Speech processing apparatus and method for two-wheeled electric vehicle, and two-wheeled electric vehicle

Abstract

A speech processing apparatus and method for a two-wheeled electric vehicle, and a two-wheeled electric vehicle. The speech processing apparatus for a two-wheeled electric vehicle is arranged in an instrument panel of a two-wheeled electric vehicle in front of a driver, and comprises a double-microphone array speech acquisition module (110) and a speech processing module (120); the double-microphone array speech acquisition module (110) is connected to the speech processing module (120), and is used for generating a digital speech signal on the basis of collected sound; and the speech processing module (120) identifies an effective speech signal and a noise signal on the basis of the digital speech signal, enhances the speech signal, and suppresses the noise signal. According to the present solution, by using the characteristics of the arrangement position of the apparatus and the characteristics of repeated pickup of sound in some areas during speech pickup of the double-microphone array speech acquisition module (110), the speech processing module (120) can quickly and accurately recognize effective speech signals and noise signals, enhances the effective speech signals, and suppresses the noise signals.

Description

Two-wheeled electric vehicle voice processing device, method and two-wheeled electric vehicle Technical Field

[0001] The embodiments of the present invention relate to the technical field of voice interaction for two-wheeled electric vehicles, and more particularly to a voice processing device and method for a two-wheeled electric vehicle and a two-wheeled electric vehicle. Background Art

[0002] With technological advancements, two-wheeled electric vehicles are becoming more intelligent, convenient, and differentiated. Human-machine interaction in electric two-wheeled vehicles is gradually transitioning from traditional button-based interaction to touch and voice interaction. For rider convenience and safety, voice calls are also being integrated into the instrumentation systems of electric two-wheeled vehicles. However, the world we live in is filled with noise, and useful voice information is often obscured by various noise signals, making it difficult for electric two-wheeled vehicles to accurately recognize valid speech.

[0003] Summary of the Invention

[0004] The embodiments of the present invention provide a two-wheeled electric vehicle speech processing device, method and two-wheeled electric vehicle, so as to enhance effective speech signals and suppress noise signals so that the two-wheeled electric vehicle cannot accurately recognize effective speech.

[0005] In a first aspect, an embodiment of the present invention provides a two-wheeled electric vehicle voice processing device, which is arranged in the dial of the two-wheeled electric vehicle directly in front of the driver; the two-wheeled electric vehicle voice processing device includes a dual-microphone array voice acquisition module and a voice processing module;

[0006] The dual-microphone array voice acquisition module is connected to the voice processing module. The dual-microphone array voice acquisition module is used to generate a digital voice signal based on the collected sound. The voice processing module identifies the valid voice signal and the noise signal based on the digital voice signal, and enhances the valid voice signal and suppresses the noise signal.

[0007] Optionally, the dual-microphone array voice acquisition module includes two analog microphones arranged on the same horizontal line, an analog-to-digital conversion unit, and a pull-up unit;

[0008] Each of the analog microphones is respectively connected to the analog-to-digital conversion unit and the pull-up unit, and the analog-to-digital conversion unit is connected to the voice processing module; the analog microphone is used to generate an analog voice signal based on the acquired sound, the analog-to-digital conversion unit is used to convert the analog voice signal into the digital voice signal, and the pull-up unit is used to pull up the potential of the analog microphone.

[0009] Optionally, the analog-to-digital conversion unit includes a PCM1808 stereo audio analog-to-digital converter;

[0010] The distance between the two simulated microphones arranged on the same horizontal line is 3 cm-16 cm.

[0011] Optionally, the analog microphone includes an electret condenser microphone, a first electrostatic diode and a second electrostatic diode;

[0012] The first end of the electret condenser microphone and the first pole of the first electrostatic diode are both connected to the pull-up unit and the analog-to-digital conversion unit, the second end of the electret condenser microphone is connected to the first pole of the second electrostatic diode, and the second pole of the first electrostatic diode and the second pole of the second electrostatic diode are grounded.

[0013] Optionally, the dual-microphone array voice acquisition module includes two digital microphones arranged on the same horizontal line;

[0014] Each of the digital microphones is connected to the voice processing module, and the digital microphone is used to generate a digital voice signal according to the acquired sound.

[0015] Optionally, the distance between the two digital microphones arranged on the same horizontal line is 3 cm-16 cm.

[0016] Optionally, the voice processing module includes a digital signal processor model NR2048.

[0017] In a second aspect, an embodiment of the present invention further provides a two-wheeled electric vehicle, which includes the two-wheeled electric vehicle voice processing device provided by any embodiment of the present invention.

[0018] In a third aspect, an embodiment of the present invention further provides a two-wheeled electric vehicle voice processing method, which is executed by a two-wheeled electric vehicle voice processing device provided by any embodiment of the present invention, and the two-wheeled electric vehicle voice processing method includes:

[0019] Generate digital voice signals based on the collected sounds;

[0020] An effective speech signal and a noise signal are identified according to the digital speech signal, and the speech signal is enhanced and the noise signal is suppressed.

[0021] Optionally, the identifying a valid voice signal and a noise signal according to the digital voice signal, and enhancing the voice signal and suppressing the noise signal to obtain a noise-reduced voice signal includes:

[0022] Performing spectrum analysis on the digital voice signal to obtain a first spectrum and a second spectrum;

[0023] determining an overlapping spectrum and a non-overlapping spectrum according to the first spectrum and the second spectrum;

[0024] The digital speech signal corresponding to the non-overlapping spectrum is the noise signal, and noise reduction processing is performed on most noise signals;

[0025] The digital speech signal corresponding to the overlapping spectrum is the effective speech signal, and enhancement processing and self-noise suppression processing are performed on the effective speech signal.

[0026] The speech processing device for a two-wheeled electric vehicle, provided by an embodiment of the present invention, leverages its inherent location and the fact that the dual-microphone array speech acquisition module picks up repetitive sounds in certain areas. This ensures that digital speech signals containing valid speech have repetitive characteristics, while digital speech signals containing noise have non-repetitive characteristics. Consequently, the speech processing module can quickly and accurately distinguish valid speech signals from noise signals based on whether the digital speech signals are repetitive, enhancing the valid speech signals and suppressing the noise signals. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0028] FIG1 is a schematic structural diagram of a speech processing device for a two-wheeled electric vehicle provided by an embodiment of the present invention;

[0029] FIG2 is a schematic structural diagram of a voice pickup range of a dual-microphone array voice acquisition module provided by an embodiment of the present invention;

[0030] FIG3 is a schematic structural diagram of another two-wheeled electric vehicle voice processing device provided by an embodiment of the present invention;

[0031] FIG4 is a schematic diagram of a circuit structure of a pull-up unit provided in an embodiment of the present invention;

[0032] FIG5 is a schematic diagram of a circuit structure of an analog microphone provided by an embodiment of the present invention;

[0033] FIG6 is a schematic structural diagram of another two-wheeled electric vehicle voice processing device provided by an embodiment of the present invention;

[0034] FIG7 is a flow chart of a method for processing speech in a two-wheeled electric vehicle according to an embodiment of the present invention;

[0035] FIG8 is a flowchart illustrating steps of identifying a valid speech signal and a noise signal based on a digital speech signal, enhancing the speech signal, and suppressing the noise signal, provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0036] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0037] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0038] Currently, two-wheeled electric vehicles operate outdoors, and there is noise in all directions around them, which makes them unable to identify the direction of useful voice signals. To address this problem, the two-wheeled electric vehicle voice processing device provided by this solution can distinguish between effective voice and noise, thereby specifically enhancing the effective voice signal and suppressing the noise signal.

[0039] Figure 1 is a structural schematic diagram of a two-wheeled electric vehicle voice processing device provided by an embodiment of the present invention. As shown in Figure 1, the two-wheeled electric vehicle voice processing device is arranged in the dial of the two-wheeled electric vehicle directly in front of the driver; the two-wheeled electric vehicle voice processing device includes a dual-microphone array voice acquisition module 110 and a voice processing module 120.

[0040] The dual-microphone array voice acquisition module 110 is connected to the voice processing module 120. The dual-microphone array voice acquisition module 110 is used to generate a digital voice signal based on the collected sound. The voice processing module 120 identifies the valid voice signal and the noise signal based on the digital voice signal, and enhances the valid voice signal and suppresses the noise signal.

[0041] The dual-microphone array voice acquisition module 110 can collect sounds from the external environment and convert them into digital voice signals. The sounds from the external environment include ambient noise and user voices. Some of the sounds picked up by the dual-microphone array voice acquisition module 110 are repeated sounds from the same area. This solution utilizes this characteristic of the dual-microphone array voice acquisition module 110 in picking up voices to assist in distinguishing valid voice from noise. The voice processing module 120 can filter out repeated digital voice signals and non-repeated digital voice signals based on the digital voice signals, thereby distinguishing valid voice signals from noise signals based on the repeated digital voice signals and non-repeated digital voice signals, and enhance the valid voice signals and filter out the noise signals.

[0042] FIG2 is a structural diagram of the voice pickup range of a dual-microphone array voice acquisition module provided by an embodiment of the present invention. As shown in FIG2 , the sound in area ① is the repeated voice picked up by the dual-microphone array voice acquisition module 110, and the sound in area ② and area ③ are the non-repeated voices picked up by the dual-microphone array voice acquisition module 110. Since the dual-microphone array voice acquisition module 110 is set in the dial of the two-wheeled electric vehicle, and the dial of the two-wheeled electric vehicle is directly in front of the driver, the driver will be in area ① where the dual-microphone array voice acquisition module 110 repeatedly picks up voices. Obviously, the voice processing module 120 filters out the repeated digital voice signals according to the digital voice signals, including valid voice signals, and the non-repeated digital voice signals including noise signals. Therefore, the voice processing module 120 can quickly identify the valid voice signals and the noise signals according to the characteristics of whether the digital voice signals are repeated, and perform enhancement processing on the valid voice signals and suppression processing on the noise signals.

[0043] The two-wheeled electric vehicle voice processing device provided by the present invention utilizes the unique positioning of its own device and the characteristic of partial repetition of sound picked up by the dual-microphone array voice acquisition module 110. This ensures that digital voice signals containing valid speech have repetitive characteristics, while digital voice signals containing noise have non-repetitive characteristics. Consequently, the voice processing module 120 can quickly and accurately distinguish valid and noise signals based on whether the digital voice signals are repetitive, and perform enhancement processing on the valid voice signals and suppression processing on the noise signals.

[0044] FIG3 is a schematic structural diagram of another two-wheeled electric vehicle voice processing device provided by an embodiment of the present invention. As shown in FIG3 , the dual-microphone array voice acquisition module 110 includes two analog microphones 111 arranged on the same horizontal line, an analog-to-digital conversion unit 112, and a pull-up unit 113;

[0045] Each analog microphone 111 is connected to an analog-to-digital conversion unit 112 and a pull-up unit 113 respectively, and the analog-to-digital conversion unit 112 is connected to the voice processing module 120; the analog microphone 111 is used to generate an analog voice signal based on the acquired sound, the analog-to-digital conversion unit 112 is used to convert the analog voice signal into a digital voice signal, and the pull-up unit 113 is used to pull up the potential of the analog microphone 111.

[0046] Figure 4 is a schematic diagram of the circuit structure of a pull-up unit provided in an embodiment of the present invention. As shown in Figure 4, the pull-up unit 113 includes a first resistor R1, a second resistor R2, a third resistor R3 and a capacitor C; wherein, the first end of the first resistor R1 is connected to one analog microphone 111, the first end of the second resistor R2 is connected to another analog microphone 111, the second end of the first resistor R1, the second end of the second resistor R2, the first end of the third resistor R3 and the first end of the capacitor C are connected, the second end of the third resistor R3 is connected to a high potential (for example, 3.3V), and the second end of the capacitor C is grounded.

[0047] The analog microphone 111 pulls up the potential through the pull-up unit 113, which can amplify and enhance the analog voice signal converted from sound by the analog microphone 111, thereby facilitating the analog-to-digital conversion unit 112 to accurately identify the electrical signal converted from sound.

[0048] The analog-to-digital conversion unit 112 includes a stereo audio analog-to-digital converter of model PCM1808; the distance between the two analog microphones 111 arranged on the same horizontal line is 3 cm-16 cm.

[0049] Among them, if the distance between two analog microphones 111 set on the same horizontal line is less than 3cm, the voice pickup overlapping area between the two analog microphones 111 set on the same horizontal line is too large, which will lead to a decrease in the recognition rate of effective voice, even if the two-wheeled electric vehicle voice processing device cannot recognize effective voice signals and noise signals. If the distance between two analog microphones 111 set on the same horizontal line is greater than 16cm, it will cause the two analog microphones 111 set on the same horizontal line to be unable to pick up effective voice. Therefore, the distance between the two analog microphones 111 set on the same horizontal line is 3cm-16cm.

[0050] It should be noted that the distance between two analog microphones 111 set on the same horizontal line is related to the voice pickup range of each analog microphone 111, and the distance between two analog microphones 111 set on the same horizontal line is also related to the distance between the driver and each analog microphone 111 along the horizontal plane (the distance between the driver and the dial of the two-wheeled electric vehicle along the horizontal plane).

[0051] FIG5 is a schematic diagram of a circuit structure of an analog microphone provided by an embodiment of the present invention. As shown in FIG5 , the analog microphone 111 includes an electret condenser microphone M, a first electrostatic diode D1 and a second electrostatic diode D2;

[0052] The first end of the electret condenser microphone M and the first pole of the first electrostatic diode D1 are both connected to the pull-up unit 113 and the analog-to-digital conversion unit 112, the second end of the electret condenser microphone M is connected to the first pole of the second electrostatic diode D2, and the second pole of the first electrostatic diode D1 and the second pole of the second electrostatic diode D2 are grounded.

[0053] The second ends of the two electret condenser microphones M are connected to a common ground. The electret condenser microphones M can collect ambient sound and convert it into an analog voice signal. Both the first and second electrostatic diodes D1 and D2 have an anti-static function, preventing static electricity from entering the electret condenser microphones M.

[0054] Figure 6 is a structural schematic diagram of another two-wheeled electric vehicle voice processing device provided by an embodiment of the present invention. As shown in Figure 6, the dual-microphone array voice acquisition module 110 includes two digital microphones 114 arranged on the same horizontal line; each digital microphone 114 is connected to the voice processing module 120, and the digital microphone 114 is used to generate a digital voice signal based on the acquired sound.

[0055] The distance between two digital microphones 114 disposed on the same horizontal line is 3 cm-16 cm.

[0056] If the distance between two analog microphones 111 arranged on the same horizontal line is less than 3 cm, the overlapping area of ​​voice pickup between the two analog microphones 111 arranged on the same horizontal line will be too large, which will result in a reduced recognition rate of effective voice, even if the two-wheeled electric vehicle voice processing device cannot recognize effective voice signals and noise signals. If the distance between two analog microphones 111 arranged on the same horizontal line is greater than 16 cm, the two analog microphones 111 arranged on the same horizontal line will not be able to pick up effective voice. Therefore, the distance between the two analog microphones 111 arranged on the same horizontal line is 3 cm-16 cm.

[0057] It should be noted that the analog microphone 111 is more cost-effective than the digital microphone 114 , and the analog microphone 111 is preferably used in this solution.

[0058] Optionally, the voice processing module 120 includes a digital signal processor model NR2048.

[0059] Among them, the NR2048 digital signal processor integrates advanced voice processing technology. The NR2048 digital signal processor has a built-in dual-core digital signal processor (DSP) subsystem and a hardware computing accelerator, which can improve the clarity of voice calls in noisy environments and help improve voice recognition command input. In addition, the NR2048 digital signal processor has advanced dual-microphone array pickup beam forming technology, which can track the caller's voice, filter out unwanted background noise, and provide clear conversations for users in any environment. The NR2048 digital signal processor also provides noise suppression, acoustic echo cancellation (AEC) and other voice enhancement functions for adaptive handheld and hands-free communications. The NR2048 digital signal processor also contains specific processing modules to increase the voice recognition rate (VR) rate and improve noisy voice recording environments.

[0060] In summary, the two-wheeled electric vehicle voice processing device can filter out conventional steady-state regular noise, and at the same time can also filter out non-steady-state irregular noise outside the regional sound pickup beam range.

[0061] An embodiment of the present invention further provides a two-wheeled electric vehicle, which includes the two-wheeled electric vehicle voice processing device provided by any embodiment of the present invention. Therefore, the beneficial effects of the two-wheeled electric vehicle voice processing device provided by any embodiment of the present invention are included and will not be repeated here.

[0062] In addition, the control chip of the electric vehicle instrument display can configure the status of the voice processing module (NR2048 digital signal processor has a built-in dual-core digital signal processor (DSP) subsystem) through IIC communication, thereby controlling the voice processing module to switch between three working states: noise suppression, voice enhancement, and echo cancellation, so that the two-wheeled electric vehicle can be suitable for different scenarios.

[0063] Figure 7 is a flow chart of a method for processing speech in a two-wheeled electric vehicle provided by an embodiment of the present invention. The method is executed by a two-wheeled electric vehicle speech processing device provided by any embodiment of the present invention. The specific steps of the method include:

[0064] S110: Generate a digital voice signal based on the collected sound.

[0065] S120 . Identify a valid voice signal and a noise signal according to the digital voice signal, enhance the voice signal, and suppress the noise signal.

[0066] The two-wheeled electric vehicle speech processing method provided by an embodiment of the present invention is executed by the two-wheeled electric vehicle speech processing device provided by any embodiment of the present invention. As a result, the collected sound generates a digital speech signal containing valid speech that has a repetitive characteristic, while the digital speech signal containing noise has a non-repetitive characteristic. This allows for rapid and accurate identification of valid speech signals from noise signals based on whether the digital speech signals are repetitive, and enhances the valid speech signals while processing the noise signals.

[0067] Based on the above embodiment, optionally, FIG8 is a flowchart of the steps of identifying a valid voice signal and a noise signal according to a digital voice signal, enhancing the voice signal, and suppressing the noise signal according to an embodiment of the present invention, further explaining the steps of identifying a valid voice signal and a noise signal according to a digital voice signal, enhancing the voice signal, and suppressing the noise signal:

[0068] S210 , performing spectrum analysis on the digital voice signal to obtain a first spectrum and a second spectrum.

[0069] S220: Determine an overlapping spectrum and a non-overlapping spectrum according to the first spectrum and the second spectrum.

[0070] S230 , the digital speech signals corresponding to the non-overlapping frequency spectra are noise signals, and noise reduction processing is performed on the majority of the noise signals.

[0071] S240 , the digital speech signal corresponding to the overlapping spectrum is a valid speech signal, and enhancement processing and self-noise suppression processing are performed on the valid speech signal.

[0072] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0073] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A voice processing device for a two-wheel electric vehicle, characterized in that The voice processing device of the two-wheeled electric vehicle is arranged in the instrument panel of the two-wheeled electric vehicle directly in front of the driver; The voice processing device of the two-wheeled electric vehicle includes a dual-microphone array voice acquisition module and a voice processing module; The dual-microphone array voice acquisition module is connected to the voice processing module. The dual-microphone array voice acquisition module is used to generate a digital voice signal according to the collected sound, and the voice processing module identifies the valid voice signal and the noise signal according to the digital voice signal, and enhances the valid voice signal and suppresses the noise signal.

2. The voice processing device for a two-wheeled electric vehicle according to claim 1, wherein The dual-microphone array voice acquisition module includes two analog microphones arranged on the same horizontal line, an analog-to-digital conversion unit and a pull-up unit; Each of the analog microphones is respectively connected to the analog-to-digital conversion unit and the pull-up unit, and the analog-to-digital conversion unit is connected to the voice processing module; the analog microphone is used to generate an analog voice signal according to the acquired sound, the analog-to-digital conversion unit is used to convert the analog voice signal into the digital voice signal, and the pull-up unit is used to raise the potential of the analog microphone.

3. The voice processing device for a two-wheel electric vehicle according to claim 2, wherein The analog-to-digital conversion unit includes a stereo audio analog-to-digital converter with the model PCM1808; The distance between the two analog microphones arranged on the same horizontal line is 3 cm - 16 cm.

4. The voice processing device for a two-wheeled electric vehicle according to claim 2, wherein, The analog microphone includes an electret condenser microphone, a first electrostatic diode and a second electrostatic diode; The first end of the electret condenser microphone and the first pole of the first electrostatic diode are both connected to the pull-up unit and the analog-to-digital conversion unit, the second end of the electret condenser microphone is connected to the first pole of the second electrostatic diode, and the second pole of the first electrostatic diode and the second electrostatic diode are grounded together.

5. The voice processing device for a two-wheel electric vehicle according to claim 1, characterized in that, The dual-microphone array voice acquisition module includes two digital microphones arranged on the same horizontal line; Each of the digital microphones is connected to the voice processing module, and the digital microphone is used to generate a digital voice signal according to the acquired sound.

6. The voice processing device for a two-wheeled electric vehicle according to claim 5, wherein, The distance between the two digital microphones arranged on the same horizontal line is 3 cm - 16 cm.

7. The voice processing device for a two-wheeled electric vehicle according to claim 1, characterized in that The voice processing module includes a digital signal processor with the model NR2048.

8. A two-wheeled electric vehicle, characterized in that, It includes the voice processing device of the two-wheeled electric vehicle according to any one of claims 1-7.

9. A voice processing method for a two-wheeled electric vehicle, which is executed by the two-wheeled electric vehicle voice processing device according to any one of claims 1-7, characterized in that, It includes: Generating a digital voice signal according to the collected sound; Identifying the valid voice signal and the noise signal according to the digital voice signal, and enhancing the voice signal and suppressing the noise signal.

10. The voice processing method for a two-wheeled electric vehicle according to claim 9, characterized in that, The identifying the valid voice signal and the noise signal according to the digital voice signal, and enhancing the voice signal and suppressing the noise signal includes: Performing spectral analysis on the digital voice signal to obtain a first spectrum and a second spectrum; Determining an overlapping spectrum and a non-overlapping spectrum according to the first spectrum and the second spectrum; The digital voice signal corresponding to the non-overlapping spectrum is the noise signal, and noise reduction processing is performed on most of the noise signals ; The digital voice signal corresponding to the overlapping spectrum is the valid voice signal, and enhancement processing and self-noise suppression processing are performed on the valid voice signal.

Images