System for improving accuracy of sound heard by hearing impaired audience and hearing aid sound box
Patent Information
- Application Number
- CN202410563563.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-08
- Publication Date
- 2024-12-06
AI Technical Summary
The existing hearing aid system has poor effect, noise problems, and hearing aids are uncomfortable to wear, high prices, and frequent fitting, resulting in low usage rate for people with hearing loss.
A system including voice pickup module, processor, frequency shift module, dynamic compression module, clamor suppression module, adaptive noise reduction module, boom suppression module and wind noise reduction module were designed. Through frequency shift and dynamic compression, Adaptive noise reduction and noise suppression technology improves sound clarity and accuracy.
Effectively eliminate whistling and sudden sounds, reduce wind noise, improve hearing-impaired persons' ability to recognize sounds, reduce wear discomfort, and adapt to multi-scene environments.
Smart Images

Figure CN119094964A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of hearing aids, and in particular, to a system and a hearing aid speaker for improving the accuracy of sound heard by hearing-impaired listeners. Background Art
[0002] Hearing problems are a major public health issue facing the world. The World Hearing Report released by the World Health Organization (WHO) in March 2021 shows that hearing loss currently affects more than 1.5 billion people worldwide, of which 430 million people have moderate or higher hearing loss in their better hearing ears; it is estimated that by 2050, a quarter of the world's population will have hearing problems, nearly 2.5 billion people will suffer from some degree of hearing loss, and at least 700 million people will need hearing rehabilitation services. Hearing aids are an effective auxiliary means to solve hearing loss, but only 17% of people who can benefit from hearing aids actually use them. The main reasons are high prices, complicated fitting, and inconvenient wearing.
[0003] In addition, the existing hearing aid system has poor hearing aid effect, has certain noise, and cannot shield some sudden sounds, causing troubles to listeners with hearing impairment. Therefore, it needs to be improved. In addition, there is currently no product called hearing aid speakers, and hearing aids can cause discomfort after wearing for a long time. Summary of the invention
[0004] The purpose of the embodiments of the present application is to provide a system and a hearing-aid speaker that improves the accuracy of sound heard by hearing-impaired listeners, which can solve the above-mentioned technical problems.
[0005] The embodiment of the present application provides a system for improving the accuracy of hearing impaired listeners hearing sound, including a voice pickup module, a processor, a frequency shift module, a dynamic compression module, a shouting suppression module, an adaptive noise reduction module, a sudden sound suppression module, a wind noise reduction module and a microphone, wherein the voice pickup module is used to pick up the sound of the current environment and send the sound to the processor; the processor is used to detect and identify the sound and send the identified sound to the frequency shift module; the frequency shift module is used to shift the frequency of vowels and high-frequency consonants in the sound to a reasonable frequency band and send it to the dynamic compression module; the dynamic compression module The module compresses the frequency-shifted sound appropriately according to the compression ratio based on the preset audiogram, and sends it to the shouting suppression module; the shouting suppression module is used to adaptively eliminate the howling sound generated, and sends it to the adaptive noise reduction module, the adaptive noise reduction module dynamically distinguishes between speech and noise according to ANR, reduces fixed noise in different frequency bands, and sends it to the sudden sound suppression module; the sudden sound suppression module is used to eliminate the burst sound in the environment and send it to the wind noise reduction module; the wind noise reduction module is used to reduce the wind noise frequency in the sound, and output the processed audio through the microphone.
[0006] Preferably, the frequency shifting module distinguishes the audio segments of 0-2000Hz, 2000-4000Hz, 4000-6000Hz and above 6000Hz of the sound, compresses the audio segments of 0-2000Hz and 2000-4000Hz with a compression ratio of 0.3-0.5; compresses the audio segment of 4000-6000Hz with a compression ratio of 0.5-0.6; and frequency shifts the audio segments above 6000Hz, and the frequency shift interval is within the range of 0 to 6000Hz.
[0007] Preferably, the dynamic compression module gains the audio passing through the channels according to the channels divided in the sound range, and then outputs the audio signal through WOLA synthesis. The dynamic compression module does not process the audio of 0-1000Hz, amplifies the audio of 1000-2000Hz, compresses the audio of 2000-3000Hz, and limits the audio above 3000Hz.
[0008] Preferably, the noise suppression module performs noise reduction based on a deep learning neural network, calculates the maximum stable gain of the closed-loop system based on the Nyquist instability criterion, and adjusts the gain to within 3 dB below the maximum stable gain, thereby generating a large amount of data with acoustic feedback characteristics for training the deep neural network by simulating the acoustic feedback production of the closed-loop system.
[0009] Preferably, the adaptive noise reduction module performs noise reduction processing based on ANR, and the steps of ANR noise reduction processing are: amplifying the background audio and the human voice audio together, and then performing noise reduction processing on the background audio through a preset algorithm.
[0010] Preferably, the noise-spurting suppression module extracts audio features when sound audio is detected, and analyzes audio with audio feature changes greater than 1000Hz. If the audio of the noise-spurting sound is 2-3 times greater than the audio of the human voice, the noise-spurting sound in the environment is directly compressed and then subjected to noise reduction processing.
[0011] Preferably, the wind noise reduction module eliminates the wind noise inside the sound through a noise estimation module and a noise filtering module. The noise estimation module estimates the wind noise based on spectral subtraction or VAD, and sends the estimation result to the noise filtering module. The noise filtering module eliminates the wind noise based on a Wiener filter.
[0012] A hearing aid for improving the accuracy of sound heard by hearing-impaired listeners includes the above-mentioned system for improving the accuracy of sound heard by hearing-impaired listeners.
[0013] Beneficial effects of the present invention:
[0014] The system for improving the accuracy of hearing impaired listeners hearing sound provided by the present invention comprises a voice pickup module, a processor, a frequency shift module, a dynamic compression module, a shouting suppression module, an adaptive noise reduction module, a sudden sound suppression module, a wind noise reduction module and a microphone, wherein the voice pickup module is used to pick up the sound of the current environment and send the sound to the processor; the processor is used to detect and identify the sound and send the identified sound to the frequency shift module; the frequency shift module is used to shift the frequency of vowels and high-frequency consonants in the sound to a reasonable frequency band and send it to the dynamic compression module; the dynamic compression module appropriately compresses the sound after frequency shift according to the compression ratio according to a preset audiogram and sends it to the shouting suppression module; the shouting suppression module The block is used to adaptively eliminate the howling sound generated and send it to the adaptive noise reduction module. The adaptive noise reduction module dynamically distinguishes between speech and noise according to ANR, reduces fixed noise in different frequency bands, and sends it to the sudden sound suppression module; the sudden sound suppression module is used to eliminate the burst sound in the environment and send it to the wind noise reduction module; the wind noise reduction module is used to reduce the wind noise frequency in the sound, and output the processed audio through the microphone. The present invention can process the audio that the hearing impaired cannot hear through frequency shifting and dynamic compression, and perform shouting suppression and noise reduction processing in the later stage to make the audio clearer. In addition, the present invention suppresses sudden sound waves to prevent the hearing impaired from being startled by sudden sound waves. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0016] Figure 1 The audio image before frequency shifting of the present invention;
[0017] Figure 2 The frequency-shifted audio image of the present invention;
[0018] Figure 3 The audio change diagram after compression and limitation of the present invention;
[0019] Figure 4 It is a schematic diagram of the deep neural network feedback control algorithm of the present invention;
[0020] Figure 5 This is an ANR noise reduction processing effect diagram of the present invention;
[0021] Figure 6This is a comparison diagram before and after the sudden noise reduction of the present invention;
[0022] Figure 7 The wind noise reduction performance diagram of the present invention is shown in FIG. DETAILED DESCRIPTION
[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.
[0024] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.
[0025] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.
[0026] In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, or the positions or positional relationships in which the product of the application is usually placed when in use. They are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific position, be constructed and operated in a specific position, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.
[0027] In addition, the terms "horizontal", "vertical", "overhanging" and the like do not mean that the components are required to be absolutely horizontal or overhanging, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", and does not mean that the structure must be completely horizontal, but can be slightly tilted.
[0028] In the description of this application, it should also be noted that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.
[0029] Embodiment 1
[0030] like Figure 1-6 As shown, a system for improving the accuracy of hearing impaired listeners hearing sound comprises a voice pickup module, a processor, a frequency shift module, a dynamic compression module, a shouting suppression module, an adaptive noise reduction module, a spurt suppression module, a wind noise reduction module and a microphone, wherein the voice pickup module is used to pick up the sound of the current environment and send the sound to the processor; the processor is used to detect and identify the sound and send the identified sound to the frequency shift module; the frequency shift module is used to shift the frequency of vowels and high-frequency consonants in the sound to a reasonable frequency band and send it to the dynamic compression module; the dynamic compression module appropriately compresses the sound after frequency shift according to the compression ratio according to a preset audiogram and sends it to the shouting suppression module; the shouting suppression module It is used to adaptively eliminate the howling sound generated and send it to the adaptive noise reduction module. The adaptive noise reduction module dynamically distinguishes between speech and noise according to ANR, reduces fixed noise in different frequency bands, and sends it to the sudden sound suppression module; the sudden sound suppression module is used to eliminate the burst sound in the environment and send it to the wind noise reduction module; the wind noise reduction module is used to reduce the wind noise frequency in the sound, and output the processed audio through the microphone. The present invention can process the audio that the hearing impaired cannot hear through frequency shifting and dynamic compression, and perform shouting suppression and noise reduction processing in the later stage to make the audio clearer. In addition, the present invention suppresses sudden sound waves to prevent the hearing impaired from being startled by sudden sound waves.
[0031] like Figure 1-2As shown, in this embodiment, the frequency shifting module distinguishes the audio segments of 0-2000Hz, 2000-4000Hz, 4000-6000Hz, and above 6000Hz of the sound, compresses the audio segments of 0-2000Hz and 2000-4000Hz, and the compression ratio is 0.3-0.5; compresses the audio segment of 4000-6000Hz, and the compression ratio is 0.5-0.6; the audio segment above 6000Hz is frequency shifted, and the frequency shift interval is within the range of 0 to 6000Hz. The main working principle of the frequency shifting module is to compress the high-frequency sound in proportion, and move the high-frequency speech information to the low-frequency area with better residual hearing, so that the patient's high-frequency hearing threshold is reduced, so that the patient can hear the initial consonant and consonant information, and can distinguish the length of the syllable and understand the content of the syllable in speech communication, thereby improving the patient's speech recognition ability. For example, if the patient's sound compensation at 4000Hz is not ideal, but 2000Hz can compensate well, the frequency shifting will transfer the received 4000Hz to 2000Hz, so that the patient can hear the 4000Hz sound and achieve a better compensation effect.
[0032] In this embodiment, the dynamic compression module gains the audio passing through the channels according to the channels divided in the sound range, and then outputs the audio signal through WOLA synthesis. The dynamic compression module does not process the audio of 0-1000Hz, amplifies the audio of 1000-2000Hz, compresses the audio of 2000-3000Hz, and limits the audio above 3000Hz. The audio changes after compression and limitation are as follows: Figure 3 shown.
[0033] like Figure 4 As shown, in this embodiment, the howling suppression module performs noise reduction based on a deep learning neural network, calculates the maximum stable gain of the closed-loop system based on the Nyquist instability criterion, and adjusts the gain to within 3dB below the maximum stable gain, and then generates a large amount of data with acoustic feedback characteristics by simulating the acoustic feedback production of the closed-loop system for training the deep neural network. The howling sound can be quickly eliminated based on the deep learning neural network.
[0034] like Figure 5As shown, in this embodiment, the adaptive noise reduction module performs noise reduction processing based on ANR, and the steps of ANR noise reduction processing are: amplifying the background audio and the human voice audio together, and then performing noise reduction processing on the background audio through a preset algorithm; specifically, the noise reduction parameters can be adjusted manually, and ANR dynamically distinguishes between speech and noise, reduces fixed noise in different frequency bands, and retains clear speech; number of frequency bands: 16 / number of microphones: 1 / maximum noise reduction: ≥15dB; level: number of user-adjustable levels / 7 for each mode; user-adjustable enable switch for each mode Performance chart: SNR improvement = with ANR (speech-noise) - without ANR (speech-noise).
[0035] like Figure 6 As shown, in this embodiment, the sudden sound suppression module extracts audio features when sound audio is detected, and analyzes audio with audio feature changes greater than 1000Hz. If the audio of the sudden sound is 2-3 times greater than the audio of the human voice, the sudden sound in the environment is directly compressed and then subjected to noise reduction processing. The present invention can quickly eliminate sudden sounds in the environment and prevent the sudden sound from scaring the user.
[0036] like Figure 7 As shown, in this embodiment, the wind noise reduction module eliminates the wind noise inside the sound through the noise estimation module and the noise filtering module. The noise estimation module estimates the wind noise based on spectral subtraction or VAD, and sends the estimation result to the noise filtering module. The noise filtering module eliminates the wind noise based on the Wiener filter. The present invention can quickly eliminate the wind noise, so that the sound heard by the hearing impaired is clearer.
[0037] Embodiment 2
[0038] like Figure 1-6 As shown, a hearing-aid speaker for improving the accuracy of sound heard by hearing-impaired listeners includes the above-mentioned system for improving the accuracy of sound heard by hearing-impaired listeners; the present invention can process audio that cannot be heard by the hearing-impaired through frequency shifting and dynamic compression, and perform shouting suppression and noise reduction processing in the later stage to make the audio clearer. In addition, the present invention suppresses sudden sound waves to prevent the hearing-impaired from being startled by sudden sound waves.
[0039] In addition, the present invention uses a hearing-aid speaker box, which can reduce the discomfort felt by hearing-impaired people when wearing the hearing aid, and can make the sound louder and adapt to multiple scene environments.
[0040] The above are only preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims
1. A system for improving the accuracy of sound heard by a hearing-impaired listener, characterized in that: It includes a voice pickup module, a processor, a frequency shift module, a dynamic compression module, a shouting suppression module, an adaptive noise reduction module, a sudden wave suppression module, a wind noise reduction module and a microphone. The voice pickup module is used to pick up the sound of the current environment and send the sound to the processor; the processor is used to detect and identify the sound and send the identified sound to the frequency shift module; the frequency shift module is used to shift the vowels and high-frequency consonants in the sound to a reasonable frequency band and send it to the dynamic compression module; The dynamic compression module appropriately compresses the frequency-shifted sound according to the compression ratio based on the preset audiogram, and sends it to the shouting suppression module; the shouting suppression module is used to adaptively eliminate the generated howling sound, and sends it to the adaptive noise reduction module, the adaptive noise reduction module dynamically distinguishes between speech and noise according to ANR, reduces fixed noise in different frequency bands, and sends it to the sudden sound suppression module; the sudden sound suppression module is used to eliminate the burst sound in the environment, and sends it to the wind noise reduction module; the wind noise reduction module is used to reduce the wind noise frequency in the sound, and output the processed audio through the microphone.
2. The system for improving the accuracy of hearing of hearing-impaired listeners according to claim 1, characterized in that: The frequency shifting module distinguishes the audio segments of 0-2000Hz, 2000-4000Hz, 4000-6000Hz and above 6000Hz of the sound, compresses the audio segments of 0-2000Hz and 2000-4000Hz with a compression ratio of 0.3-0.5; compresses the audio segment of 4000-6000Hz with a compression ratio of 0.5-0.6; and frequency shifts the audio segments above 6000Hz, and the frequency shift interval is within the range of 0 to 6000Hz.
3. The system for improving the accuracy of hearing of hearing-impaired listeners according to claim 1, characterized in that: The dynamic compression module gains the audio passing through the channels according to the channels divided in the sound range, and then outputs the audio signal through WOLA synthesis. The dynamic compression module does not process the audio of 0-1000Hz, amplifies the audio of 1000-2000Hz, compresses the audio of 2000-3000Hz, and limits the audio above 3000Hz.
4. The system for improving the accuracy of hearing of hearing-impaired listeners according to claim 1, characterized in that: The noise suppression module performs noise reduction based on a deep learning neural network, calculates the maximum stable gain of the closed-loop system based on the Nyquist instability criterion, and adjusts the gain to within 3dB below the maximum stable gain, and then generates a large amount of data with acoustic feedback characteristics by simulating the acoustic feedback production of the closed-loop system for training the deep neural network.
5. The system for improving the accuracy of hearing of hearing-impaired listeners according to claim 1, characterized in that: The adaptive noise reduction module performs noise reduction processing based on ANR, and the steps of ANR noise reduction processing are: amplifying the background audio and the human voice audio together, and then performing noise reduction processing on the background audio through a preset algorithm.
6. The system for improving the accuracy of hearing of hearing-impaired listeners according to claim 1, characterized in that: The sudden sound suppression module extracts audio features when sound audio is detected, and analyzes audio with audio feature changes greater than 1000Hz. If the audio of the sudden sound is 2-3 times greater than the audio of the human voice, the sudden sound in the environment is directly compressed and then noise reduction is performed.
7. The system for improving the accuracy of hearing of hearing-impaired listeners according to claim 1, characterized in that: The wind noise reduction module eliminates the wind noise inside the sound through the noise estimation module and the noise filtering module. The noise estimation module estimates the wind noise based on spectral subtraction or VAD, and sends the estimation result to the noise filtering module. The noise filtering module eliminates the wind noise based on the Wiener filter.
8. A hearing aid speaker for improving the accuracy of sound heard by hearing-impaired listeners, characterized in that: The invention comprises the system for improving the accuracy of hearing sound for hearing-impaired listeners as described in claims 1 to 7 above.
