound output state of the electronic equipment is a state without sound output, determining that the power consumption mode of the electronic equipment is a high power consumption mode, and determining the second sub-processor as a processor matched with the high power consumption mode.
Wherein the second sub-processor is a high power processor. When the electronic equipment is in a bright screen state and no sound is output, the power consumption mode of the electronic equipment at the moment can be determined as a high power consumption mode, the second sub-processor is determined as a processor matched with the high power consumption mode, so that voice recognition is directly carried out on the second sub-processor with high power consumption instead of the first processor or the first sub-processor, and the equipment performance and the wake-up passing rate are improved.
In the embodiment of the application, when the electronic device is in the low power consumption mode, the voice monitoring and the recognition can be performed by adopting a low power consumption voice awakening scheme matched with the low power consumption mode. If the electronic equipment is switched from the low-power-consumption mode to the interrupt mode, the low-power-consumption voice wake-up scheme can be switched to a second high-power-consumption voice wake-up scheme matched with the interrupt mode for voice monitoring and recognition. If the electronic equipment is switched from the interrupt mode to the high power consumption mode, the secondary high power consumption voice awakening scheme can be switched to be in voice monitoring and recognition with the high power consumption voice awakening scheme. That is, when the electronic device switches between the low power consumption mode, the interrupt mode and the high power consumption mode, the electronic device can switch the matched voice awakening scheme accordingly, so that the electronic device can deal with a complex use scene, and the switching of various voice awakening schemes ensures that the device performance is guaranteed and better voice awakening experience is brought on the premise that the power consumption is acceptable.
Step 103: and performing voice recognition on the monitored voice data through a processor matched with the power consumption mode of the electronic equipment, and performing voice awakening on the electronic equipment according to a voice recognition result.
As an example, if the power consumption modes of the electronic device are divided into two power consumption modes, and the multiple processors configured in the electronic device include a first processor and a second processor, where the power consumption of the first processor is less than the power consumption of the second processor, performing voice recognition on the monitored voice data by using a processor matched with the power consumption mode of the electronic device, and performing voice wake-up on the electronic device according to a voice recognition result may include the following two cases:
in the first case: if the power consumption mode of the electronic equipment is a first power consumption mode, voice monitoring is carried out through the first processor, and if voice data are monitored, voice recognition is carried out on the monitored voice data through a first voice awakening algorithm; and if the voice data is recognized to comprise the appointed awakening word through the first processor, performing voice recognition on the monitored voice data through the second processor by adopting a second voice awakening algorithm.
Furthermore, after the second processor performs voice recognition on the monitored voice data by adopting a second voice wake-up algorithm, if the voice data is recognized to include a designated wake-up word by the second processor, the electronic device can be directly triggered to wake up, or voiceprint recognition can be performed on the voice data by the second processor, and if the recognized voiceprint features are matched with the stored voiceprint features, the electronic device is triggered to wake up.
In the second case: and if the power consumption mode of the electronic equipment is the second power consumption mode, performing voice monitoring through the second processor, and if voice data is monitored, performing voice recognition on the monitored voice data by adopting a second voice awakening algorithm.
Further, after the second voice wake-up algorithm is adopted to perform voice recognition on the monitored voice data, if the voice data is recognized to include the designated wake-up word through the second processor, the electronic device can be directly triggered to wake up, or voiceprint recognition can be performed on the voice data through the second processor, and if the recognized voiceprint features are matched with the stored voiceprint features, the electronic device is triggered to wake up.
As another example, it is also possible to divide the power consumption mode of the electronic device into three power consumption modes, configure three processors having different power consumption in the electronic device, and then determine a processor matching each power consumption mode from among the three processors, respectively.
In a possible implementation manner, if the second power consumption mode includes an interrupt mode and a high power consumption mode, and the second processor includes the first sub-processor and the second sub-processor, performing voice recognition on the monitored voice data by using the processor matched with the power consumption mode where the electronic device is located, and performing voice wake-up on the electronic device according to a voice recognition result may include the following three cases:
In the first case: if the power consumption mode of the electronic equipment is a first power consumption mode, performing voice monitoring through a first processor, and if voice data is monitored, performing voice recognition on the monitored voice data by adopting a first voice awakening algorithm; and if the voice data recognized by the first processor comprises the appointed awakening word, performing voice recognition on the monitored voice data by adopting a second voice awakening algorithm through the second sub-processor.
Further, after the second sub-processor performs voice recognition on the monitored voice data by adopting a second voice wake-up algorithm, if the voice data is recognized to include the designated wake-up word by the second sub-processor, the electronic device can be directly triggered to wake up, or voiceprint recognition can be performed on the voice data by the second sub-processor, and if the recognized voiceprint features are matched with the stored voiceprint features, the electronic device is triggered to wake up.
In the second case: if the power consumption mode of the electronic equipment is an interruption mode, voice monitoring is carried out through the first sub-processor, if voice data are monitored, echo cancellation is carried out on the monitored voice data, and voice recognition is carried out on the voice data after the echo cancellation by adopting a third voice awakening algorithm; and if the voice data is recognized to comprise the appointed awakening word, performing voice recognition on the monitored voice data by adopting a second voice awakening algorithm through a second sub-processor.
Because when the electronic equipment is in the interruption mode, the electronic equipment also outputs sound, and when the electronic equipment monitors the sound through the first sub-processor, the electronic equipment not only can monitor the voice data of a user, but also can monitor the sound data sent by the electronic equipment, so that in order to improve the accuracy of voice recognition, echo cancellation can be firstly carried out on the monitored voice data so as to eliminate the sound sent by the electronic equipment.
In a third case: if the power consumption mode of the electronic equipment is a high power consumption mode, voice monitoring is carried out through the second sub-processor, and if voice data are monitored, voice recognition is carried out on the monitored voice data through a second voice awakening algorithm.
Further, after the third voice wake-up algorithm is adopted to perform voice recognition on the monitored voice data, if the voice data is recognized to include the designated wake-up word, the electronic device can be directly triggered to wake up, or voiceprint recognition can be performed on the voice data through the second sub-processor, and if the recognized voiceprint features are matched with the stored voiceprint features, the electronic device is triggered to wake up.
It should be noted that, in the embodiment of the present application, the manner of triggering to wake up the electronic device includes at least one of triggering the electronic device to turn on a screen, triggering the electronic device to turn on the screen and unlock the electronic device, triggering the electronic device to unlock the electronic device, finding the electronic device, and waking up a voice assistant of the electronic device.
As an example, if the screen state of the electronic device is an off-screen state, the manner of triggering the wake-up of the electronic device includes: triggering the electronic equipment to light the screen, triggering the electronic equipment to light the screen and unlock, searching the electronic equipment, and waking up at least one of the voice assistants of the electronic equipment. If the screen state of the electronic device is a bright screen state, the manner of triggering and awakening the electronic device comprises the following steps: triggering at least one of unlocking the electronic device, finding the electronic device, and waking up a voice assistant of the electronic device.
In the embodiment of the application, the equipment state of the electronic equipment is detected firstly, then the power consumption mode of the electronic equipment is determined according to the equipment state of the electronic equipment, the processor matched with the power consumption mode of the electronic equipment is used for carrying out voice recognition on the monitored voice data, and the electronic equipment is subjected to voice awakening according to the voice recognition result, so that the aim of different power consumption modes is fulfilled, the processors with different power consumption are adopted for carrying out voice awakening recognition and detection, so that the actual use scene of the electronic equipment can be combined, the equipment performance is ensured on the premise that the power consumption is acceptable by switching of multiple voice awakening modes, the power consumption and the performance of the equipment are balanced, and the influence on the voice awakening passing rate is avoided. In addition, the embodiment of the application can automatically identify the mode of the equipment, and balance between power consumption and performance is balanced by combining the characteristics of the equipment. Moreover, the advantages and disadvantages of the low-power-consumption processor and the high-power-consumption processor can be found accurately, a mixed-mode voice awakening scheme is provided by combining the scene characteristics of the equipment, and the problem that the performance of the equipment is limited and the voice awakening passing rate is influenced due to the fixed voice awakening scheme adopted in the related technology is solved.
A voice wake-up method of dividing the power consumption mode of the electronic device into two power consumption modes will be exemplified next. Fig. 2 is a flowchart of another voice wake-up method provided in an embodiment of the present application, where the method is applied to a voice wake-up apparatus, and as shown in fig. 2, the method includes the following steps:
step 201: a device state of an electronic device is detected, the device state including a screen state and a sound output state, the electronic device having a low power consumption processor and a high power consumption processor disposed therein.
Step 202: and if the screen state of the electronic equipment is the screen off state and the sound output state of the electronic equipment is the state without sound output, determining that the electronic equipment is in the low power consumption mode.
Step 203: if the electronic equipment is in the low-power-consumption mode, firstly carrying out voice monitoring through the low-power-consumption processor, carrying out voice recognition on the monitored voice data, and then carrying out voice recognition on the voice data through the high-power-consumption processor.
As an example, voice monitoring is performed through a low-power processor, and if voice data is monitored, voice recognition is performed on the monitored voice data by using a first voice wake-up algorithm; and if the voice data is recognized to comprise the appointed awakening word, performing voice recognition on the monitored voice data by adopting a second voice awakening algorithm through the high-power-consumption processor. And the voice recognition accuracy of the second voice awakening algorithm is greater than that of the first voice awakening algorithm.
Step 204: if the voice data is recognized to comprise the appointed awakening word through the high-power-consumption processor, the high-power-consumption processor continues to perform voiceprint recognition on the voice data, and if the voiceprint recognition is passed, the electronic equipment is triggered to be awakened.
Step 205: and if the screen state of the electronic equipment is a bright screen state and/or the sound output state of the electronic equipment is a sound output state, determining that the electronic equipment is in a high power consumption mode.
Step 206: and if the electronic equipment is in the high power consumption mode, directly performing voice monitoring through the high power consumption processor, and performing voice recognition on the monitored voice data.
As an example, if the electronic device is in the high power consumption mode, performing voice monitoring through the high power consumption processor, and if voice data is monitored, performing voice recognition on the monitored voice data by using a second voice wake-up algorithm.
Step 207: and if the voice data is recognized to comprise the appointed awakening word through the high-power-consumption processor, performing voiceprint recognition on the voice data through the high-power-consumption processor, and if the voiceprint recognition is passed, triggering and awakening the electronic equipment.
In the embodiment of the application, the power consumption modes of the electronic equipment can be divided into the low power consumption mode and the high power consumption mode, when the electronic equipment is switched between the low power consumption mode and the high power consumption mode, the electronic equipment can switch the matched voice awakening scheme accordingly, so that the electronic equipment can cope with complex use scenes, the equipment performance is guaranteed on the premise that the power consumption is acceptable through switching of various voice awakening schemes, and better voice awakening experience is brought.
As an example, a schematic diagram of the voice wake-up scheme that the electronic device switches to match when the electronic device switches between the low power consumption mode and the high power consumption mode may be as shown in fig. 3.
A voice wake-up method of dividing the power consumption mode of the electronic device into three power consumption modes will be exemplified next. Fig. 4 is a flowchart of another voice wake-up method provided in an embodiment of the present application, where the method is applied to a voice wake-up apparatus, and as shown in fig. 4, the method includes the following steps:
step 401: the method comprises the steps of detecting the device state of the electronic device, wherein the device state comprises a screen state and a sound output state, and the electronic device is provided with a low-power-consumption processor, a second-highest-power-consumption processor and a high-power-consumption processor.
Step 402: and if the screen state of the electronic equipment is the screen off state and the sound output state of the electronic equipment is the state without sound output, determining that the electronic equipment is in the low power consumption mode.
Step 403: if the electronic equipment is in the low-power-consumption mode, firstly carrying out voice monitoring through the low-power-consumption processor, carrying out voice recognition on the monitored voice data, and then carrying out voice recognition on the voice data through the high-power-consumption processor.
As an example, voice monitoring is performed through a low-power processor, and if voice data is monitored, voice recognition is performed on the monitored voice data by using a first voice wake-up algorithm; and if the voice data comprises the appointed awakening words, performing voice recognition on the monitored voice data by adopting a second voice awakening algorithm through the high-power-consumption processor. And the voice recognition accuracy of the second voice awakening algorithm is greater than that of the first voice awakening algorithm.
Step 404: if the voice data is recognized to comprise the appointed awakening word through the high-power-consumption processor, the high-power-consumption processor continues to perform voiceprint recognition on the voice data, and if the voiceprint recognition is passed, the electronic equipment is triggered to be awakened.
Step 405: and if the screen state of the electronic equipment is a bright screen state or a screen off state and the sound output state of the electronic equipment is a sound output state, determining that the electronic equipment is in the interrupt mode.
Step 406: if the electronic equipment is in the interruption mode, firstly carrying out voice monitoring through the secondary high-power processor, carrying out voice recognition on the monitored voice data, and then carrying out voice recognition on the voice data through the high-power processor.
As an example, if the electronic device is in the interrupt mode, first performing voice monitoring through the second highest power processor, if voice data is monitored, performing echo cancellation on the monitored voice data through the second highest power processor, performing voice recognition on the voice data after echo cancellation by using a third voice wake-up algorithm, and if the voice data is recognized to include a designated wake-up word, performing voice recognition on the voice data through the second highest power processor by using a second voice wake-up algorithm. And the voice recognition accuracy of the second voice awakening algorithm is higher than that of the third voice awakening algorithm.
In addition, the third voice wakeup algorithm may be the same as or different from the first voice wakeup algorithm, which is not limited in this embodiment of the present application. For example, the third voice wake-up algorithm may be a multi-microphone voice wake-up algorithm.
Step 407: if the voice data is recognized to comprise the appointed awakening word through the high-power-consumption processor, the high-power-consumption processor continues to perform voiceprint recognition on the voice data, and if the voiceprint recognition is passed, the electronic equipment is triggered to be awakened.
Step 408: and if the screen state of the electronic equipment is a bright screen state and the sound output state of the electronic equipment is a state without sound output, determining that the electronic equipment is in a high power consumption mode.
Step 409: and if the electronic equipment is in the high power consumption mode, directly performing voice monitoring through the high power consumption processor, and performing voice recognition on the monitored voice data.
As an example, if the electronic device is in the high power consumption mode, performing voice monitoring through the high power consumption processor, and if voice data is monitored, performing voice recognition on the monitored voice data by using a second voice wake-up algorithm.
Step 410: and if the voice data is recognized to comprise the appointed awakening word through the high-power-consumption processor, performing voiceprint recognition on the voice data through the high-power-consumption processor, and if the voiceprint recognition is passed, triggering and awakening the electronic equipment.
In the embodiment of the application, the power consumption mode of the electronic equipment can be divided into the low power consumption mode, the interruption mode and the high power consumption mode, when the electronic equipment is switched among the low power consumption mode, the interruption mode and the high power consumption mode, the electronic equipment can switch the matched voice awakening scheme along with the power consumption mode, so that the electronic equipment can deal with the complex use scene, the equipment performance is ensured on the premise of acceptable power consumption through switching of various voice awakening schemes, and better voice awakening experience is brought.
As an example, a schematic diagram of the electronic device switching the matched voice wake-up scheme when the electronic device is in the low power consumption mode, the interrupt mode and the high power consumption mode may be as shown in fig. 5.
Fig. 6 is a block diagram of an apparatus for waking up a voice device according to an embodiment of the present application, and as shown in fig. 6, the apparatus includes: a detection module 601, a determination module 602, and an identification module 603.
A detection module 601, configured to detect a device state of an electronic device, where the electronic device is configured with multiple processors, and power consumptions of the multiple processors are different;
a determining module 602, configured to determine, according to a device state of the electronic device, a power consumption mode in which the electronic device is located, and determine, from the multiple processors, a processor that matches the power consumption mode in which the electronic device is located;
the recognition module 603 is configured to perform voice recognition on the monitored voice data through a processor matched with the power consumption mode of the electronic device, and perform voice wake-up on the electronic device according to a voice recognition result.
Optionally, the device state of the electronic device includes a screen state and a sound output state.
Optionally, the plurality of processors includes a first processor and a second processor, and the power consumption of the first processor is less than the power consumption of the second processor;
The determining module 602 is configured to:
if the screen state of the electronic equipment is a screen off state and the sound output state of the electronic equipment is a state without sound output, determining that the power consumption mode of the electronic equipment is a first power consumption mode, and determining the first processor and the second processor as processors matched with the first power consumption mode;
if the screen state of the electronic equipment is a bright screen state and/or the sound output state of the electronic equipment is a sound output state, determining that the power consumption mode of the electronic equipment is a second power consumption mode, and determining the second processor as a processor matched with the second power consumption mode, wherein the power consumption of the second power consumption mode is greater than that of the first power consumption mode.
Optionally, the identifying module 603 is configured to:
if the power consumption mode of the electronic equipment is the first power consumption mode, performing voice monitoring through the first processor, and if voice data is monitored, performing voice recognition on the monitored voice data by adopting a first voice awakening algorithm; if the voice data is recognized to comprise the appointed awakening word, performing voice recognition on the monitored voice data by adopting a second voice awakening algorithm through the second processor;
And if the power consumption mode of the electronic equipment is the second power consumption mode, performing voice monitoring through the second processor, and if voice data are monitored, performing voice recognition on the monitored voice data by adopting the second voice awakening algorithm.
Optionally, the identifying module 603 is configured to:
if the power consumption mode of the electronic equipment is the second power consumption mode and the sound output state of the electronic equipment is a sound output state, performing voice monitoring through the second processor;
and if the voice data are monitored, performing echo cancellation on the monitored voice data through the second processor, and performing voice recognition on the voice data subjected to echo cancellation by adopting the second voice awakening algorithm.
Optionally, the second power consumption mode includes a break mode and a high power consumption mode, the power consumption of the break mode and the high power consumption mode is greater than that of the first power consumption mode, the second processor includes a first sub-processor and a second sub-processor, the power consumption of the first sub-processor and the power consumption of the second sub-processor are greater than that of the first processor, and the power consumption of the first sub-processor is less than that of the second sub-processor;
The determining module 602 is configured to:
if the screen state of the electronic equipment is a screen lightening state or a screen extinguishing state, and the sound output state of the electronic equipment is a sound output state, determining that the power consumption mode of the electronic equipment is the interrupt mode, and determining the first sub-processor and the second sub-processor as processors matched with the interrupt mode;
and if the screen state of the electronic equipment is a bright screen state and the sound output state of the electronic equipment is a state without sound output, determining that the power consumption mode of the electronic equipment is the high power consumption mode, and determining the second sub-processor as a processor matched with the high power consumption mode.
Optionally, the identifying module 603 is configured to:
if the power consumption mode of the electronic equipment is the interrupt mode, voice monitoring is carried out through the first sub-processor, if voice data are monitored, echo cancellation is carried out on the monitored voice data, and voice recognition is carried out on the voice data after the echo cancellation by adopting a third voice wake-up algorithm; if the voice data is recognized to comprise the designated awakening word, performing voice recognition on the monitored voice data by adopting a second voice awakening algorithm through the second sub-processor;
If the power consumption mode of the electronic equipment is the high power consumption mode, voice monitoring is carried out through the second sub-processor, and if voice data are monitored, voice recognition is carried out on the monitored voice data through the second voice wake-up algorithm.
In the embodiment of the application, the equipment state of the electronic equipment is detected firstly, then the power consumption mode of the electronic equipment is determined according to the equipment state of the electronic equipment, the processor matched with the power consumption mode of the electronic equipment is used for carrying out voice recognition on the monitored voice data, and the electronic equipment is subjected to voice awakening according to the voice recognition result, so that the recognition and detection of voice awakening are carried out by adopting the processors with different power consumptions aiming at different power consumption modes, the actual use scene of the electronic equipment can be combined, the equipment performance is ensured on the premise of acceptable power consumption by switching of various voice awakening modes, the power consumption and the performance of the equipment are balanced, and the influence on the voice awakening passing rate is avoided.
It should be noted that: in the voice wake-up apparatus provided in the foregoing embodiment, only the division of the functional modules is used for illustration when performing voice wake-up, and in practical applications, the function distribution may be completed by different functional modules according to needs, that is, the internal structure of the apparatus is divided into different functional modules, so as to complete all or part of the functions described above. In addition, the voice wake-up apparatus and the voice wake-up method provided in the foregoing embodiments belong to the same concept, and specific implementation processes thereof are described in the method embodiments in detail and are not described herein again.
Fig. 7 is a schematic structural diagram of an electronic device 700 provided in an embodiment of the present application, where the electronic device may be a smart sound box, a smart television, a smart wearable device or a terminal, and the terminal may be a mobile phone, a tablet computer, a computer, or the like. The electronic device may have a relatively large difference due to different configurations or performances, and may include one or more processors 701 and one or more memories 702, where the memory 702 stores therein at least one instruction, and the at least one instruction is loaded and executed by the processor 701 to implement the method for identifying an access point provided in the foregoing method embodiments. For example, the electronic device includes a low power processor and a high power processor. Alternatively, the electronic device includes a low power processor, a second highest power processor, and a high power processor. Of course, the electronic device may further have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input/output, and the electronic device may further include other components for implementing the functions of the device, which is not described herein again.
The embodiment of the present application further provides a computer-readable medium, where at least one instruction is stored, and the at least one instruction is loaded and executed by the processor to implement the call method according to the above embodiments.
The embodiment of the present application further provides a computer program product, where at least one instruction is stored, and the at least one instruction is loaded and executed by the processor to implement the call method according to the above embodiments.
Those skilled in the art will recognize that the functionality described in the embodiments of the present application may be implemented in hardware, software, firmware, or any combination thereof, in one or more of the examples described above. When implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
The above description is intended only to illustrate the alternative embodiments of the present application, and should not be construed as limiting the present application, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (12)
1. A voice wake-up method, the method comprising:
detecting a device state of an electronic device, wherein the electronic device is provided with a plurality of processors, the plurality of processors comprise a first processor and a second processor, the power consumption of the first processor is less than that of the second processor, and the device state comprises a screen state and a sound output state;
determining a power consumption mode of the electronic equipment according to the equipment state of the electronic equipment, determining a processor matched with the power consumption mode of the electronic equipment from the plurality of processors, wherein a bright screen state and/or a sound output state are/is matched with the second processor, if the screen state of the electronic equipment is in a screen extinguishing state and the sound output state of the electronic equipment is a state without sound output, determining the power consumption mode of the electronic equipment to be a first power consumption mode, and determining the first processor and the second processor to be processors matched with the first power consumption mode;
the method comprises the steps of carrying out voice recognition on monitored voice data through a processor matched with a power consumption mode where the electronic equipment is located, and carrying out voice awakening on the electronic equipment according to a voice recognition result, wherein the second processor is used for carrying out echo cancellation on the monitored voice data when the sound output state of the electronic equipment is a sound output state, and carrying out voice recognition on the voice data after the echo cancellation by adopting a second voice awakening algorithm, and the accuracy of the second voice awakening algorithm is higher than that of a first voice awakening algorithm corresponding to the first processor.
2. The method according to claim 1, wherein determining the power consumption mode of the electronic device according to the device state of the electronic device, and determining a processor from the plurality of processors that matches the power consumption mode of the electronic device comprises:
if the screen state of the electronic equipment is a bright screen state and/or the sound output state of the electronic equipment is a sound output state, determining that the power consumption mode of the electronic equipment is a second power consumption mode, and determining the second processor as a processor matched with the second power consumption mode, wherein the power consumption of the second power consumption mode is greater than that of the first power consumption mode.
3. The method of claim 2, wherein performing voice recognition on the intercepted voice data through a processor matching a power consumption pattern of the electronic device comprises:
if the power consumption mode of the electronic equipment is the first power consumption mode, voice monitoring is carried out through the first processor, and if voice data are monitored, voice recognition is carried out on the monitored voice data through a first voice awakening algorithm; if the voice data is recognized to comprise the appointed awakening word, performing voice recognition on the monitored voice data by adopting a second voice awakening algorithm through the second processor;
And if the power consumption mode of the electronic equipment is the second power consumption mode, performing voice monitoring through the second processor, and if voice data are monitored, performing voice recognition on the monitored voice data by adopting the second voice awakening algorithm.
4. The method of claim 2, wherein the second power consumption mode includes a break mode and a high power consumption mode, wherein the break mode and the high power consumption mode both consume more power than the first power consumption mode, wherein the second processor includes a first sub-processor and a second sub-processor, wherein the first sub-processor and the second sub-processor each consume more power than the first processor, and wherein the first sub-processor consumes less power than the second sub-processor;
if the screen state of the electronic device is a bright screen state and/or the sound output state of the electronic device is a sound output state, determining that the power consumption mode in which the electronic device is located is a second power consumption mode, and determining the second processor as a processor matched with the high power consumption mode, including:
if the screen state of the electronic equipment is a screen lightening state or a screen extinguishing state, and the sound output state of the electronic equipment is a sound output state, determining that the power consumption mode of the electronic equipment is the interrupt mode, and determining the first sub-processor and the second sub-processor as processors matched with the interrupt mode;
And if the screen state of the electronic equipment is a bright screen state and the sound output state of the electronic equipment is a state without sound output, determining that the power consumption mode of the electronic equipment is the high power consumption mode, and determining the second sub-processor as a processor matched with the high power consumption mode.
5. The method of claim 4, wherein performing voice recognition on the intercepted voice data through a processor matching a power consumption pattern of the electronic device comprises:
if the power consumption mode of the electronic equipment is the interrupt mode, voice monitoring is carried out through the first sub-processor, if voice data are monitored, echo cancellation is carried out on the monitored voice data, and voice recognition is carried out on the voice data after the echo cancellation by adopting a third voice wake-up algorithm; if the voice data is recognized to comprise the appointed awakening word, performing voice recognition on the monitored voice data by adopting a second voice awakening algorithm through the second sub-processor;
if the power consumption mode of the electronic equipment is the high power consumption mode, voice monitoring is carried out through the second sub-processor, and if voice data are monitored, voice recognition is carried out on the monitored voice data through the second voice wake-up algorithm.
6. A voice wake-up apparatus, the apparatus comprising:
the device comprises a detection module, a processing module and a control module, wherein the detection module is used for detecting the device state of electronic equipment, a plurality of processors are configured in the electronic equipment, the plurality of processors comprise a first processor and a second processor, the power consumption of the first processor is smaller than that of the second processor, and the device state comprises a screen state and a sound output state;
the determining module is used for determining the power consumption mode of the electronic equipment according to the equipment state of the electronic equipment, determining a processor matched with the power consumption mode of the electronic equipment from the plurality of processors, wherein the screen-on state and/or the sound output state are/is matched with the second processor, if the screen state of the electronic equipment is the screen-off state and the sound output state of the electronic equipment is the state without sound output, determining the power consumption mode of the electronic equipment to be a first power consumption mode, and determining the first processor and the second processor to be processors matched with the first power consumption mode;
the recognition module is used for performing voice recognition on monitored voice data through a processor matched with a power consumption mode where the electronic equipment is located, and performing voice awakening on the electronic equipment according to a voice recognition result, wherein the second processor is used for performing echo cancellation on the monitored voice data when the sound output state of the electronic equipment is a sound output state, and performing voice recognition on the voice data after echo cancellation by adopting a second voice awakening algorithm, and the accuracy of the second voice awakening algorithm is higher than that of a first voice awakening algorithm corresponding to the first processor.
7. The apparatus of claim 6, wherein the determination module is configured to:
if the screen state of the electronic equipment is a bright screen state and/or the sound output state of the electronic equipment is a sound output state, determining that the power consumption mode of the electronic equipment is a second power consumption mode, and determining the second processor as a processor matched with the second power consumption mode, wherein the power consumption of the second power consumption mode is greater than that of the first power consumption mode.
8. The apparatus of claim 7, wherein the identification module is configured to:
if the power consumption mode of the electronic equipment is the first power consumption mode, performing voice monitoring through the first processor, and if voice data is monitored, performing voice recognition on the monitored voice data by adopting a first voice awakening algorithm; if the voice data is recognized to comprise the appointed awakening word, performing voice recognition on the monitored voice data by adopting a second voice awakening algorithm through the second processor;
and if the power consumption mode of the electronic equipment is the second power consumption mode, performing voice monitoring through the second processor, and if voice data is monitored, performing voice recognition on the monitored voice data by adopting the second voice awakening algorithm.
9. The apparatus of claim 7, wherein the second power consumption mode comprises a break mode and a high power consumption mode, wherein the break mode and the high power consumption mode both consume more power than the first power consumption mode, wherein the second processor comprises a first sub-processor and a second sub-processor, wherein the first sub-processor and the second sub-processor both consume more power than the first processor, and wherein the first sub-processor consumes less power than the second sub-processor;
the determination module is to:
if the screen state of the electronic equipment is a bright screen state or a screen off state, and the sound output state of the electronic equipment is a sound output state, determining that the power consumption mode of the electronic equipment is the interrupt mode, and determining the first sub-processor and the second sub-processor as processors matched with the interrupt mode;
and if the screen state of the electronic equipment is a bright screen state and the sound output state of the electronic equipment is a state without sound output, determining that the power consumption mode of the electronic equipment is the high power consumption mode, and determining the second sub-processor as a processor matched with the high power consumption mode.
10. The apparatus of claim 9, wherein the identification module is configured to:
if the power consumption mode of the electronic equipment is the interrupt mode, voice monitoring is carried out through the first sub-processor, if voice data are monitored, echo cancellation is carried out on the monitored voice data, and voice recognition is carried out on the voice data after the echo cancellation by adopting a third voice awakening algorithm; if the voice data is recognized to comprise the appointed awakening word, performing voice recognition on the monitored voice data by adopting a second voice awakening algorithm through the second sub-processor;
if the power consumption mode of the electronic equipment is the high power consumption mode, voice monitoring is carried out through the second sub-processor, and if voice data are monitored, voice recognition is carried out on the monitored voice data through the second voice awakening algorithm.
11. An electronic device, wherein the electronic device comprises a processor and a memory; the memory stores at least one instruction for execution by the processor to implement a voice wake-up method as claimed in any of claims 1 to 5.
12. A computer-readable storage medium having stored thereon at least one instruction for execution by a processor to implement a voice wake-up method as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911143250.XA CN110853644B (en) | 2019-11-20 | 2019-11-20 | Voice wake-up method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911143250.XA CN110853644B (en) | 2019-11-20 | 2019-11-20 | Voice wake-up method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110853644A CN110853644A (en) | 2020-02-28 |
| CN110853644B true CN110853644B (en) | 2022-06-28 |
Family
ID=69602786
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911143250.XA Active CN110853644B (en) | 2019-11-20 | 2019-11-20 | Voice wake-up method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110853644B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111429911A (en) * | 2020-03-11 | 2020-07-17 | 云知声智能科技股份有限公司 | Method and device for reducing power consumption of speech recognition engine in noise scene |
| CN117253488A (en) * | 2022-06-10 | 2023-12-19 | Oppo广东移动通信有限公司 | Speech recognition method, device, equipment and storage medium |
| CN115171664A (en) * | 2022-07-05 | 2022-10-11 | 小米汽车科技有限公司 | Voice awakening method and device, intelligent voice equipment, vehicle and storage medium |
| CN117133283A (en) * | 2023-03-27 | 2023-11-28 | 荣耀终端有限公司 | Voice wake-up circuit and method and electronic equipment |
| CN117409779B (en) * | 2023-12-14 | 2024-02-23 | 四川蜀天信息技术有限公司 | Voice wakeup method, device, system and readable medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008276684A (en) * | 2007-05-07 | 2008-11-13 | Toshiba Corp | Information processor, and electric power saving control method |
| WO2009040614A1 (en) * | 2007-09-26 | 2009-04-02 | Sony Ericsson Mobile Communications Ab | Portable electronic equipment with automatic control to keep display turned on and method |
| CN108847232A (en) * | 2018-05-31 | 2018-11-20 | 联想(北京)有限公司 | A kind of processing method and electronic equipment |
| CN109360567A (en) * | 2018-12-12 | 2019-02-19 | 苏州思必驰信息科技有限公司 | The customizable method and apparatus waken up |
| CN109979438A (en) * | 2019-04-04 | 2019-07-05 | Oppo广东移动通信有限公司 | Voice awakening method and electronic equipment |
-
2019
- 2019-11-20 CN CN201911143250.XA patent/CN110853644B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008276684A (en) * | 2007-05-07 | 2008-11-13 | Toshiba Corp | Information processor, and electric power saving control method |
| WO2009040614A1 (en) * | 2007-09-26 | 2009-04-02 | Sony Ericsson Mobile Communications Ab | Portable electronic equipment with automatic control to keep display turned on and method |
| CN108847232A (en) * | 2018-05-31 | 2018-11-20 | 联想(北京)有限公司 | A kind of processing method and electronic equipment |
| CN109360567A (en) * | 2018-12-12 | 2019-02-19 | 苏州思必驰信息科技有限公司 | The customizable method and apparatus waken up |
| CN109979438A (en) * | 2019-04-04 | 2019-07-05 | Oppo广东移动通信有限公司 | Voice awakening method and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110853644A (en) | 2020-02-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110853644B (en) | Voice wake-up method, device, equipment and storage medium | |
| US11244672B2 (en) | Speech recognition method and apparatus, and storage medium | |
| CN103871408B (en) | Method and device for voice identification and electronic equipment | |
| CN105912092B (en) | Voice awakening method and speech recognition equipment in human-computer interaction | |
| US9252890B2 (en) | Near field communication device and method for saving applied power | |
| CN108566634B (en) | Method and device for reducing continuous awakening delay of Bluetooth sound box and Bluetooth sound box | |
| CN110427097A (en) | Voice data processing method, apparatus and system | |
| CN108712566B (en) | Voice assistant awakening method and mobile terminal | |
| CN110968353A (en) | Central processing unit awakening method and device, voice processor and user equipment | |
| CN111402877B (en) | Noise reduction method, device, equipment and medium based on vehicle-mounted multitone area | |
| JP2014503097A (en) | Method and system for managing sleep state of an interrupt controller in a portable computing device | |
| CN112230877A (en) | Voice operation method and device, storage medium and electronic equipment | |
| US20210201894A1 (en) | N/a | |
| CN107566609B (en) | Download task processing method, device, terminal and storage medium | |
| CN108563468B (en) | Bluetooth sound box data processing method and device and Bluetooth sound box | |
| CN109389977B (en) | Voice interaction method and device | |
| CN110543333B (en) | Sleep processing method and device for processor, mobile terminal and storage medium | |
| CN113031749A (en) | Electronic device | |
| CN106249874A (en) | The report method of a kind of sensing data, processor and mobile terminal | |
| WO2019024643A1 (en) | Data synchronization control method, device and electronic equipment | |
| CN117407130A (en) | Application management and control method and device, electronic equipment and computer readable storage medium | |
| CN111045641B (en) | Electronic terminal and voice recognition method | |
| CN112992135A (en) | Electronic equipment and voice control display method | |
| CN113889084A (en) | Audio recognition method and device, electronic equipment and storage medium | |
| CN113852944A (en) | Audio output method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |