Masking tone generation method and system based on hearing loss, medium and equipment

Abstract

The invention discloses a masking tone generation method and system based on hearing loss, a medium and equipment, and the method comprises the steps: matching a plurality of audio clips according to a user hearing loss spectrogram and a preset audio database; calculating an adjustment weight of each audio track in each audio clip, and adjusting each audio clip according to the adjustment weight of each audio track to obtain each first audio clip; adjusting the volume of each first audio clip according to a preset volume adjustment algorithm to obtain each second audio clip; according to the hearing loss spectrogram, adjusting an audio signal of each frequency band of each second audio clip to obtain each third audio clip; and synthesizing the third audio clips, and outputting a masking tone. The dynamic tinnitus masking audio generation method based on user hearing loss features realizes personalized and acyclic perception dynamic tinnitus masking audio generation through a dynamic audio generation and optimization algorithm based on user hearing loss features.

Description

Technical Field

[0001] The present invention belongs to the field of tinnitus masking audio generation, and relates to a masking sound generation method, system, medium and equipment based on hearing loss. Background Art

[0002] Tinnitus is a common hearing problem, which is manifested by patients perceiving noises such as buzzing and hissing when there is no external sound source, seriously affecting the quality of life. Currently, tinnitus masking is an effective intervention method that reduces the impact of tinnitus by covering the patient's tinnitus perception with specific audio. However, existing tinnitus masking technology faces many challenges in practical applications.

[0003] However, existing tinnitus masking audios usually have the problem of monotonous repetition, which makes it easy for users to notice that the audio is playing in a loop, thus reducing the masking effect. In addition, these audios fail to fully consider the individual hearing loss characteristics of users and cannot provide personalized masking solutions, which limits their effectiveness and user experience. Summary of the invention

[0004] In response to the deficiencies in the prior art, the present application provides a method, system, medium and device for generating masking sound based on hearing loss, which realizes personalized, non-cyclically perceived dynamic tinnitus masking audio generation through dynamic audio generation and optimization algorithm based on the user's hearing loss characteristics.

[0005] To achieve the above objectives, in a first aspect, the present invention provides a method for generating masking sound based on hearing loss, comprising:

[0006] Matching several audio clips according to the user's hearing loss spectrum and a preset audio database;

[0007] Calculating an adjustment weight of each audio track in each of the audio clips, and adjusting each audio clip according to the adjustment weight of each audio track to obtain each first audio clip;

[0008] adjusting the volume of each of the first audio clips according to a preset volume adjustment algorithm to obtain each of the second audio clips;

[0009] According to the hearing loss spectrum diagram, adjusting the audio signals of each frequency band of each second audio segment to obtain each third audio segment;

[0010] The third audio segments are synthesized to output a masking sound.

[0011] Compared with the prior art, the embodiments of the present application have the following beneficial effects: by analyzing the user's hearing loss spectrum and combining it with a preset audio database, the audio clips suitable for the user's hearing characteristics are accurately matched, ensuring that the subsequently generated masking audio can cover the user's tinnitus frequency range in a targeted manner, thereby improving the tinnitus masking effect. At the same time, the preset audio library is used to provide a variety of audio materials, increasing the possibility of audio changes; by calculating the adjustment weights of each track in each audio clip, and adjusting according to these weights, the proportion of sound elements within each audio clip is dynamically optimized, which not only ensures the coordination between different frequency components within the audio clip, avoids the situation where a certain level is too prominent or masked, but also enhances the level and richness of the audio. The dynamic adjustment ensures that the audio always maintains a rich sense of change during playback, further improving the user's auditory comfort and masking effect; through specific The volume adjustment algorithm is used to change the volume of the audio clips, ensuring the fade-in and fade-out effect during audio playback, making the volume connection between the audio clips natural and harmonious, and improving the user's auditory experience; by adjusting the audio signal of each frequency band based on the hearing loss spectrum diagram, accurate optimization for individual hearing loss is achieved to ensure that the audio signal of each frequency band can adapt to the user's hearing needs. The frequency band adjustment also takes into account the balance between different frequency bands to avoid excessive enhancement or weakening of certain frequency bands, ensuring the overall harmony and naturalness of the audio, and further improving the tinnitus masking effect and user satisfaction; finally, all the processed audio clips are synthesized into a complete audio file, and the final masking sound is output, which not only has personalized frequency band optimization and volume adjustment, but also maintains the dynamic change characteristics of the audio, ensuring that the user will not notice the looping of the audio, improving the tinnitus masking effect and the user's auditory comfort.

[0012] In some embodiments of the first aspect of the present application, the calculating the adjustment weight of each audio track in each audio clip, and adjusting each audio clip according to the adjustment weight of each audio track to obtain each first audio clip includes:

[0013] Calculating the adjustment weight of each audio track according to the frequency characteristics, volume characteristics and timing characteristics of each audio track in each of the audio clips;

[0014] The audio segments are adjusted according to the adjustment weights of the audio tracks to obtain first audio segments.

[0015] Compared with the prior art, the above embodiments have the following beneficial effects: by combining the weight calculation method of frequency characteristics, it is possible to accurately match the hearing loss characteristics of the user, ensuring that the generated masking audio provides an effective masking effect where it is most needed; by combining the weight calculation method of volume characteristics, it is possible to optimize the layering and richness between different tracks within the audio clip, avoiding that some tracks are too prominent or masked; at the same time, by combining the weight calculation method of timing characteristics, a fade-in and fade-out effect can be introduced to enhance the sense of change and natural transition during audio playback, ultimately providing each user with a highly customized tinnitus masking solution, greatly improving the tinnitus masking effect and user satisfaction.

[0016] In some embodiments of the first aspect of the present application, adjusting the volume of each of the first audio segments according to a preset volume adjustment algorithm to obtain each of the second audio segments includes:

[0017] The volume adjustment algorithm is as follows:

[0018] Where V(t) represents the volume at time t, V start and V end They represent the volume values ​​at the beginning and end of the audio clip respectively, f(t) represents the time function, fade_in_time and fade_out_time represent the fade-in time and fade-out time of the audio clip respectively.

[0019] Compared with the prior art, the above embodiment has the following beneficial effects: by introducing a volume adjustment algorithm, the volume of the audio clips is linearly changed, thereby ensuring the fade-in and fade-out effect during audio playback, and making the volume connection between the audio clips natural and harmonious.

[0020] In some embodiments of the first aspect of the present application, adjusting the audio signals of each frequency band of each second audio segment according to the hearing loss spectrogram to obtain each third audio segment includes:

[0021] Extracting hearing loss features according to the hearing loss spectrum, and calculating gain coefficients corresponding to each audio frequency according to the hearing loss features;

[0022] According to a preset frequency band division rule, each of the second audio segments is divided into a plurality of original frequency band signals of different frequencies;

[0023] Adjusting each of the original frequency band signals according to the center frequency and the corresponding gain coefficient of each of the frequency band signals to obtain each of the frequency band signals;

[0024] The frequency band signals are combined and reconstructed to obtain third audio segments.

[0025] Compared with the prior art, the above embodiment has the following beneficial effects: by dividing each audio segment into frequency bands and calculating the gain coefficient of each frequency band according to the user's hearing loss characteristics, accurate optimization for individual hearing loss is achieved, ensuring that the audio signal of each frequency band can adapt to the user's hearing needs.

[0026] In some embodiments of the first aspect of the present application, extracting hearing loss features according to the hearing loss spectrum, and calculating gain coefficients corresponding to each audio frequency according to the hearing loss features, includes:

[0027] According to the preset weight function, the gain coefficient is optimized and adjusted, wherein the algorithm is as follows:

[0028] Where G(f) represents the gain coefficient of frequency f, c represents a constant, H(f) represents the hearing loss of the user at frequency f, and w(f) represents a weight function.

[0029] Compared with the prior art, the above embodiment has the following beneficial effects: by introducing the weight function, the distribution of the gain coefficient is further optimized, ensuring that the calculation of the gain coefficient is more accurate, so that the enhancement of the audio signal in different frequency bands is more in line with the user's auditory needs, thereby significantly improving the effectiveness and personalization of the tinnitus masking audio.

[0030] In a second aspect, the present invention also provides a masking sound generation system based on hearing loss, comprising: a matching module, a track adjustment module, a volume adjustment module, a frequency band adjustment module and a result output module;

[0031] Wherein, the matching module is used to match a number of audio clips according to the user's hearing loss spectrum and a preset audio database;

[0032] The audio track adjustment module is used to calculate the adjustment weight of each audio track in each audio segment, and adjust each audio segment according to the adjustment weight of each audio track to obtain each first audio segment;

[0033] The volume adjustment module is used to adjust the volume of each of the first audio segments according to a preset volume adjustment algorithm to obtain each of the second audio segments;

[0034] The frequency band adjustment module is used to adjust the audio signals of each frequency band of each second audio segment according to the hearing loss spectrum to obtain each third audio segment;

[0035] The result output module is used to synthesize each of the third audio segments and output a masking sound.

[0036] Compared with the prior art, the embodiments of the present application have the following beneficial effects: by analyzing the user's hearing loss spectrum and combining it with a preset audio database, the audio clips suitable for the user's hearing characteristics are accurately matched, ensuring that the subsequently generated masking audio can cover the user's tinnitus frequency range in a targeted manner, thereby improving the tinnitus masking effect. At the same time, the preset audio library is used to provide a variety of audio materials, increasing the possibility of audio changes; by calculating the adjustment weights of each track in each audio clip, and adjusting according to these weights, the proportion of sound elements within each audio clip is dynamically optimized, which not only ensures the coordination between different frequency components within the audio clip, avoids the situation where a certain level is too prominent or masked, but also enhances the level and richness of the audio. The dynamic adjustment ensures that the audio always maintains a rich sense of change during playback, further improving the user's auditory comfort and masking effect; through specific The volume adjustment algorithm is used to change the volume of the audio clips, ensuring the fade-in and fade-out effect during audio playback, making the volume connection between the audio clips natural and harmonious, and improving the user's auditory experience; by adjusting the audio signal of each frequency band based on the hearing loss spectrum diagram, accurate optimization for individual hearing loss is achieved to ensure that the audio signal of each frequency band can adapt to the user's hearing needs. The frequency band adjustment also takes into account the balance between different frequency bands to avoid excessive enhancement or weakening of certain frequency bands, ensuring the overall harmony and naturalness of the audio, and further improving the tinnitus masking effect and user satisfaction; finally, all the processed audio clips are synthesized into a complete audio file, and the final masking sound is output, which not only has personalized frequency band optimization and volume adjustment, but also maintains the dynamic change characteristics of the audio, ensuring that the user will not notice the looping of the audio, improving the tinnitus masking effect and the user's auditory comfort.

[0037] In some embodiments of the second aspect of the present application, the track adjustment module includes: an adjustment weight calculation unit and a track adjustment unit;

[0038] The adjustment weight calculation unit is used to calculate the adjustment weight of each audio track according to the frequency characteristics, volume characteristics and timing characteristics of each audio track in each audio segment;

[0039] The audio track adjustment unit is used to adjust each audio segment according to the adjustment weight of each audio track to obtain each first audio segment.

[0040] Compared with the prior art, the above embodiments have the following beneficial effects: by combining the weight calculation method of frequency characteristics, it is possible to accurately match the hearing loss characteristics of the user, ensuring that the generated masking audio provides an effective masking effect where it is most needed; by combining the weight calculation method of volume characteristics, it is possible to optimize the layering and richness between different tracks within the audio clip, avoiding that some tracks are too prominent or masked; at the same time, by combining the weight calculation method of timing characteristics, a fade-in and fade-out effect can be introduced to enhance the sense of change and natural transition during audio playback, ultimately providing each user with a highly customized tinnitus masking solution, greatly improving the tinnitus masking effect and user satisfaction.

[0041] In some embodiments of the second aspect of the present application, the volume adjustment module includes:

[0042] The volume adjustment algorithm is as follows:

[0043] V(t)=V start +(V end -V start )×f(t); Where V(t)

[0044] represents the volume at time t, V start and V end They represent the volume values ​​at the beginning and end of the audio clip respectively, f(t) represents the time function, fade_in_time and fade_out_time represent the fade-in time and fade-out time of the audio clip respectively.

[0045] Compared with the prior art, the above embodiment has the following beneficial effects: by introducing a volume adjustment algorithm, the volume of the audio clips is linearly changed, thereby ensuring the fade-in and fade-out effect during audio playback, and making the volume connection between the audio clips natural and harmonious.

[0046] In a third aspect, the present invention also provides a masking sound generation device based on hearing loss, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the masking sound generation method based on hearing loss when loaded into the processor.

[0047] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for generating masking sounds based on hearing loss are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1: A flowchart of a method for generating masking sound based on hearing loss provided in some embodiments of the present invention.

[0049] Figure 2 : is a structural schematic diagram of a masking sound generation system based on hearing loss provided in some embodiments of the present invention.

[0050] Figure 3 : is a structural diagram of a masking sound generation device based on hearing loss provided in some embodiments of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments 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 creative work are within the scope of protection of the present invention.

[0052] Embodiment 1:

[0053] Please refer to Figure 1 , a method for generating masking sound based on hearing loss provided by an embodiment of the present invention, comprising steps S1 to S5:

[0054] Step S1: Matching several audio clips according to the user's hearing loss spectrum and a preset audio database.

[0055] In the specific implementation, the frequency band where the user's tinnitus is located is determined according to the hearing loss spectrum diagram. The preset audio database is classified according to different frequency bands and can also be classified according to different scene types. Suitable audio is recommended according to the frequency band where the tinnitus is located. Then the user can select several segments (usually three segments) of audio clips with different characteristics from the preset audio library according to his or her preferences for subsequent dynamic audio generation. Among them, the audio database is divided according to the scene and can be divided into these types of audio files: white noise, pink noise, blue noise, Brown noise and other sounds in life (such as waves, rain, thunder, insects, cafe sounds, book turning sounds, etc.).

[0056] In this embodiment, step S1 analyzes the hearing loss spectrum of the user and combines it with a preset audio database to accurately match the audio clips suitable for the user's hearing characteristics, thereby ensuring that the subsequently generated masking audio can specifically cover the user's tinnitus frequency range, thereby improving the tinnitus masking effect. At the same time, the preset audio library is used to provide diverse audio materials, increasing the possibility of audio changes.

[0057] Step S2: calculating the adjustment weight of each audio track in each audio segment, and adjusting each audio segment according to the adjustment weight of each audio track to obtain each first audio segment.

[0058] Preferably, in this embodiment, step S2 can be implemented by the following preferred implementation, including steps S21-S22, which are specifically as follows:

[0059] S21: calculating the adjustment weight of each audio track according to the frequency characteristics, volume characteristics and timing characteristics of each audio track in each of the audio clips;

[0060] S22: adjusting each audio segment according to the adjustment weight of each audio track to obtain each first audio segment.

[0061] In specific implementation, the algorithm for calculating the adjustment weight can be as follows:

[0062] W main =α·f main +β·V main +γ·T main ;

[0063] W deep =α·f deep +β·V deep +γ·T deep ;

[0064] W bright =α·f bright +β·V bright +γ·T bright ; Among them, W main , W deep and W bright

[0065] represents the adjustment weights of the main track layer, low-frequency track layer, and high-frequency track layer in each track. α, β, and γ represent weight coefficients. main 、f deep and f bright Respectively represent the frequency characteristics of the main audio track layer, the low-frequency audio track layer, and the high-frequency audio track layer, V main 、V deep and V bright Respectively represent the volume characteristics of the main audio track layer, the low-frequency audio track layer, and the high-frequency audio track layer, T main 、T deep and T bright Respectively represent the timing characteristics of the main audio track layer, the low-frequency audio track layer, and the high-frequency audio track layer.

[0066] In this preferred embodiment, step S2 can accurately match the hearing loss characteristics of the user by combining the weight calculation method of frequency characteristics, ensuring that the generated masking audio provides an effective masking effect where it is most needed; the weight calculation method combined with the volume characteristics can optimize the layering and richness between different tracks within the audio clip, avoiding some tracks from being too prominent or masked; at the same time, the weight calculation method combined with the timing characteristics can introduce a fade-in and fade-out effect, enhance the sense of change and natural transition during audio playback, and ultimately provide each user with a highly customized tinnitus masking solution, greatly improving the tinnitus masking effect and user satisfaction.

[0067] Step S3: adjusting the volume of each of the first audio segments according to a preset volume adjustment algorithm to obtain each of the second audio segments.

[0068] Preferably, the volume adjustment algorithm described in step S3 is as follows:

[0069] V(t)=V start +(V end -V start )×f(t); Where V(t)

[0070] represents the volume at time t, V start and V end They represent the volume values ​​at the beginning and end of the audio clip respectively, f(t) represents the time function, fade_in_time and fade_out_time represent the fade-in time and fade-out time of the audio clip respectively.

[0071] In this preferred embodiment, step S3 introduces a volume adjustment algorithm to perform linear change processing on the volume of the audio clips, thereby ensuring a fade-in and fade-out effect during audio playback and making the volume connection between the audio clips natural and harmonious.

[0072] Step S4: adjusting the audio signals of each frequency band of each second audio segment according to the hearing loss spectrum to obtain each third audio segment.

[0073] Preferably, in this embodiment, step S4 can be implemented by the following preferred implementation, including steps S41-S44, which are specifically as follows:

[0074] S41: extracting hearing loss features according to the hearing loss spectrum, and calculating gain coefficients corresponding to each audio frequency according to the hearing loss features;

[0075] S42: dividing each of the second audio segments into a plurality of original frequency band signals according to a preset frequency band division rule;

[0076] S43: adjusting each of the original frequency band signals according to the center frequency and the corresponding gain coefficient of each of the frequency band signals to obtain each frequency band signal;

[0077] S44: According to the frequency band signals, merge and reconstruct to obtain third audio segments.

[0078] In this preferred embodiment, step S4 achieves precise optimization for individual hearing loss by dividing each audio segment into frequency bands and calculating the gain coefficient of each frequency band according to the user's hearing loss characteristics, thereby ensuring that the audio signal of each frequency band can adapt to the user's hearing needs.

[0079] In the specific implementation, the audio clip is first divided into different frequency bands, such as 20Hz to 500Hz as the low frequency band, 500Hz to 2kHz as the medium frequency band, and 2kHz to 20kHz as the high frequency band. The gain coefficient is calculated for each frequency band based on the center frequency of each frequency band. The algorithm is as follows:

[0080] Where G(f) represents the gain coefficient at frequency f, c represents a constant, and H(f) represents the user's hearing loss at frequency f;

[0081] Then, a signal decomposition algorithm (such as short-time Fourier transform or wavelet transform or other similar algorithms) is used to realize the frequency decomposition of the audio signal. After decomposition, the gain coefficient is used to adjust the decomposed original frequency band signal. The algorithm is as follows:

[0082] Y i (f) = G(f)·X i (f); where X i (f) represents the original frequency band signal, Y i (f) represents the frequency band signal after adjustment.

[0083] After the adjustment, an inverse filtering algorithm such as an inverse Fourier transform or an inverse wavelet transform algorithm is used to merge the adjusted frequency band signals to obtain a third audio segment.

[0084] In addition, when adjusting, on the one hand, the dynamic range of the audio signal may become too wide, resulting in nonlinear distortion or sound quality problems. The gain factor can be limited by a dynamic compressor or limiter to prevent excessive gain. On the other hand, if the user's hearing loss is based on nonlinear changes in frequency, the gain factor needs to be further adjusted as follows:

[0085] According to the preset weight function, the gain coefficient is optimized and adjusted, wherein the algorithm is as follows:

[0086] Where G(f) represents the gain coefficient of frequency f, c represents a constant, H(f) represents the hearing loss of the user at frequency f, and w(f) represents a weight function.

[0087] In a specific implementation, the weight function w(f) represents the weight within a specific frequency range, for example, the weight of the high frequency band is higher and the weight of the medium frequency band is lower, and it can be adjusted according to actual needs.

[0088] In this preferred embodiment, step S41 further optimizes the distribution of gain coefficients by introducing a weight function, ensuring that the calculation of the gain coefficients is more accurate, so that the enhancement of audio signals in different frequency bands better meets the user's auditory needs, thereby significantly improving the effectiveness and personalization of tinnitus masking audio.

[0089] Step S5: synthesizing the third audio segments and outputting masking sounds.

[0090] In specific implementation, masking sound can be generated in real time, and output in multiple formats (such as MP3, WAV, etc.) is supported.

[0091] In this embodiment, step S5 synthesizes all processed audio clips into a complete audio file and outputs the final masking sound, which not only has personalized frequency band optimization and volume adjustment, but also maintains the dynamic change characteristics of the audio, ensuring that the user will not notice the looping of the audio, thereby improving the tinnitus masking effect and the user's auditory comfort.

[0092] In summary, compared with the prior art, the above embodiments of the present application have the following beneficial effects: by analyzing the user's hearing loss spectrum and combining it with a preset audio database, the audio clips suitable for the user's hearing characteristics are accurately matched, ensuring that the subsequently generated masking audio can cover the user's tinnitus frequency range in a targeted manner, thereby improving the tinnitus masking effect. At the same time, the preset audio library is used to provide a variety of audio materials, increasing the possibility of audio changes; by calculating the adjustment weights of each audio track in each audio clip, and adjusting according to these weights, the proportion of sound elements within each audio clip is dynamically optimized, which not only ensures the coordination between different frequency components within the audio clip, avoids the situation where a certain level is too prominent or masked, but also enhances the layering and richness of the audio. The dynamic adjustment allows the audio to always maintain a rich sense of change during playback, further improving the user's auditory comfort and masking effect; A specific volume adjustment algorithm changes the volume of audio clips, ensuring the fade-in and fade-out effect during audio playback, making the volume connection between audio clips natural and harmonious, and improving the user's auditory experience; by adjusting the audio signal of each frequency band based on the hearing loss spectrum diagram, accurate optimization for individual hearing loss is achieved, ensuring that the audio signal of each frequency band can adapt to the user's hearing needs. The frequency band adjustment also takes into account the balance between different frequency bands, avoiding excessive enhancement or weakening of certain frequency bands, ensuring the overall harmony and naturalness of the audio, and further improving the tinnitus masking effect and user satisfaction; finally, all processed audio clips are synthesized into a complete audio file, and the final masking sound is output, which not only has personalized frequency band optimization and volume adjustment, but also maintains the dynamic change characteristics of the audio, ensuring that the user will not notice the looping of the audio, improving the tinnitus masking effect and the user's auditory comfort.

[0093] Embodiment 2:

[0094] Please refer to Figure 2 , based on the same inventive concept, a masking sound generation system based on hearing loss disclosed in an embodiment of the present invention includes: a matching module M1, a track adjustment module M2, a volume adjustment module M3, a frequency band adjustment module M4 and a result output module M5;

[0095] The matching module M1 is used to match a number of audio clips according to the user's hearing loss spectrum and a preset audio database;

[0096] The matching module M1 of this embodiment analyzes the user's hearing loss spectrum and combines it with a preset audio database to accurately match audio clips suitable for the user's hearing characteristics, ensuring that the subsequently generated masking audio can specifically cover the user's tinnitus frequency range, thereby improving the tinnitus masking effect. At the same time, the preset audio library is used to provide diverse audio materials, increasing the possibility of audio changes.

[0097] The audio track adjustment module M2 is used to calculate the adjustment weight of each audio track in each audio segment, and adjust each audio segment according to the adjustment weight of each audio track to obtain each first audio segment;

[0098] The audio track adjustment module M2 includes: an adjustment weight calculation unit and an audio track adjustment unit;

[0099] The adjustment weight calculation unit is used to calculate the adjustment weight of each audio track according to the frequency characteristics, volume characteristics and timing characteristics of each audio track in each audio segment;

[0100] The audio track adjustment unit is used to adjust each audio segment according to the adjustment weight of each audio track to obtain each first audio segment.

[0101] The audio track adjustment module M2 of this embodiment can accurately match the user's hearing loss characteristics by combining the weight calculation method of frequency characteristics, ensuring that the generated masking audio provides an effective masking effect where it is most needed; the weight calculation method combined with the volume characteristics can optimize the layering and richness between different audio tracks within the audio clip, avoiding some audio tracks from being too prominent or masked; at the same time, the weight calculation method combined with the timing characteristics can introduce a fade-in and fade-out effect, enhance the sense of change and natural transition during the audio playback process, and ultimately provide each user with a highly customized tinnitus masking solution, greatly improving the tinnitus masking effect and user satisfaction.

[0102] The volume adjustment module M3 is used to adjust the volume of each of the first audio segments according to a preset volume adjustment algorithm to obtain each second audio segment;

[0103] The volume adjustment algorithm is as follows:

[0104] V(t)=V start +(V end -V start )×f(t); Where V(t)

[0105] represents the volume at time t, V start and V end They represent the volume values ​​at the beginning and end of the audio clip respectively, f(t) represents the time function, fade_in_time and fade_out_time represent the fade-in time and fade-out time of the audio clip respectively.

[0106] In this embodiment, the volume adjustment module M3 introduces a volume adjustment algorithm to perform linear change processing on the volume of the audio clips, thereby ensuring a fade-in and fade-out effect during audio playback and making the volume connection between the audio clips natural and harmonious.

[0107] The frequency band adjustment module M4 is used to adjust the audio signals of each frequency band of each second audio segment according to the hearing loss spectrum diagram to obtain each third audio segment.

[0108] The frequency band adjustment module M4 includes: a gain coefficient calculation unit, a division unit, a gain application unit and a merging unit;

[0109] The gain coefficient calculation unit is used to extract hearing loss characteristics according to the hearing loss spectrum diagram, and calculate the gain coefficient corresponding to each audio frequency according to the hearing loss characteristics;

[0110] The division unit is used to divide each of the second audio segments into a plurality of original frequency band signals according to a preset frequency band division rule;

[0111] The gain application unit is used to adjust each of the original frequency band signals according to the center frequency of each of the frequency band signals and the corresponding gain coefficient to obtain each frequency band signal;

[0112] The merging unit is used to merge and reconstruct the frequency band signals to obtain the third audio segments.

[0113] The frequency band adjustment module M4 of this embodiment divides each audio segment into frequency bands and calculates the gain coefficient of each frequency band according to the user's hearing loss characteristics, thereby achieving precise optimization for individual hearing loss and ensuring that the audio signal of each frequency band can adapt to the user's hearing needs.

[0114] Furthermore, the gain coefficient calculation unit includes: a gain optimization subunit:

[0115] The gain optimization subunit is used to optimize and adjust the gain coefficient according to a preset weight function, wherein the algorithm is as follows:

[0116] Where G(f) represents the gain coefficient of frequency f, c represents a constant, H(f) represents the hearing loss of the user at frequency f, and w(f) represents a weight function.

[0117] In this embodiment, the gain optimization subunit further optimizes the distribution of gain coefficients by introducing a weight function, ensuring that the calculation of the gain coefficients is more accurate, so that the enhancement of audio signals in different frequency bands is more in line with the user's auditory needs, thereby significantly improving the effectiveness and personalization of tinnitus masking audio.

[0118] The result output module M5 is used to synthesize each of the third audio segments and output a masking sound.

[0119] In summary, compared with the prior art, the above embodiments of the present application have the following beneficial effects: by analyzing the user's hearing loss spectrum and combining it with a preset audio database, the audio clips suitable for the user's hearing characteristics are accurately matched, ensuring that the subsequently generated masking audio can cover the user's tinnitus frequency range in a targeted manner, thereby improving the tinnitus masking effect. At the same time, the preset audio library is used to provide a variety of audio materials, increasing the possibility of audio changes; by calculating the adjustment weights of each audio track in each audio clip, and adjusting according to these weights, the proportion of sound elements within each audio clip is dynamically optimized, which not only ensures the coordination between different frequency components within the audio clip, avoids the situation where a certain level is too prominent or masked, but also enhances the layering and richness of the audio. The dynamic adjustment allows the audio to always maintain a rich sense of change during playback, further improving the user's auditory comfort and masking effect; A specific volume adjustment algorithm changes the volume of audio clips, ensuring the fade-in and fade-out effect during audio playback, making the volume connection between audio clips natural and harmonious, and improving the user's auditory experience; by adjusting the audio signal of each frequency band based on the hearing loss spectrum diagram, accurate optimization for individual hearing loss is achieved, ensuring that the audio signal of each frequency band can adapt to the user's hearing needs. The frequency band adjustment also takes into account the balance between different frequency bands, avoiding excessive enhancement or weakening of certain frequency bands, ensuring the overall harmony and naturalness of the audio, and further improving the tinnitus masking effect and user satisfaction; finally, all processed audio clips are synthesized into a complete audio file, and the final masking sound is output, which not only has personalized frequency band optimization and volume adjustment, but also maintains the dynamic change characteristics of the audio, ensuring that the user will not notice the looping of the audio, improving the tinnitus masking effect and the user's auditory comfort.

[0120] The division of the modules described above is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules may be combined or integrated into another system.

[0121] Embodiment three:

[0122] Figure 3 The structure diagram of a masking sound generating device based on hearing loss of the present application is shown. Figure 3 As shown, the masking sound generating device based on hearing loss may include: a processor N1, a memory N2, a data interface N3 and a communication bus N4.

[0123] Among them: the processor N1, the memory N2, and the data interface N3 communicate with each other through the communication bus N4; the data interface N3 is used for data communication with other devices such as an input device or an output device; the processor N1 is used to execute the program N5, which can specifically execute the relevant steps in the above-mentioned embodiment of the masking sound generation method based on hearing loss.

[0124] Specifically, the program N5 may include program codes, and the program codes include computer executable instructions.

[0125] The processor N1 may be a central processing unit CPU, or an application specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the masking sound generation device based on hearing loss may be processors of the same type, such as one or more CPUs, or may be processors of different types, such as one or more CPUs and one or more ASICs.

[0126] The memory N2 is used to store the program N5. The memory N2 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage.

[0127] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system or other device. In addition, the embodiments of the present application are not directed to any particular programming language.

[0128] Embodiment 4:

[0129] An embodiment of the present invention also provides a computer-readable storage medium, which stores at least one executable instruction. When the executable instruction is executed on a masking sound generating device / system based on hearing loss, the masking sound generating device / system based on hearing loss executes the distribution robot performance evaluation method in any of the above method embodiments.

[0130] In the specification provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. Similarly, in order to simplify the application and help understand one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present application, the various features of the embodiments of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. Wherein, the claims that follow the specific embodiment are thus clearly incorporated into the specific embodiment, wherein each claim itself is used as a separate embodiment of the application.

[0131] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and further may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive.

Claims

1. A method for generating masking sound based on hearing loss, characterized in that: include: Matching several audio clips according to the user's hearing loss spectrum and a preset audio database; Calculating an adjustment weight of each audio track in each of the audio clips, and adjusting each audio clip according to the adjustment weight of each audio track to obtain each first audio clip; adjusting the volume of each of the first audio clips according to a preset volume adjustment algorithm to obtain each of the second audio clips; According to the hearing loss spectrum diagram, adjusting the audio signals of each frequency band of each second audio segment to obtain each third audio segment; The third audio segments are synthesized to output a masking sound.

2. A method for generating masking sound based on hearing loss as claimed in claim 1, characterized in that: The calculating the adjustment weight of each audio track in each audio segment, and adjusting each audio segment according to the adjustment weight of each audio track to obtain each first audio segment, includes: Calculating the adjustment weight of each audio track according to the frequency characteristics, volume characteristics and timing characteristics of each audio track in each of the audio clips; The audio segments are adjusted according to the adjustment weights of the audio tracks to obtain first audio segments.

3. The method for generating masking sound based on hearing loss according to claim 2, characterized in that: The step of adjusting the volume of each of the first audio segments according to a preset volume adjustment algorithm to obtain each of the second audio segments includes: The volume adjustment algorithm is as follows: V(t) = V start +(V end - V start ) × f(t); Wherein, V(t) represents the volume at time t, V start and V end They represent the volume values ​​at the beginning and end of the audio clip respectively, f(t) represents the time function, fade_in_time and fade_out_time represent the fade-in time and fade-out time of the audio clip respectively.

4. The method for generating masking sound based on hearing loss according to claim 3, characterized in that: The step of adjusting the audio signals of each frequency band of each second audio segment according to the hearing loss spectrum to obtain each third audio segment includes: Extracting hearing loss features according to the hearing loss spectrum, and calculating gain coefficients corresponding to each audio frequency according to the hearing loss features; According to a preset frequency band division rule, each of the second audio segments is divided into a plurality of original frequency band signals of different frequencies; Adjusting each of the original frequency band signals according to the center frequency and the corresponding gain coefficient of each of the frequency band signals to obtain each of the frequency band signals; The frequency band signals are combined and reconstructed to obtain third audio segments.

5. The method for generating masking sound based on hearing loss according to claim 4, characterized in that: The step of extracting hearing loss features according to the hearing loss spectrum diagram, and calculating gain coefficients corresponding to each audio frequency according to the hearing loss features, includes: According to the preset weight function, the gain coefficient is optimized and adjusted, wherein the algorithm is as follows: Where G(f) represents the gain coefficient of frequency f, c represents a constant, H(f) represents the hearing loss of the user at frequency f, and w(f) represents a weight function.

6. A masking sound generation system based on hearing loss, characterized in that: include: Matching module, audio track adjustment module, volume adjustment module, frequency band adjustment module and result output module; Wherein, the matching module is used to match a number of audio clips according to the user's hearing loss spectrum and a preset audio database; The audio track adjustment module is used to calculate the adjustment weight of each audio track in each audio segment, and adjust each audio segment according to the adjustment weight of each audio track to obtain each first audio segment; The volume adjustment module is used to adjust the volume of each of the first audio segments according to a preset volume adjustment algorithm to obtain each of the second audio segments; The frequency band adjustment module is used to adjust the audio signals of each frequency band of each second audio segment according to the hearing loss spectrum to obtain each third audio segment; The result output module is used to synthesize each of the third audio segments and output a masking sound.

7. A masking sound generation system based on hearing loss as claimed in claim 6, characterized in that: The audio track adjustment module includes: an adjustment weight calculation unit and an audio track adjustment unit; The adjustment weight calculation unit is used to calculate the adjustment weight of each audio track according to the frequency characteristics, volume characteristics and timing characteristics of each audio track in each audio segment; The audio track adjustment unit is used to adjust each audio segment according to the adjustment weight of each audio track to obtain each first audio segment.

8. The masking sound generation system based on hearing loss according to claim 7, characterized in that: The volume adjustment module comprises: The volume adjustment algorithm is as follows: V(t) = V start + (V end - V start ) × f(t); Wherein, V(t) represents the volume at time t, V start and V end They represent the volume values ​​at the beginning and end of the audio clip respectively, f(t) represents the time function, fade_in_time and fade_out_time represent the fade-in time and fade-out time of the audio clip respectively.

9. A masking sound generating device based on hearing loss, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the computer program is loaded into a processor, the steps of the method for generating masking sound based on hearing loss according to any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for generating masking sound based on hearing loss according to any one of claims 1 to 5 are implemented.

Images