AUDIO FILTER SYSTEM FOR A VEHICLE

Abstract

A computer-implemented method, executed by data processing hardware, that causes the data processing hardware to perform operations to design an audio filter. The operations include receiving multiple audio signals from a sensor array, where the multiple audio signals comprise a target audio signal and noise audio signals, and evaluating the noise audio signals. The multiple audio signals are processed using a short-time Fourier transform (STFT) for each of the multiple audio signals. The operations also include designing the audio filter using the determined a priori signal-to-noise ratio (SNR), improving the target audio signal using the evaluated noise audio signals and the designed audio filter, and attenuating the noise audio signals.

Description

INITIATIONThe information provided in this section is for the purpose of generally presenting the context of the disclosure. Both the work of the presently named inventors, to the extent it is described in this section, and the aspects of the description that cannot otherwise qualify as prior art at the time of filing, are neither expressly nor impliedly admitted as prior art against the present disclosure.The present disclosure relates generally to an audio filter system for a vehicle.Interference cancellation and source separation tasks are required for both telecommunication and virtual assistance applications to boost the desired speaker and suppress interference, such as unwanted speakers. When a microphone array is installed in a vehicle, interference cancellation is usually achieved by the use of spatial filters such as beamformers. Beamformers usually provide a high white noise gain, which reduces the noise suppression performance. As a result, residual interference signals may still be present in the output of the beamformer, resulting in degradation of application level performance.SUMMARYIn some aspects, a computer-implemented method is performed by computing hardware that causes the computing hardware to perform operations for designing an audio filter. The operations include receiving multiple audio signals from a sensor array including a target audio signal and spurious audio signals. The plurality of audio signals are processed using a short-time Fourier transform (STFT), and an output vector is generated for each of the plurality of audio signals via a beamformer. The operations further include estimating a noise variance for each of the plurality of audio signals and extracting a speech energy for a respective speaker corresponding to each of the plurality of audio signals using the generated output vector from the beamformer. An a priori signal-to-noise ratio (a priori SNR) is determined using the generated output vectors, the estimated noise variance and the voice energy for each of the multiple audio signals and a gain value is determined based on the a priori SNR.In some examples, the target audio signal may be amplified using the designed audio filter and the spurious audio signals may be attenuated. Optionally, the plurality of audio signals may be processed using STFT, including determining a time frame index and a frequency band index. In some configurations, generating the output vector for each of the plurality of audio signals via the beamformer may include providing a number of speakers and generating dimensions for the output vector based on the provided number of speakers. The a priori SNR may be determined by calculating an individual a priori SNR for each of the multiple audio signals and by estimating the a priori SNR as a common a priori SNR of each individual a priori SNR. In some examples, estimating the noise variance for each of the plurality of audio signals may include expressing each noise variance as a respective linear equation for each generated output vector from the beamformer, and extracting the speech energy for the respective speaker may include determining the speech energy using the respective linear equation for each generated output vector from the beamformer.In some aspects, an audio filter system for a vehicle includes data processing hardware and memory hardware. The memory hardware is in communication with the data processing hardware and stores instructions that, when executed on the data processing hardware, cause the data processing hardware to perform operations for 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 interfering audio signals. The interfering audio signals are evaluated and an a priori signal-to-noise ratio (a priori SNR) is determined for each of the multiple audio signals. The audio filter is designed using the determined a priori SNR, and the target audio signal is amplified using the evaluated interfering audio signals and the designed audio filter, and the interfering signals are attenuated using the designed audio filter.In some examples, the operations may include processing the plurality of audio signals using a short-time Fourier transform (STFT), and generating an output vector for each of the plurality of audio signals via a beamformer. The operation of processing the plurality of audio signals using the STFT may include determining a time frame index and a frequency band index. Optionally, the operation of generating the output vector for each of the plurality of audio signals via the beamformer may include providing a number of speakers and generating dimensions for the output vector based on the provided number of speakers. In some examples, determining the a priori SNR may include calculating an individual a priori SNR for each of the plurality of audio signals and estimating the a priori SNR as a common a priori SNR of each individual a priori SNR. In other examples, the operations may also include estimating a noise vector for each of the plurality of audio signals and extracting a speech energy for a respective speaker corresponding to each of the plurality of audio signals using the estimated noise vector. 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 for the respective speaker may include determining the speech energy using the corresponding linear equation for each noise vector.In further aspects, a computer-implemented method is provided that is executed by data processing hardware and that causes the data processing hardware to perform operations for 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 interfering audio signals, and evaluating the interfering audio signals. 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 the audio filter using the determined a priori SNR and improving the target audio signal using the evaluated spurious audio signals and the designed audio filter, as well as attenuating the spurious audio signals.In some examples, the operations may include processing the plurality of audio signals using a short-time Fourier transform (STFT), and generating an output vector for each of the plurality of audio signals via a beamformer. The operation of processing the plurality of audio signals using the STFT may include determining a time frame index and a frequency band index. Optionally, the operation of generating the output vector for each of the plurality of audio signals via the beamformer may include identifying a number of speakers and generating dimensions for the output vector based on the identified number of speakers. In some examples, determining the a priori SNR may include calculating an individual a priori SNR for each of the plurality of audio signals and estimating the a priori SNR as a common a priori SNR of each individual a priori SNR. In other examples, the operations may also include estimating a noise vector for each of the plurality of audio signals and extracting a speech energy for a respective speaker corresponding to each of the plurality of audio signals using a respective linear equation for each generated output vector. The operation of estimating the noise variance may include estimating each noise variance by the corresponding linear equation, and the operation of extracting the speech energy for the respective speaker may include determining the speech energy using the corresponding linear equation for each generated output vector from the beamformer.BRIEF DESCRIPTION OF THE DRAWINGSThe drawings described herein are for illustrative purposes only of selected configurations and are not intended to limit the scope of the present disclosure; it shows: FIG. 1 is a schematic view of a vehicle with an audio filter system according to the present disclosure; FIG. 2 is a partial perspective view of an interior of a passenger compartment of a vehicle having a sensor array in accordance with the present disclosure; FIG. 3 is an example diagram of a RMSE (root mean square error) a priori signal to noise ratio (a priori SNR) of a desired source as a function of SNR measured at an input of an audio filter system according to the present disclosure; FIG. 4 is a functional block diagram of a vehicle controller including an audio filter system according to the present disclosure; FIG. 5A illustrates an example schematic illustration of multiple zones of an audio filter system in accordance with the present disclosure; FIG. 5B is an example schematic illustration of the audio filter system of FIG. 5A filtering multiple audio signals from each of the multiple zones in accordance with the present disclosure; and FIG. 6 is an example flow diagram of an audio filter system according to the present disclosure.In all drawings, corresponding reference numerals designate corresponding parts.DETAILED DESCRIPTIONExemplary configurations will now be described more fully with reference to the accompanying drawings. Example configurations are provided so that this disclosure will be thorough and will fully convey the scope of the disclosure to those skilled in the art. Specific details such as examples of specific components, apparatus, and methods are set forth in order to provide a thorough understanding of configurations of the present disclosure. It will be apparent to those skilled in the art that specific details need not be employed, that example configurations may be embodied in many different forms, and that the specific details and the example configurations are not to be construed to limit the scope of the disclosure.The terminology used herein is for describing particular exemplary configurations only and is not intended to be limiting. As used herein, the singular articles "a", "an", and "the" may be intended to include the plural forms as well, unless the context clearly indicates otherwise. The terms "comprises", "comprises", "including" and "having" are inclusive and therefore specify the presence of features, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more further features, steps, operations, elements, components and / or groups thereof. The method steps, processes, and operations described herein are not to be construed as necessarily requiring their execution in the particular order discussed or illustrated, unless specifically identified as an order of execution. Additional or alternative steps may be employed.When an element or layer is referred to as being "on," "engaging with," "connected to," "attached to," or "coupled to" another element or layer, it may be directly on, engaging with, connected to, attached to, or coupled to the other element or layer, or intervening elements or layers may be present. In contrast, when an element is referred to as being "directly on," "directly engaging with," "directly connected to," "directly attached to," or "directly coupled to" another element or layer, there need be no intervening elements or layers present. 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.The terms "first," "second," "third," etc., may be used herein to describe various elements, components, regions, layers, and / or portions. These elements, components, regions, layers, and / or portions are not intended to be limited by these terms. These terms may be used only to distinguish one element, component, region, layer, or portion from another region, layer, or portion. Terms such as "first," "second," and other numerical terms do not imply a sequence or order unless clearly indicated by the context. Thus, a first element, component, region, layer, or portion discussed below may be referred to as a second element, component, region, layer, or portion without departing from the teaching of the example configurations.In this application, including the definitions below, the term "module" may be replaced by the term "circuit". The term "module" may refer to, be part of, 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 a processor; other suitable hardware components that provide the described functionality; or a combination of some or all of the above, such as those described above, as pertaining to a system on a chip.The term "code" as used above may include software, firmware, and / or microcode, and may refer to programs, routines, functions, classes, and / or objects. 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, in combination with additional processors, executes some or all of the code from multiple modules. The term "shared memory" includes a single memory that stores a portion or all of the code from multiple modules. The term "group memory" includes a memory that, in combination with additional memories, stores a portion or all of the code from one or more modules. The term "memory" may be a subset of the term "computer readable medium.". The term "computer readable medium" includes non-transitory, electrical, and electromagnetic signals propagating through a medium and may therefore be considered tangible and non-transitory memory. Non-limiting examples of non-transitory memory include a tangible computer-readable medium including non-transitory memory, magnetic memory, and optical memory.The apparatuses and methods described in this application may be partially or fully implemented by one or more computer programs executed by one or more processors. The computer programs include processor-executable instructions stored on at least one non-transitory tangible computer-readable medium. The computer programs may also contain and / or rely on stored data.A software application (i.e., a software resource) may refer to computer software that causes a computing device to perform a task. In certain examples, a software application may be referred to as an "application," an "app," or a "program.". 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.The non-transitory memory may be physical devices used to store programs (e.g., sequences of instructions) or data (e.g., program state information) on a transitory or persistent basis for use by a computing device. The non-transitory memory may 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) / electronically erasable programmable read only memory (EEPROM) (e.g., typically used for firmware such as boot programs). 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 disks or tapes.These computer programs (also known as programs, software, software applications, or code) contain machine instructions for a programmable processor and may be implemented in a high level procedural and / or object oriented programming language and / or in assembly / machine language. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to a computer program product, a non-transitory computer-readable medium, apparatus, and / or apparatus (e.g., magnetic disks, optical disks, memories, programmable logic devices (PLDs)) used to provide 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 a signal used to provide machine instructions and / or data to a programmable processor.Various implementations of the systems and techniques described herein may be implemented in digital electronics and / or optical circuitry, integrated circuitry, dedicated ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include an implementation in one or more computer programs executable and / or interpretable in a programmable system including at least one programmable processor, which may be special or general purpose and is coupled to receive data and instructions from and send data and instructions to a storage system, at least one input device, and at least one output device.The processes and logic flows described in this application text may be performed by one or more programmable processors, also referred to as data processing hardware, that execute one or more computer programs to perform functions by operating on input data and generating outputs. The processes and logic flows may also be performed by special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit). Processors suitable for executing a computer program include, by way of example, both general purpose microprocessors and special purpose microprocessors and one or more processors of any type of digital computer. Generally, a processor will receive instructions and data from a read-only memory and / or a read / write memory. The essential elements of a computer are a processor for performing instructions and one or more memory devices for storing instructions and data. Generally, a computer also includes, or is operatively coupled to, receive data from and / or transmit data to one or more mass storage devices for storing data, e.g., magnetic disks, magneto-optical disks, or optical disks. However, a computer does not need to have such devices. Computer readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including by way of example semiconductor memory devices, e.g., EPROM, EEPROM, and flash memory devices; magnetic media, e.g., internal hard disks or removable media; magneto-optical media; and CD-ROM and DVD-ROM media. The processor and memory may be supplemented by or incorporated into special purpose logic circuitry.To provide interaction with a user, one or more aspects of the disclosure may be implemented in a computer having a display device, e.g., a CRT (cathode ray tube), an LCD (liquid crystal display device) monitor, or a touch screen for displaying information to the user, and optionally a keyboard and a pointing device, e.g., a mouse or trackball, whereby the user may provide input to the computer. Other types of devices may also be used to provide interaction with a user; e.g., feedback provided to the user may be any form of sensory feedback, e.g., visual feedback, audible feedback, or haptic feedback; and input may be received from the user in any form including audible, linguistic, or tactile input. Additionally, a computer may interact with a user by sending documents to and receiving documents from a device used by the user; e.g., by sending webpages to an Internet browser in a user's client device in response to requests received from the Internet browser.Referring to FIGS. 1-6, an audio filter system 10 may be installed in a vehicle 100. In some examples, the audio filter system 10 may be installed at any practical location within the vehicle 100 where audio filtering may be advantageous. For example, the audio filter system 10 may be incorporated in both vehicle-related and off-vehicle audio capture settings. Audio filter system 10 is described herein with reference to vehicle 100 to exemplify the function. However, the audio filter system 10 may also be used in non-vehicle examples. The audio filter system 10 is configured to subdivide the vehicle 100 into multiple spatial audio zones Z 1- Z 4 (FIG. 5A ), including, but not limited to, a driver zone Z 1, a front passenger zone Z 2, a right rear passenger zone Z 3 and a left rear passenger zone Z 4. As described in more detail below, the audio filter system 10 is configured to use audio signals 12 received from the respective spatial audio zones Z 1- Z 4 to amplify a target audio signal 12 aby evaluating spurious audio signals 12 b. The spurious audio signals 12 bmay be generated by speakers 106 within the vehicle 100, as mentioned below. Each of the audio signals 12 is used to design an audio filter 14 of the audio filter system 10 based on a position of one or more speakers within the vehicle 100 by evaluating the audio signals 12 from each respective spatial audio zone Z 1- Z 4.The audio filter system 10 is configured to estimate a speaker 106 abased on the audio signals 12. The audio filter system 10 may thus identify the target audio signal 12 abetween the interfering signals 12 b. As described herein, the audio filter system 10 is configured to evaluate the knowledge about the target audio signal 12 arelative to the spurious audio signals 12 bto specifically design the audio filter 14 to amplify only the target audio signal 12 ausing data from all detected audio signals 12. Thus, the audio filter system 10 may build or otherwise design the audio filter 14 based on a position of an occupant speaker 106 within the vehicle 100.Referring to FIGS. 1-3, the vehicle 100 is equipped with a sensor array 102 configured to sense the audio signals 12 within the vehicle 100. The sensor array 102 may include, but is not limited to, a microphone array that captures and sends the audio signals 12 to the audio filter system 10. Audio filter system 10 includes data processing hardware 16 and memory hardware 18 in communication with data processing hardware 16. The data processing hardware 16 is configured to receive the audio signals 12. Generally, it is contemplated that audio filter system 10 includes a computer-implemented method 20 that is executed by computing hardware 16 and causes computing hardware 16 to perform various operations described herein to design audio filter 14. Additionally or alternatively, the memory hardware 18 may store the computer-implemented method 20 as an instruction that, when executed on the computing hardware 16, causes the computing hardware 16 to perform the operations described herein.The audio filter system 10 may be configured as part of a vehicle computer or controller 104. For example, the sensor array 102 receives the audio signals 12 and sends the audio signals 12 to the vehicle controller 104. The vehicle controller 104 may initiate the audio filter system 10 in response to receiving the audio signals 12. For example, the vehicle controller 104 may execute the computer-implemented method 20 of the audio filter system 10 to begin designing the audio filter 14. Audio filter 14 is configured to filter audio signals 12 and identify a speaker. The speaker is typically an occupant 106 in the vehicle 100. It is contemplated that the audio filter system 10 may distinguish between multiple occupants 106 speaking simultaneously using the computer-implemented method 20 described herein.The audio filter system 10 uses the spatial audio zones Z 1- Z 4, to enhance the clarity of the target speaker 106a. For example, audio filter system 10 uses spurious audio signals 12 bto identify target speaker 106 a. The spurious audio signals 12b may then be used to design the audio filter 14 and amplify the target audio signal 12a. Finally, the spurious audio signals 12b are 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 may be a driver 106 aof the vehicle 100, as mentioned below. The audio signals 12 are captured by the sensor array 102, and the audio filter system 10 determines the target audio signal 12 acorresponding to the driver 106 a. The audio signals 12 assigned to a passenger 106 bare thus interference audio signals 12 band are deleted.As already mentioned, the audio signals 12 may comprise one or more target audio signals 12 aand one or more interfering audio signals 12 b. Finally, the audio filter system 10 is configured to attenuate the interfering audio signals 12 band amplify or otherwise enhance the target audio signals 12 a. The resulting signal is a filtered audio signal 12c containing only minimal to no spurious audio signals 12b. The filtered audio signal 12 cmay be sent to a third party processor that communicates with the vehicle controller 104 and is configured to receive the filtered audio signals 12 c.For example, FIG. 2 shows a first occupant 106 aand a second occupant 106 bthat simultaneously emit audio signals 12 with the sensor array 102 disposed in an interior of the passenger compartment 108 of the vehicle 100. In the illustrated example, the sensor array 102 is configured to receive each audio signal 12 a, 12 bfrom the respective occupants 106 a, 106 b, which are then transmitted to the audio filter system 10. While the sensor array 102 is shown as being in a front portion within the interior of the passenger compartment 108, it is contemplated that the sensor array 102 may be disposed at any convenient location within the interior of the passenger compartment 108 for the detection of the audio signals 12. For example, the sensor array 102 may be disposed at locations including, but not limited to, a rear portion, side portions, and a middle portion.Of FIGS. 3-6, FIG. 3 shows an example implementation of the audio filter system 10 and the enhancement of the audio filter system 10 by using an increased number of spurious audio signals 12b. For example, the number of interfering audio signals 12 bmay increase based on a number of speakers (N) within the vehicle 100. The audio filter system 10 is configured to use each audio signal 12 detected by the sensor array 102 to adjust the target audio signal 12 a, such that the precision of the audio filter 14 with multiple spurious audio signals 12 bis improved. For example, the example diagram shown in FIG. 3 shows a difference in the performance of the audio filter 14 based on a single speaker, two speakers, and four speakers. For a single speaker in the vehicle 100, where N=1, the audio filter 14 may be designed based on a single target audio signal 12 a. If two speakers are present in the vehicle 100, where N=2, the audio filter system 10 may have a lower estimation error due to the comparison between the two audio signals 12. The audio filter system 10 can be further improved if four speakers are in the vehicle, where N=4. Thus, the increased number of speakers may reduce the estimation error that may occur during the design of the audio filter 14.However, it is contemplated that for a predefined number of speakers, the estimation error begins to deviate in the opposite direction in a similar manner as for a single speaker at a high level of signal-to-noise ratio (SNR). For example, the deviation is a function of the SNR level and the predefined number of speakers. In some examples, the predefined number of speakers may be five speakers within the vehicle 100, but in other examples, it may be any natural predefined number of speakers. Audio filter system 10 is configured to take advantage of the non-target speakers to develop an improved audio filter 14 that more efficiently filters spurious audio signals 12 bto achieve amplified or filtered audio signal 12 c. In other words, the spurious audio signals 12 bmay be used in designing the audio filter 14. Each of the audio signals 12 is analyzed by the audio filter system 10 to estimate the target audio signal 12 aand to design the audio filter 14 to estimate the target audio signal 12 a.The presence of multiple spurious audio signals 12b helps to amplify the target audio signal 12a based on speech quality and general speech enhancement. A larger number of spurious audio signals 12 bmay result in the audio filter system 10 having an improved refinement in designing the audio filter 14. The improved refinement is a result of the increased comparison possibility of the disturbance audio signals 12 b. The main object of the audio filter system 10 is to design the audio filter 14 so that the target audio signal 12a is isolated and all remaining spurious audio signals 12b are attenuated using beamforming techniques followed by the audio filter 14 described herein. Once the audio filter 14 is designed as described below, the audio filter 14 receives all audio signals 12 from the vehicle 100 to estimate the filtered audio signal 12 cat the output of the audio filter 14.With continued reference to FIGS. 3-6, audio filter system 10 begins designing audio filter 14 after receiving audio signals 12, including target audio signal 12 aand spurious audio signals 12 bfrom sensor array 102. Audio filter system 10 estimates target audio signal 12 afrom received audio signals 12 and uses each of audio signals 12, including noise signals 12 b, to design audio filter 14 as described herein to amplify estimated target audio signal 12 a. The audio signals 12 received by the audio filter system 10 are processed using a short-time Fourier transform (STFT) 30. The STFT 30 is used to determine a time frame index (n) and a frequency band index (k) of each respective audio signal output 32, which is represented by (X) in FIG. 5B.The respective audio signal outputs 32 may be indicated for a particular time frame index (n) and a corresponding particular frequency band index (k). Each of the audio signals 12 may have different iterations 34, which may be represented by (X i). Like the respective audio signal outputs (X), each of the iterations 34 depends on the time frame index (n) and the frequency band index (k). Subscript (i) may be used as a place holder for a number associated with a respective speaker. For example, if there are four (4) speakers, there may be four iterations 34, each represented as one of (X 1- X 4). However, it is contemplated that the number of iterations 34 is not limited to four, as each iteration 34 is based on a respective speaker, which may be more than four speakers or less than four speakers.With continued reference to FIGS. 3-6, each iteration 34 of the audio signal outputs 32 may then be passed through a set of beamformers 36 to generate a beamforming output 38 for each of the audio signal outputs 32, represented as (y i). The beamforming outputs 38 may then be used in combination with an estimated a priori signal-to-noise ratio (a priori SNR) 40 described below to further define an output vector 42. For example, each output vector 42 may be determined using the following example equation, where the output vector 42 is represented by:Further, the speech energy (Q) for the respective speaker can be determined using the respective linear equation for each of the generated output vectors from the beamformers 36. An exemplary linear equation that results in speech energy (Q) includes: wherein and provided that [P] ii ≅ 1.The output vectors 38 outlined in the example equation above may be solved using, for example. The a priori signal-to-noise ratio (a priori SNR) 40 may be determined using each of the generated output vectors 38, the estimated noise variance, and the extracted voice energy. The a priori SNR 40 at each of the output vectors 42 may be represented by the following example equation:It is generally contemplated that a priori SNR 40 is estimated as a common a priori SNR 40. The common a priori SNR 40 is a summary of the respective individual a priori SNR 40 for each of the audio signals 12. Each a priori SNR 40 represents a relationship between a respective channel expressed in a matrix and the separately estimated noise variance (σ vi).With continued reference to FIGS. 3-6, any a priori SNR 40 may be used to calculate a probability ratio (LR i) of the audio filter 14. The probability ratio (LR i) can be represented by the following example equation:Each individual a priori SNR 40 may be used separately to determine a respective probability ratio (LR i) for each speaker 106. As described herein, the audio filter system 10 is configured to identify a speaker 106 a(FIG. 2 ) and evaluate the spurious audio signals 12 bto amplify the target audio signals 12 aassociated with the speaker 106 a. For example, the probability ratio (LR i) associated with the target audio signal 12a may be used to perform a series of gain computations 44 to obtain a set of gain values 44a. It is also contemplated that the probability ratio (LR i) is also calculated for each of the spurious audio signals 12b that may be evaluated by the audio filter system 10 to ultimately amplify the target audio signal 12a.The gain calculations 44 are configured to represent the designed audio filter 14 to obtain the gain values 44a used to amplify the target audio signal 12a. The gain calculations 44 are obtained by the following example equation:Referring to FIGS. 3-6, an example method for designing the audio filter 14 will be described. In a first step 300, the audio filter system 10 receives the audio signals 12. The audio filter system 10 processes 302 the audio signals 12 in the STFT 30 to obtain the audio signal outputs 32. Audio signal outputs 32 are passed through beamformers 36 at 304, and audio filter system 10 extracts the speech energy (Q) of each speaker at 306. The audio filter system 10 determines the a priori SNR 40 for each of the beamforming outputs 38 at 308, and determines the probability ratio (LR i). at 310. Subsequently, in 312, the audio filter system 10 determines the gain value 28 aand finally the audio filter system 10 amplifies the target audio signal 12 abased on the determined gain value 28 ain 314.Several implementations have been described. Nevertheless, it is to be understood that various modifications may be made without departing from the spirit and scope of the disclosure. Accordingly, further implementations are within the scope of the following claims.The foregoing description has been provided by way of illustration and description. It is not intended to be exhaustive or to limit the disclosure. Individual elements or features of a particular configuration are generally not limited to that particular configuration, but, where applicable, are interchangeable and can be used in a selected configuration, even if not specifically shown or described. They can also be varied in many ways. Such variations are not to be regarded as a departure from the disclosure, and all such variations are intended to be included within the scope of the disclosure.

Claims

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 for designing an audio filter comprising: receiving a plurality of audio signals from a sensor array, the plurality of audio signals comprising a target audio signal and interfering audio signals; evaluating the interfering audio signals; determining an a priori signal-to-noise ratio (a priori SNR) for each of the plurality of audio signals; designing the audio filter using the determined a priori SNR; amplifying the target audio signal using the evaluated spurious audio signals and the designed audio filter by attenuating the spurious audio signals using the designed audio filter.The audio filter system of claim 1, further comprising processing the plurality of audio signals using a short-time Fourier transform (STFT).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.The audio filter system of claim 2, wherein processing the plurality of audio signals using the STFT comprises determining a time frame index and a frequency band index.The audio filter system of claim 3, wherein generating the output vector for each of the plurality of audio signals via the beamformers comprises providing a number of speakers and generating dimensions for the output vector based on the provided number of speakers.The audio filter system of claim 5, wherein determining the a priori SNR comprises calculating an individual a priori SNR for each of the plurality of audio signals and estimating the a priori SNR as a common a priori SNR of each individual a priori SNR.The audio filter system of claim 5, further comprising estimating a noise variance for each of the generated output vectors from the beamformers.The audio filter system of claim 7, further comprising extracting a speech energy for a respective speaker corresponding to each of the plurality of audio signals using a respective linear equation.The audio filter system of claim 8, wherein estimating the noise variance for each of the plurality of audio signals comprises expressing each noise variance as a respective linear equation for each generated output vector from a set of beamformers.The audio filter system of claim 9, wherein extracting the speech energy for the respective speaker comprises determining the speech energy using the corresponding linear equation for each generated output vector from the set of beamformers.

Images