Search

CN-121985252-A - Audio equalization adjustment method, device and storage medium

CN121985252ACN 121985252 ACN121985252 ACN 121985252ACN-121985252-A

Abstract

The present application relates to the field of audio signal processing technologies, and in particular, to an audio equalization adjustment method, apparatus, and storage medium. The audio equalization adjustment method comprises the steps of obtaining physiological motion signals and environment audio signals of a user, respectively processing the physiological motion signals and the environment audio signals to obtain physiological motion characteristics and environment noise characteristics, conducting fusion decision based on the physiological motion characteristics and the environment noise characteristics to generate a target equalization parameter set, and conducting equalization adjustment on audio output signals of near-eye display equipment based on the target equalization parameter set. The method provided by the application can intelligently optimize the hearing experience of the near-eye display equipment in the sports scene.

Inventors

  • HU LITIAN

Assignees

  • 珠海莫界科技有限公司

Dates

Publication Date
20260505
Application Date
20251230

Claims (10)

  1. 1. An audio equalization adjustment method for use with a near-eye display device, the method comprising: acquiring physiological motion signals and environmental audio signals of a user; Processing the physiological motion signal and the environmental audio signal respectively to obtain physiological motion characteristics and environmental noise characteristics; performing fusion decision based on the physiological motion characteristics and the environmental noise characteristics to generate a target balance parameter set; and carrying out balance adjustment on the audio output signal of the near-eye display device based on the target balance parameter set.
  2. 2. The method of claim 1, wherein the generating a target equalization parameter set based on the physiological motion characteristic and the ambient noise characteristic to make a fusion decision comprises: when the physiological motion characteristic or the environmental noise characteristic is switched from a normal state to a high-order state, and at least a first switching duration is preset in the high-order state, generating a first target equalization parameter set corresponding to the high-order state; and when the physiological motion characteristic or the environmental noise characteristic is switched back to the normal state from the high-order state, and at least a second switching time period is kept in the normal state, generating a second target equalization parameter set for releasing the correspondence of the high-order state, wherein the second switching time period is longer than the first switching time period.
  3. 3. The method of claim 1, wherein the near-eye display device has a dual microphone array integrated thereon, wherein the ambient noise signature further comprises overall ambient noise energy and wind noise direction, wherein processing the ambient audio signal to obtain the ambient noise signature comprises: processing the environmental audio signals acquired by the double-microphone array on the left side and the right side of the near-eye display device by adopting a noise power estimation algorithm to obtain left channel environmental noise energy and right channel environmental noise energy; calculating the average value of the left channel environmental noise energy and the right channel environmental noise energy to obtain overall environmental noise energy; And calculating the difference value of the left channel environmental noise energy and the right channel environmental noise energy, and comparing the difference value with a preset noise difference threshold value to obtain the wind noise direction.
  4. 4. The method of claim 1, wherein the generating a target equalization parameter set based on the physiological motion characteristic and the ambient noise characteristic to make a fusion decision comprises: Respectively matching the physiological motion characteristics and the environmental noise characteristics with a preset frequency response gain rule set, a sound channel balance rule set and an overall volume gain rule set as input characteristics to determine a matched frequency response gain rule, a sound channel balance rule and an overall volume gain rule; And generating corresponding frequency response gain parameters, channel balance parameters and integral volume gain parameters to form a target balance parameter set according to the matched frequency response gain rule, channel balance rule and integral volume gain rule.
  5. 5. The method of claim 4, wherein the set of frequency response gain rules includes a first frequency response gain rule that generates a first frequency response gain parameter for boosting a preset mid-to-high band gain when a duration of a heart rate exceeding a preset high heart rate threshold is greater than a first preset duration, and a second frequency response gain rule that generates a second frequency response gain parameter for boosting a preset low band dynamic range when a duration of a step frequency exceeding a preset high step frequency threshold is greater than a second preset duration.
  6. 6. The method of claim 4, wherein the set of overall volume gain rules includes overall volume gain rules that generate an overall volume gain parameter for boosting overall output volume when overall ambient noise energy exceeds a preset high noise threshold for a duration greater than a third preset duration; The channel balance rule set comprises a channel balance rule that when the duration time that the absolute value of the difference value of the left channel environment noise energy and the right channel environment noise energy is larger than the preset noise difference threshold value is longer than the fourth preset duration time and the head gesture of the user is a non-turning gesture, channel balance parameters for improving the gain of the loudspeaker on the opposite side of the wind noise direction are generated.
  7. 7. The method of claim 1, wherein the generating a target equalization parameter set based on the physiological motion characteristic and the ambient noise characteristic to make a fusion decision comprises: determining the current motion state of the user through a preset motion scene recognition model based on the physiological motion characteristics; And carrying out fusion decision based on the current motion state and the environmental noise characteristics to generate a target equalization parameter set.
  8. 8. The method of any of claims 1-7, wherein said equalizing the audio output signal of the near-eye display device based on the target equalization parameter set comprises: And carrying out equalization adjustment on the audio output signal of the near-eye display device in a fifth preset duration based on a parameter set sequence of which at least part of parameters gradually change in the fifth preset duration by adopting a parameter smoothing algorithm on at least part of parameters in the target equalization parameter set.
  9. 9. A near-eye display device comprising at least one processor and a memory communicatively coupled to the at least one processor, the memory storing instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 8.
  10. 10. A computer storage medium storing instructions or a program which, when executed by at least one processor, cause the at least one processor to perform the method of any one of claims 1 to 8.

Description

Audio equalization adjustment method, device and storage medium Technical Field The present application relates to the field of audio signal processing technologies, and in particular, to an audio equalization adjustment method, apparatus, and storage medium. Background With the popularity of near-eye display devices such as augmented Reality (Augmented Reality, AR), virtual Reality (VR), etc., their application in dynamic scenes such as commute, sports, outdoor exploration, etc., is becoming increasingly widespread. In order to achieve wearing comfort and environmental perception safety, the equipment mostly adopts an open type or semi-open type loudspeaker to output audio. In the related art, most schemes of near-eye display devices use a fixed equalizer (Equalization, EQ), and perform fixed wind noise suppression and simple automatic gain control only according to the environmental noise intensity, so that complex acoustic changes in a moving scene cannot be dealt with. Therefore, it is needed to provide a scheme capable of merging the motion state of the user and the environmental sound field information to perform multidimensional and intelligent dynamic audio balance adjustment, so as to comprehensively improve the hearing experience of the near-eye display device in the motion scene. Disclosure of Invention The embodiment of the application aims to provide an audio balance adjustment method, equipment and a storage medium, which can intelligently optimize the hearing experience of near-eye display equipment in a motion scene. In order to solve the technical problems, the embodiment of the application provides the following technical scheme: in a first aspect, an embodiment of the present application provides an audio equalization adjustment method, applied to a near-eye display device, where the method includes: acquiring physiological motion signals and environmental audio signals of a user; Processing the physiological motion signal and the environmental audio signal respectively to obtain physiological motion characteristics and environmental noise characteristics; performing fusion decision based on the physiological motion characteristics and the environmental noise characteristics to generate a target balance parameter set; and carrying out balance adjustment on the audio output signal of the near-eye display device based on the target balance parameter set. Optionally, the performing a fusion decision based on the physiological motion feature and the environmental noise feature, generating a target equalization parameter set includes: when the physiological motion characteristic or the environmental noise characteristic is switched from a normal state to a high-order state, and at least a first switching duration is preset in the high-order state, generating a first target equalization parameter set corresponding to the high-order state; and when the physiological motion characteristic or the environmental noise characteristic is switched back to the normal state from the high-order state, and at least a second switching time period is kept in the normal state, generating a second target equalization parameter set for releasing the correspondence of the high-order state, wherein the second switching time period is longer than the first switching time period. Optionally, the near-eye display device is integrated with a dual microphone array, the environmental noise feature further includes overall environmental noise energy and wind noise direction, the processing the environmental audio signal, and obtaining the environmental noise feature includes: Processing the environmental audio signals acquired by the double-microphone array on the left side and the right side of the near-eye display device by adopting a noise power estimation algorithm to obtain left-right channel environmental noise energy and right channel environmental noise energy; calculating the average value of the left channel environmental noise energy and the right channel environmental noise energy to obtain overall environmental noise energy; and calculating the difference value of the left channel environmental noise energy and the right channel environmental noise energy, and comparing the difference value with a preset noise difference threshold value to obtain the wind noise direction. Optionally, the performing a fusion decision based on the physiological motion feature and the environmental noise feature, generating a target equalization parameter set includes: Respectively matching the physiological motion characteristics and the environmental noise characteristics with a preset frequency response gain rule set, a sound channel balance rule set and an overall volume gain rule set as input characteristics to determine a matched frequency response gain rule, a sound channel balance rule and an overall volume gain rule; And generating corresponding frequency response gain parameters, channel balance parameters and integr