Systems and methods for voice reception and detection

Abstract

Systems and methods for voice reception and detection related to a communication system are disclosed.

Description

[0001] Cross-reference to related applications

[0002] This application claims the benefit of U.S. Provisional Patent Application No. 63 / 012,814, filed April 20, 2020, entitled "System and Method for Voice Reception and Detection," the entire disclosure of which is expressly incorporated herein by reference. This application also relates to U.S. Provisional Patent Application No. 63 / 012,811, filed April 20, 2020, entitled "System and Method for Communication Information," the entire disclosure of which is expressly incorporated herein by reference. Technical Field

[0003] This disclosure generally relates to communication systems, and more specifically, to communication systems having microphones for voice reception and / or detection. Background Technology

[0004] Recreational vehicles such as motorcycles or off-road vehicles such as all-terrain vehicles (ATVs) and snowmobiles are widely used for recreational purposes. While riding, users (e.g., drivers / riders) can control some functions of the recreational vehicle via voice commands and / or participate in telephone or radio communications. For this purpose, users of recreational vehicles (e.g., drivers / riders) can wear wearable devices with one or more microphones (e.g., headsets or helmets with microphones) to capture the user's voice or speech. However, in addition to the user's voice, the microphones inevitably capture noise (e.g., engine noise, road noise, wind noise). Summary of the Invention

[0005] As described above, the embodiments provided herein relate to voice capture in recreational vehicles. Exemplary embodiments include, but are not limited to, the following examples.

[0006] In one aspect, a recreational vehicle is provided. The recreational vehicle includes: a frame; a front grounding member and a rear grounding member supporting the frame; a powertrain drivably coupled to one of the front grounding member and the rear grounding member; a steering assembly coupled to the front grounding member for steering the recreational vehicle; a seat supported by the frame; and a communication system. The communication system has a microphone located between the seat and the steering assembly.

[0007] In some embodiments, the recreational vehicle may further include a fuel tank supported by the frame and located between the seat and the steering assembly. The microphone may be mounted on top of the fuel tank.

[0008] In some embodiments, the recreational vehicle may further include an airbox supported by the frame and located between the seat and the steering assembly. The microphone may be mounted on top of the airbox.

[0009] In some embodiments, the communication system may be configured to receive user voice from the recreational vehicle via the microphone.

[0010] In some embodiments, the steering assembly may further include a front fairing and a user handle. In such an embodiment, the microphone may be located behind the front fairing and below the user handle to reduce the amount of airflow in contact with the microphone.

[0011] In some embodiments, the microphone may be mounted at an angle, facing upwards toward the user of the recreational vehicle, to reduce exhaust noise and / or engine noise.

[0012] In other respects, a wearable device for voice detection is provided. The wearable device has a communication system including: a processor; a microphone configured to generate audio data of a user's voice; an accelerometer configured to generate accelerometer data capturing vibrations of the user's head and / or neck; and a memory including instructions, when executed by the processor, to cause the processor to use the accelerometer data to detect the user's voice.

[0013] In some embodiments, generating the audio data may include generating audio data of the user's speech in response to the detection of the user's speech.

[0014] In some embodiments, detecting the user's speech using the accelerometer data may include detecting the user's speech by associating the audio data with the accelerometer data.

[0015] In some embodiments, the microphone may be connected to a wearable device near the user's mouth to receive voice from the user.

[0016] In some embodiments, the accelerometer may be coupled to the wearable device at a location where the wearable device may come into contact with the user's head and / or neck, in order to detect audio frequencies generated by the user's vocal cords in real time.

[0017] In some embodiments, the wearable device may be a helmet.

[0018] In some embodiments, the accelerometer may be located on the chin strap of the wearable device.

[0019] In some embodiments, the memory may further include instructions that, when executed by the processor, cause the processor to: process the audio data using beamforming technology to achieve spatial selectivity; filter the processed audio data to remove low-frequency noise; and filter the accelerometer data to remove high-frequency noise. In some embodiments, detecting the user's voice using the accelerometer data may include correlating the filtered processed audio data with the filtered accelerometer data to detect the user's voice.

[0020] In some embodiments, the communication system may further include a low-pass filter configured to receive the accelerometer output signal generated by the accelerometer to remove high-frequency noise.

[0021] In some embodiments, the communication system may further include a high-pass filter configured to receive an audio output signal generated by the microphone to remove low-frequency noise.

[0022] In other aspects, a method for voice detection is provided. The method includes generating accelerometer data by capturing vibrations of the user's head and / or neck using the accelerometer of the wearable device; and detecting the user's voice using the accelerometer data.

[0023] In some embodiments, the method may further include generating audio data of the user's voice via the microphone of the wearable device in response to detecting the user's voice.

[0024] In some embodiments, the method may further include generating audio data of the user's voice through the microphone of the wearable device, wherein detecting the user's voice using the accelerometer data includes detecting the user's voice by associating the audio data with the accelerometer data.

[0025] In some embodiments, the microphone may be connected to a wearable device near the user's mouth to receive voice from the user.

[0026] In some embodiments, the accelerometer is coupled to the wearable device at a location where the wearable device may come into contact with the user's head and / or neck to detect audio frequencies generated by the user's vocal cords in real time.

[0027] In some embodiments, the wearable device may be a helmet.

[0028] In some embodiments, the accelerometer may be located on the chin strap of the wearable device.

[0029] In some embodiments, the method may further include: processing the audio data using beamforming technology to achieve spatial selectivity; filtering the processed audio data to remove low-frequency noise; and filtering the accelerometer data to remove high-frequency noise. In some embodiments, detecting the user's voice may include detecting the user's voice by associating the filtered processed audio data with the filtered accelerometer data.

[0030] In one aspect, a communication system for noise processing is provided. The communication system includes: a processor; and a memory including instructions that, when executed by the processor, cause the processor to: receive audio data including a user's voice via a microphone; process the audio data based on current vehicle information of the user's recreational vehicle to remove unwanted ambient noise; and output the processed audio data.

[0031] In some embodiments, predictable noise includes engine noise based on the engine status of the recreational vehicle in which the user is riding.

[0032] In some embodiments, unpredictable noise includes road noise, wind noise, and / or any other ambient noise.

[0033] In some embodiments, the microphone may be mounted on the recreational vehicle.

[0034] In some embodiments, the microphone may be mounted on the user's wearable device.

[0035] In some embodiments, processing the audio data includes removing a first set of noises from the audio data based on the current vehicle information, wherein the current vehicle information includes the type, model and / or brand of the recreational vehicle, a vehicle noise profile associated with the recreational vehicle, and / or the current state of the recreational vehicle's engine.

[0036] In some embodiments, the current state of the engine of the recreational vehicle includes any current state of the engine parameters, and the vehicle noise profile is generated based on the engine parameters of the recreational vehicle.

[0037] In some embodiments, the engine parameters include engine phase, engine speed, transmission gear, clutch position, throttle position, and wheel speed.

[0038] In some embodiments, processing the audio data includes removing a second set of noise from the audio data using a moving average filter.

[0039] In another aspect, a method for noise processing is provided. The method includes: receiving audio data including a user's voice via a microphone; processing the audio data based on current vehicle information of the user's recreational vehicle to remove unwanted ambient noise; and outputting the processed audio data.

[0040] In some embodiments, predictable noise includes engine noise based on the state of the engine of the recreational vehicle in which the user is riding.

[0041] In some embodiments, unpredictable noise includes road noise, wind noise, and / or any other environmental noise.

[0042] In some embodiments, the microphone may be mounted on the recreational vehicle.

[0043] In some embodiments, the microphone may be mounted on the user's wearable device.

[0044] In some embodiments, processing the audio data includes removing a first set of noises from the audio data based on the current vehicle information, wherein the current vehicle information includes the type, model and / or brand of the recreational vehicle, a vehicle noise profile associated with the recreational vehicle and / or the current state of the recreational vehicle's engine.

[0045] In some embodiments, the current state of the engine of the recreational vehicle includes any current state of the engine parameters, and the vehicle noise profile is generated based on the engine parameters of the recreational vehicle.

[0046] In some embodiments, the engine parameters may include engine phase, engine speed, transmission gear, clutch position, throttle position, and wheel speed.

[0047] In some embodiments, processing the audio data may include removing a second set of noise from the audio data using a moving average filter.

[0048] Although several embodiments have been disclosed, other embodiments of the subject matter will become apparent to those skilled in the art from the following detailed description, which shows and describes exemplary embodiments of the disclosed subject matter. Therefore, the drawings and detailed description are to be considered illustrative rather than limiting in nature. Attached Figure Description

[0049] The above and other features and advantages of this disclosure, as well as the ways of achieving these features and advantages, will become more apparent and better understood by referring to the following description of embodiments of the invention in conjunction with the accompanying drawings.

[0050] In the picture:

[0051] Figure 1 This is a side perspective view of a recreational vehicle according to certain embodiments of the present invention;

[0052] Figure 2 Example Figure 1 A block diagram of the communication system for recreational vehicles;

[0053] Figure 3 An example of a system for user voice reception according to this disclosure is provided, including a system having communication...

[0054] The system's user wearable devices;

[0055] Figure 4 Example usage Figure 3 Methods for wearable devices to perform voice detection on users; and

[0056] Figure 5 This is a flowchart illustrating a computer-implemented method for noise reduction of audio data.

[0057] Corresponding reference numerals indicate the relevant parts in several views. Although the drawings illustrate embodiments of this disclosure, they are not necessarily drawn to scale, and certain features may be exaggerated to better illustrate and explain this disclosure. The examples set forth herein illustrate embodiments of this disclosure in one form, and such examples should not be construed as limiting the scope of this disclosure in any way. Detailed Implementation

[0058] Various embodiments of the invention are described in detail with reference to the accompanying drawings, wherein similar reference numerals denote similar parts and components in several views. Reference to various embodiments does not limit the scope of the invention, which is limited only by the scope of the appended claims. Furthermore, any examples set forth in this specification are not intended to be limiting, but merely illustrate a portion of the many possible embodiments of the claimed invention.

[0059] Now refer to Figure 1 This indicates that the recreational vehicle 100 is specifically a motorcycle. It should be understood that although the recreational vehicle 100 is... Figure 1 While illustrated as a motorcycle, a recreational vehicle can be specifically any off-road vehicle, such as an all-terrain vehicle (ATV) and a snowmobile, which are widely used for recreational purposes. Recreational vehicles may include features that can be controlled by a user (e.g., a driver / rider) via voice commands. Additionally or optionally, the user may wish to engage in telephone or radio communications while in the recreational vehicle. For this purpose, an exemplary recreational vehicle 100 has one or more microphones directly mounted on the recreational vehicle 100 to capture the user's voice or speech without the need for wearable devices (e.g., headphones or a helmet).

[0060] like Figure 1As shown, the recreational vehicle 100 includes multiple grounding members 102. Each grounding member 102 includes wheels, pedals, skis, and other suitable equipment that supports the vehicle 100 relative to the ground. The recreational vehicle 100 also includes a frame 104 supported by the multiple grounding members 102. The front and / or rear wheels 102 are coupled to a powertrain assembly 114 to propel the vehicle 100 during operation. The powertrain assembly 114 includes an engine and a transmission. The transmission is coupled to the engine and provides power to the front and / or rear wheels 102.

[0061] Seat 106 is operably supported by frame 104. Seat 106 may include straddle-type seats, bench seats, bucket seats, and other suitable support members. In addition to seat 106, recreational vehicle 100 may also include a passenger seat. Exemplary passenger seats include straddle-type seats, bench seats, bucket seats, and other suitable support members. In some cases, the passenger seat is located directly behind the user seat. One or more floor plates 112 are supported by frame 104. Vehicle floor plates 112 are adapted to support the user's lower body when the user operates vehicle 100. For example, when the user is seated in seat 106, the user can place their shoes, boots, and / or other accessories on floor plate 112.

[0062] The steering system 120 is coupled to at least one grounding member 102 and typically includes a user input or steering member 108 adapted to be gripped by a user of the vehicle 100. An exemplary steering member 108 includes handlebars and / or a steering wheel. Additionally and / or optionally, the steering member 108 includes one or more user handlebars 110. An exemplary user handlebar 110 is a handle (e.g., a motorcycle handlebar).

[0063] The recreational vehicle 100 also includes a communication system 130, which in Figure 2 The communication system 130 includes a microphone 118 to capture the user's voice. In an exemplary embodiment, the microphone 118 is mounted on the recreational vehicle 100 between the steering system 120 and the seat 106 to capture the user's voice to activate voice commands and / or participate in telephone or radio communications. For this purpose, the microphone 118 is mounted on the recreational vehicle 100 in a specific configuration to minimize noise (e.g., wind noise, engine noise, and road noise) that may be captured by the microphone 118. More specifically, the microphone 118 is configured to be located behind the front fairing 122 and below the user's handlebars 110 to reduce the amount of airflow in contact with the microphone 118. Furthermore, the microphone 118 is mounted at an angle, facing upwards towards the user, to reduce engine noise and / or exhaust noise that may be captured from the muffler 124 at the rear of the recreational vehicle 100.

[0064] In the exemplary recreational vehicle 100, the fuel tank 116 is located between the steering system 120 and the seat 106, and the microphone 118 is located on top of the fuel tank 116. However, it should be understood that, depending on the recreational vehicle, the microphone may be located on top of the fuel tank between the steering system 120 and the seat 106. In other words, the microphone 118 is adapted to be mounted on the component located between the steering system 120 and the seat 106 of the recreational vehicle. It should also be understood that, although Figure 1 A microphone 118 is shown, but a communication system for a recreational vehicle may include multiple microphones mounted on the recreational vehicle to capture user voice.

[0065] Now for reference Figure 2 The diagram illustrates a block diagram of a recreational vehicle 100 having a communication system 130. In an exemplary embodiment, the communication system 130 of the recreational vehicle 100 includes a processor 132, a memory 134, an input / output (I / O) controller 136 (e.g., a network transceiver), a memory unit 138, a user interface 140, one or more speakers 142, and a microphone 118, all of which can be interconnected via one or more address / data buses. Although the I / O controller 136 is shown as a single block, it should be understood that the I / O controller 136 may include many different types of I / O components. The user interface 140 may include one or more input devices (e.g., buttons, touchpads, keyboards) capable of receiving user input.

[0066] The processor 132 disclosed herein can be any electronic device capable of processing data, such as a central processing unit (CPU), graphics processing unit (GPU), system-on-a-chip (SoC), or any other suitable type of processor. It should be understood that the various operations of the example methods described herein (i.e., performed by the communication system 130) can be performed by one or more processors 132. The memory 134 can be random access memory (RAM), read-only memory (ROM), flash memory, or any other suitable type of memory capable of storing data such as instruction code that the processor 132 needs to access to implement any of the methods disclosed herein. It should be understood that although only one processor 132 is shown, the communication system 130 may include multiple processors 132.

[0067] The communication system 130 also includes a database 144. As used herein, the term "database" may refer to a single database or other structured data store, or a collection of two or more different databases or structured data storage components. In an exemplary embodiment, database 144 is part of the communication system 130. In some embodiments, the communication system 130 may access database 144 via a network (not shown).

[0068] The communication system 130 may also include multiple software applications stored in a memory unit 138, which may be referred to as program memory. The various software applications on the communication system 130 may include specific programs, routines, or scripts for performing processing functions associated with the methods described herein. Additionally or optionally, the various software applications on the communication system 130 may include general-purpose software applications for data processing, database management, data analysis, network communication, web server operation, or other functions described herein or typically performed by the communication system of a recreational vehicle. The various software applications may execute on the same computer processor or different computer processors. Additionally or optionally, the software applications may interact with various hardware modules that may be installed within or connected to the communication system 130. Such modules may implement some or all of the various exemplary method functions or other related embodiments discussed herein.

[0069] One or more speakers 142 can be any electronic device capable of generating sound in response to an electrical audio signal input. For example, communication system 130 can be communicatively connected to a user's mobile device. In this case, the electrical audio signal input can be received from the user's mobile device, for example, to transmit audio conversations during a telephone call, play music, and / or play text messages or emails to the user through one or more speakers 142. In other examples, the communication system of recreational vehicle 100 can be communicatively connected to the communication system of another recreational vehicle. In this case, electrical audio signal input can be received from another user through the communication system of the other recreational vehicle to transmit communications or messages from that user.

[0070] Microphone 118 can be any electronic device capable of capturing sound and converting it into an electronic audio output signal. As described above, in an exemplary embodiment, microphone 118 is mounted on recreational vehicle 100 to capture a user's voice to activate voice commands and / or participate in telephone or radio communications. The audio output signal from microphone 118 can be transmitted to a user's mobile device during a telephone call and / or to create a voice-text message or email to be sent to another computing device. Furthermore, the audio output signal can be transmitted to another communication system in another user's recreational vehicle to transmit communication or information from that user to another user.

[0071] By mounting the microphone 118 directly on the recreational vehicle 100 as part of the recreational vehicle's communication system 130, users can avoid using separate microphones that require a physical connection to the recreational vehicle 100 or a communicatively connected (e.g., via Bluetooth) connection to the recreational vehicle 100. However, it should be understood that in some embodiments, such as Figure 3As shown in detail, a microphone can be integrated into a user's wearable device (e.g., a helmet) to capture the user's voice.

[0072] Now for reference Figure 3 This illustration shows a system 300 for detecting the voice of a user (e.g., driver / rider) of a recreational vehicle 340 via a wearable device 302 (e.g., a helmet). The wearable device 302 is adapted for the user to wear while riding the recreational vehicle 340 to detect voice or speech during riding. Detecting the user's voice using a microphone 324 coupled to the wearable device 302 during riding can be challenging due to the microphone 324's sensitivity to ambient sounds such as engine noise, tire noise, and wind noise. To improve the efficiency and effectiveness of voice reception, the exemplary wearable device 302 also includes an accelerometer 326, which will be described in detail below.

[0073] In an exemplary embodiment, system 300 includes a communication system 310 having a wireless communication connection (e.g., via Bluetooth or Wi-Fi) with recreational vehicle 340. However, it should be understood that in some embodiments, wearable device 302 can be wired to recreational vehicle 340. System 300 may also include one or more wearable devices 330 and / or one or more computing devices 360 (e.g., mobile devices, servers) that are communicatively connected to wearable device 302 via network 350.

[0074] In an exemplary embodiment, the communication system 310 of the wearable device 302 includes a processor 312, a memory 314, an input / output (I / O) controller 316 (e.g., a network transceiver), a memory unit 318, a user interface 320, one or more speakers 322, one or more microphones 324, and an accelerometer 326, all of which can be interconnected via one or more address / data buses. Although the I / O controller 316 is shown as a single block, it should be understood that the I / O controller 316 may include many different types of I / O components. The user interface 320 may include one or more input devices (e.g., buttons, touchpads, keyboards) capable of receiving user input.

[0075] The processor 312 disclosed herein can be any electronic device capable of processing data, such as a central processing unit (CPU), graphics processing unit (GPU), system-on-a-chip (SoC), or any other suitable processor type. It should be understood that the various operations of the example methods described herein (i.e., performed by the communication system 310) can be performed by one or more processors 312. The memory 314 can be random access memory (RAM), read-only memory (ROM), flash memory, or any other suitable type of memory capable of storing data such as instruction code that the processor 312 needs to access to implement any of the methods disclosed herein. It should be understood that although only one processor 312 is shown, the communication system 310 may include multiple processors 312.

[0076] Communication system 310 may also include database 328. As used herein, the term "database" may refer to a single database or other structured data store, or a collection of two or more different databases or structured data storage components. In an exemplary embodiment, database 328 is part of communication system 310. In some embodiments, communication system 310 may access database 328 via a network (e.g., network 350). Database 328 may store data received from or transmitted to one or more communication systems of other wearable devices 330, computing devices 340, or one or more servers 360. It should be understood that each of the other wearable devices 330 includes a communication system similar to communication system 310 of wearable device 302.

[0077] Typically, computing device 360 ​​may include any existing or future device capable of receiving and / or transmitting data to a user. For example, computing device may be, but is not limited to, mobile devices, smartphones, tablets, wearable devices, smart glasses, computers, laptops, or any other suitable computing device capable of communicating with the communication system 310 of wearable device 302. It should be understood that in some embodiments, computing device 360 ​​may be directly connected to wearable device 302 via a wire.

[0078] The communication system 310 may also include multiple software applications stored in a memory unit 318, which may be referred to as program memory. The various software applications on the communication system 310 may include specific programs, routines, or scripts for performing processing functions related to the methods described herein. Additionally or optionally, the various software applications on the communication system 310 may include general-purpose software applications for data processing, database management, data analysis, network communication, web server operation, or other functions described herein or typically performed by the communication system of a wearable device (e.g., a helmet). The various software applications may execute on the same computer processor or different computer processors. Additionally or optionally, the software applications may interact with various hardware modules that may be installed within or connected to the communication system 310. Such modules may implement some or all of the functions of the various exemplary methods discussed herein, or other related embodiments.

[0079] One or more speakers 322 can be any electronic device capable of generating sound in response to an electronic audio signal input. In an exemplary embodiment, the speaker 322 is located near the user's ear to transmit audible sound to the user. If the wearable device 302 is specifically a helmet, the speaker 322 may be located inside the helmet near the user's ear to deliver audible sound to the user. For example, electronic audio signal input can be received from a recreational vehicle 340 via one or more speakers 322 for voice commands, telephone communications, and / or radio communications (e.g., vehicle-to-vehicle communications). In some embodiments, electronic audio signal input can be received directly from the communication system of another wearable device (e.g., 330) to receive communications or messages from another user. In other embodiments, the communication system 310 of the wearable device 302 can be communicatively coupled to a user's mobile device (e.g., computing device 360). In this case, electronic audio signal input can be received directly from the user's mobile device (e.g., computing device 360), for example, to transmit audio conversations during a telephone call, play music, and / or play text messages or emails to the user via one or more speakers 322.

[0080] One or more microphones 324 can be any electronic device capable of capturing sound and converting it into an electro-audio output signal. In an exemplary embodiment, microphone 324 may be mounted near a user's mouth to receive audible sound from the user. If the wearable device 302 is specifically a helmet, the microphone may be mounted outside and / or inside the helmet, close to the user's mouth. For example, the electro-audio output signal from one or more microphones 324 may be transmitted to a recreational vehicle 340 for voice commands, telephone communications, and / or radio communications (e.g., vehicle-to-vehicle communications). The electro-audio output signal may be transmitted directly to the communication system of another wearable device (e.g., 330) of another user to pass communications or messages from one user to another. Furthermore, in some embodiments, communication system 310 may communicate directly with a user's mobile device (e.g., computing device 340) for telephone communications and / or to create voice-text messages or emails to send to another computing device.

[0081] Accelerometer 326 can be any sensor capable of measuring frequency vibrations. In an exemplary embodiment, accelerometer 326 is located where wearable device 302 may come into contact with a user's head and / or neck. This allows accelerometer 326 to capture vibrations of the user's head and / or neck to detect the user's voice or speech. For example, if wearable device 302 is specifically a helmet, the accelerometer is mounted or embedded on the inner surface of the helmet and located where the user's cheek may come into contact when wearing the helmet. Additionally, if the helmet has headphones or earmuffs inside (e.g., noise-canceling headphones or earmuffs), the accelerometer may be mounted or embedded in the ear pads of the earmuffs. However, it should be understood that in some embodiments, the accelerometer may be located anywhere inside the helmet that comes into contact with the user's body (e.g., the user's head, face, and / or neck). It should also be understood that in some embodiments, accelerometer 326 may be located on the chin strap of wearable device 302. By mounting the accelerometer 326 in a wearable device or on a chin strap that contacts the user's head and / or neck, audio generated by the user's vocal cords can be detected in real time. The accelerometer signal is minimally affected by ambient audio noise (such as engine noise). In one example, the accelerometer 326 can be specifically a low-noise, high-bandwidth 3-axis accelerometer with a time-division multiplexed slave interface. In this example, the signal bandwidth can be 2340 Hz, and the power supply voltage can be between 1.71 and 1.99 volts.

[0082] Network 350 is any suitable type of computer network that functionally connects the communication system 310 of wearable device 302 to another wearable device 330 and / or computing device 360. In some embodiments, network 350 can be any suitable type of computer network that functionally connects recreational vehicle 340 to one or more computing devices 360 and / or one or more wearable devices. Network 350 may include a private network, a secure public internet, a virtual private network, and / or one or more other types of networks, such as a dedicated access line, a regular telephone line, a satellite link, a cellular data network, or a combination thereof. In embodiments where network 350 includes the internet, data communication can be performed on network 350 using internet communication protocols.

[0083] Network 350 can be or includes any number of different types of communication networks, such as bus networks, Short Message Service (SMS), Local Area Networks (LANs), Wireless LANs (WLANs), Wide Area Networks (WANs), Personal Area Networks (PANs), the Internet, P2P networks, custom-designed communication or messaging protocols, and / or similar. Network 350 may include a combination of multiple networks.

[0084] It should be understood that this figure is merely an example and should not unduly limit the scope of the claims. Those skilled in the art will recognize many variations, substitutions, and modifications.

[0085] Now for reference Figure 4 This illustrates a computer-implemented method 400 for speech detection using an accelerometer 326 and a microphone 324 in a wearable device 302. In an exemplary embodiment, method 400 is performed by a communication system 310 of the wearable device 302. As discussed above, detecting a user's speech in a noisy environment using a microphone coupled to a wearable device can be challenging due to the microphone's sensitivity to ambient audio noise or environmental noise such as engine noise. However, unlike the audio output signal produced by a microphone, the accelerometer output signal is minimally affected by ambient audio noise because the accelerometer is configured to detect the audio frequencies produced by the user's vocal cords in real-time or near real-time. Based on the accelerometer data, the communication system 310 is able to detect whether the user is making a sound and activate the microphone 324 to acquire microphone data. In other words, the microphone 324 can be inactive or muted until the communication system 310 detects the user's speech or voice. It should be understood that in some embodiments, the microphone 324 can be always active. Therefore, the communication system 310 of the wearable device 302 uses the output signals from the microphone 324 and accelerometer 326 of the wearable device 302 to detect the user's voice more accurately.

[0086] As described above, the accelerometer 326 is configured to detect audio frequencies generated by the user's vocal cords in real time. The detected frequencies can then be emphasized in the signal path of the microphone 324 to improve speech detection accuracy. In an exemplary embodiment, frequency detection and emphasis are performed using standard digital signal processing techniques, employing a low-pass filter 402, beamforming 404, and a high-pass filter 406. Figure 4 As shown, the low-pass filter 402 is connected to the accelerometer 326. However, the high-pass filter 406 is connected to the microphone 324 via a beamformer or spatial filter 404.

[0087] Low-pass filter 402 is configured to receive the accelerometer output signal generated by accelerometer 326 to remove high-frequency noise. In other words, accelerometer data provides a low-frequency audio representation of the user's speech.

[0088] High-pass filter 406 is configured to receive the audio output signal generated by microphone 324 of wearable device 302 to remove low-frequency noise (e.g., ambient noise). To this end, the audio output signal from microphone 324 is processed using beamforming technology via beamformer or spatial filter 404 for directional signal reception to achieve spatial selectivity. It should be understood that different types of beamforming technology may be used depending on how the microphone is mounted or aligned relative to the user's mouth.

[0089] Once the accelerometer output signal and the audio output signal are processed, the communication system 310 of the wearable device 302 is configured to combine the filtered output signals to detect the user's voice or speech. In other words, vibrations of the user's head and / or neck detected by the accelerometer 326 are correlated with the sound captured by the microphone 324 to improve the accuracy of speech detection. The combined filtered output signal is transmitted to a destination via wired or wireless communication. The destination may include another wearable device performing speech recognition, another vehicle, and / or a software application or server.

[0090] It should be understood that in some embodiments, sound transmitted through the user's head may cause distortion of the accelerometer signal at high frequencies; therefore, the audio quality of the accelerometer signal may be more representative at low frequencies. In such embodiments, the communication system may process the signal from the accelerometer separately from the audio output signal from the microphone to detect user speech in the low-frequency range (e.g., 150 Hz to 1.5 kHz). Furthermore, in such embodiments, method 400 (i.e., using the output signals from the accelerometer and the microphone) may be performed to detect user speech in the higher speech conversation range, such as 1.5 kHz to 4 kHz.

[0091] Now for reference Figure 5A computer-implemented method 500 for noise cancellation of audio data is illustrated. In an exemplary embodiment, method 500 is performed by a communication system (e.g., communication system 130 of recreational vehicle 100 or communication system 130 of helmet 302). In block 502, the communication system receives or acquires audio data in real-time or near real-time. It should be understood that the audio data can be collected via a microphone configured to capture a user's voice or speech. Figure 1 In the example of the recreational vehicle 100 shown, a microphone 118 mounted on the recreational vehicle 100 is configured to capture the voice of a user (e.g., rider / driver) while riding in the recreational vehicle 100. Similarly, in Figure 3 In the example of helmet 302 shown, microphones 324 of one or more helmets 302, which may be located or mounted inside or outside the helmet 302, are configured to capture user (e.g., wearer) voice while riding a recreational vehicle (e.g., recreational vehicle 100). Therefore, in addition to user voice, the microphones will inevitably capture noise (e.g., engine noise, road noise, wind noise).

[0092] To reduce unwanted ambient noise in the audio data captured from the microphone, the communication system is configured to execute a noise processing algorithm to remove unwanted ambient noise from the audio data, as shown in box 504. Unwanted ambient noise can be predictable or unpredictable. Predictable noise may include engine noise based on the engine status of the recreational vehicle the user is currently riding, while unpredictable noise may include road noise, wind noise, and / or any other ambient noise captured during riding.

[0093] In block 506, the communication system removes predictable noise from the audio data based on current vehicle information of the recreational vehicle the user is currently riding in. Current vehicle information includes the type / model / brand of the recreational vehicle, a vehicle noise profile associated with the recreational vehicle, and the current or near-real-time state of the recreational vehicle's engine. The current engine state includes any current state of engine parameters, such as engine phase, engine speed, transmission gear, clutch position, throttle position, and wheel speed of the recreational vehicle. It should be understood that the vehicle noise profile is generated based on known engine parameters (e.g., engine phase, engine speed, transmission gear, clutch position, throttle position, and wheel speed) of a corresponding or similar recreational vehicle.

[0094] In other words, based on the current state of the recreational vehicle's engine, the communication system can predict what the expected noise will be. This allows the communication system to eliminate sudden noise generated by the vehicle that may not otherwise be manifested as noise. It should be understood that, in the exemplary embodiment, a vehicle noise profile is pre-loaded onto the communication system before audio data is received. However, in some embodiments, the vehicle noise profile can be obtained in real time.

[0095] Subsequently or simultaneously, in block 508, the communication system also removes unpredictable noise from the audio data. For this purpose, the communication system may, for example, utilize a moving average filter to determine noise by collecting audio data over a predetermined time period and averaging the audio data. For example, the communication system may utilize a four-second window filter to collect data, calculate what the noise is, and remove the noise from the collected data in the next time window. However, since the noise is determined based on the previous time window, it may not respond to sudden changes (e.g., noise generated by sudden acceleration). Therefore, the communication system utilizes a vehicle noise profile to identify and eliminate sudden noises generated by the vehicle, as described above. It should be understood that in some embodiments, the communication system may execute block 508 before executing block 506.

[0096] Once unwanted ambient sounds have been removed or eliminated from the audio data, the communication system outputs the processed audio data along with the user's voice or speech, as shown in box 510. The improved noise cancellation performance of the communication system allows users to communicate with recreational vehicles using voice commands. It can also be used for telephone conversations and / or long-distance radio conversations.

[0097] The foregoing description, embodiments, and data provide a complete description of the manufacture and use of the components of this invention. Since many embodiments of the invention can be arranged without departing from the spirit and scope of the invention, the invention is subject to the appended claims.

Claims

1. A recreational vehicle, comprising: Frame; The front grounding member and the rear grounding member support the vehicle frame; A power system, which is drivenly connected to one of the front grounding member and the rear grounding member; A steering assembly, connected to the front grounding member, for steering the recreational vehicle; Seat, the seat being supported by the vehicle frame; as well as A communication system having a microphone located between the seat and the steering assembly along a direction from the front grounding member to the rear grounding member, the communication system including a processor and a memory, the memory including instructions that, when executed by the processor, cause the processor to: Audio data, including the user's voice, is received via microphone; The audio data is processed based on the current vehicle information of the recreational vehicle to remove predictable noise, wherein the current vehicle information includes the type, model and / or brand of the recreational vehicle, a vehicle noise profile generated based on engine parameters, and the current state of the recreational vehicle's engine, wherein the engine parameters include engine phase, engine speed, transmission gear, clutch position, throttle position, and wheel speed. Remove unpredictable noise from the audio data; as well as Output the processed audio data. The predictable noise includes engine noise based on the engine status of the recreational vehicle the user is riding in, and The unpredictable noise includes road noise and / or wind noise.

2. The recreational vehicle of claim 1, further comprising a fuel tank supported by the frame and located between the seat and the steering assembly, wherein, The microphone is mounted on top of the fuel tank.

3. The recreational vehicle of claim 1, further comprising an air box supported by the frame and located between the seat and the steering assembly, wherein, The microphone is mounted on top of the air box.

4. The recreational vehicle according to claim 1, wherein, The steering assembly also includes a front fairing and a user handle, with the microphone located behind the front fairing and below the user handle to reduce airflow contact with the microphone.

5. The recreational vehicle according to claim 1, wherein, The microphone is installed at an angle, facing upwards toward the user of the recreational vehicle, in order to reduce exhaust noise and / or engine noise.

6. A communication system for noise processing, the communication system comprising: processor; as well as The memory includes instructions that, when executed by the processor, cause the processor to: Audio data, including the user's voice, is received via microphone; The audio data is processed based on the current vehicle information of the user's recreational vehicle to remove predictable noise, wherein the current vehicle information includes the type, model and / or brand of the recreational vehicle, a vehicle noise profile generated based on engine parameters, and the current state of the recreational vehicle's engine, wherein the engine parameters include engine phase, engine speed, transmission gear, clutch position, throttle position, and wheel speed. Remove unpredictable noise from the audio data; as well as Output processed audio data. The predictable noise includes engine noise based on the engine status of the recreational vehicle the user is riding in, and The unpredictable noise includes road noise and / or wind noise.

7. The communication system according to claim 6, wherein, The microphone is mounted on the recreational vehicle.

8. The communication system according to claim 6, wherein, The microphone is installed on the user's wearable device.

9. The communication system according to claim 6, wherein, The current state of the engine of the recreational vehicle includes any current state of the engine parameters.

10. The communication system according to claim 6, wherein, Removing unpredictable noise includes using a moving average filter to remove the unpredictable noise from the audio data.

11. A method for noise processing, the method comprising: Audio data, including the user's voice, is received via microphone; The audio data is processed based on the current vehicle information of the user's recreational vehicle to remove predictable noise, wherein the current vehicle information includes the type, model and / or brand of the recreational vehicle, a vehicle noise profile generated based on engine parameters, and the current state of the recreational vehicle's engine, wherein the engine parameters include engine phase, engine speed, transmission gear, clutch position, throttle position, and wheel speed. Remove unpredictable noise from the audio data; as well as Output processed audio data. The predictable noise includes engine noise based on the state of the engine of the recreational vehicle the user is riding in, and The unpredictable noise includes road noise and / or wind noise.

12. The method according to claim 11, wherein, The microphone is mounted on the recreational vehicle.

13. The method according to claim 11, wherein, The microphone is installed on the user's wearable device.

14. The method according to claim 11, wherein, The current state of the engine of the recreational vehicle includes any current state of the engine parameters.

15. The method according to claim 11, wherein, Removing unpredictable noise includes using a moving average filter to remove the unpredictable noise from the audio data.

Images