Methods, systems, electronic devices, and media for processing alert sounds in intelligent driving vehicles.

Abstract

The application discloses a processing method and system of an intelligent driving vehicle prompt sound, electronic equipment and a medium, and comprises the following steps: S1: inputting a to-be-recognized sound into a timbre recognition module; S2: the timbre recognition module judges whether the input to-be-recognized sound is an alarm sound, if the to-be-recognized sound is an alarm sound, executing step S5, if the to-be-recognized sound is a non-alarm sound, executing step S3; S3: inputting the non-alarm sound into a first equalizer for first audio filtering; S4: inputting the non-alarm sound filtered by the first audio into a second equalizer for second audio filtering; S5: outputting the alarm sound in step S2 and the non-alarm sound filtered by the second audio in step S4 through an audio player. The application reduces the sound intensity of the non-alarm sound through the equalizer, distinguishes the non-alarm sound from the alarm prompt sound, and makes the alarm prompt sound more prominent and easy to distinguish.

Description

Technical Field

[0001] This invention relates to the field of sound control technology, specifically to methods, systems, electronic devices, and media for processing prompt sounds in intelligent driving vehicles. Background Technology

[0002] With the rapid development of the automotive industry, integrated intelligent driving assistance systems are becoming increasingly complex. Consequently, when system failures or hardware malfunctions lead to safety issues, drivers are prompted to take over vehicle control. According to the automotive intended functional safety standard ISO 21448, a whole-vehicle intended functional safety analysis reveals that drivers often use navigation, play music, or listen to the radio while driving. Certain frequency bands can easily cause auditory fatigue and reduce the driver's sensitivity to human voices. When the same human voice is present as a warning takeover alert, the alert may not be prominent enough, preventing the driver from immediately recognizing the warning message. Summary of the Invention

[0003] In view of the shortcomings of the prior art described above, the present invention provides a method, system, electronic device and medium for processing the alarm sound of intelligent driving vehicles, which is used to solve the problem of auditory fatigue in the alarm sound of intelligent driving vehicles. When the alarm takeover alarm sound with the same human voice appears, the driver can obtain the alarm content more clearly.

[0004] To achieve the above effects, the technical solution of the present invention is as follows:

[0005] In a first aspect, the present invention provides a method for processing prompt sounds in intelligent driving vehicles, comprising the following steps:

[0006] S1: Input the sound to be recognized into the timbre recognition module;

[0007] S2: The timbre recognition module determines whether the input sound to be recognized is an alarm sound. If the sound to be recognized is an alarm sound, proceed to step S5; if the sound to be recognized is a non-alarm sound, proceed to step S3.

[0008] S3: Input non-alarm sounds to the first equalizer for first audio filtering;

[0009] S4: Non-alarm sounds after the first audio filter are input to the second equalizer for the second audio filter;

[0010] S5: The alarm sounds in step S2 and the non-alarm sounds after the second audio filter in step S4 are output through the audio player.

[0011] Furthermore, the determination of whether the input sound to be identified is an alarm sound by the timbre recognition module in step S2 is as follows: the timbre recognition module performs timbre recognition on the input sound to be identified and obtains the timbre recognition result. If the timbre recognition result is an alarm sound, then the sound to be identified is an alarm sound; if the timbre recognition result is a non-alarm sound, then the sound to be identified is a non-alarm sound.

[0012] Furthermore, in step S3, the first equalizer includes a first bandpass filter and a first proportional amplifier connected in sequence; the second equalizer includes a second bandpass filter and a second proportional amplifier connected in sequence; wherein, the timbre recognition module is connected to the first bandpass filter, the first proportional amplifier is connected to the second bandpass filter, and the second proportional amplifier is connected to the audio player.

[0013] Furthermore, the first bandpass filter only allows audio frequencies in the 2kHz-4kHz range to pass through.

[0014] Furthermore, both the first proportional amplifier and the second proportional amplifier have values ​​of [-1, 0].

[0015] Furthermore, step S4 specifically involves: the second equalizer performing a second audio filter on the non-alarm sounds after the first audio filter, allowing only the sound signals in the critical frequency band of the alarm prompt tone to pass through; the non-alarm sounds after the second audio filter are sound signals that only pass through the critical frequency band of the alarm prompt tone.

[0016] Furthermore, the frequencies of the non-alarm sounds are outside the ERB range of the alarm prompt audio frequency. The ERB calculation formula is as follows:

[0017]

[0018] Where ERB is measured in Hz; F C The frequency of the alarm tone, measured in kHz.

[0019] Secondly, the present invention provides a sound adjustment system, comprising a sound input module, a timbre recognition module, a first equalizer, a second equalizer, and a sound output module; wherein,

[0020] The sound input module is used to input the sound to be recognized into the timbre recognition module;

[0021] The timbre recognition module is used to determine whether the input sound to be recognized is an alarm sound. If the sound to be recognized is an alarm sound, it is input to the sound output module; if the sound to be recognized is a non-alarm sound, it is input to the first equalizer.

[0022] The first equalizer is used to input non-alarm sounds to the first equalizer for first audio filtering.

[0023] The second equalizer is used to perform a second audio filter on the non-alarm sounds after the first audio filter.

[0024] The sound output module is used to output alarm sounds and non-alarm sounds after secondary audio filtering.

[0025] Thirdly, the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute a method for processing intelligent driving vehicle prompt sounds through the computer program.

[0026] Fourthly, the present invention provides a computer-readable storage medium comprising a stored computer program, wherein the computer program, when executed, performs a method for processing prompts for intelligent driving vehicles.

[0027] When the vehicle enters intelligent driver mode, all non-alarm sounds will first pass through the sound adjustment device of this invention, using an equalizer to attenuate sounds in the 2kHz-4kHz range, reducing the intensity of sound in frequency bands that are prone to causing auditory fatigue for the driver. When the vehicle needs to issue an alarm, it will directly output an alarm prompt sound.

[0028] Compared with the prior art, the beneficial effects of the technical solution of the present invention are:

[0029] This invention reduces the sound intensity of non-alarm sounds from intelligent driving vehicles using an equalizer, thus distinguishing the non-alarm sounds from the alarm sounds and making the alarm sounds more prominent and easily distinguishable. Attached Figure Description

[0030] The accompanying drawings are for illustrative purposes only and should not be construed as limiting the invention. To better illustrate this embodiment, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual product dimensions. It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0031] Figure 1 A schematic diagram illustrating a method for processing prompt sounds in intelligent driving vehicles according to an embodiment of the present invention;

[0032] Figure 2 This is a schematic diagram of the sound adjustment system provided in an embodiment of the present invention;

[0033] Figure 3 This is a schematic diagram of the equalizer components provided in an embodiment of the present invention. Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0035] Before introducing the embodiments of this application, the relevant terms involved in the embodiments of this application are first explained as follows:

[0036] Bandpass filter: A filter that can pass frequency components within a certain frequency range, but attenuates frequency components in other ranges to a very low level, as opposed to the concept of bandstop filter.

[0037] An equalizer is an electronic device that can adjust the amplification of electrical signals at various frequencies. It compensates for deficiencies in speakers and sound fields, modifies various sound sources, and performs other special functions by adjusting electrical signals of different frequencies. Generally, equalizers on mixing consoles can only adjust the high-frequency, mid-frequency, and low-frequency electrical signals separately. The principle is to subtract a specific ratio signal from the original signal using a bandpass filter.

[0038] The critical band, characterizing the most important auditory characteristic of humans, was discovered during the study of the masking effect of pure tones on narrow-band noise. When widening the noise bandwidth, the masking effect initially increases, but after the bandwidth exceeds a certain value, the masking effect no longer increases; this bandwidth is called the critical band. The critical bandwidth can be equivalent to the equivalent rectangular bandwidth (ERB). Auditory critical band: When noise masks a pure tone, the noise frequencies within a certain bandwidth centered on the pure tone frequency take effect. If the noise power within this band is equal to the power of the pure tone that is just audible within the noise, then this band is called the auditory critical band.

[0039] ERB, or equivalent rectangular bandwidth, is an acoustic metric.

[0040] The center frequency is the geometric mean of the frequencies of the bandpass filter (or bandstop filter).

[0041] Timbre refers to the unique characteristics of different sounds in terms of waveform; different objects vibrate with different characteristics. The healthy human ear has a very strong ability to distinguish frequencies; the human ear's auditory bandwidth is 20–20kHz, with the strongest frequency resolution around 1kHz–3kHz.

[0042] Example

[0043] For easier understanding, please refer to Figure 1 This invention provides a method for processing prompt sounds in intelligent driving vehicles, comprising the following steps:

[0044] S1: Input the sound to be recognized into the timbre recognition module;

[0045] S2: The timbre recognition module determines whether the input sound to be recognized is an alarm sound. If the sound is an alarm sound, proceed to step S5; if the sound is not an alarm sound, proceed to step S3. The specific steps are as follows:

[0046] The timbre recognition module performs timbre recognition on the input sound to be recognized and obtains the timbre recognition result. If the timbre recognition result is an alarm timbre, then the sound to be recognized is an alarm timbre; if the timbre recognition result is a non-alarm timbre, then the sound to be recognized is a non-alarm timbre.

[0047] It is understandable that, based on the vehicle's alarm prompts, the vehicle's system prompts and navigation prompts are designed to be in different critical frequency bands from the alarm prompts, meaning that these regular prompts are considered non-alarm sounds.

[0048] S3: Input non-alarm sounds to the first equalizer for first audio filtering (i.e., filtering processing);

[0049] In this embodiment, as Figure 2 The first equalizer includes a first bandpass filter and a first proportional amplifier connected in sequence; the second equalizer includes a second bandpass filter and a second proportional amplifier connected in sequence; wherein, the timbre recognition module is connected to the first bandpass filter, the first proportional amplifier is connected to the second bandpass filter, and the second proportional amplifier is connected to the audio player.

[0050] The first bandpass filter only allows audio frequencies in the 2kHz-4kHz range to pass through.

[0051] In this configuration, both the first and second proportional amplifiers are set to values ​​of [-1, 0] to reduce sound intensity. Different amplifier ratios can be configured for different audio types, with a minimum amplifier value of -1 and a maximum value of 0. For example, navigation voices often have frequencies below 1.2kHz, so the amplifier ratio can be set lower to avoid affecting the navigation voices while minimizing frequency bands that cause auditory fatigue. When the input sound signal is music, the amplifier value can be set slightly higher to preserve more musical detail for a better driving experience while reducing driver auditory fatigue.

[0052] S4: Non-alarm sounds after the first audio filter are input to the second equalizer for the second audio filter; the specific steps are as follows:

[0053] The second equalizer uses a second bandpass filter to perform a second audio filter on the non-alarm sounds after the first audio filter, allowing only the sound signals in the critical frequency band of the alarm prompt tone to pass through; the non-alarm sounds after the second audio filter are sound signals that only pass through the critical frequency band of the alarm prompt tone.

[0054] Among them, the frequencies of non-alarm sounds are outside the ERB range of the alarm prompt audio frequency. The formula for calculating ERB is as follows:

[0055]

[0056] Where ERB is measured in Hz; F C The frequency of the alarm tone is measured in kHz. The frequency of the alarm tone is determined by the specific audio design of the vehicle model. The frequency value of the alarm tone is calculated by adding or subtracting ERBhz from the center of the alarm tone.

[0057] S5: The alarm sounds in step S2 and the non-alarm sounds after the second audio filter in step S4 are output through the audio player.

[0058] In another embodiment of the present invention, the present invention also provides a sound adjustment system, such as... Figure 3 It includes a sound input module, a timbre recognition module, a first equalizer, a second equalizer, and a sound output module; among which,

[0059] The sound input module is used to input the sound to be recognized into the timbre recognition module;

[0060] The timbre recognition module is used to determine whether the input sound to be recognized is an alarm sound. If the sound to be recognized is an alarm sound, it is input to the sound output module; if the sound to be recognized is a non-alarm sound, it is input to the first equalizer.

[0061] The first equalizer is used to perform first audio filtering on non-alarm-type sounds input to the first equalizer;

[0062] The second equalizer is used to perform a second audio filter on the non-alarm sounds after the first audio filter.

[0063] The sound output module is used to output alarm sounds and non-alarm sounds after secondary audio filtering.

[0064] Furthermore, in this embodiment, the sound adjustment system and audio player are integrated into the vehicle controller. The audio player is a vehicle speaker.

[0065] Furthermore, the vehicle speaker model described in this embodiment is: EDIFIER-R10U2.0.

[0066] Furthermore, in this embodiment, the timbre recognition module is an FPGA of the AT40K05-2BQC.

[0067] In another embodiment of the present invention, the present invention also provides an electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause a vehicle to implement the intelligent driving vehicle prompt tone processing method as described in any of the above embodiments.

[0068] In this embodiment, the computer system suitable for implementing the electronic device of the present invention includes a Central Processing Unit (CPU), which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) or a program loaded from storage into random access memory (RAM), such as performing the methods described in the above embodiments. Various programs and data required for system operation are also stored in RAM. The CPU, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0069] The following components are connected to the I / O interface: input sections including keyboards, mice, etc.; output sections including cathode ray tubes (CRTs), liquid crystal displays (LCDs), and speakers; storage sections including hard drives; and communication sections including network interface cards such as LAN (Local Area Network) cards and modems. The communication sections perform communication processing via networks such as the Internet. Drives are also connected to the I / O interface as needed. Removable media, such as disks, optical discs, magneto-optical discs, semiconductor memories, etc., are installed on the drive as needed so that computer programs read from them can be installed into the storage section as required.

[0070] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing computer programs for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), it performs various functions defined in the system of the present invention.

[0071] It should be noted that although several modules or units of the device for performing actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0072] In another embodiment of the present invention, a computer-readable storage medium is also provided, on which a computer program is stored. When the computer program is executed by a computer processor, the computer performs the intelligent driving vehicle prompt tone processing method as provided in any of the foregoing embodiments. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not incorporated into the electronic device.

[0073] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, portable hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the method according to the embodiments of the present invention.

[0074] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the implementation of the present invention. Those skilled in the art can make other variations or modifications based on the above description. It is neither necessary nor possible to exhaustively describe all embodiments here. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A method for processing prompt sounds in intelligent driving vehicles, characterized in that, Includes the following steps: S1: Input the sound to be recognized into the timbre recognition module; S2: The timbre recognition module determines whether the input sound to be recognized is an alarm sound. If the sound to be recognized is an alarm sound, proceed to step S5; if the sound to be recognized is a non-alarm sound, proceed to step S3. S3: Input non-alarm sounds to the first equalizer for first audio filtering; S4: Non-alarm sounds after the first audio filter are input to the second equalizer for the second audio filter; S5: The alarm sounds in step S2 and the non-alarm sounds after the second audio filter in step S4 are output through the audio player; The first equalizer includes a first bandpass filter and a first proportional amplifier connected in sequence; the second equalizer includes a second bandpass filter and a second proportional amplifier connected in sequence; the timbre recognition module is connected to the first bandpass filter, the first proportional amplifier is connected to the second bandpass filter, and the second proportional amplifier is connected to the audio player; the first bandpass filter only allows audio frequencies of 2kHz-4kHz to pass through, and the second equalizer performs second audio filtering on non-alarm sounds after the first audio filtering through the second bandpass filter, allowing only sound signals in the critical frequency band of the alarm prompt tone to pass through, and the non-alarm sounds after the second audio filtering are sound signals that only pass through the critical frequency band of the alarm prompt tone; the values ​​of the first proportional amplifier and the second proportional amplifier are in the range of [-1, 0], and the ratio of the first proportional amplifier configured when the input sound to be recognized is a navigation voice is less than the ratio of the first amplifier configured when the input sound signal is music.

2. The method for processing prompt sounds of intelligent driving vehicles according to claim 1, characterized in that, The specific steps of step S2, where the timbre recognition module determines whether the input sound to be recognized is an alarm sound, are as follows: the timbre recognition module performs timbre recognition on the input sound to be recognized and obtains the timbre recognition result. If the timbre recognition result is an alarm sound, then the sound to be recognized is an alarm sound; if the timbre recognition result is a non-alarm sound, then the sound to be recognized is a non-alarm sound.

3. The method for processing prompt sounds in an intelligent driving vehicle according to claim 1, characterized in that, The frequencies of the non-alarm sounds are outside the ERB range of the alarm prompt audio frequency. The ERB calculation formula is as follows: In this context, ERB is measured in Hz; FC is the sound frequency of the alarm tone, measured in kHz.

4. A sound adjustment system, applied to the processing method of intelligent driving vehicle prompt sounds as described in any one of claims 1 to 3, characterized in that, It includes a sound input module, a timbre recognition module, a first equalizer, a second equalizer, and a sound output module; among which, The sound input module is used to input the sound to be recognized into the timbre recognition module; The timbre recognition module is used to determine whether the input sound to be recognized is an alarm sound. If the sound to be recognized is an alarm sound, it is input to the sound output module; if the sound to be recognized is a non-alarm sound, it is input to the first equalizer. The first equalizer is used to input non-alarm sounds to the first equalizer for first audio filtering. The second equalizer is used to perform a second audio filter on the non-alarm sounds after the first audio filter. The sound output module is used to output alarm sounds and non-alarm sounds after secondary audio filtering.

5. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the intelligent driving vehicle prompt sound processing method according to any one of claims 1 to 3 through the computer program.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein the computer program, when executed, performs the intelligent driving vehicle prompt tone processing method according to any one of claims 1 to 3.

Images