Voice wake-up method and device

Abstract

The invention discloses a voice wake-up method and device, the device comprises a voice wake-up device, a voice wake-up device system, a computer program and a computer readable storage medium, the voice wake-up method comprises the following steps: obtaining a first channel audio signal and a second channel audio signal in a wake-up time period of each voice wake-up device; calculating a coherent reverberation signal-to-noise ratio of each voice wake-up device based on the first channel audio signal and the second channel audio signal of each voice wake-up device; and determining a target voice wake-up device based on the coherent reverberation signal-to-noise ratio of each voice wake-up device, and controlling the target voice wake-up device to perform voice interaction with the user. Through the above mode, according to the voice wake-up method, the coherent reverberation signal-to-noise ratio of each voice wake-up device can be calculated through the first channel audio signal and the second channel audio signal, and the target voice wake-up device for straight-face wake-up is determined based on the coherent reverberation signal-to-noise ratio, so that the straight-face wake-up effect is improved.

Description

Technical Field

[0001] The present application relates to the field of voice wake-up technology, and in particular to a voice wake-up method and device thereof, wherein the device includes a voice wake-up device, a voice wake-up device system, a computer program, and a computer-readable storage medium. Background Art

[0002] With the popularity of current voice wake-up devices, there will be multiple voice wake-up devices in the same room or area at the same time. When the user shouts out the wake-up word, multiple voice wake-up devices may respond at the same time. There are many logics for selecting voice wake-up devices in the prior art. The simpler wake-up logic is nearby wake-up, which means waking up the voice wake-up device closest to the user. However, the nearby voice wake-up device may not be the voice wake-up device that the user is facing. From the user experience point of view, the voice wake-up device that the user is facing is the device he wants to wake up, not the one close to him. Therefore, the above method cannot accurately wake up the voice wake-up device that the user is facing, affecting the user experience. Summary of the invention

[0003] In order to solve the above problems, the present application proposes a voice wake-up method and a device thereof, aiming to solve the above problems.

[0004] In order to solve the above technical problems, a technical solution adopted in the present application is: to provide a voice wake-up method, which includes: obtaining the first channel audio signal and the second channel audio signal of each voice wake-up device during the wake-up time period; calculating the coherent reverberation signal-to-noise ratio of each voice wake-up device based on the first channel audio signal and the second channel audio signal of each voice wake-up device respectively; determining the target voice wake-up device based on the coherent reverberation signal-to-noise ratio of each voice wake-up device, and controlling the target voice wake-up device to perform voice interaction with the user.

[0005] Among them, the steps of calculating the coherent reverberation signal-to-noise ratio of each voice wake-up device based on the first channel audio signal and the second channel audio signal of each voice wake-up device respectively include: performing short-time Fourier transform on the first channel audio signal and the second channel audio signal to obtain a first complex spectrum and a second complex spectrum; calculating the coherent reverberation signal-to-noise ratio based on the first complex spectrum and the second complex spectrum.

[0006] Among them, the step of performing short-time Fourier transform on the first channel audio signal and the second channel audio signal to obtain the first complex spectrum and the second complex spectrum includes: obtaining a preset window length and a preset window shift corresponding to the short-time Fourier transform; performing short-time Fourier transform on the first channel audio signal and the second channel audio signal with the preset window length and the preset window shift to obtain the first complex spectrum and the second complex spectrum, respectively.

[0007] Among them, the step of calculating the coherent reverberation signal-to-noise ratio based on the first complex spectrum and the second complex spectrum includes: calculating the first self-spectrum of the first complex spectrum, the second self-spectrum of the second complex spectrum, and the cross-spectrum of the first complex spectrum and the second complex spectrum based on the first complex spectrum and the second complex spectrum respectively; calculating the coherence based on the first self-spectrum, the second self-spectrum and the cross-spectrum; obtaining the reverberation field correlation function between the first channel and the second channel of the voice wake-up device; and obtaining the coherent reverberation signal-to-noise ratio based on the reverberation field correlation function and the coherence.

[0008] Among them, the step of obtaining the reverberation field correlation function between the first channel and the second channel of the voice wake-up device includes: obtaining the spacing and sound speed between the first channel and the second channel; and obtaining the reverberation field correlation function based on the frequency, spacing and sound speed at each frequency point.

[0009] Among them, the step of determining the target voice wake-up device based on the coherent reverberation signal-to-noise ratio of each voice wake-up device includes: calculating the parameter value corresponding to each voice wake-up device in the wake-up time period based on the coherent reverberation signal-to-noise ratio of each voice wake-up device; and taking the voice wake-up device corresponding to the maximum value among all parameter values ​​as the target voice wake-up device.

[0010] Among them, the step of obtaining the first channel audio signal and the second channel audio signal within the wake-up time period of each voice wake-up device includes: determining whether the voice wake-up device receives a wake-up word; in response to receiving the wake-up word, determining the wake-up starting point and the wake-up end point of the voice wake-up device based on the time when the wake-up word is received, and determining the wake-up time period based on the wake-up starting point and the wake-up end point to obtain the first channel audio signal and the second channel audio signal within the wake-up time period.

[0011] Before the step of obtaining the first channel audio signal and the second channel audio signal of each voice wake-up device in the wake-up time period, the method further includes: performing echo cancellation on the first channel audio signal and the second channel audio signal of each voice wake-up device.

[0012] To solve the above technical problems, another technical solution adopted in the present application is: providing a voice wake-up device, which includes a wake-up module, a coherent reverberation signal-to-noise ratio calculation module and a signal-to-noise ratio comparison module, the wake-up module is used to obtain the first channel audio signal and the second channel audio signal within the wake-up time period of the voice wake-up device; the coherent reverberation signal-to-noise ratio calculation module is used to calculate the coherent reverberation signal-to-noise ratio of the voice wake-up device based on the first channel audio signal and the second channel audio signal; the signal-to-noise ratio comparison module is used to determine the target voice wake-up device based on the coherent reverberation signal-to-noise ratios of multiple voice wake-up devices, and send a response instruction to the target voice wake-up device to control the target voice wake-up device to perform voice interaction with the user.

[0013] To solve the above technical problems, another technical solution adopted in the present application is: providing a voice wake-up device system, which includes multiple voice wake-up devices and a signal-to-noise ratio comparison module, each voice wake-up device includes a wake-up module and a coherent reverberation signal-to-noise ratio calculation module, the wake-up module is used to obtain the first channel audio signal and the second channel audio signal within the wake-up time period of the voice wake-up device; the coherent reverberation signal-to-noise ratio calculation module is used to calculate the coherent reverberation signal-to-noise ratio of the voice wake-up device based on the first channel audio signal and the second channel audio signal, the signal-to-noise ratio comparison module is used to determine the target voice wake-up device based on the coherent reverberation signal-to-noise ratio of multiple voice wake-up devices, and send a response instruction to the target voice wake-up device to control the target voice wake-up device to perform voice interaction with the user.

[0014] The signal-to-noise ratio comparison module is integrated into at least one of the multiple voice wake-up devices.

[0015] Among them, the voice wake-up device system also includes a central control device, the signal-to-noise ratio comparison module is integrated in the central control device, and the central control device is communicated with each voice wake-up device to obtain the coherent reverberation signal-to-noise ratio of each voice wake-up device, and the signal-to-noise ratio comparison module is used to determine the target voice wake-up device based on the coherent reverberation signal-to-noise ratio of each voice wake-up device, and send a response instruction to the target voice wake-up device to control the target voice wake-up device to interact with the user by voice.

[0016] In order to solve the above technical problems, another technical solution adopted by the present application is: providing a computer-readable storage medium, which stores program instructions therein, and the program instructions are executed by a processor to implement any of the above voice wake-up methods.

[0017] The beneficial effect of the present application is that, different from the prior art, the voice wake-up method of the present application includes: obtaining the first channel audio signal and the second channel audio signal of each voice wake-up device within the wake-up time period; calculating the coherent reverberation signal-to-noise ratio of each voice wake-up device based on the first channel audio signal and the second channel audio signal of each voice wake-up device respectively; determining the target voice wake-up device based on the coherent reverberation signal-to-noise ratio of each voice wake-up device, and controlling the target voice wake-up device to perform voice interaction with the user. In the above manner, the voice wake-up method of the present application can calculate the coherent reverberation signal-to-noise ratio of each voice wake-up device through the first channel audio signal and the second channel audio signal, and determine the target voice wake-up device for face-to-face wake-up based on the coherent reverberation signal-to-noise ratio, thereby improving the effect of face-to-face wake-up. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of the first embodiment of the voice wake-up method provided by the present application;

[0019] Figure 2 yes Figure 1 A flow chart of an embodiment of step S102;

[0020] Figure 3 yes Figure 2 A schematic diagram of a flow chart of an embodiment of step S201;

[0021] Figure 4 yes Figure 2 A flow chart of an embodiment of step S202;

[0022] Figure 5 yes Figure 4 A schematic diagram of a flow chart of an embodiment of step S403;

[0023] Figure 6 yes Figure 1 A schematic diagram of a flow chart of an embodiment of step S103;

[0024] Figure 7 yes Figure 1 A schematic diagram of a flow chart of an embodiment of step S101;

[0025] Figure 8 This is a flow chart of the second embodiment of the voice wake-up method provided by the present application;

[0026] Fig. 9 It is a structural diagram of an embodiment of a voice wake-up device of the present application;

[0027] Fig.10 It is a structural diagram of the first embodiment of the voice wake-up device system of the present application;

[0028] Fig.11 It is a structural diagram of the second embodiment of the voice wake-up device system of the present application;

[0029] Fig.12 It is a structural diagram of an embodiment of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0031] With the popularity of current voice wake-up devices, there will be multiple voice wake-up devices in the same room or area at the same time. When the user shouts out the wake-up word, multiple voice wake-up devices may respond at the same time. There are many logics for selecting voice wake-up devices in the prior art. The simpler wake-up logic is nearby wake-up, which means waking up the voice wake-up device closest to the user. However, the nearby voice wake-up device may not be the voice wake-up device that the user is facing. From the user experience point of view, the voice wake-up device that the user is facing is the device he wants to wake up, not the one close to him. Therefore, the above method cannot accurately wake up the voice wake-up device that the user is facing, affecting the user experience.

[0032] In order to solve the above problems, this application proposes a voice wake-up method, please refer to Figure 1 , Figure 1 1 is a flow chart of the first embodiment of the voice wake-up method provided by the present application. Figure 1 As shown, the voice wake-up method of this embodiment specifically includes steps S101 to S103:

[0033] Step S101: obtaining a first channel audio signal and a second channel audio signal within a wake-up time period of each voice wake-up device.

[0034] In this embodiment, the applicant found that after the user shouts the wake-up word, the coherent reverberation signal-to-noise ratio of the voice wake-up device directly facing the user among multiple voice wake-up devices in the same room or area is greater than the coherent reverberation signal-to-noise ratio of the voice wake-up devices not directly facing the user.

[0035] Therefore, in this embodiment, the target voice wake-up device that the user is facing among the voice wake-up devices can be determined based on the coherent reverberation signal-to-noise ratio of each voice wake-up device. Before obtaining the coherent reverberation signal-to-noise ratio of each voice wake-up device, it is first necessary to obtain the first channel audio signal and the second channel audio signal during the wake-up time period of each voice wake-up device.

[0036] In this embodiment, each voice wake-up device needs to obtain the first channel audio signal and the second channel audio signal within the wake-up time period. Therefore, in this embodiment, each voice wake-up device in this embodiment needs to be provided with at least two audio collection components, and in this embodiment, the audio collection component can be a microphone component, that is, in this embodiment, each voice wake-up device needs to be provided with at least two microphone components to obtain the first channel audio signal and the second channel audio signal respectively within the wake-up time period.

[0037] Step S102: calculating the coherent reverberation signal-to-noise ratio of each voice wake-up device based on the first channel audio signal and the second channel audio signal of each voice wake-up device respectively.

[0038] After each voice wake-up device obtains the first channel audio signal and the second channel audio signal in the wake-up time period corresponding to itself, each voice wake-up device can calculate its corresponding coherent reverberation signal-to-noise ratio based on its corresponding first channel audio signal and second channel audio signal. The specific method for calculating the coherent reverberation signal-to-noise ratio is described below and will not be described in detail here.

[0039] Step S103: determining a target voice wake-up device based on the coherent reverberation signal-to-noise ratio of each voice wake-up device, and controlling the target voice wake-up device to perform voice interaction with the user.

[0040] After obtaining the coherent reverberation signal-to-noise ratio of each voice wake-up device, the signal-to-noise ratio comparison module can use the coherent reverberation signal-to-noise ratio of each voice wake-up device for comparison, thereby determining that the voice wake-up device corresponding to the maximum value of the coherent reverberation signal-to-noise ratio of each voice wake-up device is the target voice wake-up device, and sending a response instruction to the target voice wake-up device to control the target voice wake-up device to perform voice interaction with the user after receiving the user's wake-up word. Among them, the specific comparison method of the signal-to-noise ratio comparison module is also described below and will not be described in detail here.

[0041] Different from the prior art, the voice wake-up method of the present application includes: obtaining the first channel audio signal and the second channel audio signal within the wake-up time period of each voice wake-up device; calculating the coherent reverberation signal-to-noise ratio of each voice wake-up device based on the first channel audio signal and the second channel audio signal; determining the target voice wake-up device based on the coherent reverberation signal-to-noise ratio of each voice wake-up device, and controlling the target voice wake-up device to perform voice interaction with the user. In the above manner, the voice wake-up method of the present application can calculate the coherent reverberation signal-to-noise ratio of each voice wake-up device through the first channel audio signal and the second channel audio signal, and determine the target voice wake-up device for face-to-face wake-up based on the coherent reverberation signal-to-noise ratio, thereby improving the effect of face-to-face wake-up.

[0042] Optionally, a method for calculating the coherent reverberation signal-to-noise ratio of each voice wake-up device based on the first channel audio signal and the second channel audio signal of each voice wake-up device is as follows: Figure 2 See Figure 2 , Figure 2 yes Figure 1 FIG. 1 is a flow chart of an embodiment of step S102 in FIG. Figure 2 As shown, this embodiment can be Figure 2 The steps shown implement step S102, which specifically includes steps S201 to S202:

[0043] Step S201: performing short-time Fourier transform on the first channel audio signal and the second channel audio signal to obtain a first complex spectrum and a second complex spectrum.

[0044] In this embodiment, a coherent reverberation signal-to-noise ratio calculation module is provided in each voice wake-up device. When the voice wake-up device uses two microphone components to obtain the first channel audio signal and the second channel audio signal respectively, the coherent reverberation signal-to-noise ratio calculation module can be used to perform short-time Fourier transform on the first channel audio signal and the second channel audio signal to obtain the first complex spectrum A1(t,f) and the second complex spectrum A2(t,f). In this embodiment, the dimensions of the first complex spectrum A1(t,f) and the second complex spectrum A2(t,f) are (t, f), t is the time dimension, and f is the frequency dimension.

[0045] Step S202: Calculate the coherent reverberation signal-to-noise ratio based on the first complex spectrum and the second complex spectrum.

[0046] After obtaining the first complex spectrum A1(t, f) and the second complex spectrum A2(t, f), the coherent reverberation signal-to-noise ratio calculation module can calculate the coherent reverberation signal-to-noise ratio corresponding to the voice wake-up device itself based on the first complex spectrum A1(t, f) and the second complex spectrum A2(t, f). The specific calculation method is described below.

[0047] Optionally, a method for performing short-time Fourier transform on the first channel audio signal and the second channel audio signal to obtain a first complex spectrum and a second complex spectrum is as follows: Figure 3 See Figure 3 , Figure 3 yes Figure 2 FIG. 1 is a flow chart of an embodiment of step S201 in FIG. Figure 3 As shown, this embodiment can be Figure 3 The steps shown implement step S201, which specifically includes steps S301 to S302:

[0048] Step S301: Obtaining a preset window length and a preset window shift corresponding to a short-time Fourier transform.

[0049] Short-time Fourier transform is a mathematical transformation related to Fourier transform, which is used to determine the frequency and phase of the sine wave in the local area of ​​the time-varying signal. When performing short-time Fourier transform on the audio signal, it is first necessary to determine the preset window length and preset window shift corresponding to the short-time Fourier transform. In this embodiment, the preset window length can be set to 1024, and the preset window shift can be set to 512. In other embodiments, the preset window length and preset window shift can be set based on actual conditions, and are not limited here.

[0050] Step S302: Perform short-time Fourier transform on the first channel audio signal and the second channel audio signal with a preset window length and a preset window shift to obtain a first complex spectrum and a second complex spectrum respectively.

[0051] After obtaining the preset window length and the preset window shift, the first channel audio signal and the second channel audio signal can be subjected to short-time Fourier transform with the preset window length and the preset window shift to obtain the first complex spectrum A1(t,f) and the second complex spectrum A2(t,f) respectively.

[0052] Optionally, a method for calculating the coherent reverberation signal-to-noise ratio based on the first complex spectrum and the second complex spectrum is as follows: Figure 4 See Figure 4 , Figure 4 yes Figure 2 FIG. 1 is a flow chart of an embodiment of step S202 in FIG. Figure 4 As shown, this embodiment can be Figure 4 The steps shown implement step S202, which specifically includes steps S401 to S404:

[0053] Step S401: Calculate a first self-spectrum of the first complex spectrum, a second self-spectrum of the second complex spectrum, and a cross-spectrum between the first complex spectrum and the second complex spectrum based on the first complex spectrum and the second complex spectrum.

[0054] As mentioned above, after obtaining the first complex spectrum A1(t, f) and the second complex spectrum A2(t, f), the coherent reverberation signal-to-noise ratio calculation module can calculate the first self-spectrum Sxx1(t, f) of the first complex spectrum, the second self-spectrum Sxx2(t, f) of the second complex spectrum and the mutual spectrum Sxy(t, f) between the first complex spectrum and the second complex spectrum based on the first complex spectrum A1(t, f) and the second complex spectrum A2(t, f).

[0055] The calculation formulas of the first autospectrum Sxx1(t, f), the second autospectrum Sxx2(t, f) and the cross-spectrum Sxy(t, f) are shown in formulas (1) to (3):

[0056] Sxx1(t,f)=A1(t,f) * *A1(t,f) (1)

[0057] Sxx2(t,f)=A2(t,f) * *A2(t,f) (2)

[0058] Sxy(t,f)=A1(t,f) * *A2(t,f) (3)

[0059] Among them, Sxx1(t,f) represents the first self-spectrum of the first complex spectrum, f1(t,f) * It is represented as the conjugate complex spectrum of the first complex spectrum; A1(t,f) is represented as the first complex spectrum; Sxx2(t,f) is represented as the second self spectrum of the second complex spectrum; A2(t,f) *It is represented as the conjugate complex spectrum of the second complex spectrum; A2(t,f) is represented as the second complex spectrum; Sxy(t,f) is represented as the cross spectrum of the first complex spectrum and the second complex spectrum.

[0060] Step S402: Calculate coherence based on the first autospectrum, the second autospectrum and the cross-spectrum.

[0061] After obtaining the first self-spectrum Sxx1(t,f), the second self-spectrum Sxx2(t,f) and the cross-spectrum Sxy(t,f), the coherent reverberation signal-to-noise ratio calculation module can calculate the coherence Cxx(t,f) based on the first self-spectrum Sxx1(t,f), the second self-spectrum Sxx2(t,f) and the cross-spectrum Sxy(t,f). The calculation formula of the coherence Cxx(t,f) is shown in formula (4):

[0062]

[0063] Among them, Cxx(t,f) represents coherence; Sxy(t,f) represents the cross-spectrum of the first complex spectrum and the second complex spectrum; Sxx1(t,f) represents the first self-spectrum of the first complex spectrum; Sxx2(t,f) represents the second self-spectrum of the second complex spectrum.

[0064] Step S403: obtaining a reverberation field correlation function between the first channel and the second channel of the voice wake-up device.

[0065] After calculating the coherence Cxx(t,f), the coherent reverberation signal-to-noise ratio calculation module also needs to obtain the reverberation field correlation function Cnn(t,f) between the first channel and the second channel of the voice wake-up device. The specific calculation method of the reverberation field correlation function Cnn(t,f) is described below and will not be described in detail here.

[0066] Step S404: obtaining a coherent reverberation signal-to-noise ratio based on the reverberation field correlation function and coherence.

[0067] After obtaining the coherence Cxx(t,f) and the reverberation field correlation function Cnn(t,f), the coherent reverberation signal-to-noise ratio calculation module can calculate the coherent reverberation signal-to-noise ratio CRSNR(t,f) based on the coherence Cxx(t,f) and the reverberation field correlation function Cnn(t,f). The calculation formula of CRSNR(t,f) is shown in formula (5):

[0068]

[0069] Among them, CRSNR(t,f) represents the coherent reverberation signal-to-noise ratio, Cxx(t,f) represents the coherence; Cnn(t,f) represents the reverberation field correlation function.

[0070] Optionally, a method for obtaining a reverberation field correlation function between a first channel and a second channel of a voice wake-up device is as follows: Figure 5 See Figure 5 , Figure 5 yes Figure 4 FIG. 4 is a flow chart of an embodiment of step S403 in FIG. Figure 5 As shown, this embodiment can be Figure 5 The steps shown implement step S403, which specifically includes steps S501 to S502:

[0071] Step S501: Obtain the distance and sound velocity between the first channel and the second channel.

[0072] When the coherent reverberation signal-to-noise ratio calculation module obtains the reverberation field correlation function Cnn(t,f), it is necessary to obtain the distance d between the first channel and the second channel and the sound speed c, wherein the distance d between the first channel and the second channel in this embodiment is the distance between the two microphone components set in the voice wake-up device, and the sound speed refers to the speed of sound propagation.

[0073] Step S502: obtaining a reverberation field correlation function based on the frequency, spacing and sound speed at each frequency point.

[0074] After obtaining the spacing d and the sound speed c, the coherent reverberation signal-to-noise ratio calculation module can obtain the reverberation field correlation function Cnn(t,f) based on the frequency, spacing d and sound speed c at each frequency point, where the reverberation field correlation function Cnn(t,f) is shown in formula (6):

[0075]

[0076] Among them, Cnn(t,f) represents the reverberation field related function, f represents the frequency of each frequency point, d represents the distance between two microphone components set for the voice wake-up device, and c represents the speed of sound.

[0077] Optionally, the method for determining the target voice wake-up device based on the coherent reverberation signal-to-noise ratio of each voice wake-up device is as follows: Figure 6 See Figure 6 , Figure 6 yes Figure 1 FIG. 1 is a flow chart of an embodiment of step S103 in FIG. Figure 6 As shown, this embodiment can be Figure 6 The steps shown implement step S103, which specifically includes steps S601 to S602:

[0078] Step S601: Calculate the parameter value corresponding to each voice wake-up device in the wake-up time period based on the coherent reverberation signal-to-noise ratio of each voice wake-up device.

[0079] After the coherent reverberation signal-to-noise ratio calculation module obtains the coherent reverberation signal-to-noise ratio CRSNR(t,f) of each voice wake-up device, the coherent reverberation signal-to-noise ratio calculation module of each voice wake-up device can send its corresponding coherent reverberation signal-to-noise ratio CRSNR(t,f) to the signal-to-noise ratio comparison module, and the signal-to-noise ratio comparison module can calculate the parameter value TotalCRSNR corresponding to each voice wake-up device based on the coherent reverberation signal-to-noise ratio CRSNR(t,f) of each voice wake-up device. The calculation formula of the parameter value TotalCRSNR is shown in formula (7):

[0080]

[0081] Among them, TotalCRSNR represents the parameter value corresponding to the voice wake-up device, CRSNR(t,f) represents the coherent reverberation signal-to-noise ratio CRSNR(t,f) of the voice wake-up device, T represents the maximum time value in the time dimension of CRSNR(t,f), and F represents the maximum frequency value in the frequency dimension of CRSNR(t,f).

[0082] Step S602: The voice wake-up device corresponding to the maximum value among all parameter values ​​is used as the target voice wake-up device.

[0083] After the noise ratio comparison module obtains the parameter value TotalCRSNR corresponding to all voice wake-up devices based on formula (7), all parameter values ​​TotalCRSNR can be compared, and the voice wake-up device corresponding to the maximum value of all parameter values ​​TotalCRSNR is used as the target voice wake-up device.

[0084] Optionally, the method for obtaining the first channel audio signal and the second channel audio signal within the wake-up time period of each voice wake-up device is as follows: Figure 7 See Figure 7 , Figure 7 yes Figure 1 FIG. 1 is a flow chart of an embodiment of step S101. Figure 7 As shown, this embodiment can be Figure 7 The steps shown implement step S101, which specifically includes steps S701 to S702:

[0085] Step S701: Determine whether the voice wake-up device receives the wake-up word.

[0086] In this embodiment, each voice wake-up device is provided with a wake-up module. The wake-up module of the voice wake-up device needs to receive the corresponding wake-up word before controlling the voice wake-up device to respond and work. Therefore, in this embodiment, when the voice wake-up device obtains the first channel audio signal and the second channel audio signal within the wake-up time period, the wake-up module needs to determine whether the voice wake-up device has received the wake-up word.

[0087] If the voice wake-up device receives the wake-up word, the process goes to step S702. If the voice wake-up device does not receive the wake-up word, the process goes into standby mode, waiting to be woken up.

[0088] Step S702: Determine the voice wake-up device wake-up start point and wake-up end point based on the time when the wake-up word is received, and determine the wake-up time period based on the wake-up start point and the wake-up end point to obtain the first channel audio signal and the second channel audio signal within the wake-up time period.

[0089] When the voice wake-up device receives the wake-up word, the wake-up module of the voice wake-up device can determine the wake-up start point and the wake-up end point of the voice wake-up device based on the time when the wake-up word is received. Specifically, in the present embodiment, the wake-up module includes a wake-up start point detection module and a wake-up end point detection module, the wake-up start point detection module is used to determine the start time of the wake-up time period, and the wake-up end point detection module is used to determine the end time of the wake-up time period, and the time period between the start time and the end time is the wake-up time period, wherein the start time of the wake-up time period can be set to the time point when the first word of the wake-up word is received, and the end time of the wake-up time period can be set to the time point when the last word of the wake-up word is received. At this point, after determining the wake-up time period, the wake-up module can intercept the first channel audio signal and the second channel audio signal in the wake-up time period for subsequent processing.

[0090] Optionally, this application further proposes a voice wake-up method, see Figure 8 , Figure 8 1 is a flow chart of the second embodiment of the voice wake-up method provided by the present application. Figure 8 As shown, the voice wake-up method of this embodiment specifically includes steps S801 to S804:

[0091] Step S801: performing echo cancellation on the first channel audio signal and the second channel audio signal of each voice wake-up device.

[0092] In this embodiment, before each voice wake-up device obtains the first channel audio signal and the second channel audio signal within its corresponding wake-up time period, it is necessary to perform echo cancellation on the first channel audio signal and the second channel audio signal of each voice wake-up device. Therefore, each voice wake-up device can set an echo cancellation module to eliminate echoes.

[0093] In addition, in this embodiment, echo cancellation is also required when the voice wake-up device makes a broadcast. If the voice wake-up device is in a double-talk state at the same time, the voice wake-up device needs to use a high suppression mode to suppress nonlinear noise to reduce the impact of echo on face-to-face wake-up.

[0094] Step S802: Acquire the first channel audio signal and the second channel audio signal within the wake-up time period of each voice wake-up device.

[0095] Step S802 is consistent with step S101 and will not be described again.

[0096] Step S803: Calculate the coherent reverberation signal-to-noise ratio of each voice wake-up device based on the first channel audio signal and the second channel audio signal of each voice wake-up device respectively.

[0097] Step S803 is the same as step S102 and will not be described again.

[0098] Step S804: determining a target voice wake-up device based on the coherent reverberation signal-to-noise ratio of each voice wake-up device, and controlling the target voice wake-up device to perform voice interaction with the user.

[0099] Step S804 is consistent with step S103 and will not be described again.

[0100] Optionally, the present application further proposes a voice wake-up device. Fig. 9 , Fig. 9 Schematic diagram of the structure of an embodiment of the voice wake-up device of the present application. Fig. 9 As shown, the voice wake-up device 100 of this embodiment includes a wake-up module 10 , a coherent reverberation signal-to-noise ratio calculation module 20 and a signal-to-noise ratio comparison module 30 .

[0101] Among them, the wake-up module 10 is used to obtain the first channel audio signal and the second channel audio signal within the wake-up time period of the voice wake-up device 100; the coherent reverberation signal-to-noise ratio calculation module 20 is used to calculate the coherent reverberation signal-to-noise ratio of the voice wake-up device 100 based on the first channel audio signal and the second channel audio signal; the signal-to-noise ratio comparison module 30 is used to determine the target voice wake-up device based on the coherent reverberation signal-to-noise ratios of multiple voice wake-up devices 100, and send a response instruction to the target voice wake-up device to control the target voice wake-up device to perform voice interaction with the user.

[0102] As mentioned above, the wake-up module 10 is provided with a wake-up start point detection module and a wake-up end point detection module. The wake-up start point detection module is used to determine the start time of the wake-up time period, and the wake-up end point detection module is used to determine the end time of the wake-up time period. The time period between the start time and the end time is the wake-up time period. In addition, the voice wake-up device 100 is also provided with an echo cancellation module (not shown) for performing echo cancellation on the first channel audio signal and the second channel audio signal of the voice wake-up device 100.

[0103] Optionally, the present application further proposes a voice wake-up device system. Fig.10 , Fig.10Schematic diagram of the structure of the first embodiment of the voice wake-up device system of the present application. Fig. 9 As shown, the voice wake-up device system 200 of this embodiment includes a plurality of voice wake-up devices 100 and a signal-to-noise ratio comparison module 30 .

[0104] Among them, each voice wake-up device 100 includes a wake-up module 10 and a coherent reverberation signal-to-noise ratio calculation module 20. The wake-up module 10 is used to obtain the first channel audio signal and the second channel audio signal within the wake-up time period of the voice wake-up device 100; the coherent reverberation signal-to-noise ratio calculation module 20 is used to calculate the coherent reverberation signal-to-noise ratio of the voice wake-up device 100 based on the first channel audio signal and the second channel audio signal. The signal-to-noise ratio comparison module 30 is used to determine the target voice wake-up device based on the coherent reverberation signal-to-noise ratios of multiple voice wake-up devices 100, and send a response instruction to the target voice wake-up device to control the target voice wake-up device to interact with the user by voice.

[0105] Optionally, in this embodiment, if Fig.10 As shown, the signal-to-noise ratio comparison module 30 is integrated into at least one of the plurality of voice wake-up devices 100 .

[0106] That is, in this embodiment, a signal-to-noise ratio comparison module 30 can be set in at least one of the multiple voice wake-up devices 100. After the other voice wake-up devices 100 calculate their corresponding coherent reverberation signal-to-noise ratios, they send them to the voice wake-up device 100 provided with the signal-to-noise ratio comparison module 30. The voice wake-up device 100 uses the signal-to-noise ratio comparison module 30 to determine the target voice wake-up device based on the coherent reverberation signal-to-noise ratios of the multiple voice wake-up devices 100, and sends a response instruction to the target voice wake-up device to control the target voice wake-up device to perform voice interaction with the user.

[0107] Alternatively, in other embodiments, see Fig.11 , Fig.11 Schematic diagram of the structure of the second embodiment of the voice wake-up device system of the present application. Fig.11 As shown, the voice wake-up device system 200 also includes a central control device 210, in which the signal-to-noise ratio comparison module 30 is integrated, and the central control device 210 is communicatively connected with each voice wake-up device 100 to obtain the coherent reverberation signal-to-noise ratio of each voice wake-up device 100, and the signal-to-noise ratio comparison module 30 is used to determine the target voice wake-up device based on the coherent reverberation signal-to-noise ratio of each voice wake-up device 100, and a response instruction is sent to the target voice wake-up device to control the target voice wake-up device to perform voice interaction with the user.

[0108] Optionally, the present application further proposes a computer program, which includes instructions, and when the instructions are executed by an information processing device, the information processing device executes the voice wake-up method of any of the above embodiments.

[0109] In addition, if the above functions are implemented in the form of software functions and sold or used as independent products, they can be stored in a storage medium readable by a mobile terminal, that is, the present application also provides a storage device storing program data, the program data can be executed to implement the method of the above embodiment, and the storage device can be, for example, a USB flash drive, an optical disk, a server, etc. In other words, the present application can be embodied in the form of a software product, which includes a number of instructions for enabling a smart terminal to execute all or part of the steps of the method described in each embodiment.

[0110] Optionally, the present application further proposes a computer-readable storage medium. Fig.12 , Fig.12 It is a structural diagram of an embodiment of a computer-readable storage medium of the present application.

[0111] The computer-readable storage medium 300 of the embodiment of the present application stores program instructions 310 therein, and the program instructions 310 are executed by a processor to implement the voice wake-up method of any of the above embodiments.

[0112] Among them, the program instructions 310 can form a program file and be stored in the above-mentioned storage medium in the form of a software product, so that an electronic device (which can be a personal computer, a server, or a network device, etc.) or a processor (processor) executes all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes, or terminal devices such as computers, servers, mobile phones, tablets, etc.

[0113] The computer-readable storage medium 300 of this embodiment may be, but is not limited to, a USB flash drive, an SD card, a PD optical drive, a mobile hard disk, a large-capacity floppy drive, a flash memory, a multimedia memory card, a server, and the like.

[0115] In addition, if the above functions are implemented in the form of software functions and sold or used as independent products, they can be stored in a storage medium readable by a mobile terminal, that is, the present application also provides a storage device storing program data, the program data can be executed to implement the method of the above embodiment, and the storage device can be, for example, a USB flash drive, an optical disk, a server, etc. In other words, the present application can be embodied in the form of a software product, which includes a number of instructions for enabling a smart terminal to execute all or part of the steps of the method described in each embodiment.

[0116] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0117] Any process or method description in a flowchart or otherwise described herein may be understood to represent a mechanism, segment or portion of a code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0118] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (which can be a personal computer, server, network device or other system that can fetch instructions from the instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0119] The above descriptions are merely embodiments of the present application and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A voice wake-up method, characterized in that: include: Acquire the first channel audio signal and the second channel audio signal of each voice wake-up device within the wake-up time period; Calculating the coherent reverberation signal-to-noise ratio of each of the voice wake-up devices based on the first channel audio signal and the second channel audio signal of each of the voice wake-up devices respectively; A target voice wake-up device is determined based on the coherent reverberation signal-to-noise ratio of each of the voice wake-up devices, and the target voice wake-up device is controlled to perform voice interaction with the user.

2. The voice wake-up method according to claim 1, characterized in that: The step of calculating the coherent reverberation signal-to-noise ratio of each of the voice wake-up devices based on the first channel audio signal and the second channel audio signal of each of the voice wake-up devices respectively includes: Performing short-time Fourier transform on the first channel audio signal and the second channel audio signal to obtain a first complex spectrum and a second complex spectrum; The coherent reverberation signal-to-noise ratio is calculated based on the first complex spectrum and the second complex spectrum.

3. The voice wake-up method according to claim 2, characterized in that: The step of performing short-time Fourier transform on the first channel audio signal and the second channel audio signal to obtain the first complex spectrum and the second complex spectrum includes: Obtaining a preset window length and a preset window movement corresponding to the short-time Fourier transform; The short-time Fourier transform is performed on the first channel audio signal and the second channel audio signal with the preset window length and the preset window shift to respectively obtain the first complex spectrum and the second complex spectrum.

4. The voice wake-up method according to claim 2, characterized in that: The step of calculating the coherent reverberation signal-to-noise ratio based on the first complex spectrum and the second complex spectrum includes: Based on the first complex spectrum and the second complex spectrum, respectively calculate a first self-spectrum of the first complex spectrum, a second self-spectrum of the second complex spectrum, and a cross-spectrum of the first complex spectrum and the second complex spectrum; calculating coherence based on the first autospectrum, the second autospectrum, and the cross-spectrum; Obtaining a reverberation field correlation function between a first channel and a second channel of the voice wake-up device; The coherent reverberation signal-to-noise ratio is obtained based on the reverberation field correlation function and the coherence.

5. The voice wake-up method according to claim 4, characterized in that: The step of obtaining the reverberation field correlation function between the first channel and the second channel of the voice wake-up device includes: Obtaining the distance and sound speed between the first channel and the second channel; The reverberation field correlation function is obtained based on the frequency at each frequency point, the spacing and the sound speed.

6. The voice wake-up method according to claim 1, characterized in that: The step of determining a target voice wake-up device based on the coherent reverberation signal-to-noise ratio of each of the voice wake-up devices comprises: Calculating a parameter value corresponding to each of the voice wake-up devices in the wake-up time period based on the coherent reverberation signal-to-noise ratio of each of the voice wake-up devices; The voice wake-up device corresponding to the maximum value among all the parameter values ​​is used as the target voice wake-up device.

7. The voice wake-up method according to claim 1, characterized in that: The step of obtaining the first channel audio signal and the second channel audio signal within the wake-up time period of each voice wake-up device includes: Determining whether the voice wake-up device receives a wake-up word; In response to receiving the wake-up word, the wake-up start point and the wake-up end point of the voice wake-up device are determined based on the time when the wake-up word is received, and the wake-up time period is determined based on the wake-up start point and the wake-up end point to obtain the first channel audio signal and the second channel audio signal within the wake-up time period.

8. The voice wake-up method according to any one of claims 1 to 7, characterized in that: Before the step of acquiring the first channel audio signal and the second channel audio signal within the wake-up time period of each voice wake-up device, the method further includes: Echo cancellation is performed on the first channel audio signal and the second channel audio signal of each of the voice wake-up devices.

9. A voice wake-up device, characterized in that: include: A wake-up module, used to obtain a first channel audio signal and a second channel audio signal within a wake-up time period of the voice wake-up device; A coherent reverberation signal-to-noise ratio calculation module, configured to calculate a coherent reverberation signal-to-noise ratio of the voice wake-up device based on the first channel audio signal and the second channel audio signal; A signal-to-noise ratio comparison module is used to determine a target voice wake-up device based on the coherent reverberation signal-to-noise ratios of the multiple voice wake-up devices, and send a response instruction to the target voice wake-up device to control the target voice wake-up device to perform voice interaction with the user.

10. A voice wake-up device system, characterized in that: include: Multiple voice wake-up devices, each of which includes a wake-up module and a coherent reverberation signal-to-noise ratio calculation module, wherein the wake-up module is used to obtain a first channel audio signal and a second channel audio signal within a wake-up time period of the voice wake-up device; the coherent reverberation signal-to-noise ratio calculation module is used to calculate the coherent reverberation signal-to-noise ratio of the voice wake-up device based on the first channel audio signal and the second channel audio signal; A signal-to-noise ratio comparison module is used to determine a target voice wake-up device based on the coherent reverberation signal-to-noise ratios of the multiple voice wake-up devices, and send a response instruction to the target voice wake-up device to control the target voice wake-up device to perform voice interaction with the user.

11. The voice wake-up device system according to claim 10, characterized in that: The signal-to-noise ratio comparison module is integrated in at least one of the plurality of voice wake-up devices.

12. The voice wake-up device system according to claim 10, characterized in that: The system also includes a central control device, in which the signal-to-noise ratio comparison module is integrated, and the central control device is communicatively connected with each of the voice wake-up devices to obtain the coherent reverberation signal-to-noise ratio of each of the voice wake-up devices, and uses the signal-to-noise ratio comparison module to determine the target voice wake-up device based on the coherent reverberation signal-to-noise ratio of each of the voice wake-up devices, and sends a response instruction to the target voice wake-up device to control the target voice wake-up device to perform voice interaction with the user.

13. A computer program, characterized in that The computer program includes instructions, and when the instructions are executed by an information processing device, the information processing device executes the voice wake-up method according to any one of claims 1 to 8.

14. A computer-readable storage medium, characterized in that: Program instructions are stored thereon, and the program instructions are executed to implement the voice wake-up method according to any one of claims 1 to 8.

Images