Audio filter system for vehicle

Abstract

A computer-implemented method performed by data processing hardware, the method causing the data processing hardware to perform an operation of designing an audio filter. The operations include receiving a plurality of audio signals from a sensor array, the plurality of audio signals including a target audio signal and an interfering audio signal, and utilizing the interfering audio signal. The plurality of audio signals are processed using a short-time Fourier transform (STFT) for each of the plurality of audio signals. These operations also include designing an audio filter using the determined a priori SNR, and enhancing the target audio signal using the utilized interfering audio signal and the designed audio filter, and attenuating the interfering audio signal.

Description

Technical Field

[0001] The present invention generally relates to an audio filter system for a vehicle. Background Art

[0002] The information provided in this section is for the purpose of generally presenting the background of the present disclosure. To the extent described in this section, the work of the presently named inventors, as well as aspects of the description that may not qualify as prior art at the time of filing, are neither explicitly nor implicitly admitted to be prior art with respect to the present disclosure.

[0003] Both telecommunication and virtual assistance applications require interference cancellation and source separation tasks to enhance the desired speaker and eliminate interference, such as undesired speakers. Typically, when a microphone array is installed in a vehicle, interference cancellation is obtained by applying a spatial filter, such as a beamformer. Beamformers typically produce high white noise gain, which degrades noise reduction performance. As a result, residual interference signals may still be present in the beamformer output, resulting in application layer performance degradation. Summary of the invention

[0004] In some aspects, a computer-implemented method is performed by data processing hardware, which causes the data processing hardware to perform operations to design an audio filter. These operations include receiving multiple audio signals including a target audio signal and an interfering audio signal from a sensor array. Multiple audio signals are processed using a short-time Fourier transform (STFT), and an output vector is generated for each of the multiple audio signals via a beamformer. These operations also include estimating a noise variance for each of the multiple audio signals, and using the output vector generated from the beamformer to extract the speech energy of the corresponding speaker corresponding to each of the multiple audio signals. A priori signal-to-noise ratio (a priori SNR) is determined using the generated output vector, the estimated noise variance, and the speech energy of each of the multiple audio signals, and a gain value is determined based on the a priori SNR.

[0005] In some examples, the designed audio filter can be used to enhance the target audio signal, and the interfering audio signal can be attenuated. Optionally, the STFT can be used to process multiple audio signals, including determining a time frame index and a frequency bin index. In some configurations, generating an output vector for each of the multiple audio signals via a beamformer can include providing a certain number of speakers, and generating dimensions for the output vector based on the number of speakers provided. The a priori SNR can be determined by calculating a separate a priori SNR for each of the multiple audio signals and estimating the a priori SNR as a joint a priori SNR of each separate a priori SNR. In some examples, estimating the noise variance for each of the multiple audio signals can include expressing each noise variance as a corresponding linear equation for each output vector generated from the beamformer, and extracting the speech energy of the corresponding speaker can include determining the speech energy using the corresponding linear equation for each output vector generated from the beamformer.

[0006] In some aspects, an audio filter system for a vehicle includes data processing hardware and memory hardware. The memory hardware communicates with the data processing hardware and stores instructions that, when executed on the data processing hardware, cause the data processing hardware to perform operations to design an audio filter. These operations include receiving a plurality of audio signals from a sensor array, the plurality of audio signals including a target audio signal and an interfering audio signal. The interfering audio signal is utilized, and a priori signal-to-noise ratio (a priori SNR) is determined for each of the plurality of audio signals. The determined a priori SNR is used to design an audio filter, and the target audio signal is enhanced using the utilized interfering audio signal and the designed audio filter, and the interfering signal is attenuated using the designed audio filter.

[0007] In some examples, the operation may include processing multiple audio signals using a short-time Fourier transform (STFT), and generating an output vector for each of the multiple audio signals via a beamformer. The operation of processing multiple audio signals using the STFT may include determining a time frame index and a frequency bin index. Optionally, the operation of generating an output vector for each of the multiple audio signals via a beamformer may include providing a certain number of speakers, and generating dimensions for the output vector based on the number of speakers provided. In some examples, determining the priori SNR may include calculating a separate priori SNR for each of the multiple audio signals, and estimating the priori SNR as a joint priori SNR of each separate priori SNR. In other examples, the operations may also include estimating a noise vector for each of the multiple audio signals, and using the estimated noise vector to extract the speech energy of the corresponding speaker corresponding to each of the multiple audio signals. The operation of estimating the noise vector may include estimating each noise vector by a corresponding linear equation, and the operation of extracting the speech energy of the corresponding speaker may include determining the speech energy using the corresponding linear equation of each noise vector.

[0008] In other aspects, a computer-implemented method performed by data processing hardware is provided, the method causing the data processing hardware to perform operations to design an audio filter. The operations include receiving a plurality of audio signals from a sensor array, the plurality of audio signals including a target audio signal and an interfering audio signal, and utilizing the interfering audio signal. The plurality of audio signals are processed using a short-time Fourier transform (STFT) for each of the plurality of audio signals. The operations also include designing an audio filter using the determined prior SNR, and using the utilized interfering audio signal and the designed audio filter to enhance the target audio signal and attenuate the interfering audio signal.

[0009] In some examples, the operation may include processing multiple audio signals using a short-time Fourier transform (STFT), and generating an output vector for each of the multiple audio signals via a beamformer. The operation of processing multiple audio signals using the STFT may include determining a time frame index and a frequency bin index. Optionally, the operation of generating an output vector for each of the multiple audio signals via a beamformer may include identifying a certain number of speakers, and generating dimensions for the output vector based on the number of speakers identified. In some examples, determining the prior SNR may include calculating a separate prior SNR for each of the multiple audio signals, and estimating the prior SNR as a joint prior SNR of each separate prior SNR. In other examples, the operation may also include estimating a noise vector for each of the multiple audio signals, and extracting the speech energy of the corresponding speaker corresponding to each of the multiple audio signals using the corresponding linear equation of each output vector generated. The operation of estimating the noise variance may include estimating each noise variance by a corresponding linear equation, and the operation of extracting the speech energy of the corresponding speaker may include determining the speech energy for each output vector generated from the beamformer using the corresponding linear equation. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings described herein are for illustrative purposes only of selected configurations and are not intended to limit the scope of the present disclosure.

[0011] Figure 1 is a schematic diagram of a vehicle having an audio filter system according to the present disclosure;

[0012] Figure 2 is a partial perspective view of an interior cabin of a vehicle having a sensor array according to the present disclosure;

[0013] Figure 3 is an example graph of the RMSE (root mean square error) of the a priori signal-to-noise ratio (a priori SNR) of a desired source as a function of the SNR measured at the input of an audio filter system in accordance with the present disclosure;

[0014] Figure 4 is a functional block diagram of a vehicle controller including an audio filter system according to the present disclosure;

[0015] Figure 5A is an example schematic diagram of multiple zones of an audio filter system according to the present disclosure;

[0016] Figure 5B A method of filtering a plurality of audio signals from each of a plurality of zones according to the present disclosure Figure 5A An example schematic diagram of an audio filter system; and

[0017] Figure 6 is an example flow chart of an audio filter system according to the present disclosure.

[0018] Corresponding reference characters indicate corresponding parts throughout the several views. DETAILED DESCRIPTION

[0019] Example configurations will now be described more fully with reference to the accompanying drawings. Example configurations are provided so that the present disclosure will be thorough and will fully convey the scope of the present disclosure to those of ordinary skill in the art. Specific details, such as examples of specific components, devices, and methods, are set forth to provide a thorough understanding of the configurations of the present disclosure. It will be apparent to those of ordinary skill in the art that specific details need not be employed, that example configurations may be implemented in many different forms, and that the specific details and exemplary configurations should not be construed as limiting the scope of the present disclosure.

[0020] The terms used herein are only for describing specific exemplary configurations, not for limiting. As used herein, the singular articles "a", "an" and "the" may also be intended to include plural forms, unless the context clearly indicates otherwise. The terms "comprise", "include", "contain" and "have" are inclusive, thus specifying the presence of features, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, steps, operations, elements, parts and / or groups thereof. The method steps, processes and operations described herein should not be interpreted as necessarily requiring them to be performed in the specific order discussed or shown, unless specifically identified as an execution order. Additional or alternative steps may be adopted.

[0021] When an element or layer is referred to as being "on another element or layer," "engaged to," "connected to," "attached to," or "coupled to" another element or layer, it may be directly on, engaged, connected, attached to, or coupled to another element or layer, or there may be intermediate elements or layers. Conversely, when an element is referred to as being "directly on another element or layer," "directly engaged to," "directly connected to," "directly attached to," or "directly coupled to" another element or layer, there may be no intermediate elements or layers. Other words used to describe the relationship between elements should be interpreted in a similar manner (e.g., "between" versus "directly between," "adjacent" versus "directly adjacent," etc.). As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0022] The terms first, second, third, etc. can be used here to describe various elements, components, regions, layers and / or parts. These elements, components, regions, layers and / or parts should not be limited by these terms. These terms are only used to distinguish each element, component, region, layer or part. Terms such as "first", "second" and other numerical terms do not imply order or sequence unless the context clearly indicates. Therefore, the first element, component, region, layer or part discussed below can be referred to as the second element, component, region, layer or part, without departing from the teaching of the example configuration.

[0023] In this application, including the definitions below, the term module may be replaced by the term circuit. The term "module" may refer to or be part of an application specific integrated circuit (ASIC), or include an application specific integrated circuit (ASIC); a digital, analog, or mixed analog / digital discrete circuit; a digital, analog, or mixed analog / digital integrated circuit; a combinational logic circuit; a field programmable gate array (FPGA); a processor (shared, dedicated, or group) that executes code; a memory (shared, dedicated, or group) that stores code executed by the processor; other suitable hardware components that provide the functionality; or a combination of some or all of the above, such as in a system on a chip.

[0024] The term code used above may include software, firmware and / or microcode, and may refer to a program, a routine, a function, a class and / or an object. The term shared processor includes a single processor that executes some or all of the code from multiple modules. The term group processor includes a processor that executes some or all of the code from one or more modules in combination with an additional processor. The term shared memory includes a single memory that stores some or all of the code from multiple modules. The term group memory includes a memory that stores some or all of the code from one or more modules in combination with an additional memory. The term memory may be a subset of the term computer-readable medium. The term computer-readable medium does not include transient electrical signals and electromagnetic signals propagated through the medium and can therefore be considered to be tangible non-transitory memory. Non-limiting examples of non-transitory memory include tangible computer-readable media, including non-volatile memory, magnetic memory, and optical memory.

[0025] The apparatus and methods described in this application may be implemented in part or in whole by one or more computer programs executed by one or more processors. The computer program includes processor executable instructions stored on at least one non-transitory tangible computer readable medium. The computer program may also include and / or rely on stored data.

[0026] Software applications (i.e., software resources) may refer to computer software that enables a computing device to perform tasks. In some examples, software applications may be referred to as "applications," "apps," or "programs." Example applications include, but are not limited to, system diagnostic applications, system management applications, system maintenance applications, word processing applications, spreadsheet applications, messaging applications, media streaming applications, social networking applications, and gaming applications.

[0027] Non-transitory memory can be a physical device used to temporarily or permanently store programs (e.g., instruction sequences) or data (e.g., program state information) for use by a computing device. Non-transitory memory can be volatile and / or non-volatile addressable semiconductor memory. Examples of non-volatile memory include, but are not limited to, flash memory and read-only memory (ROM) / programmable read-only memory (PROM) / erasable programmable read-only memory (EPROM) / electrically erasable programmable read-only memory (EEPROM) (e.g., commonly used for firmware, such as bootloaders). Examples of volatile memory include, but are not limited to, random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), phase change memory (PCM), and disk or tape.

[0028] These computer programs (also referred to as programs, software, software applications, or code) include machine instructions for a programmable processor and may be implemented in high-level procedural and / or object-oriented programming languages ​​and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, non-transitory computer-readable medium, apparatus, and / or device (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0029] Various implementations of the systems and techniques described herein can be realized in digital electronic and / or optical circuits, integrated circuits, specially designed ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs executable and / or interpretable on a programmable system comprising at least one programmable processor, which may be special purpose or general purpose, coupled to receive data and instructions from a storage system, and to send data and instructions to the storage system.

[0030] The processes and logic flows described in this specification can be performed by one or more programmable processors, also known as data processing hardware, executing one or more computer programs to perform functions by operating on input data and generating outputs. These processes and logic flows can also be performed by dedicated logic circuits, such as FPGAs (field programmable gate arrays) or ASICs (application-specific integrated circuits). For example, processors suitable for executing computer programs include general-purpose and special-purpose microprocessors, and any one or more processors of any kind of digital computer. Typically, the processor will receive instructions and data from a read-only memory or a random access memory or both. The basic elements of a computer are a processor for executing instructions and one or more storage devices for storing instructions and data. Typically, a computer will also include or be operably connected to one or more large-capacity storage devices for storing data, such as magnetic disks, magneto-optical disks, or optical disks, to receive data from the large-capacity storage device or to transmit data to it, or both. However, a computer does not need to have such a device. Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and storage devices, including, for example, semiconductor memory devices, such as EPROM, EEPROM and flash memory devices; magnetic disks, such as internal hard disks or removable disks; magneto-optical disks; and CD ROM and DVD-ROM disks. The processor and memory may be supplemented by or incorporated in special purpose logic circuitry.

[0031] To provide interaction with a user, one or more aspects of the present disclosure may be implemented on a computer having a display device for displaying information to the user, such as a CRT (cathode ray tube), LCD (liquid crystal display) monitor, or touch screen, and an optional keyboard and pointing device, such as a mouse or trackball, through which the user can provide input to the computer. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback, such as visual feedback, auditory feedback, or tactile feedback; and input from the user may be received in any form, including sound, voice, or tactile input. In addition, the computer may interact with the user by sending documents to and receiving documents from a device used by the user; for example, by sending a web page to a web browser on a user's client device in response to a request received from the web browser.

[0032] refer to Figure 1-6, the audio filter system 10 can be incorporated into a vehicle 100. In some examples, the audio filter system 10 can be incorporated into any feasible location within the vehicle 100 where audio filtering may be beneficial. For example, the audio filter system 10 can be incorporated into both vehicle and non-vehicle audio capture settings. For purposes of exemplary functional explanation, the audio filter system 10 is described herein with respect to the vehicle 100. However, the audio filter system 10 can be used in non-vehicle examples. The audio filter system 10 is configured to divide the vehicle 100 into a plurality of spatial audio zones Z1-Z4 ( Figure 5A ), including but not limited to the driver zone Z1, the front passenger zone Z2, the right rear passenger zone Z3 and the left rear passenger zone Z4. As described in more detail below, the audio filter system 10 is configured to utilize the audio signal 12 received from each corresponding spatial audio zone Z1-Z4 to enhance the target audio signal 12a by utilizing the interfering audio signal 12b. As described below, the interfering audio signal 12b can be generated by a speaker 106 in the vehicle 100. By utilizing the audio signal 12 from each corresponding spatial audio zone Z1-Z4, each audio signal 12 is used to design the audio filter 14 of the audio filter system 10 based on the position of one or more speakers in the vehicle 100.

[0033] The audio filter system 10 is configured to estimate a target speaker 106 a based on the audio signal 12. The audio filter system 10 can therefore identify the target audio signal 12 a among the interfering audio signals 12 b. As described herein, the audio filter system 10 is configured to utilize the knowledge of the target audio signal 12 a compared to the interfering audio signals 12 b to specifically design the audio filter 14 to enhance only the target audio signal 12 a by utilizing data from all detected audio signals 12. Thus, the audio filter system 10 can construct or otherwise design the audio filter 14 based on the location of the passenger speaker 106 within the vehicle 100.

[0034] refer to Figure 1-3, the vehicle 100 is equipped with a sensor array 102 configured to capture an audio signal 12 within the vehicle 100. The sensor array 102 may include, but is not limited to, a microphone array that captures the audio signal 12 and transmits the audio signal 12 to the audio filter system 10. The audio filter system 10 includes data processing hardware 16 and memory hardware 18 in communication with the data processing hardware 16. The data processing hardware 16 is configured to receive the audio signal 12. It is generally contemplated that the audio filter system 10 includes a computer-implemented method 20 that is executed by the data processing hardware 16 and causes the data processing hardware 16 to perform the various operations described herein to design the audio filter 14. Additionally or alternatively, the memory hardware 18 may store the computer-implemented method 20 as instructions that, when executed on the data processing hardware 16, cause the data processing hardware 16 to perform the operations described herein.

[0035] The audio filter system 10 can be configured as part of a vehicle computer or controller 104. For example, the sensor array 102 receives the audio signal 12 and transmits the audio signal 12 to the vehicle controller 104. The vehicle controller 104, in response to receiving the audio signal 12, can initiate the audio filter system 10. For example, the vehicle controller 104 can execute the computer-implemented method 20 of the audio filter system 10 to begin designing the audio filter 14. The audio filter 14 is configured to filter the audio signal 12 and identify the speaker. The speaker is typically an occupant 106 in the vehicle 100. It is contemplated that the audio filter system 10 can use the computer-implemented method 20 described herein to distinguish between multiple occupants 106 who are speaking simultaneously.

[0036] The audio filter system 10 utilizes the spatial audio zones Z1-Z4 to enhance the clarity of the target speaker 106a. For example, the audio filter system 10 uses the interfering audio signal 12b to identify the target speaker 106a. Then, the interfering audio signal 12b can be used to design the audio filter 14 and enhance the target audio signal 12a. Finally, the interfering audio signal 12b is attenuated by the designed audio filter 14 to further enhance the clarity of the target audio signal 12a. In some examples, the target speaker 106 can be the driver 106a of the vehicle 100, as described below. The audio signal 12 is captured by the sensor array 102, and the audio filter system 10 determines the target audio signal 12a corresponding to the driver 106a. Therefore, the audio signal 12 associated with the passenger 106b is an interfering audio signal 12b and is eliminated.

[0037] As described above, the audio signal 12 may include one or more target audio signals 12a and one or more interfering audio signals 12b. Ultimately, the audio filter system 10 is configured to attenuate the interfering audio signals 12b and amplify or enhance the target audio signal 12a. The resulting signal is a filtered audio signal 12c containing minimal to no interfering audio signals 12b. The filtered audio signal 12c may be communicated to a third-party processor that is in communication with the vehicle controller 104 and configured to receive the filtered audio signal 12c.

[0038] For example, Figure 2 A first passenger 106a and a second passenger 106b are shown emitting audio signals 12 simultaneously, and a sensor array 102 is disposed within an interior cabin 108 of the vehicle 100. In the illustrated example, the sensor array 102 is configured to receive each audio signal 12a, 12b from the respective passenger 106a, 106b, which are then transmitted to the audio filter system 10. Although the sensor array 102 is illustrated as being located at the front of the interior cabin 108, it is contemplated that the sensor array 102 may be located at any feasible location within the interior cabin 108 to capture the audio signals 12. For example, the sensor array 102 may be located at locations including, but not limited to, the rear, the side, and the center.

[0039] Reference now Figure 3-6 , Figure 3 An example implementation of an audio filter system 10 and improvements to the audio filter system 10 utilizing an increased number of interfering audio signals 12b are shown. For example, the number of interfering audio signals 12b may be increased based on the number of speakers (N) within the vehicle 100. The audio filter system 10 is configured to utilize each audio signal 12 detected by the sensor array 102 to tune the target audio signal 12a, thereby utilizing multiple interfering audio signals 12b to improve the accuracy of the audio filter 14. For example, Figure 3 The example graphs shown in show the performance differences of the audio filter 14 based on a single speaker, two speakers, and four speakers. If there is a single speaker in the vehicle 100, where N=1, the audio filter 14 can be designed based on a single target audio signal 12a. If there are two speakers in the vehicle 100, where N=2, the audio filter system 10 can have a reduced estimation error as a result of the comparison between the two audio signals 12. If there are four speakers in the vehicle, where N=4, the audio filter system 10 can be further improved. Therefore, the increase in the number of speakers can reduce the estimation error that may occur during the design of the audio filter 14.

[0040] However, it is contemplated that at a predetermined number of speakers, the estimation error may begin to deviate in the opposite direction in a similar manner as it does with a single speaker at high signal-to-noise ratio (SNR) levels. For example, the deviation is a function of the SNR level and the predetermined number of speakers. In some examples, the predetermined number of speakers may be five speakers within the vehicle 100, but in other examples, may be any natural predetermined number of speakers. The audio filter system 10 is configured to utilize non-target speakers in order to design an improved audio filter 14 to more effectively filter the interfering audio signal 12b to achieve an enhanced or filtered audio signal 12c. In other words, the interfering audio signal 12b may be used to design the audio filter 14. The audio filter system 10 analyzes each audio signal 12 to estimate the target audio signal 12a and designs the audio filter 14 for estimating the target audio signal 12a.

[0041] The presence of multiple interfering audio signals 12b helps to enhance the target audio signal 12a based on voice quality and overall voice enhancement. When designing the audio filter 14, more interfering audio signals 12b can cause the audio filter system 10 to have improved precision. The improved precision is the result of the increased comparison opportunity of the interfering audio signal 12b. The main task of the audio filter system 10 is to design the audio filter 14 to isolate the target audio signal 12a, and use the beamforming method followed by the audio filter 14 to attenuate all remaining interfering audio signals 12b, as described herein. As described below, once the audio filter 14 is designed, the audio filter 14 receives all audio signals 12 from the vehicle 100 to estimate the filtered audio signal 12c at the output of the audio filter 14.

[0042] Further references Figure 3-6 , the audio filter system 10 begins designing an audio filter 14 upon receiving an audio signal 12 including a target audio signal 12a and an interfering audio signal 12b from a sensor array 102. The audio filter system 10 estimates the target audio signal 12a from the received audio signal 12, and designs the audio filter 14 using each audio signal 12 including the interfering signal 12b, as described herein, to enhance the estimated target audio signal 12a. The audio signal 12 received by the audio filter system 10 is processed using a short-time Fourier transform (STFT) 30. The STFT 30 is used to determine a time frame index (n) and a frequency bin index (k) for each corresponding audio signal output 32, Figure 5B Indicated by (X).

[0043] A corresponding audio signal output 32 may be specified for a particular time frame index (n) and a corresponding particular frequency bin index (k). Each audio signal 12 may have a i) are various iterations 34 represented by (X1-X4). Like the corresponding audio signal output (X), each iteration 34 depends on the time frame index (n) and the frequency bin index (k). As used herein, the subscript (i) can be used as a placeholder for a number associated with a corresponding speaker. For example, in the case of four (4) speakers, there can be four iterations 34, each represented by one of (X1-X4). However, it is contemplated that the number of iterations 34 is not limited to four, as each iteration 34 is based on a corresponding speaker, which can be more than four or less than four.

[0044] Still refer to Figure 3-6 , each iteration 34 of the audio signal output 32 may then be passed through a set of beamformers 36 to generate a beamformed output 38 for each audio signal output 32, represented as (y i ). The beamformed output 38 may then be used in conjunction with an estimated joint a priori signal-to-noise ratio (a priori SNR) 40, as described below, to further define output vectors 42. For example, each output vector 42 may be identified using the following example equations, where an output vector 42 is given by express:

[0045]

[0046] Additionally, the speech energy (Q) of the corresponding speaker may be determined using a corresponding linear equation for each output vector generated from the beamformer 36. Example linear equations that produce the speech energy (Q) include:

[0047] Q=Pσ 2 (n,k)+d

[0048] in, And assume

[0049] The output vector 38 outlined in the example equation above may be expressed using, for example, To solve. Using each generated output vector 38, the estimated noise variance and the extracted speech energy, a priori signal-to-noise ratio (a priori SNR) 40 can be determined. The a priori SNR 40 at each output vector 42 can be represented by the following example equation:

[0050]

[0051] It is generally contemplated that the a priori SNR 40 is estimated as a joint a priori SNR 40. The joint a priori SNR 40 is a compilation of the individual a priori SNRs 40 for each audio signal 12. Each individual a priori SNR 40 can be obtained by dividing the speech energy (Q) by the estimated noise variance Each a priori SNR40 represents the corresponding channel and the individual estimated noise variance represented by the matrix The relationship between.

[0052] Further references Figure 3-6 Each prior SNR 40 can be used to calculate the likelihood ratio (LR) of the audio filter 14 i ). Likelihood ratio (LR i ) can be represented by the following example equation:

[0053]

[0054] Each individual prior SNR 40 may be used individually to determine a corresponding likelihood ratio (LR i As described herein, the audio filter system 10 is configured to identify the target speaker 106a ( Figure 2 ) and utilize the interfering audio signal 12b to enhance the target audio signal 12a associated with the target speaker 106a. For example, the likelihood ratio (LR) associated with the target audio signal 12a may be utilized. i ) to perform a series of gain calculations 44 to obtain a set of gain values ​​44a. It is also conceivable that a likelihood ratio (LR) is also calculated for each interfering audio signal 12b. i ), the audio filter system 10 can use the likelihood ratio to ultimately enhance the target audio signal 12a.

[0055] The gain calculation 44 is configured to represent the designed audio filter 14 to obtain a gain value 44a for enhancing the target audio signal 12a. The gain calculation 44 is implemented by the following example equation:

[0056]

[0057] Still refer to Figure 3-6 , describes an example method for designing an audio filter 14. At an initial step 300, the audio filter system 10 receives an audio signal 12. At 302, the audio filter system 10 processes the audio signal 12 in the STFT 30 to obtain an audio signal output 32. At 304, the audio signal output 32 passes through the beamformer 36, and at 306, the audio filter system 10 extracts the speech energy (Q) of each speaker. At 308, the audio filter system 10 determines the prior SNR 40 of each beamformed output 38, and at 310 determines the likelihood ratio (LR i ). The audio filter system 10 then determines the gain value 28a at 312 and finally at 314 the audio filter system 10 enhances the target audio signal 12a based on the determined gain value 28a.

[0058] Many embodiments have been described. However, it should be understood that various modifications can be made without departing from the spirit and scope of the present disclosure. Therefore, other embodiments are also within the scope of the following claims.

[0059] The foregoing description has been provided for the purpose of illustration and description. It is not intended to be exhaustive or to limit the present disclosure. Individual elements or features of a particular configuration are generally not limited to that particular configuration, but where applicable, they are interchangeable and can be used in a selected configuration even if not specifically shown or described. This can also be varied in a variety of ways. Such variations should not be considered a departure from the present disclosure, and all such modifications are intended to be included within the scope of the present disclosure.

Claims

1. An audio filter system for a vehicle, the audio filter system comprising: Data processing hardware; and Memory hardware in communication with the data processing hardware, the memory hardware storing instructions that, when executed on the data processing hardware, cause the data processing hardware to perform operations including the following to design an audio filter: receiving a plurality of audio signals from a sensor array, the plurality of audio signals comprising a target audio signal and an interfering audio signal; Using interfering audio signals; determining an a priori signal-to-noise ratio (a priori SNR) for each of the plurality of audio signals; designing an audio filter using the determined a priori SNR; as well as The interfering audio signal is attenuated by using the designed audio filter, and the target audio signal is enhanced using the utilized interfering audio signal and the designed audio filter.

2. The audio filter system of claim 1, further comprising processing the plurality of audio signals using a short-time Fourier transform (STFT). 3 . The audio filter system of claim 2 , further comprising generating an output vector for each of the plurality of audio signals via a set of beamformers.

4. The audio filter system according to claim 2, wherein: Processing the plurality of audio signals using the STFT includes determining a time frame index and a frequency bin index.

5. The audio filter system according to claim 3, wherein: Generating, by the beamformer, an output vector for each of the plurality of audio signals includes providing a number of speakers, and generating a dimension for the output vector based on the provided number of speakers.

6. The audio filter system according to claim 5, wherein: Determining the a priori SNR includes calculating an individual a priori SNR for each of the plurality of audio signals and estimating the a priori SNR as a joint a priori SNR of each individual a priori SNR.

7. The audio filter system of claim 5, further comprising estimating a noise variance for each output vector generated from the beamformer.

8. The audio filter system of claim 7, further comprising extracting speech energy of a corresponding speaker corresponding to each of the plurality of audio signals using a corresponding linear equation.

9. The audio filter system according to claim 8, wherein: Estimating a noise variance for each of the plurality of audio signals includes expressing each noise variance as a corresponding linear equation for each output vector generated from a set of beamformers.

10. The audio filter system according to claim 9, wherein: Extracting speech energy for the corresponding speaker includes determining speech energy for each output vector generated from the set of beamformers using a corresponding linear equation.

Images