Voice activity detection method and system, voice enhancement method and system

Abstract

The voice activity detection method and system, and the speech enhancement method and system according to the present specification determine a voice presence probability that a target speech signal is present in a microphone signal by calculating a linear correlation between a signal subspace in which the microphone signal is located and a target subspace in which the target speech signal is located. The speech enhancement method and system can perform speech enhancement on the microphone signal by calculating a filtering coefficient based on the voice presence probability. The method and system can improve the speech enhancement effect by improving the calculation accuracy of the voice presence probability.

Description

[Technical field]

[0001] The present specification relates to the technical field of target voice signal processing, in particular to a voice activity detection method and system, and a voice enhancement method and system. [Background technology]

[0002] In a voice enhancement technique based on a beamforming algorithm, especially in an adaptive beamforming algorithm of Minimum Variance Distortionless Response (abbreviated as MVDR), how to solve a parameter--noise covariance matrix that describes the relationship of the statistical characteristics of noise between different microphones is extremely important. The main method in the prior art is to calculate the noise covariance matrix based on the method of voice presence probability, for example, estimating the voice presence probability by a voice activity detection method (abbreviated as Voice Activity Detection, VAD), and then calculating the noise covariance matrix. However, the estimation accuracy rate of the voice presence probability in the prior art is not sufficient, so the estimation accuracy of the noise covariance matrix is ​​low, and the voice enhancement effect of the MVDR algorithm is low. In particular, when the number of microphones is small, for example, less than five, the effect drops sharply. Therefore, the MVDR algorithm in the prior art is often used in microphone array devices with a large number of microphones and large spacing, such as mobile phones and smart speakers, but the voice enhancement effect is low in devices with a small number of microphones and small spacing, such as earphones.

[0003] Therefore, there is a need to provide more accurate voice activity detection methods and systems, and speech enhancement methods and systems. Summary of the Invention

[0004] The present specification provides more accurate voice activity detection methods and systems, and speech enhancement methods and systems.

[0005] According to a first aspect, the present specification provides a voice activity detection method, applied to M microphones distributed in a pre-defined array shape, where M is an integer greater than 1, the method includes: obtaining microphone signals output by the M microphones; determining a signal subspace constituted by the microphone signals based on the microphone signals; determining a target subspace constituted by a target voice signal; and determining and outputting a voice presence probability that the target voice signal is present in the microphone signals based on a linear correlation between the signal subspace and the target subspace.

[0006] In some embodiments, determining a signal subspace constituted by the microphone signal based on the microphone signal includes determining a sampling covariance matrix of the microphone signal based on the microphone signal, performing eigenvalue decomposition on the sampling covariance matrix to determine a plurality of eigenvectors of the sampling covariance matrix, and defining a matrix consisting of at least a portion of the eigenvectors of the plurality of eigenvectors as a fundamental matrix of the signal subspace.

[0007] In some embodiments, determining a signal subspace constituted by the microphone signals based on the microphone signals includes determining signal steering vectors of the microphone signals by determining azimuth angles of signal sources in the microphone signals based on the microphone signals using a spatial estimation method including at least one of a DOA estimation method and a spatial spectrum estimation method, and determining that the signal steering vector is a fundamental matrix of the signal subspace.

[0008] In some embodiments, determining the target subspace constituted by the target audio signal includes determining that a predetermined target steering vector corresponding to the target audio signal is a fundamental matrix of the target subspace.

[0009] In some embodiments, determining and outputting a voice presence probability that the target voice signal is present in the microphone signal based on a linear correlation between the signal subspace and the target subspace comprises determining a volume correlation function between the signal subspace and the target subspace, determining a linear correlation coefficient between the signal subspace and the target subspace based on the volume correlation function, where the linear correlation coefficient is negatively correlated with the volume correlation function, and outputting the linear correlation coefficient as the voice presence probability.

[0010] In some embodiments, determining a linear correlation coefficient between the signal subspace and the target subspace based on the volume correlation function includes one of the following cases: determining that the volume correlation function is greater than a first threshold and determining that the linear correlation coefficient is 0; determining that the volume correlation function is smaller than a second threshold and determining that the linear correlation coefficient is 1, where the second threshold is smaller than the first threshold; determining that the volume correlation function is between the first threshold and the second threshold, the linear correlation coefficient is between 0 and 1, and determining that the linear correlation coefficient is a function that is negatively correlated with the volume correlation function.

[0011] According to a second aspect, the present specification further provides a voice activity detection system, the system comprising at least one storage medium and at least one processor, the at least one storage medium having stored therein at least one instruction set for voice activity detection, the at least one processor being communicatively connected to the at least one storage medium, wherein when the voice activity detection system is operational, the at least one processor reads the at least one instruction set and performs the voice activity detection method as described in the first aspect of the present specification.

[0012] According to a third aspect, the present specification further provides a speech enhancement method, for use with M microphones distributed in a pre-defined array shape, where M is an integer greater than 1, the method including: acquiring microphone signals output by the M microphones; determining a voice presence probability that the target speech signal is present in the microphone signals based on the voice activity detection method described in the first aspect of the present specification; determining a filtering coefficient vector corresponding to the microphone signals based on the voice presence probability; and integrating the microphone signals based on the filtering coefficient vector to obtain and output a target audio signal.

[0013] In some embodiments, determining a filtering coefficient vector corresponding to the microphone signal based on the voice presence probability comprises determining a noise covariance matrix of the microphone signal based on the voice presence probability, and determining the filtering coefficient vector based on an MVDR method and the noise covariance matrix.

[0014] In some embodiments, determining a filtering coefficient vector corresponding to the microphone signals based on the voice presence probability includes setting the voice presence probability as a filtering coefficient corresponding to a target microphone signal among the microphone signals, wherein the target microphone signal includes a one-way microphone signal among the microphone signals having the highest signal-to-noise ratio, and determining that filtering coefficients corresponding to other microphone signals among the microphone signals other than the target microphone signal are 0, and the filtering coefficient vector includes a vector consisting of filtering coefficients corresponding to the target microphone signal and filtering coefficients corresponding to the other microphone signals.

[0015] According to a fourth aspect, the present specification further provides a voice enhancement system, the system including at least one storage medium and at least one processor, the at least one storage medium storing at least one instruction set for performing voice enhancement, the at least one processor being communicatively connected to the at least one storage medium, wherein when the voice enhancement system is operating, the at least one processor reads the at least one instruction set and performs the voice enhancement method described in the second aspect of the present specification.

[0016] As can be seen from the above technical solutions, the voice activity detection method, system, voice enhancement method and system according to the present specification are used in a microphone array consisting of multiple microphones. Here, the microphone array can collect a noise signal or a target voice signal and output a microphone signal. The target voice signal and the noise signal are two types of signals without cross-links. The target subspace where the target voice signal is located and the noise subspace where the noise signal is located are two subspaces without cross-links. If the target voice signal is not present in the microphone signal, the microphone signal only contains the noise signal. In this case, the signal subspace where the microphone signal is located and the target subspace where the target voice signal is located are two subspaces without cross-links, and the linear correlation between the signal subspace and the target subspace is low. If the target voice signal is present in the microphone signal, the microphone signal contains both the target voice signal and the noise signal. In this case, the signal subspace where the microphone signal is located and the target subspace where the target voice signal is located are two subspaces with cross-links, and the linear correlation between the signal subspace and the target subspace is high. Therefore, the voice activity detection method and system according to the present disclosure can determine a voice presence probability that a target voice signal is present in a microphone signal by calculating a linear correlation between a signal subspace in which the microphone signal is located and a target subspace in which the target voice signal is located. The voice enhancement method and system can perform voice enhancement on the microphone signal by calculating a filtering coefficient based on the voice presence probability. The method and system can improve the voice enhancement effect by improving the calculation accuracy of the voice presence probability.

[0017] Other features of the voice activity detection method, system, speech enhancement method and system according to the present specification are described in part in the following description. According to the description, the contents shown in the following figures and examples will be self-evident to those skilled in the art. The creative aspects of the voice activity detection method, system, speech enhancement method and system according to the present specification can be fully understood by practice or use of the methods, apparatus and combinations described in the following detailed examples. [Brief description of the drawings]

[0018] In order to more clearly describe the technical solutions in the embodiments of the present specification, the following provides a brief description of the drawings that need to be used in the description of the embodiments. It should be apparent that the drawings in the following description are only some embodiments of the present specification, and those skilled in the art can obtain other drawings based on these drawings without any creative efforts. [Figure 1] 1 is a hardware schematic diagram of a voice activity detection system according to an embodiment of the present disclosure. [Figure 2A] 1 is a schematic exploded view of an electronic device according to an embodiment of the present specification; [Figure 2B] FIG. 2 is a front view of a first case according to an embodiment of the present disclosure. [Figure 2C] FIG. 2 is a plan view of a first case according to an embodiment of the present disclosure. [Figure 2D] FIG. 13 is a front view of a second case according to an embodiment of the present disclosure. [Figure 2E] FIG. 13 is a bottom view of a second case according to an embodiment of the present disclosure. [Diagram 3] 1 is a flow chart of a voice activity detection method according to an embodiment of the present disclosure; [Figure 4] 1 is a flow chart of determining an essential matrix of a signal subspace according to an embodiment of the present disclosure; [Diagram 5] 11 is another flowchart of determining an essential matrix of a signal subspace according to an embodiment of the present disclosure; [Figure 6] 1 is a flow chart of a calculation of a voice presence probability according to an embodiment of the present disclosure; [Figure 7]FIG. 2 is a schematic diagram of canonical angles according to an embodiment of the present specification. [Figure 8] 1 is a flowchart of a speech enhancement method according to an embodiment of the present disclosure; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0019] The following description provides specific application scenarios and requirements of the present specification to enable those skilled in the art to make and use the contents of the present specification. Various partial modifications to the disclosed embodiments will be apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the present specification. Therefore, the present specification is not intended to be limited to the embodiments shown, but is accorded the widest scope consistent with the claims.

[0020] The terminology used herein is for the purpose of describing particular example embodiments only and is not intended to be limiting. For example, the singular forms "a", "an" and "the" as used herein can also include the plural unless the context clearly dictates otherwise. As used herein, the terms "comprise", "include", and / or "containing" refer to the presence of associated integers, steps, operations, elements and / or components, but do not exclude the presence of one or more other features, integers, steps, operations, elements, components and / or groups, or that other features, integers, steps, operations, elements, components and / or groups may be added to the system / method.

[0021] These and other features of the present specification, as well as the operation and function of the associated elements of structure, and the combination of parts and economies of manufacture, can be clearly improved upon in consideration of the following description. Reference is made to the drawings, all of which form a part of this specification. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended to limit the scope of this specification. It is also to be understood that the drawings are not drawn to scale.

[0022] As used herein, flowcharts illustrate operations of a system implementation according to some embodiments of the present invention. It should be clearly understood that the operations of the flowcharts may be implemented out of order. Conversely, the operations may be implemented in reverse order or simultaneously. It should be noted that one or more other operations may be added to the flowcharts. One or more operations may be removed from the flowcharts.

[0023] To facilitate the explanation, the terms appearing in this specification are first explained as follows. <Minimum Variance Distortionless Response (abbreviated as MVDR)> An adaptive beamforming algorithm based on the maximum signal-to-interference-and-noise ratio (SINR) criterion, the MVDR algorithm can adaptively minimize the power of the array output in the desired direction while maximizing the signal-to-interference-and-noise ratio. The goal is to minimize the variance of the recorded signal. If the noise signal and the desired signal are uncorrelated, the variance of the recorded signal is the sum of the variances of the desired and noise signals. Therefore, the MVDR solution seeks to reduce the effect of the noise signal by minimizing this sum. The principle is to select appropriate filter coefficients to minimize the average power of the array output under the constraint that the desired signal is undistorted.

[0024] <Voice Activity Detection> This is a processing procedure for dividing a target speech signal into speech segments and non-speech segments.

[0025] <Gaussian distribution> Normal distribution, also known as "stationary distribution" and also known as Gaussian distribution. The normal curve is bell-shaped, low at both ends, high in the middle, and symmetrical, and is often called a bell curve. The random variable X has an expectation of μ and a deviation of σ. 2 If the normal distribution is 2) The desired value μ for a probability density function of a normal distribution determines its location, and its standard deviation σ determines the amplitude of the distribution. When μ=0 and σ=1, the normal distribution is the standard normal distribution.

[0026] 1 shows a hardware schematic diagram of a voice activity detection system according to an embodiment of the present disclosure. The voice activity detection system may be used in an electronic device 200.

[0027] In some embodiments, the electronic device 200 may be a device with audio processing capabilities, such as a wireless earphone, a wired earphone, a smart wearable device, such as a smart glass, a smart helmet, or a smart watch. The electronic device 200 may also be a mobile device, a tablet computer, a laptop, an in-car device, or the like, or any combination thereof. In some embodiments, the mobile device may include a smart home device, a smart mobile device, or the like, or any combination thereof. For example, the smart mobile device may include a mobile phone, a personal digital assistant, a gaming device, a navigation device, an ultra-mobile personal computer (UMPC), or the like, or any combination thereof. In some embodiments, the smart home device may include a smart television, a desktop computer, or the like, or any combination thereof. In some embodiments, the in-car device may include an in-car computer, an in-car television, or the like.

[0028] In this specification, the inventors take the electronic device 200 as an example of an earphone. The earphone may be a wireless earphone or a wired earphone. As shown in FIG. 1, the electronic device 200 may include a microphone array 220 and a computing device 240.

[0029] The microphone array 220 may be an audio collecting device of the electronic device 200. The microphone array 220 may be configured to acquire local audio and output a microphone signal, i.e., an electronic signal with audio information. The microphone array 220 may include M microphones 222 distributed in a predefined array shape, where M is an integer greater than 1. The M microphones 222 may be uniformly or non-uniformly distributed. The M microphones 222 may output microphone signals. The M microphones 222 may output M microphone signals. Each microphone 222 corresponds to one microphone signal. The M microphone signals are collectively referred to as the microphone signals. In some embodiments, the M microphones 222 may be linearly distributed. In some embodiments, the M microphones 222 may be distributed as an array of other shapes, for example, a circular array, a rectangular array, etc. For ease of explanation, in the following description, the inventors will take the M microphones 222 as an example of being linearly distributed. In some embodiments, M may be any integer greater than 1, such as 2, 3, 4, 5, or more. In some embodiments, due to space constraints, M may be an integer greater than 1 and less than or equal to 5, for example, in products such as earphones. When the electronic device 200 is an earphone, the spacing between adjacent microphones 222 among the M microphones 222 may be 20 mm to 40 mm. In some embodiments, the spacing between adjacent microphones 222 may be smaller, such as 10 mm to 20 mm.

[0030] In some embodiments, the microphone 222 may be a bone conduction microphone that directly collects human body vibration signals. The bone conduction microphone may include a vibration sensor, such as an optical vibration sensor, an acceleration sensor, etc. The vibration sensor can collect mechanical vibration signals (e.g., signals due to vibrations generated by the skin or bones when the user is speaking) and convert the mechanical vibration signals into electrical signals. The mechanical vibration signals here mainly refer to vibrations that propagate through solid bodies. The bone conduction microphone collects vibration signals generated by the skin or bones when the user speaks by contacting the skin or bones of the user through the vibration sensor or a vibration component connected to the vibration sensor, and converts the vibration signals into electrical signals. In some embodiments, the vibration sensor may be a device that is sensitive to mechanical vibrations but not air vibrations (i.e., the response capability of the vibration sensor to mechanical vibrations exceeds the response capability of the vibration sensor to air vibrations). The bone conduction microphone can directly pick up vibration signals from the speaking part, thereby reducing the influence of environmental noise.

[0031] In some embodiments, the microphone 222 may be an air conduction microphone that directly collects air vibration signals generated when a user speaks and converts the air vibration signals into electrical signals.

[0032] In some embodiments, the M microphones 222 may be M bone conduction microphones. In some embodiments, the M microphones 222 may be M air conduction microphones. In some embodiments, the M microphones 222 may include bone conduction microphones or air conduction microphones. Of course, the microphones 222 may be other types of microphones, such as optical microphones, microphones that receive myoelectric signals, etc.

[0033] The computing device 240 may be communicatively connected to the microphone array 220. The communicative connection refers to any form of connection that can receive information directly or indirectly. In some embodiments, the computing device 240 can communicate data with the microphone array 220 via a wireless communication connection, in some embodiments, the computing device 240 can also communicate data with the microphone array 220 directly connected to the microphone array 220 by wires, and in some embodiments, the computing device 240 can also directly connect to other circuits by wires to establish an indirect connection with the microphone array 220 to realize data communication between them. In this specification, the computing device 240 is directly connected to the microphone array 220 by wires as an example.

[0034] The computing device 240 may be a hardware device having data processing capabilities. In some embodiments, the voice activity detection system may include the computing device 240. In some embodiments, the voice activity detection system may be used in the computing device 240, i.e., the voice activity detection system may run on the computing device 240. The voice activity detection system may include a hardware device having data processing capabilities and a program necessary to drive the operation of the hardware device. Of course, the voice activity detection system may be only a hardware device having data processing capabilities, or only a program running on the hardware device.

[0035] The voice activity detection system may store data or instructions and may execute the data and / or instructions to perform the voice activity detection methods described herein. When the voice activity detection system operates on a computing device 240, the voice activity detection system may obtain the microphone signals from the microphone array 220 based on the communication connection, execute the data or instructions of the voice activity detection methods described herein, and calculate a voice presence probability that a target voice signal is present in the microphone signals. The voice activity detection methods are introduced elsewhere herein. For example, the voice activity detection methods are introduced in the description of Figures 3-8.

[0036] 1, the computing device 240 may include at least one storage medium 243 and at least one processor 242. In some embodiments, the electronic device 200 may further include a communication port 245 and an internal communication bus 241.

[0037] The internal communication bus 241 may connect to different system components including a storage medium 243 , a processor 242 , and a communication port 245 .

[0038] The communication port 245 can be used for data communication between the computing device 240 and the outside world. For example, the computing device 240 can obtain the microphone signals from the microphone array 220 via the communication port 245.

[0039] At least one storage medium 243 may include a data storage device. The data storage device may be a non-transitory or a transitory storage medium. For example, the data storage device may include one or more of a magnetic disk, a read-only storage medium (ROM), or a random access storage medium (RAM). When the voice activity detection system is operable on a computing device 240, the storage medium 243 may further include at least one set of instructions stored in the data storage device for performing voice activity detection on the microphone signal. The instructions may be computer program code, and the computer program code may include programs, routines, objects, components, data structures, processes, modules, etc., for performing the voice activity detection method according to the present disclosure.

[0040] The at least one processor 242 can be communicatively connected to the at least one storage medium 243 via an internal communication bus 241. The communicative connection refers to any form of connection capable of receiving information directly or indirectly. The at least one processor 242 is for executing the at least one instruction set. When the voice activity detection system is operable on the computing device 240, the at least one processor 242 reads the at least one instruction set and executes the voice activity detection method according to the present disclosure according to the instructions of the at least one instruction set. The processor 242 can execute all steps included in the voice activity detection method. The processor 242 may be in the form of one or more processors, and in some embodiments, the processor 242 may include one or more hardware processors, such as a microcontroller, a microprocessor, a reduced instruction set computer (RISC), a special-purpose integrated circuit (ASIC), an application-specific instruction set processor (ASIP), a central processing unit (CPU), a graphics processing unit (GPU), a physical processing unit (PPU), a microcontroller unit, a digital signal processor (DSP), a field programmable gate array (FPGA), an advanced RISC machine (ARM), a programmable logic device (PLD), any circuit or processor capable of performing one or more functions, or any combination thereof. For the sake of illustrative purposes only, only one processor 242 is described herein for the computing device 240. However, it should be noted that the computing device 240 herein may further include multiple processors 242, such that the operations and / or method steps disclosed herein may be performed by one processor or jointly by multiple processors as described herein.For example, where in this specification a processor 242 of a computing device 240 performs steps A and B, it should be understood that steps A and B may be performed jointly or separately by two different processors 242 (e.g., a first processor performs step A and a second processor performs step B, or the first and second processors perform steps A and B jointly).

[0041] 2A illustrates an exploded structural schematic diagram of an electronic device 200 according to an embodiment of the present disclosure. As shown in FIG. 2A, the electronic device 200 may include a microphone array 220, a computing device 240, a first case 260, and a second case 280.

[0042] The first case 260 may be a mounting substrate for the microphone array 220. The microphone array 220 may be mounted inside the first case 260. The shape of the first case 260 may be adaptively designed according to the distribution shape of the microphone array 220, and this specification does not limit this too much. The second case 280 may be a mounting substrate for the computing device 240. The computing device 240 may be mounted inside the second case 280. The shape of the second case 280 may be adaptively designed according to the shape of the computing device 240, and this specification does not limit this too much. If the electronic device 200 is an earphone, the second case 280 may be connected to the wearing site. The second case 280 may be connected to the first case 260. As described above, the microphone array 220 may be electrically connected to the computing device 240. Specifically, the microphone array 220 can realize an electrical connection with the computing device 240 through the connection between the first case 260 and the second case 280.

[0043] In some embodiments, the first case 260 may be fixedly connected to the second case 280 by integral molding, welding, crimping, adhesive, or the like. In some embodiments, the first case 260 may be removably connected to the second case 280. The computing device 240 may be communicatively connected to different microphone arrays 220. Specifically, different microphone arrays 220 may differ in the number of microphones 222 in the microphone array 220, the array shape, the spacing between the microphones 222, the mounting angle of the microphone array 220 in the first case 260, the mounting position of the microphone array 220 in the first case 260, and the like. The wearer can replace the corresponding microphone array 220 according to different application scenarios to apply the electronic device 200 to a wider range of scenarios. For example, when the distance between the wearer and the electronic device 200 is short in the application scenario, the wearer can replace the microphone array 220 with a microphone array 220 with a smaller spacing. Further, for example, if the distance between the wearer and the electronic device 200 is long in an application scenario, the wearer can switch to a microphone array 220 with a larger number of microphones spaced apart.

[0044] The detachable connection may be any form of physical connection, such as a screw connection, a snap connection, a magnetic attraction connection, etc. In some embodiments, the first case 260 and the second case 280 may be connected by a magnetic attraction, i.e., the first case 260 and the second case 280 are detachably connected by the attraction force of a magnetic device.

[0045] 2B shows a front view of the first case 260 according to an embodiment of the present specification, and FIG. 2C shows a plan view of the first case 260 according to an embodiment of the present specification. As shown in FIG. 2B and FIG. 2C, the first case 260 may include a first interface 262. In some embodiments, the first case 260 may further include a touch point 266. In some embodiments, the first case 260 may further include an angle sensor (not shown in FIG. 2B and FIG. 2C).

[0046] The first interface 262 may be a mounting interface of the first case 260 and the second case 280. In some embodiments, the first interface 262 may be circular. The first interface 262 may be rotatably connected to the second case 280. When the first case 260 is mounted on the second case 280, the angle of the microphone array 220 can be adjusted by rotating the first case 260 relative to the second case 280 and adjusting the angle of the first case 260 relative to the second case 280.

[0047] A first magnetic device 263 may be installed on the first interface 262. The first magnetic device 263 may be installed at a position close to the second case 280 of the first interface 262. The first magnetic device 263 may realize a detachable connection with the second case 280 by generating a magnetic attraction force. When the first case 260 approaches the second case 280, the attraction force quickly connects the first case 260 to the second case 280. In some embodiments, after the first case 260 is connected to the second case 280, the first case 260 can still rotate relative to the second case 280, thereby adjusting the angle of the microphone array 220. Due to the action of the attraction force, the connection between the first case 260 and the second case 280 can be maintained even if the first case 260 rotates relative to the second case 280.

[0048] In some embodiments, the first interface 262 may further include a first positioning device (not shown in FIGS. 2B and 2C ). The first positioning device may be a positioning step protruding outward or a positioning hole extending inward. The first positioning device may be engaged with the second case 280 to realize quick mounting of the first case 260 and the second case 280.

[0049] As shown in FIG. 2B and FIG. 2C, in some embodiments, the first case 260 may further include a touch point 266. The touch point 266 may be mounted at the first interface 262. The touch point 266 may protrude outward from the first interface 262. The touch point 266 may be elastically connected to the first interface 262. The touch point 266 may be communicatively connected to the M microphones 222 in the microphone array 220. The touch point 266 may be made of elastic metal to realize data transmission. When the first case 260 is connected to the second case 280, the microphone array 220 may realize a communicative connection with the computing device 240 through the touch point 266. In some embodiments, the touch points 266 may be distributed in a circular shape. After the first case 260 is connected to the second case 280, when the first case 260 rotates relative to the second case 280, the touch points 266 can also rotate relative to the second case 280 and maintain a communication connection with the computing device 240.

[0050] In some embodiments, an angle sensor (not shown in FIGS. 2B and 2C ) may further be installed on the first case 260. The angle sensor may be communicatively connected to the touch point 266, thereby achieving a communicative connection with the computing device 240. The angle sensor may collect angle data of the first case 260 to determine the angle at which the microphone array 220 is located, and provide reference data for subsequent calculation of the voice presence probability.

[0051] 2D illustrates a front view of second case 280 according to an embodiment of the present disclosure, and FIG. 2E illustrates a bottom view of second case 280 according to an embodiment of the present disclosure. As shown in FIG. 2D and FIG. 2E, second case 280 may include a second interface 282. In some embodiments, second case 280 may further include a guide rail 286.

[0052] The second interface 282 may be a mounting interface of the second case 280 and the first case 260. In some embodiments, the second interface 282 may be circular. The second interface 282 may be rotatably connected to the first interface 262 of the first case 260. When the first case 260 is mounted on the second case 280, the angle of the microphone array 220 can be adjusted by rotating the first case 260 relative to the second case 280 and adjusting the angle of the first case 260 relative to the second case 280.

[0053] A second magnetic device 283 may be installed on the second interface 282. The second magnetic device 283 may be installed at a position of the second interface 282 close to the first case 260. The second magnetic device 283 can realize a detachable connection with the first interface 262 by generating a magnetic attraction force. The second magnetic device 283 can be used by engaging with the first magnetic device 263. When the first case 260 approaches the second case 280, the attraction force between the second magnetic device 283 and the first magnetic device 263 can quickly mount the first case 260 on the second case 280. When the first case 260 is mounted on the second case 280, the second magnetic device 283 faces the position of the first magnetic device 263. In some embodiments, after the first case 260 is connected to the second case 280, the first case 260 can still rotate relative to the second case 280, thereby adjusting the angle of the microphone array 220. Due to the action of the suction force, the connection between the first case 260 and the second case 280 can be maintained even if the first case 260 rotates relative to the second case 280.

[0054] In some embodiments, a second positioning device (not shown in FIGS. 2D and 2E ) may be further installed on the second interface 282. The second positioning device may be a positioning step protruding outward or a positioning hole extending inward. The second positioning device may engage with the first positioning device of the first case 260 to realize quick mounting of the first case 260 and the second case 280. When the first positioning device is the positioning step, the second positioning device may be the positioning hole. When the first positioning device is the positioning hole, the second positioning device may be the positioning step.

[0055] As shown in FIG. 2D and FIG. 2E, in some embodiments, the second case 280 may further include a guide rail 286. The guide rail 286 may be mounted at the second interface 282. The guide rail 286 may be communicatively connected to the computing device 240. The guide rail 286 may be made of a metal material to realize data transmission. When the first case 260 is connected to the second case 280, the touch point 266 may contact the guide rail 286 to form a communicative connection, thereby realizing the communicative connection between the microphone array 220 and the computing device 240 and realizing data transmission. As mentioned above, the touch point 266 may be elastically connected to the first interface 262. Therefore, after the first case 260 is connected to the second case 280, the elastic action of the elastic connection can make the touch point 266 fully contact the guide rail 286 to realize a reliable communicative connection. In some embodiments, the guide rail 286 may be distributed in a circular shape. After the first case 260 is connected to the second case 280, when the first case 260 rotates relative to the second case 280, the touch points 266 can also rotate relative to the guide rails 286 and maintain a communication connection with the guide rails 286.

[0056] 3 shows a flowchart of a voice activity detection method P100 according to an embodiment of the present disclosure. The method P100 can calculate a voice presence probability that a target voice signal is present in the microphone signal. Specifically, the processor 242 can execute the method P100.

[0057] As shown in FIG. 3, the method P100 includes: S120: The method may include obtaining microphone signals output by the M microphones 222.

[0058] As described above, each microphone 222 can output a corresponding microphone signal. The M microphones 222 correspond to the M microphone signals. When the method P100 calculates the voice presence probability that the target voice signal is present in the microphone signals, the method P100 may calculate the voice presence probability based on all or some of the M microphone signals. Therefore, the microphone signals may include M microphone signals corresponding to the M microphones 222 or some of the microphone signals. In the following description of this specification, it is taken as an example that the microphone signals may include M microphone signals corresponding to the M microphones 222.

[0059] In some embodiments, the microphone signal may be a time domain signal. For ease of explanation, we label the microphone signal at time t as x(t). The microphone signal x(t) may be a signal vector consisting of M microphone signals. In this case, the microphone signal x(t) may be expressed as:

number

[0060] The microphone signal x(t) is a time-domain signal. In some embodiments, in step S120, the calculation device 240 can further perform a spectrum analysis on the microphone signal x(t). Specifically, the calculation device 240 can perform a Fourier transform based on the time-domain signal x(t) of the microphone signal to obtain a frequency-domain signal x(t) of the microphone signal. f,t In the following description, the microphone signal x in the frequency domain can be obtained. f,t Let us take the microphone signal x as an example. f,t may be an M-dimensional signal vector consisting of M microphone signals. In this case, the microphone signal x f,t may be expressed as follows:

number

[0061] As described above, the microphone 222 can collect noise from the surrounding environment and output a noise signal, and can also collect the voice of the target user and output the target voice signal. When the target user does not make a sound, the microphone signal includes only the noise signal. When the target user makes a sound, the microphone signal includes the target voice signal and the noise signal. Microphone signal x f,t may be expressed as follows:

number

[0062] Here, s f,t is the complex amplitude of the target audio signal. P is the target steering vector of the target audio signal. d f,t is the microphone signal x f,t Q is the noise steering vector of the noise signal.

[0063] s f,tis the complex amplitude of the target sound signal. In some embodiments, there is one target sound signal source around the microphone 222. In some embodiments, there are L target sound signal sources around the microphone 222. In this case, s f,t can be an L×1 dimensional vector. f,t may be expressed as follows:

number

[0064] The target steering vector P is a matrix with dimensions M×L. The target steering vector P may be expressed by the following equation:

number

[0065] where f0 is the carrier frequency; d is the distance between adjacent microphones 222; c is the speed of sound; θ1, . . . , θ L are the angles of incidence between the L target sound signal sources and the microphone 222, respectively. In some embodiments, the target sound signal sources s f,t The angles of θ1, θ2, θ3, θ4, θ5, θ6, θ7, θ8, θ9, θ10, θ11, θ12, θ13, θ14, θ15, θ16, θ17, θ18, θ19, θ111, θ112, θ193, θ194, θ195, θ196, θ L is known. The calculation device 240 stores in advance a relative positional relationship such as a relative distance or a relative coordinate of the M microphones 222. That is, the calculation device 240 stores in advance a distance d between adjacent microphones 222. That is, the calculation device 240 may store in advance a target steering vector P.

[0066] Noise signal d f,t may be an M-dimensional signal vector collected by the M microphones 222. f,t may be expressed by the following formula: d f,tis the complex amplitude of the noise signal. In some embodiments, there are N noise signal sources around the microphone 222. In this case, d f,t can be a vector of dimension N×1. f,t may be expressed as follows:

number

[0067] The noise steering vector Q is a matrix of dimensions M×N. Due to the irregularity of the noise signal, the noise signal d f,t and the noise steering vector Q is unknown.

[0068] In some embodiments, equation (3) may be further expressed as:

number

[0069] where [P,Q] is the microphone signal x f,t is the signal steering vector of

[0070] As previously mentioned, the microphone 222 receives the target audio signal s f,t We can also collect the noise signal d f,t It is also possible to collect the target speech signal s f,t and the noise signal d f,t are two types of signals with no cross-links. Therefore, the target speech signal s f,t The target subspace in which lies and the noise signal d f,t The noise subspace in which x exists is the two subspaces with no cross-links. f,t to the target audio signal s f,t If there is no microphone signal x f,t is a noise signal d f,t In this case, only the microphone signal x f,t The signal subspace in which lies and the target speech signal sf,t The target subspace in which the microphone signal x exists is a subspace with no cross-links, and the linear correlation between the signal subspace and the target subspace is low or zero. f,t to the target audio signal s f,t If there is a microphone signal x f,t The target speech signal s f,t and the noise signal d f,t In this case, the microphone signal x f,t The signal subspace in which lies and the target speech signal s f,t The target subspace in which the microphone signal x exists is a subspace with two cross-links, and the linear correlation between the signal subspace and the target subspace is high. Therefore, the calculation device 240 calculates the microphone signal x f,t The signal subspace in which lies and the target speech signal s f,t The microphone signal x is linearly correlated with the target subspace in which it is located. f,t to the target audio signal s f,t For ease of explanation, we define the signal subspace as span(U s ), and the target subspace is defined as span(U t ) is defined as

[0071] As shown in FIG. 3, the method P100 includes: S140: The microphone signal x f,t Based on the microphone signal x f,t The signal subspace span(U s )

[0072] In some embodiments, the signal subspace span(U s ) is determined by the signal subspace span(U s )'s fundamental matrix U s In some embodiments, the computing device 240 determines the microphone signal x f,tBased on the sampling covariance matrix of s )'s fundamental matrix U s For ease of explanation, we define the sampling covariance matrix as M x FIG. 4 shows the signal subspace span(U s )'s fundamental matrix U s The steps shown in FIG. 4 are a flowchart of the determination of the microphone signal x f,t The sampling covariance matrix M x Based on this, the signal subspace span(U s )'s fundamental matrix U s As shown in FIG. 4, step S140 may include:

[0073] S142: Microphone signal x f,t Based on the microphone signal x f,t The sampling covariance matrix M x Confirm.

[0074] Sampling covariance matrix M x may be expressed as follows:

number

[0075] S144: Sampling covariance matrix M x Perform eigenvalue decomposition on the sampling covariance matrix M x A number of eigenvectors of are determined.

[0076] Furthermore, the sampling covariance matrix M x Perform eigenvalue decomposition on the sampling covariance matrix M x We obtain multiple features of the sampling covariance matrix M x is a matrix of dimension M × M. The sampling covariance matrix M x The number of features is M, and the M features may be expressed by the following formula:

number

[0077] The M features correspond to the M eigenvectors. For ease of explanation, we denote the M eigenvectors as u1, u2, . . . , u q ,u q+1 ,···,u M Here, the M feature quantities correspond one-to-one to the M eigenvectors.

[0078] S146: A matrix consisting of at least a part of the eigenvectors of the plurality of eigenvectors is calculated based on the signal subspace span(U s )'s fundamental matrix U s Let us assume that.

[0079] In some embodiments, the computation device 240 computes a matrix of M eigenvectors over the signal subspace span(U s )'s fundamental matrix U s In some embodiments, the computing device 240 may calculate a matrix of a portion of the M eigenvectors over the signal subspace span(U s )'s fundamental matrix U s It is also possible to use λ q = λ q+1 ==λ M Therefore, the calculation device 240 calculates q different features λ1, λ2, . . . , λ q The q eigenvectors u1, u2, . . . , u q The matrix consisting of the signal subspace span(U s )'s fundamental matrix U s The signal subspace span(U s )'s fundamental matrix U s is an M×q full column rank matrix.

[0080] In some embodiments, the computing device 240 may convert the microphone signal x f,t Based on the signal steering vector [P,Q] ofs )'s fundamental matrix U s FIG. 5 shows a signal subspace span(U s )'s fundamental matrix U s 5 shows another flow chart of the determination of the microphone signal x. f,t Based on the signal steering vector [P,Q] of s )'s fundamental matrix U s As shown in FIG. 5, step S140 may include:

[0081] S148: Microphone signal x f,t Based on the microphone signal x f,t By determining the azimuth angle of the signal source at f,t Determine the signal steering vector [P,Q] of

[0082] As mentioned above, the target steering vector P may be pre-stored in the computing device 240, and the noise steering vector Q is unknown. The computing device 240 may determine the signal steering vector [P,Q] by estimating the noise steering vector Q based on a spatial estimation method. The spatial estimation method may include at least one of a DOA estimation method (abbreviated as DOA, also called direction of arrival estimation) and a spatial spectrum estimation method. The DOA estimation method may include, but is not limited to, line spectrum estimation (e.g., periodogram method, etc.), maximum likelihood spectrum estimation method, maximum entropy method, MUSIC algorithm (also called Multiple Signal Classification algorithm), ESPRIT algorithm (Estimating signal parameters via rotational invariance techniques, also called rotation invariance technique), etc.

[0083] S149: The signal steering vector [P,Q] spans the signal subspace span(U s )'s fundamental matrix U s It is determined that.

[0084] In this case, the signal subspace span(U s )'s fundamental matrix U s is a full-rank column matrix of dimension M×(L+N).

[0085] As shown in FIG. 3, the method P100 includes: S160: Target subspace span(U t )

[0086] In some embodiments, the target subspace span(U t ) is determined by the target subspace span(U t )'s fundamental matrix U t As mentioned above, the target steering vector P may be pre-stored in the computing device. Step S160 is to determine, by the computing device 240, that the pre-defined target steering vector P corresponding to the target audio signal is determined to be within the target subspace span(U t )'s fundamental matrix U t where the target subspace span(U t )'s fundamental matrix U t is a full-rank column matrix of dimensions M×L.

[0087] As shown in FIG. 3, the method P100 includes: S180: Signal subspace span(U s ) and the target subspace span(U t ) based on the linear correlation with the microphone signal x f,t The method may further comprise determining and outputting a voice presence probability λ that the target voice signal is present.

[0088] In some embodiments, the computing device 240 may calculate the signal subspace span(U s ) and the target subspace span(U t ) to calculate the volume correlation function of the signal subspace span(U s ) and the target subspace span(U t ) can be calculated. Figure 6 shows a flowchart of the calculation of the voice presence probability λ according to an embodiment of the present specification. Shown in Figure 6 is S180.

[0089] As shown in FIG. 6, step S180 S182: Signal subspace span(U s ) and the target subspace span(U t )

[0090] Signal subspace span(U s ) and the target subspace span(U t ) is the volume correlation function of the signal subspace span(U s )'s fundamental matrix U s and the target subspace span(U t )'s fundamental matrix U t The volume correlation function vcc(U s ,U t ) may also be used.

[0091] Signal subspace span(U s )'s fundamental matrix U s But the microphone signal x f,t The sampling covariance matrix M x If the M×q dimensional column full rank matrix is ​​determined based on s ,U t ) may be expressed as follows:

number

[0092] Here, vol q (U s) is the M×q dimensional fundamental matrix U s represents the q-dimensional volume function of . L (U t ) is the M×L dimensional fundamental matrix U t represents the L-dimensional volume function of . q (U s ) may be expressed as follows:

number

[0093] Here, γ s,i is U s are the singular values ​​of , i = 1, , min {M, q}. γ s,1 ≧γ s,2 ≧ ≧ γ s,min{M,q} ≧0. vol q (U s ) is U s It may be regarded as the volume of the polyhedron spanned by the vectors of each column of

[0094] vol L (U t ) may be expressed as follows:

number

[0095] Here, γ t,j is U t are the singular values ​​of , j = 1, , min{M,L}. γ t,1 ≧γ t,2 ≧ ≧ γ t,min{M,L} ≧0. vol L (U t ) is U t It may be regarded as the volume of the polyhedron spanned by the vectors of each column of

[0096] vol q+L ([U s ,U t ]) may be represented by the following formula:

number

[0097] Here, 0≦θ1≦θ2≦ ≦ θ min{q,L} ≦π / 2. p is U t The target subspace span(U t ) and U s The signal subspace span(U s ) represents the canonical angle.

[0098] As can be seen from equations (9) and (12), the volume correlation function vcc(U s ,U t ) is actually a set of two subspaces (target subspace span(U t ) and the signal subspace span(U s ) is the product of the sines of the canonical angles formed by the planes 1 and 2. FIG. 7 shows a schematic diagram of the canonical angles formed by the embodiment of the present specification. As shown in FIG. 7, in a three-dimensional space, two intersecting planes (plane 1 and plane 2) have a common basis vector 3. Therefore, the first canonical angle θ1 is 0. The second canonical angle θ2 is equal to the included angle between the respective other basis vectors (basis vector 4 and basis vector 5). Therefore, the volume correlation function between plane 1 and plane 2 is 0.

[0099] Signal subspace span(U s )'s fundamental matrix U s If is the signal steering vector [P,Q], then the volume correlation function vcc(U s ,U t The calculation of ) is similar to the method described above and will not be further described here.

[0100] Based on the above analysis, the volume correlation function vcc(U s ,U t ) has the following property: s and the fundamental matrix U t The two subspaces spanned by the signal subspaces span(U s ) and the target subspace span(U t )) have linear correlation, i.e., the signal subspace span(Us ) and the target subspace span(U t ) have other common basis vectors other than the zero vector, then θ1,θ2,...,θ min{q,L} There exists at least one canonical angle whose sine value is 0, and in this case the volume correlation function vcc(U s ,U t ) is 0. The two subspaces are linearly independent, that is, the signal subspace span(U s ) and the target subspace span(U t ) is the only common basis vector with θ1,θ2,...,θ min{q,L} The sine values ​​of all the canonical angles in are greater than 0, and in this case the volume correlation function vcc(U s ,U t ) is greater than 0. In some embodiments, if two subspaces are orthogonal, then θ1, θ2, . . . , θ min{q,L} The sine values ​​of all the canonical angles in are the maximum value of 1, and in this case the volume correlation function vcc(U s ,U t ) reached a maximum value of 1.

[0101] Based on the above analysis, the volume correlation function vcc(U s ,U t ) are the two fundamental matrices U s and U t The signal subspace span(U s ) and the target subspace span(U t ) which provides a measure of the linear correlation between the target subspace span(U t ) and the signal subspace span(U s ) to obtain the microphone signal x f,t We consider the voice activity detection problem for the signal subspace span(U s ) and the target subspace span(U t ) two fundamental matrices U s and U t The volume correlation function vcc(U s ,U t ) problem.

[0102] S184: Volume correlation function vcc(U s ,U t ), the signal subspace span(U s ) and the target subspace span(U t ) and determine the linear correlation coefficient r.

[0103] Volume correlation function vcc(U s ,U t As can be seen from the definition and properties of the volume correlation function vcc(U s ,U t ) value is closer to 1, the signal subspace span(U s ) and the target subspace span(U t ) and approaches orthogonality, and the signal subspace span(U s ) and the target subspace span(U t ) is low, and in this case, the linear correlation coefficient with the microphone signal x f,t Therefore, it is highly likely that the signal at is from noise signals, and these components should be suppressed as much as possible. Conversely, the volume correlation function vcc(U s ,U t ) approaches 0, the signal subspace span(U s ) and the target subspace span(U t ) and the signal subspace span(U s ) and the target subspace span(U t ) is linearly correlated with the microphone signal x f,t Therefore, it is possible to retain these components. s ,U t ) is negatively correlated.

[0104] Specifically, step S184 is Volume correlation function vcc(U s ,U t) is determined to be greater than the first threshold a, and the linear correlation coefficient r = 0. In this case, the volume correlation function vcc(U s ,U t ) is determined to be smaller than the second threshold b, and the linear correlation coefficient r = 1. In this case, the volume correlation function vcc(U s ,U t ) is determined to be between the first threshold a and the second threshold b, and the linear correlation coefficient r is between 0 and 1, and the linear correlation coefficient r is determined to be the volume correlation function vcc(U s ,U t ), where the second threshold b is less than the first threshold a.

[0105] Specifically, the linear correlation coefficient r may be expressed by the following formula:

number

[0106] Here, f(vcc(U s ,U t )) is vcc(U s ,U t ) may be a function that has a negative linear correlation with f(vcc(U s ,U t ) may be expressed as follows:

number

[0107] S186: The linear correlation coefficient r is output as the voice presence probability λ.

[0108] As described above, in the voice activity detection system and method P100 according to the present specification, the computing device 240 calculates the fundamental matrix U s and U t The volume correlation function vcc(U s ,U t ) to calculate the signal subspace span(U s ) and the target subspace span(Ut ) can be calculated using the volume correlation function vcc(U s ,U t ), the higher the signal subspace span(U s ) and the target subspace span(U t ) is linearly correlated with the signal subspace span(U s ) and the target subspace span(U t ), and in this case, the microphone signal x f,t and the target speech signal becomes less consistent. In this case, the microphone signal x f,t The probability of the presence of a target voice signal in the target region λ decreases. s ,U t ) is lower, the signal subspace span(U s ) and the target subspace span(U t ) is linearly correlated with the signal subspace span(U s ) and the target subspace span(U t ), and in this case, the microphone signal x f,t and the target speech signal. In this case, the microphone signal x f,t The voice presence probability λ that the target voice signal exists in the input signal is increased. The voice activity detection system and method P100 according to the present specification can improve the accuracy of voice activity detection and the effect of voice enhancement.

[0109] The present specification further provides a voice enhancement system. The voice enhancement system can also be used in the electronic device 200. In some embodiments, the voice enhancement system can include a computing device 240. In some embodiments, the voice enhancement system can be used in the computing device 240. That is, the voice enhancement system can run on the computing device 240. The voice enhancement system can include a hardware device having a data information processing function and a program required to drive the operation of the hardware device. Of course, the voice enhancement system can also be only a hardware device having a data processing function, or only a program running on the hardware device.

[0110] The voice enhancement system may store data or instructions and may execute the data and / or instructions to perform the voice enhancement methods described herein. When the voice enhancement system runs on the computing device 240, the voice enhancement system may obtain the microphone signals from the microphone array 220 based on the communication connection and execute data or instructions of the voice enhancement methods described herein. The voice enhancement methods are introduced elsewhere herein. For example, the voice enhancement methods are introduced in the description of FIG. 8.

[0111] When the voice enhancement system runs on computing device 240, the voice enhancement system is in communication with microphone array 220. Storage medium 243 may further include at least one set of instructions stored in the data storage device for performing voice enhancement calculations on the microphone signals. The instructions may be computer program code, which may include programs, routines, objects, components, data structures, processes, modules, etc., for performing a voice enhancement method according to the present disclosure. Processor 242 may read the at least one set of instructions and perform a voice enhancement method according to the present disclosure according to instructions of the at least one set of instructions. Processor 242 may perform all steps included in the voice enhancement method.

[0112] 8 shows a flowchart of a speech enhancement method P200 according to an embodiment of the present disclosure. The method P200 can perform speech enhancement on the microphone signal. Specifically, the processor 242 can execute the method P200.

[0113] As shown in FIG. 8, the method P200 may include: S220: The microphone signals x output by the M microphones f,t Get the.

[0114] This is as described in step S120, and the description will be omitted here.

[0115] S240: Based on the voice activity detection method P100, the microphone signal x f,t 2. Determine the speech presence probability λ that the target speech signal is present in

[0116] S260: Based on the voice presence probability λ, the microphone signal x f,t The filtering coefficient vector ω f,t Confirm.

[0117] Filtering coefficient vector ω f,t may be an M×1 dimensional vector. f,t may be expressed as follows:

number

[0118] Here, the filtering coefficient corresponding to the Mth microphone 222 is ω m,f,t m = 1, 2, , M.

[0119] In some embodiments, the computing device 240 calculates the filtering coefficient vector ω based on the MVDR method. f,tSpecifically, step S260 determines the microphone signal x based on the voice presence probability λ. f,t The noise covariance matrix M f,t n and determining the MVDR method and the noise covariance matrix M f,t n Based on the filtering coefficient vector ω f,t and determining a noise covariance matrix M f,t n may be expressed as follows:

number

[0120] Filtering coefficient vector ω f,t may be expressed as follows:

number

[0121] In some embodiments, the computing device 240 may generate a filtering coefficient vector ω based on a fixed beam method. f,t Specifically, step S260 determines the voice presence probability λ based on the microphone signal x f,t Target microphone signal x k,f,t The filtering coefficient ω k,f,t and the microphone signal x f,t Target microphone signal x k,f,t and determining that filtering coefficients corresponding to other microphone signals other than k are 0, where k=1, 2, . . . , M. f,t is the target microphone signal x k,f,t The filtering coefficient ω k,f,t and a vector of filtering coefficients corresponding to the other microphone signals. f,tmay be expressed as follows:

number

[0122] In some embodiments, the target microphone signal x k,f,t is the microphone signal x f,t In some embodiments, the target microphone signal x k,f,t may be the one-way microphone signal closest to the target audio signal source (eg, mouth). In some embodiments, k may be pre-stored in the computing device 240.

[0123] S280: The filtering coefficient vector ω f,t Based on the microphone signal x f,t and integrate it to get the target audio signal y f,t and output it.

[0124] Target audio signal y f,t may be expressed as follows:

number

[0125] As described above, the voice activity detection system and method P100 and the voice enhancement system and method P200 according to the present specification are used with a microphone array 220 consisting of a plurality of microphones 222. The voice activity detection system and method P100 and the voice enhancement system and method P200 use the microphone signal x collected by the microphone array 220. f,t The microphone signal x can be obtained. f,t may contain a noise signal or a target speech signal. The target speech signal and the noise signal are two types of signals with no cross-links. The target subspace span(U t) and the noise subspace where the noise signal is located are two subspaces with no cross-links. f,t When there is no target speech signal in the microphone signal x f,t contains only the noise signal. In this case, the microphone signal x f,t The signal subspace span(U s ) and the target subspace span(U t ) are two subspaces with no cross-links, and the signal subspace span(U s ) and the target subspace span(U t ) has low linear correlation with the microphone signal x f,t When the target speech signal is present at f,t contains both the target speech signal and the noise signal. In this case, the microphone signal x f,t The signal subspace span(U s ) and the target subspace span(U t ) are two subspaces with cross-links, and the signal subspace span(U s ) and the target subspace span(U t ) has a high linear correlation with the microphone signal x f,t The signal subspace span(U s ) and the target subspace span(U t ) to obtain the microphone signal x f,t The speech enhancement method and system P200 may determine a speech presence probability λ, where λ is the presence of a target speech signal, based on the filtering coefficient vector ω f,t By calculating f,t As described above, the voice activity detection system and method P100 and the voice enhancement system and method P200 according to the present specification can improve the calculation accuracy of the voice presence probability λ and improve the effect of the voice enhancement.

[0126] Another aspect of the present specification provides a non-transitory storage medium, storing at least one set of executable instructions for voice activity detection, which when executed by a processor, directs the processor to perform steps of the voice activity detection method P100 described herein. In some possible embodiments, each aspect of the present specification may be further realized in the form of a program product including a program code. When the program product runs on a computing device (e.g., computing device 240), the program code is for causing the computing device to perform the voice activity detection steps described herein. The program product for implementing the above method may use a portable compact disc read only memory (CD-ROM), including the program code and operable on a computing device. However, the program product of the present specification is not limited thereto, and in the present specification, a readable storage medium may be any tangible medium that includes or stores a program, which may be used by or in combination with an instruction execution system (e.g., processor 242). The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. Further examples of the readable storage medium include an electrical connection having one or more conductors, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical memory device, a magnetic memory device, or any suitable combination thereof. The computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, in which the readable program code is embedded.Such propagated data signals may take various forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may transmit, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained in the readable storage medium may be transmitted in any suitable medium, including, but not limited to, wireless, wired, optical cable, RF, or the like, or any suitable combination of the above. The program code for performing the operations herein may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, or the like, general procedural programming languages ​​such as the "C" language, or similar programming languages. The program code may be executed entirely on the computing device, partially on the computing device, as separate software packets, partially on the computing device and partially on a remote computing device, or entirely on a remote computing device.

[0127] The above describes certain embodiments of the present specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the examples and still achieve desirable results. Also, the processes depicted in the figures do not necessarily require a particular order or sequential order to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or advantageous.

[0128] As described above, upon reading this detailed disclosure, those skilled in the art will understand that the detailed disclosure above may be presented by way of example only and may not be limiting. Although not expressly stated herein, the present specification should cover various reasonable changes, modifications, and alterations to the embodiments, as would be understood by those skilled in the art. These changes, modifications, and alterations are intended to be presented by this specification and are within the spirit and scope of the exemplary embodiments of the present specification.

[0129] It should be noted that certain terms in this specification are used to describe embodiments of this specification. For example, "one embodiment," "embodiment," and / or "some embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of this specification. Therefore, it should be emphasized and understood that two or more references to "an embodiment" or "one embodiment" or "alternative embodiments" in various parts of this specification do not necessarily refer to the same embodiment. It should be noted that certain features, structures, or characteristics may be suitably combined in one or more embodiments of this specification.

[0130] It should be understood that in the above description of the embodiments of this specification, in order to facilitate the understanding of one feature, this specification combines various features into a single embodiment, drawing, or description thereof for the purpose of simplifying this specification. However, it is not necessary to combine these features, and a person skilled in the art can fully extract some of the features and understand them as a single embodiment when reading this specification. In other words, the embodiments in this specification can be understood as a combination of multiple secondary embodiments. The content of each secondary embodiment can be valid even if it has less than all the features of the single embodiment disclosed above.

[0131] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, articles, etc., cited herein may be incorporated herein by reference. All content for all purposes, now or hereafter, is associated with this document, except for any claim history related thereto, any identical claim history that is inconsistent or inconsistent with this document, or any identical claim history that has a limiting effect on the broadest scope of the claims. For example, in the event of any inconsistency or discrepancy between the explanation, definition, and / or use of a term associated with any of the included materials and the explanation, definition, and / or use of the associated term in this document, the term in this document shall control and apply.

[0132] Finally, it should be understood that the embodiments of the application disclosed herein are explanations of the principles of the embodiments of the present specification. Other modified embodiments are also within the scope of the present specification. Therefore, the embodiments disclosed herein are merely examples and are not limiting. Those skilled in the art can realize the application of the present specification using alternative configurations based on the embodiments of the present specification. Therefore, the embodiments of the present specification are not limited to the embodiments exactly described in the application.

Claims

1. A voice activity detection method for M microphones distributed in a predefined array shape, where M is an integer greater than 1, comprising: A processor acquiring microphone signals output by the M microphones; determining, by the processor, based on the microphone signals, a signal subspace constituted by the microphone signals; the processor determining a target subspace comprised of a target audio signal; and outputting a sound presence probability based on a linear correlation between the signal subspace and the target subspace, the sound presence probability being determined based on a linear correlation between the signal subspace and the target subspace.

13. A method for voice activity detection comprising:

2. Determining a signal subspace constituted by the microphone signals based on the microphone signals includes: determining, by the processor, a sampling covariance matrix for the microphone signals based on the microphone signals; performing an eigenvalue decomposition on the sampled covariance matrix by the processor to determine a number of eigenvectors of the sampled covariance matrix; 2. The method of claim 1, further comprising the processor determining a fundamental matrix of the signal subspace as a matrix of at least a portion of the plurality of eigenvectors.

3. Determining a signal subspace constituted by the microphone signals based on the microphone signals includes: determining a signal steering vector of the microphone signal by determining an azimuth angle of a signal source in the microphone signal by a spatial estimation method, the spatial estimation method including at least one of a DOA estimation method and a spatial spectrum estimation method, based on the microphone signal; and determining by the processor that the signal steering vector is a fundamental matrix of the signal subspace.

4. Determining a target subspace constituted by the target audio signal includes:

2. The method of claim 1, further comprising the processor determining that a predetermined target steering vector corresponding to the target speech signal is a fundamental matrix of the target subspace.

5. determining and outputting a speech presence probability that the target speech signal is present in the microphone signal based on a linear correlation between the signal subspace and the target subspace; the processor determining a volume correlation function between the signal subspace and the target subspace; the processor determining a linear correlation coefficient between the signal subspace and the target subspace based on the volume correlation function, where the linear correlation coefficient is negatively correlated with the volume correlation function; and wherein the processor outputs the linear correlation coefficient as the voice presence probability.

6. Determining a linear correlation coefficient between the signal subspace and the target subspace based on the volume correlation function includes: the processor determines that the volume correlation function is greater than a first threshold and the processor determines that the linear correlation coefficient is zero; the processor determines that the volume correlation function is less than a second threshold and the processor determines that the linear correlation coefficient is one, where the second threshold is less than the first threshold; 6. The method of claim 5, further comprising one of the cases where the processor determines that the volume correlation function is between the first threshold and the second threshold, the linear correlation coefficient is between 0 and 1, and the linear correlation coefficient is a function that is negatively correlated with the volume correlation function.

7. 1. A voice activity detection system comprising: at least one storage medium having stored thereon at least one instruction set for voice activity detection; at least one processor in communication with the at least one storage medium; 7. The voice activity detection system according to claim 1, wherein, when the voice activity detection system is in operation, the at least one processor reads the at least one instruction set and implements the voice activity detection method according to any one of claims 1 to 6.

8. A method for speech enhancement, which is used with M microphones distributed in a predefined array shape, where M is an integer greater than 1, The processor acquiring microphone signals output by the M microphones; determining a voice presence probability that the target voice signal is present in the microphone signal, said processor being based on a voice activity detection method according to any one of claims 1 to 6; determining, by the processor, a filtering coefficient vector corresponding to the microphone signal based on the voice presence probability; and synthesizing the microphone signals based on the filtering coefficient vector to obtain and output a target audio signal.

9. Determining a filtering coefficient vector corresponding to the microphone signal based on the voice presence probability includes: determining a noise covariance matrix for the microphone signal based on the voice presence probability; 10. The method of claim 8, further comprising the processor determining the filtering coefficient vector based on an MVDR method and the noise covariance matrix.

10. determining a filtering coefficient vector corresponding to the microphone signal based on the voice presence probability, comprising: the processor determining the voice presence probability as a filtering coefficient corresponding to a target microphone signal among the microphone signals, the target microphone signal comprising a one-way microphone signal among the microphone signals having a highest signal-to-noise ratio; determining by the processor that filtering coefficients corresponding to microphone signals other than the target microphone signal among the microphone signals are zero; 9. The method of claim 8, wherein the filtering coefficient vector comprises a vector of filtering coefficients corresponding to the target microphone signal and filtering coefficients corresponding to the other microphone signals.

11. 1. A speech enhancement system, comprising: at least one storage medium having stored thereon at least one instruction set for performing speech enhancement; at least one processor in communication with the at least one storage medium; When the voice enhancement system is in operation, the at least one processor reads the at least one instruction set and performs the voice enhancement method according to any one of claims 8 to 10.

Images