Voice wake-up method and device, equipment and storage medium

Abstract

The invention relates to the technical field of intelligent equipment, and discloses a voice wake-up method and device, equipment and a storage medium. The method comprises the following steps: acquiring current position information of a current user in an action area of the voice wake-up equipment; performing wake-up word detection in a voice enhancement mode on the current pickup direction corresponding to the current position information; and under the condition that the current voice containing the wake-up word is detected, waking up the voice wake-up equipment. In this way, voice enhancement pickup is performed in the target direction, the voice recognition precision from the personnel direction is improved, and therefore the far-field voice wake-up rate is improved.

Description

Technical Field

[0001] The present application relates to the technical field of smart devices, for example, to methods, devices, equipment and storage media for voice wake-up. Background Art

[0002] With the rapid development of the national economy and the development of smart technology, home appliances such as TVs, refrigerators, and air conditioners have become smart devices that can communicate and interact with users. These smart devices can also interact with users through voice. For example, after the device is awakened by voice, the user's device can be controlled by voice. These devices are called voice awakening devices.

[0003] In related technologies, a voice wake-up device can obtain the user's voice information through a microphone array formed by multiple microphones. When the acquired voice information contains the set wake-up word, the voice wake-up device will be awakened, and the user can perform voice communication or voice control, etc. However, in the far-field voice wake-up scenario, the success rate of far-field voice wake-up will be greatly affected by interference from factors such as noise, reverberation, and echo.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0006] The embodiments of the present disclosure provide a method, apparatus, device and storage medium for voice wake-up to solve the technical problem that the wake-up success rate of the voice wake-up device needs to be improved.

[0007] In some embodiments, the method comprises:

[0008] Get the current location information of the current user within the action area of ​​the voice wake-up device;

[0009] Perform wake-up word detection in voice enhancement mode for the current sound pickup direction corresponding to the current position information;

[0010] When the current voice containing the wake-up word is detected, the voice wake-up device is woken up.

[0011] In some embodiments, obtaining the current location information of the current user within the action area of ​​the voice wake-up device includes:

[0012] The millimeter-wave radar module configured in the voice wake-up device is used to obtain the current environment information within the action area of ​​the voice wake-up device;

[0013] According to the current environment information, the current location information of the current user in the effective area is determined.

[0014] In some embodiments, obtaining the current location information of the current user within the action area of ​​the voice wake-up device includes:

[0015] Obtaining the current location information of the current user within the effective area of ​​the voice wake-up device through a wireless local area Wi-Fi network connected to the voice wake-up device; or,

[0016] Obtain the current location information of the current user within the effective area of ​​the voice wake-up device through the current user's wearable device connected to the voice wake-up device via Bluetooth; or

[0017] The current location information of the current user within the action area of ​​the voice wake-up device is obtained through the environment perception device configured by the voice wake-up device.

[0018] In some embodiments, it also includes:

[0019] When the location monitoring function is enabled, the current location information of the current user within the effective area of ​​the voice wake-up device is obtained.

[0020] In some embodiments, the wake-up word detection in the voice enhancement mode includes:

[0021] The microphone array formed by multiple microphones directionally picks up the current sound information in the current sound pickup direction, and performs voice enhancement processing to obtain the corresponding current enhanced voice information;

[0022] Perform voice analysis on the current enhanced voice information, and compare the analyzed voice information with the saved wake-up word information.

[0023] In some embodiments, it also includes:

[0024] Obtain and save the wake-up word information through the microphone array; or;

[0025] Receive and save the wake-up word information sent by the server device or terminal device.

[0026] In some embodiments, a device for voice wake-up includes:

[0027] A location detection module is configured to obtain current location information of a current user within an effective area of ​​a voice wake-up device;

[0028] A sound pickup detection module is configured to perform wake-up word detection in a voice enhancement mode for a current sound pickup direction corresponding to the current position information;

[0029] The voice wake-up module is configured to wake up the voice wake-up device when a current voice containing a wake-up word is detected.

[0030] In some embodiments, the device for voice wake-up includes a processor and a memory storing program instructions, and the processor is configured to perform the above-mentioned method for voice wake-up when executing the program instructions.

[0031] In some embodiments, the device includes a device body; the above-mentioned device for voice wake-up is installed on the device body.

[0032] In some embodiments, the storage medium stores program instructions, and when the program instructions are run, the above-mentioned method for voice wake-up is executed.

[0033] The method, device and air conditioner for voice wake-up provided by the embodiments of the present disclosure can achieve the following technical effects:

[0034] Regardless of whether the current user in the action area of ​​the voice wake-up device speaks or not, the current location information of the current user can be determined first, and then, voice-enhanced far-field pickup is performed for the current pickup direction corresponding to the current location information, and the voice wake-up device is woken up when the current voice containing the wake-up word is detected. In this way, voice-enhanced pickup is performed in a targeted direction, which improves the voice recognition accuracy from the direction of the person, thereby improving the far-field voice wake-up rate.

[0035] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0037] Figure 1 is a schematic diagram of an architecture for a voice wake-up scenario provided by an embodiment of the present disclosure;

[0038] Figure 2 is a flow chart of a method for voice wake-up provided by an embodiment of the present disclosure;

[0039] Figure 3 is a flow chart of a method for voice wake-up provided by an embodiment of the present disclosure;

[0040] Figure 4 is a structural diagram of a voice wake-up device provided by an embodiment of the present disclosure;

[0041] Figure 5 is a structural diagram of a voice wake-up device provided by an embodiment of the present disclosure;

[0042] Figure 6 is a structural diagram of a voice wake-up device provided by an embodiment of the present disclosure;

[0043] Figure 7 It is a schematic diagram of a device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0044] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0045] The terms "first", "second", etc. in the specification and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so that the embodiments of the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0046] Unless otherwise stated, the term "plurality" means two or more.

[0047] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.

[0048] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0049] Televisions, refrigerators, air conditioners and other household appliances can all perform voice interaction, and these devices can be voice wake-up devices. In the disclosed embodiment, there is a user in the action area of ​​the voice wake-up device. Regardless of whether the current user speaks or not, the current location information of the current user can be determined first, and then the direction corresponding to the current location information is used as the target direction to perform far-field sound pickup for voice enhancement, and when the current voice containing the wake-up word is detected, the voice wake-up device is awakened. In this way, voice enhancement pickup is performed in a targeted direction, which improves the accuracy of voice recognition from the direction of the person, thereby improving the far-field voice wake-up rate. In addition, there can be multiple ways to determine the current location information of the current user in the action area of ​​the voice wake-up device, including: one or more of millimeter radar, LAN WIFI, Bluetooth, environmental perception, and the like.

[0050] Figure 1 The present disclosure provides a schematic diagram of an architecture for a voice wake-up scenario. Figure 1 As shown, the scenario may include: a voice wake-up device 100 and a current user 200, wherein the voice wake-up device may be a refrigerator, a washing machine, an air conditioner, a television, a speaker, and the like, and the current user 200 is within the range of the voice wake-up device 100.

[0051] The current user 200 can perform voice interaction with the voice wake-up device 100, so the voice wake-up device 100 may include: a microphone array 110 formed by multiple microphones. Through the microphone array 110, the voice wake-up device 100 can perform far-field sound pickup and send voice.

[0052] In the embodiment of the present disclosure, it is necessary to obtain the current location information of the current user 200 within the effective area of ​​the voice wake-up device 100, and there are many ways to obtain the current location information of the current user, including: millimeter radar, local area network WIFI, Bluetooth, environmental perception, etc. One or more of the following methods.

[0053] In some embodiments, the voice wake-up device 100 is configured with a millimeter wave radar module 120 to obtain the current location information of the current user 200 in the action area of ​​the voice wake-up device 100. The millimeter wave radar module 120 is small in size and low in cost, and can be built into the voice wake-up device 100. At this time, the action area of ​​the voice wake-up device 100 can be the action area of ​​the millimeter wave radar module 120.

[0054] In this way, the voice wake-up device 100 can obtain the current position information of the current user within the action area of ​​the voice wake-up device through the millimeter wave radar module 120, and then, through the microphone array 110, perform far-field voice enhancement on the current pickup direction corresponding to the current position information, and wake up the voice wake-up device when the current voice containing the wake-up word is detected. In this way, voice enhancement pickup is performed in a targeted direction, which improves the voice recognition accuracy from the direction of the person, thereby improving the far-field voice wake-up rate.

[0055] Alternatively, in some embodiments, the voice wake-up device is in a wireless local area Wi-Fi network and can receive and send corresponding Wi-Fi signals, so that the current location information of the current user in the action area of ​​the voice wake-up device can be determined based on the strength of the Wi-Fi signal. At this time, a WIFI module is configured in the voice wake-up device, and the action area of ​​the voice wake-up device can be the action area of ​​the WIFI module. Thus, the current location information of the current user in the action area of ​​the voice wake-up device can be determined through the WIFI module according to the strength of the received or sent Wi-Fi information, that is, the current location information of the current user in the action area of ​​the voice wake-up device can be obtained through the wireless local area Wi-Fi network connected to the voice wake-up device.

[0056] Alternatively, in some embodiments, the voice wake-up module is configured with a Bluetooth module, and the current user's wearable device also has a Bluetooth module, and the two can be paired and connected, so that the action area of ​​the voice wake-up device can be the action area of ​​the Bluetooth module. Therefore, the current location information of the current user in the action area of ​​the voice wake-up device can be determined through the paired Bluetooth module, that is, the current location information of the current user in the action area of ​​the voice wake-up device can be obtained through the current user's wearable device connected to the voice wake-up device by Bluetooth.

[0057] Alternatively, in some embodiments, the voice wake-up module is configured with an environmental sensing device, such as a temperature sensor, a light sensor, etc., so that the effective area of ​​the voice wake-up device can be the effective area of ​​the environmental sensing device. Thus, the current location information of the current user in the effective area of ​​the voice wake-up device can be obtained through the environmental sensing device configured in the voice wake-up device.

[0058] It can be seen that the voice wake-up device needs to first determine the user's position, then pick up sound in a directional voice enhancement mode, and wake up the voice wake-up device when the current voice containing the wake-up word is picked up. Figure 2 is a flow chart of a method for voice wake-up provided by an embodiment of the present disclosure. A microphone array is configured in the voice wake-up device, such as Figure 2 As shown in the figure, the voice wake-up process includes:

[0059] Step 201: Acquire the current location information of the current user within the action area of ​​the voice wake-up device.

[0060] In some embodiments, Figure 1 The voice wake-up device is equipped with a millimeter-wave radar module. In this way, the current location information of the current user within the effective area of ​​the voice wake-up device can be obtained through the millimeter-wave radar module configured in the voice wake-up device.

[0061] Millimeter-wave radar is a radar sensor that works in the millimeter-wave frequency band. It has basic characteristics such as wide bandwidth, short wavelength, and large atmospheric propagation loss. Its core functions include ranging, speed measurement, azimuth measurement, micro-motion detection and 4D imaging. It is currently widely used in the fields of intelligent driving and smart home appliance perception.

[0062] After a voice wake-up device, such as a TV, refrigerator, or air conditioner, is equipped with a millimeter-wave radar module, the millimeter-wave radar module can be used to collect environmental data in the action area of ​​the voice wake-up device at regular intervals or in real time, including user activity data, space occupancy data, distance data, etc. In addition, the environmental data collected at the current moment can be the current environmental data information, so that the voice wake-up device can obtain the current environmental data information in the action area of ​​the voice wake-up device through the millimeter-wave radar module, and then determine the current location information of the current user in the action area of ​​the voice wake-up device based on the current environmental data information.

[0063] Of course, there are many ways to obtain the current location information of the current user in the action area of ​​the voice wake-up device. In some embodiments, the current location information of the current user in the action area of ​​the voice wake-up device is obtained through a wireless local area Wi-Fi network connected to the voice wake-up device. That is, the voice wake-up device is equipped with a WIFI module, so that the current location information of the current user in the action area of ​​the voice wake-up device can be determined through the WIFI module according to the strength of the received or sent Wi-Fi signal.

[0064] Alternatively, in some embodiments, the current location information of the current user in the effective area of ​​the voice wake-up device is obtained through the current user's wearable device connected to the voice wake-up device by Bluetooth. That is, the voice wake-up module is configured with a Bluetooth module, and the current user's wearable device also has a Bluetooth module, and the two can be paired and connected, so that the current location information of the current user in the effective area of ​​the voice wake-up device can be determined through the paired Bluetooth module.

[0065] Alternatively, in some embodiments, the current location information of the current user in the effective area of ​​the voice wake-up device is obtained through an environment sensing device configured in the voice wake-up device. That is, the voice wake-up module is configured with an environment sensing device, such as a temperature sensor, a light sensor, etc., so that the current location information of the current user in the effective area of ​​the voice wake-up device can be determined through the temperature value, light intensity value, etc. sensed by the environment sensing device.

[0066] Of course, in some embodiments, when it is determined that the location monitoring function is turned on, the current location information of the current user in the effective area of ​​the voice wake-up device is obtained. That is, after the location monitoring function of the voice wake-up device is turned on, the current location information of the current user in the effective area of ​​the voice wake-up device is obtained. In this way, the voice wake-up device is more flexible and saves resources.

[0067] Step 202: Perform wake-up word detection in the voice enhancement mode on the current sound pickup direction corresponding to the current position information.

[0068] Directional sound pickup is a sound collection and processing technology for a specific direction, which is widely used in speech recognition, audio processing, audio monitoring and other fields. Certain results have been achieved by using microphones to simulate this directional sound pickup capability. In the embodiment of the present disclosure, a microphone array is configured in the voice wake-up device. The microphone array is composed of a plurality of microphones distributed in space according to a specific topological structure. Like a single microphone, the microphone array is a whole and can still be regarded as a complex sensor as an interface module between the sound and the sound pickup system; but the difference is that the microphone array can obtain not only the time domain information of the sound signal but also the spatial domain information. The main goal of microphone array signal processing is to make the best use of space-time information to improve the quality of the receiving end signal.

[0069] In the embodiment of the present disclosure, after determining the current position information of the current user, the direction corresponding to the current position information can be determined as the target direction for sound pickup, that is, the current sound pickup direction corresponding to the current position information can be determined, and directional sound pickup can be performed in the current sound pickup direction.

[0070] In some embodiments, the current sound information picked up may also be subjected to voice enhancement processing to obtain current enhanced voice information with better quality.

[0071] Speech enhancement is a technology that extracts pure original speech from noisy speech. It is of great significance in improving speech quality and speech intelligibility. It suppresses and reduces noise interference and extracts useful speech signals, thereby improving the clarity and intelligibility of voice communication. Speech enhancement algorithms are the key to achieving speech enhancement. Common speech enhancement algorithms include noise cancellation and harmonic enhancement. These algorithms analyze the spectral characteristics of noisy speech, use digital signal processing technology to suppress noise interference, and extract pure original speech. With the development of deep learning technology, speech enhancement algorithms based on deep neural networks have also made great progress. They can more effectively extract useful speech information from noise.

[0072] Therefore, the voice wake-up device can use the microphone array to directionally pick up the current sound information in the current pickup direction. The current sound information includes: the time domain information and spatial domain information of the sound signal. Then, through the voice enhancement algorithm, voice enhancement processing is performed to obtain the corresponding current enhanced voice information.

[0073] Thus, in some embodiments, the wake-up word detection in the voice enhancement mode includes: using a microphone array formed by multiple microphones to directionally pick up the current sound information in the current pickup direction, and performing voice enhancement processing to obtain the corresponding current enhanced voice information; performing voice analysis on the current enhanced voice information, and comparing the analyzed voice information with the saved wake-up word information.

[0074] The voice wake-up device can perform voice interaction, so the corresponding wake-up word information needs to be saved in the voice wake-up device. In some embodiments, the wake-up word information is obtained and saved through the microphone array; or; the wake-up word information sent by the server device or the terminal device is received and saved. That is, the voice wake-up device can receive the set wake-up word information through the microphone array and save it, or communicate data with the server device or the terminal device, obtain the wake-up word information from the server device or the terminal device and save it. In this way, the normal voice interaction of the voice wake-up device and the corresponding voice application can be guaranteed.

[0075] The corresponding wake-up word information is saved in the voice wake-up device. In this way, after obtaining the current enhanced voice information, the current enhanced voice information can be voice analyzed, and then the parsed voice information is compared with the saved wake-up word information to determine whether the parsed voice information contains the saved wake-up word information.

[0076] Step 203: When the current voice containing the wake-up word is detected, the voice wake-up device is woken up.

[0077] In the embodiment of the present disclosure, when performing wake-up word detection in the voice enhancement mode, it is determined whether the parsed voice information contains the saved wake-up word information. If it does, the voice wake-up device can be awakened; if it does not, the voice wake-up device cannot be awakened, and directional sound pickup and voice enhancement processing are required to continue the wake-up word detection.

[0078] It can be seen that in the disclosed embodiment, if there is a user in the action area of ​​the voice wake-up device, regardless of whether the current user speaks or not, the current location information of the current user can be determined first, and then the direction corresponding to the current location information is used as the target direction to perform far-field sound pickup for voice enhancement, and when the current voice containing the wake-up word is detected, the voice wake-up device is awakened. In this way, voice enhancement pickup is performed in a targeted direction, which improves the accuracy of voice recognition from the direction of the person, thereby improving the far-field voice wake-up rate. In addition, there are many ways to determine the current location information of the current user in the action area of ​​the voice wake-up device, including: one or more of millimeter radar, LAN WIFI, Bluetooth, environmental perception, etc., which further improves the flexibility and wake-up rate of device wake-up.

[0079] The operation flow is summarized into a specific embodiment below to illustrate the voice wake-up process provided by the embodiment of the present invention.

[0080] In one embodiment of the present disclosure, the voice wake-up device may be a television, such as Figure 1 As shown, the TV may include not only a microphone array formed by multiple microphones, but also a millimeter wave radar module. In addition, the TV has saved the wake-up word information sent by the terminal device.

[0081] Figure 3 FIG. 1 is a flow chart of a method for voice wake-up provided by an embodiment of the present disclosure. Figure 3 As shown in the figure, the voice wake-up process includes:

[0082] Step 301: The TV obtains current environmental information within the effective area through the millimeter wave radar module.

[0083] Step 302: Based on the current environment information, determine whether there is a user in the action area. If so, execute step 303; otherwise, return to step 301.

[0084] The TV can sequentially perform intermediate frequency signal extraction, distance Fourier FFT pulse compression, STFT Doppler velocity extraction, multi-target mean constant false alarm filtering, and spatial mapping on the current environmental information to obtain the corresponding current millimeter wave point cloud data information. Then, the TV performs target detection based on the CNN algorithm of the neural network according to the current millimeter wave point cloud data information. If the current target detection result is the user, execute step 303, otherwise, return to step 301.

[0085] Step 303: The TV obtains the current location information of the current user within the active area according to the current environment information.

[0086] The television determines the detected user as the current user, and may continue to determine the current location information of the current user based on the current environment information.

[0087] Step 304: The television directionally picks up current sound information in a current sound pickup direction through a microphone array formed by a plurality of microphones, wherein the current sound pickup direction corresponds to the current position information.

[0088] Step 305: The television performs voice enhancement processing on the current sound information to obtain corresponding current enhanced voice information.

[0089] Step 306: The television performs voice analysis on the current enhanced voice information to obtain the analyzed voice information.

[0090] Step 307: Determine whether the parsed voice information matches the saved wake-up word information. If yes, execute step 308; otherwise, return to step 304.

[0091] Among them, if the parsed voice information includes the saved wake-up word information, it can be determined that the parsed voice information matches the wake-up word information, and step 308 is executed.

[0092] Step 308: The TV wakes up the voice function and performs the corresponding voice application.

[0093] The TV wake-up voice function means that it is in voice wake-up state, and can perform voice applications such as voice interaction, voice control, etc.

[0094] It can be seen that in this embodiment, a millimeter-wave radar module is configured in the TV, so that the current environmental data information within the TV's action area is obtained through the millimeter-wave radar module, and the current location information of the current user within the action area is obtained through corresponding processing. Then, the direction corresponding to the current location information is used as the target direction to perform far-field sound pickup for voice enhancement, and when the current voice containing the wake-up word is detected, the TV is awakened. In this way, voice enhancement pickup is performed in a targeted direction, which improves the accuracy of voice recognition from the direction of the person, thereby improving the TV's far-field voice wake-up rate. In addition, the millimeter-wave radar has a high acquisition frequency and a large amount of data. The corresponding processing based on the CNN algorithm of the neural network can more accurately determine the user's location information, further improving the wake-up rate and intelligence of the TV.

[0095] According to the above process for voice wake-up, a device for voice wake-up can be constructed, which can be applied to a voice wake-up device.

[0096] Figure 4Schematic diagram of a structure of a voice wake-up device provided by an embodiment of the present disclosure. Figure 4 As shown, the voice wake-up device 400 includes: a position detection module 410 , a sound pickup detection module 420 and a voice wake-up module 430 .

[0097] The position detection module 410 is configured to obtain the current position information of the current user within the effective area of ​​the voice wake-up device.

[0098] The sound pickup detection module 420 is configured to perform wake-up word detection in the voice enhancement mode for the current sound pickup direction corresponding to the current position information;

[0099] The voice wake-up module 430 is configured to wake up the voice wake-up device when a current voice containing a wake-up word is detected.

[0100] In some embodiments, the location detection module 410 includes:

[0101] The first position detection unit is configured to obtain current environmental information within the action area of ​​the voice wake-up device through a configured millimeter-wave radar module; and determine the current position information of the current user within the action area based on the current environmental information.

[0102] Among them, in some embodiments, after the first position detection unit obtains the current environment information, it can sequentially perform intermediate frequency signal extraction, range Fourier FFT pulse compression, short-time Fourier transform STFT Doppler velocity extraction, multi-target mean constant false alarm filtering, and spatial mapping on the current environment information to obtain the corresponding current millimeter wave point cloud data information, and then, according to the current millimeter wave point cloud data information, obtain the current target detection result through the saved CNN target detection model. And when the current target detection result is a user, the current location information of the current user is obtained according to the current environment information.

[0103] In some embodiments, the location detection module 410 includes:

[0104] The second position detection unit is configured to obtain the current position information of the current user within the action area of ​​the voice wake-up device through a wireless local area Wi-Fi network connected to the voice wake-up device.

[0105] In some embodiments, the location detection module 410 includes:

[0106] The third position detection unit is configured to obtain the current position information of the current user within the action area of ​​the voice wake-up device through a wearable device of the current user connected to the voice wake-up device by Bluetooth.

[0107] In some embodiments, the location detection module 410 includes:

[0108] The fourth position detection unit obtains the current position information of the current user within the action area of ​​the voice wake-up device through the configured environment perception device.

[0109] In some embodiments, it also includes: a function activation module, which is configured to call the location detection module 410 to obtain the current location information of the current user in the effective area when determining that the location monitoring function is activated.

[0110] In some embodiments, the sound pickup detection module 420 includes:

[0111] The sound pickup unit is configured as a microphone array formed by multiple microphones to directionally pick up current sound information in a current sound pickup direction, and perform voice enhancement processing to obtain corresponding current enhanced voice information.

[0112] The detection unit is configured to perform voice analysis on the current enhanced voice information and compare the analyzed voice information with the saved wake-up word information.

[0113] In some embodiments, it also includes:

[0114] The acquisition and saving module is configured to acquire and save the wake-up word information through a microphone array; or receive and save the wake-up word information sent by a server device or a terminal device.

[0115] The following further describes the voice wake-up process for the voice wake-up device in conjunction with the embodiments.

[0116] In this embodiment, Figure 1 As shown, the voice wake-up device can be an air conditioner, which can include not only a microphone array formed by multiple microphones, but also a millimeter-wave radar module.

[0117] Figure 5 Schematic diagram of a structure of a voice wake-up device provided by an embodiment of the present disclosure. Figure 5 As shown, the voice wake-up device 400 includes: a position detection module 410, a sound pickup detection module 420, a voice wake-up module 430, and an acquisition and storage module 440, wherein the position detection module 410 includes a first position detection unit 411, and the sound pickup detection module 420 includes a sound pickup unit 421 and a detection unit 422.

[0118] In this embodiment, the wake-up word information sent by the terminal device is saved in the acquisition and storage module 440. In this way, the first position detection unit 411 in the position detection module 410 can obtain the current environmental information in the air-conditioning action area through the millimeter wave radar module, and perform intermediate frequency signal extraction, distance Fourier FFT pulse compression, STFT Doppler velocity extraction, multi-target mean constant false alarm filtering, and spatial mapping on the current environmental information in turn to obtain the corresponding current millimeter wave point cloud data information, and, based on the current millimeter wave point cloud data information, perform target detection results through the CNN algorithm. And when the current target detection result is a user, the current location information of the user is obtained according to the current environmental information.

[0119] Thus, the microphone array formed by multiple microphones of the sound pickup unit 421 in the sound pickup detection module 420 directionally picks up the current sound information of the current sound pickup direction, wherein the current sound pickup direction corresponds to the current position information, and can also perform voice enhancement processing on the current sound information to obtain the corresponding current enhanced voice information.

[0120] In this way, the current enhanced voice information is voice parsed, and the detection unit 422 in the sound pickup detection module 420 compares the parsed voice information with the stored wake-up word information. If the parsed voice information matches the wake-up word information, the voice wake-up module 430 can wake up the voice function of the air conditioner and perform the corresponding voice application.

[0121] It can be seen that in this embodiment, the device for voice wake-up obtains the current environmental data information in the air-conditioning action area through the millimeter-wave radar module, and obtains the current location information of the current user in the action area. Then, the direction corresponding to the current location information is used as the target direction, and far-field sound pickup for voice enhancement is performed, and when the current voice containing the wake-up word is detected, the air conditioner is awakened. In this way, voice enhancement pickup is performed in a targeted direction, which improves the accuracy of voice recognition from the direction of the person, thereby improving the far-field voice wake-up rate of the air conditioner. In addition, the millimeter-wave radar has a high acquisition frequency and a large amount of data. The corresponding processing based on the CNN algorithm of the neural network can more accurately determine the user's location information, further improving the wake-up rate and intelligence of the air conditioner.

[0122] Combination Figure 6 The embodiment of the present disclosure provides a device 600 for voice wake-up, including:

[0123] The processor 1000 and the memory 1001 may also include a communication interface 1002 and a bus 1003. The processor 1000, the communication interface 1002, and the memory 1001 may communicate with each other through the bus 1003. The communication interface 1002 may be used for information transmission. The processor 1000 may call the logic instructions in the memory 1001 to execute the method for voice wake-up of the above embodiment.

[0124] In addition, the logic instructions in the above-mentioned memory 1001 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0125] The memory 1001 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor 1000 executes the function application and data processing by running the program instructions / modules stored in the memory 1001, that is, the method for voice wake-up in the above method embodiment is implemented.

[0126] The memory 1001 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 1001 may include a high-speed random access memory and may also include a non-volatile memory.

[0127] An embodiment of the present disclosure provides a device for voice wake-up, comprising: a processor and a memory storing program instructions, wherein the processor is configured to execute a method for voice wake-up when executing the program instructions.

[0128] Combination Figure 7 , the embodiment of the present disclosure provides a device 700, which can be a voice wake-up device, such as: an air conditioner, a television, a speaker, or a refrigerator, etc., including: a device body, and the above-mentioned voice wake-up device 400 (600). The voice wake-up device 400 (600) is installed on the device body. The installation relationship described here is not limited to placement inside the product, but also includes installation connections with other components of the product, including but not limited to physical connections, electrical connections, or signal transmission connections. It can be understood by those skilled in the art that the voice wake-up device 400 (600) can be adapted to a feasible device body, thereby realizing other feasible embodiments.

[0129] An embodiment of the present disclosure provides a storage medium storing program instructions, which, when run, execute the above-mentioned method for voice wake-up.

[0130] An embodiment of the present disclosure provides a computer program product, which includes a computer program stored on a storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the above-mentioned voice wake-up method.

[0131] The above-mentioned storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0132] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes, or a transient storage medium.

[0133] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, individual components and functions are optional, and the order of operation may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. The scope of the embodiments of the present disclosure includes the entire scope of the claims, and all available equivalents of the claims. When used in this application, although the terms "first", "second", etc. may be used in this application to describe each element, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, without changing the meaning of the description, the first element can be called the second element, and similarly, the second element can be called the first element, as long as all occurrences of the "first element" are renamed consistently and all occurrences of the "second element" are renamed consistently. The first element and the second element are both elements, but may not be the same element. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and claims, unless the context clearly indicates, the singular forms "a", "an" and "the" are intended to include the plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of one or more associated listings. In addition, when used in this application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups of these. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the presence of other identical elements in the process, method or device including the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0134] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described functions, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0135] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0136] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for voice wake-up, characterized in that: include: Get the current location information of the current user within the action area of ​​the voice wake-up device; Perform wake-up word detection in voice enhancement mode for the current sound pickup direction corresponding to the current position information; When the current voice containing the wake-up word is detected, the voice wake-up device is woken up.

2. The method according to claim 1, characterized in that The step of obtaining the current location information of the current user within the action area of ​​the voice wake-up device includes: The millimeter-wave radar module configured in the voice wake-up device is used to obtain the current environment information within the action area of ​​the voice wake-up device; According to the current environment information, the current location information of the current user in the effective area is determined.

3. The method according to claim 1, characterized in that The step of obtaining the current location information of the current user within the action area of ​​the voice wake-up device includes: Obtaining the current location information of the current user within the effective area of ​​the voice wake-up device through a wireless local area Wi-Fi network connected to the voice wake-up device; or, Obtain the current location information of the current user within the action area of ​​the voice wake-up device through the current user's wearable device connected to the voice wake-up device via Bluetooth; or The current location information of the current user within the effective area of ​​the voice wake-up device is obtained through the environment perception device configured by the voice wake-up device.

4. The method according to any one of claims 1 to 3, characterized in that: Also includes: When it is determined that the location monitoring function is turned on, the current location information of the current user within the effective area of ​​the voice wake-up device is obtained.

5. The method according to claim 1, characterized in that The wake-up word detection in the voice enhancement mode includes: The microphone array formed by multiple microphones directionally picks up the current sound information in the current sound pickup direction, and performs voice enhancement processing to obtain the corresponding current enhanced voice information; Perform voice analysis on the current enhanced voice information, and compare the analyzed voice information with the saved wake-up word information.

6. The method according to claim 5, characterized in that Also includes: Obtain and save the wake-up word information through the microphone array; or; Receive and save the wake-up word information sent by the server device or terminal device.

7. A device for voice wake-up, characterized in that: include: A location detection module is configured to obtain current location information of a current user within an effective area of ​​a voice wake-up device; A sound pickup detection module is configured to perform wake-up word detection in a voice enhancement mode for a current sound pickup direction corresponding to the current position information; The voice wake-up module is configured to wake up the voice wake-up device when a current voice containing a wake-up word is detected.

8. A device for voice wake-up, the device comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to perform the method for voice wake-up according to any one of claims 1 to 6 when executing the program instructions.

9. A device, characterized in that: include: Equipment body; The device for voice wake-up as described in claim 7 or 8 is installed on the device body.

10. A storage medium storing program instructions, characterized in that: When the program instructions are executed, the method for voice wake-up as described in any one of claims 1 to 6 is executed.

Images