Noise reduction evaluation method, device, storage medium, and program product
By comparing un-noise-reduced and noise-reduced call audio collected from the speaker array of a head-mounted display device, a noise reduction evaluation result is generated, which solves the problem of inaccurate evaluation in the prior art and improves the evaluation accuracy of the noise reduction performance of the head-mounted display device.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- GOERTEK INC
- Filing Date
- 2024-12-03
- Publication Date
- 2026-06-05
AI Technical Summary
Existing noise reduction evaluation methods are poorly applicable to head-mounted display devices, making it difficult to accurately assess their noise reduction performance.
By collecting audio from each speaker in the speaker array of a head-mounted display device under a predetermined test environment, obtaining call audio with and without noise reduction, comparing them, and generating noise reduction evaluation results.
This improves the accuracy of evaluating the noise reduction performance of head-mounted displays, is suitable for the speaker array structure of head-mounted displays, and enhances the applicability of the evaluation.
Smart Images
Figure CN122160676A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of head-mounted display technology, and more particularly to a noise reduction evaluation method, apparatus, storage medium, and program product. Background Technology
[0002] In recent years, head-mounted display devices have developed rapidly, and VR glasses, AR glasses and other head-mounted display devices have gradually entered people's lives. As the functions of head-mounted display devices become more and more abundant, the call function has become the focus of attention for many users.
[0003] However, due to the unique nature of voice calls using head-mounted displays, call quality is often more susceptible to external noise. Head-mounted displays are in close contact with the user's head during use, and typically employ speaker arrays with multiple speakers positioned at different locations on the device for audio output. Existing noise reduction evaluation methods are primarily designed for headphones. Because the application scenarios for headphones and head-mounted displays differ significantly, existing noise reduction evaluation methods are poorly applicable to head-mounted displays and struggle to accurately assess their noise reduction performance.
[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention
[0005] The main objective of this application is to provide a noise reduction evaluation method, device, storage medium, and program product, which aims to solve the technical problem that existing noise reduction evaluation methods are poorly applicable to head-mounted display devices and have difficulty in accurately evaluating the noise reduction performance of head-mounted display devices.
[0006] To achieve the above objectives, this application proposes a noise reduction evaluation method applied to a head-mounted display device, the noise reduction evaluation method comprising: In a predetermined test environment, a predetermined standard call was conducted on a head-mounted display device without noise reduction, and audio was collected from each speaker in the speaker array of the head-mounted display device to obtain the audio of the call without noise reduction. Under the predetermined test environment, a predetermined standard call was made to the head-mounted display device after noise reduction was performed, and audio was collected from each speaker in the speaker array of the head-mounted display device to obtain the noise-reduced call audio. The noise reduction evaluation result of the head-mounted display device is obtained by comparing the un-noise-reduced call audio with the noise-reduced call audio.
[0007] In one embodiment, the step of conducting a predetermined standard call on a head-mounted display device without noise reduction operation under a predetermined test environment, and collecting audio from each speaker in the speaker array of the head-mounted display device to obtain the un-noise-reduced call audio, includes: In a predetermined test environment, after establishing a communication connection between a predetermined terminal device and a head-mounted display device that has not performed noise reduction, predetermined call content is transmitted to the head-mounted display device that has not performed noise reduction in order to conduct a predetermined standard call. During the predetermined standard call, sound is collected from each speaker position in the speaker array of the head-mounted display device that has not performed noise reduction operation, to obtain the first call audio; Sound is collected from the predetermined test environment within the user listening area of the head-mounted display device to obtain a first background noise. The first call audio and the first background noise are used as the un-noise-reduced call audio.
[0008] In one embodiment, the steps of conducting a predetermined standard call on a head-mounted display device after noise reduction operation under the predetermined test environment, and acquiring audio from each speaker in the speaker array of the head-mounted display device to obtain the noise-reduced call audio, include: Under the predetermined test environment, after establishing a communication connection between the predetermined terminal device and the head-mounted display device after noise reduction, the predetermined call content is transmitted to the head-mounted display device after noise reduction to conduct a predetermined standard call; During the predetermined standard call, sound is collected from each speaker position in the speaker array of the head-mounted display device after noise reduction operation is performed, to obtain the second call audio; Sound is collected from the predetermined test environment within the user listening area of the head-mounted display device to obtain a second background noise. The second call audio and the second background noise are used as the noise-reduced call audio.
[0009] In one embodiment, prior to the step of conducting a predetermined standard call on a head-mounted display device without noise reduction operation under a predetermined test environment, the noise reduction evaluation method further includes: After the predetermined test environment is a noisy environment, the noise audio of the noisy environment is acquired and the noise audio is output. Once the predetermined test environment is a quiet environment, the output of the noise audio is canceled.
[0010] In one embodiment, the step of comparing the un-noise-reduced call audio with the noise-reduced call audio to obtain the noise reduction evaluation result of the head-mounted display device includes: The voice content of the un-noise-reduced call audio and the noise-reduced call audio are compared to obtain voice distortion information; The background noise of the un-noise-reduced call audio and the noise-reduced call audio is compared to obtain the noise reduction decibel information; Based on the speech distortion information and the noise reduction decibel information, a noise reduction evaluation result for the head-mounted display device is generated.
[0011] In one embodiment, the step of comparing the voice content of the undenoised call audio and the denoised call audio to obtain voice distortion information includes: Extract the first call voice feature from the undenoised call audio and extract the second call voice feature from the denoised call audio; Calculate the speech difference measure between the first call speech feature and the second call speech feature: The speech difference metric is used as speech distortion information.
[0012] In one embodiment, the step of comparing the background noise of the un-noise-reduced call audio and the noise-reduced call audio to obtain noise reduction decibel information includes: The first background noise in the un-noise-reduced call audio and the second background noise in the noise-reduced call audio are divided into predetermined frequency bands to obtain each first frequency band noise and each second frequency band noise; Calculate the first noise decibel level for each first frequency band and the second noise decibel level for each second frequency band; The noise decibel difference between the first noise decibel of the first frequency band noise and the second noise decibel of the second frequency band noise under the same frequency band is used as the noise reduction decibel information.
[0013] In addition, to achieve the above objectives, this application also proposes a noise reduction evaluation device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the noise reduction evaluation method as described above.
[0014] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and which, when executed by a processor, implements the steps of the noise reduction evaluation method described above.
[0015] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the noise reduction evaluation method described above.
[0016] One or more technical solutions proposed in this application have at least the following technical effects: This application obtains un-noise-reduced call audio by conducting a standard call on a head-mounted display device without noise reduction in a predetermined test environment and collecting audio from each speaker in the head-mounted display device's speaker array. Then, in the same predetermined test environment, a standard call is conducted on the head-mounted display device with noise reduction performed, and audio from each speaker in the head-mounted display device's speaker array is collected again to obtain noise-reduced call audio. Thus, by collecting audio from each speaker in the head-mounted display device's speaker array separately, both the un-noise-reduced and noise-reduced call audio samples include independent audio information from each speaker. The un-noise-reduced and noise-reduced call audio samples are then compared to obtain a noise reduction evaluation result for the head-mounted display device. This noise reduction evaluation result, based on the audio information of each speaker in the head-mounted display device's speaker array, is more suitable for head-mounted display devices than existing noise reduction evaluation methods used for headphones, effectively improving the accuracy of evaluating the noise reduction performance of head-mounted display devices. Attached Figure Description
[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0019] Figure 1 This is a flowchart illustrating an embodiment of the noise reduction evaluation method of this application. Figure 2 This is a schematic diagram of the structure of the head-mounted display device according to an embodiment of this application; Figure 3 This is a flowchart illustrating Embodiment 2 of the noise reduction evaluation method of this application; Figure 4 This is a flowchart illustrating Embodiment 2 of the noise reduction evaluation method of this application; Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the noise reduction evaluation method in the embodiments of this application.
[0020] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.
[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.
[0023] The main solution of this application embodiment is as follows: Under a predetermined test environment, a predetermined standard call is made to a head-mounted display device without noise reduction operation, and audio is collected from each speaker in the speaker array of the head-mounted display device to obtain un-noise-reduced call audio; Under the predetermined test environment, a predetermined standard call is made to a head-mounted display device after noise reduction operation is performed, and audio is collected from each speaker in the speaker array of the head-mounted display device to obtain noise-reduced call audio; The un-noise-reduced call audio and the noise-reduced call audio are compared to obtain the noise reduction evaluation result of the head-mounted display device.
[0024] In this embodiment, for ease of description, the following description uses a head-mounted display device as the execution subject.
[0025] Due to the unique nature of voice calls made using head-mounted displays, call quality is often more susceptible to external noise. Head-mounted displays are in close contact with the user's head during use, and typically employ speaker arrays with multiple speakers positioned at different locations on the device for audio output. However, existing noise reduction evaluation methods are primarily designed for headphones. Because the application scenarios for headphones and head-mounted displays differ significantly, existing noise reduction evaluation methods are poorly applicable to head-mounted displays and struggle to accurately assess their noise reduction performance.
[0026] This application provides a solution for head-mounted display devices. During testing, audio is collected from each speaker in the head-mounted display device's speaker array. Both the un-noise-reduced and noise-reduced call audio samples include independent audio information from each speaker. The un-noise-reduced and noise-reduced call audio samples are then compared to obtain a noise reduction evaluation result for the head-mounted display device. This noise reduction evaluation result, based on the audio information of each speaker in the head-mounted display device's speaker array, is more suitable for head-mounted display devices than existing noise reduction evaluation methods used for headphones, effectively improving the accuracy of evaluating the noise reduction performance of head-mounted display devices.
[0027] Based on this, embodiments of this application provide a noise reduction evaluation method, referring to... Figure 1 , Figure 1This is a flowchart illustrating the first embodiment of the noise reduction evaluation method of this application.
[0028] In this embodiment, the noise reduction evaluation method includes steps S10 to S30: Step S10: Under a predetermined test environment, a predetermined standard call is made to the head-mounted display device without noise reduction operation, and audio is collected from each speaker in the speaker array of the head-mounted display device to obtain the audio of the call without noise reduction. It should be noted that the planned test environment includes a quiet environment and at least one noisy environment, such as traffic noise, crowd noise, etc.
[0029] Additionally, it should be noted that head-mounted display devices can be virtual reality glasses, augmented reality glasses, mixed reality glasses, etc. Figure 2 As shown, a speaker array is configured on the head-mounted display device, which consists of multiple speakers disposed at different positions on the head-mounted display device.
[0030] This embodiment establishes a communication connection between a predetermined terminal device (such as a smartphone or tablet) and a head-mounted display device without noise reduction in a predetermined test environment, including a quiet environment and at least one noisy environment. A predetermined call audio containing predetermined call content is played on the predetermined terminal device, causing the speaker array of the head-mounted display device without noise reduction to play the received predetermined call content for a predetermined standard call. During the predetermined standard call, this embodiment uses multiple recording devices (such as microphones and sound level meters) to collect sound from each speaker in the speaker array of the head-mounted display device without noise reduction, obtaining a first call audio. It is understood that the first call audio includes the first audio content collected from the output audio of each speaker in the speaker array of the head-mounted display device without noise reduction. Furthermore, by collecting sound from the predetermined test environment in the user's listening area of the head-mounted display device (i.e., the area where the user's ears are when wearing the head-mounted display device), a first background noise is obtained, and the first call audio and the first background noise are used as the un-noise-reduced call audio.
[0031] In one feasible implementation, step S10 may include steps S11 to S14: Step S11: In a predetermined test environment, after establishing a communication connection between a predetermined terminal device and a head-mounted display device that has not performed noise reduction operation, the predetermined call content is transmitted to the head-mounted display device that has not performed noise reduction operation to conduct a predetermined standard call. Step S12: During the predetermined standard call, sound is collected at each speaker position in the speaker array of the head-mounted display device that has not performed noise reduction operation, to obtain the first call audio. Step S13: Collect sound from the predetermined test environment in the user listening area of the head-mounted display device to obtain the first background noise; Step S14: The first call audio and the first background noise are used as the un-noise-reduced call audio.
[0032] It should be noted that the predetermined terminal device is a terminal device pre-configured for communication with the head-mounted device, such as a smartphone or tablet. The predetermined call content is the pre-configured content of the call between the predetermined terminal device and the head-mounted device.
[0033] In this embodiment, in a quiet environment, after establishing a communication connection between a predetermined terminal device and a head-mounted display device without noise reduction, predetermined call content is transmitted to the head-mounted display device without noise reduction to conduct a predetermined standard call. During the predetermined standard call in the quiet environment, sound is collected at each speaker position in the speaker array of the head-mounted display device without noise reduction to obtain a first quiet call audio. Sound is also collected in the quiet environment to obtain a first quiet background noise. Then, in at least one noisy environment, after establishing a communication connection between a predetermined terminal device and a head-mounted display device without noise reduction, predetermined call content is transmitted to the head-mounted display device without noise reduction to conduct a predetermined standard call. During the predetermined standard call in the noisy environment, sound is collected at each speaker position in the speaker array of the head-mounted display device without noise reduction to obtain a first noisy call audio. Sound is also collected in the noisy environment to obtain a first noisy background noise. The first quiet call audio and the first noisy call audio are used as the first call audio, and the first quiet background noise and the first noisy background noise are used as the first background noise. The first call audio and the first background noise are used as the un-noise-reduced call audio.
[0034] In this embodiment, after establishing a communication connection between a predetermined terminal device and a head-mounted display device without noise reduction operation under a predetermined test environment, predetermined call content is transmitted to the head-mounted display device without noise reduction operation to conduct a predetermined standard call. During the predetermined standard call, sound is collected at each speaker position in the speaker array of the head-mounted display device without noise reduction operation to obtain a first call audio. Sound is collected in the predetermined test environment within the user listening area of the head-mounted display device to obtain a first background noise. The first call audio and the first background noise are used as the un-noise-reduced call audio. This embodiment realizes the audio collection of each speaker in the speaker array of the head-mounted display device without noise reduction operation and the background environment under a predetermined test environment.
[0035] Step S20: Under the predetermined test environment, a predetermined standard call is made to the head-mounted display device after noise reduction operation, and audio is collected from each speaker in the speaker array of the head-mounted display device to obtain the noise-reduced call audio. This embodiment establishes a communication connection between a predetermined terminal device (such as a smartphone, tablet, or other terminal device) and a noise-reduced head-mounted display device in a predetermined test environment, including a quiet environment and at least one noisy environment. A predetermined call audio containing predetermined call content is played on the predetermined terminal device, causing the speaker array of the noise-reduced head-mounted display device to play the received predetermined call content for a predetermined standard call. During the predetermined standard call, this embodiment uses multiple recording devices (such as microphones and sound level meters) to collect sound from each speaker in the speaker array of the noise-reduced head-mounted display device, obtaining a second call audio. It is understood that the second call audio includes second audio content collected from the output audio of each speaker in the speaker array of the noise-reduced head-mounted display device. Furthermore, by collecting sound from the predetermined test environment within the user's listening area of the head-mounted display device, a second background noise is obtained, and the second call audio and the second background noise are used as the noise-reduced call audio.
[0036] In one feasible implementation, step S20 may include steps S21 to S24: Step S21: Under the predetermined test environment, after establishing a communication connection between the predetermined terminal device and the head-mounted display device after noise reduction operation, the predetermined call content is transmitted to the head-mounted display device after noise reduction operation to conduct a predetermined standard call. Step S22: During the predetermined standard call, sound is collected at each speaker position in the speaker array of the head-mounted display device after noise reduction operation is performed to obtain the second call audio. Step S23: Collect sound from the predetermined test environment in the user listening area of the head-mounted display device to obtain the second background noise; Step S24: Use the second call audio and the second background noise as the noise-reduced call audio.
[0037] In this embodiment, in a quiet environment, after establishing a communication connection between a predetermined terminal device and a head-mounted display device that has undergone noise reduction, predetermined call content is transmitted to the head-mounted display device to conduct a predetermined standard call. During the predetermined standard call in the quiet environment, sound is collected at each speaker position in the speaker array of the head-mounted display device that has undergone noise reduction, resulting in a second quiet call audio. Sound is also collected in the quiet environment to obtain a second quiet background noise. Then, in at least one noisy environment, after establishing a communication connection between a predetermined terminal device and a head-mounted display device that has undergone noise reduction, predetermined call content is transmitted to the head-mounted display device to conduct a predetermined standard call. During the predetermined standard call in the noisy environment, sound is collected at each speaker position in the speaker array of the head-mounted display device that has undergone noise reduction, resulting in a second noisy call audio. Sound is also collected in the noisy environment to obtain a second noisy background noise. The second quiet call audio and the second noisy call audio are used as the second call audio, and the second quiet background noise and the second noisy background noise are used as the second background noise. The second call audio and the second background noise are used as the noise-reduced call audio.
[0038] In this embodiment, after establishing a communication connection between a predetermined terminal device and a head-mounted display device that has undergone noise reduction operation under a predetermined test environment, predetermined call content is transmitted to the head-mounted display device that has undergone noise reduction operation to conduct a predetermined standard call. During the predetermined standard call, sound is collected at each speaker position in the speaker array of the head-mounted display device that has undergone noise reduction operation to obtain a second call audio. Sound is collected in the predetermined test environment within the user listening area of the head-mounted display device to obtain a second background noise. The second call audio and the second background noise are used as the noise-reduced call audio. This embodiment realizes the audio acquisition of each speaker in the speaker array of the head-mounted display device that has undergone noise reduction operation and the background environment under a predetermined test environment.
[0039] Step S30: Compare the un-noise-reduced call audio with the noise-reduced call audio to obtain the noise reduction evaluation result of the head-mounted display device.
[0040] This embodiment compares the voice content of the un-noise-reduced call audio and the denoised call audio, and then measures the difference between the first call audio in the un-noise-reduced call audio and the second call audio in the denoised call audio in at least one descriptive speech distortion index, such as signal-to-noise ratio, segmented signal-to-noise ratio, perceptual evaluation, and speech quality assessment, as speech distortion information. This embodiment can also compare the background noise of the un-noise-reduced call audio and the denoised call audio, and then use the noise decibel difference between the first background noise in the un-noise-reduced call audio and the second background noise in the denoised call audio as noise reduction decibel information. Based on the speech distortion information and the noise reduction decibel information, a noise reduction evaluation result for the head-mounted display device is generated. For example, this embodiment can use the speech distortion information and the noise reduction decibel information as the noise reduction evaluation result for the head-mounted display device. Alternatively, the difference measures of each speech distortion index in the speech distortion information can be normalized to obtain a distortion score, and the noise decibel difference in the noise reduction decibel information can be normalized to obtain a noise reduction score. Then, by weighted summing the distortion score and the noise reduction score, a total noise reduction score is obtained as the noise reduction evaluation result.
[0041] The first embodiment of this application provides a noise reduction evaluation method applied to a head-mounted display device. Under a predetermined test environment, a predetermined standard call is conducted on the head-mounted display device without noise reduction, and audio is collected from each speaker in the head-mounted display device's speaker array to obtain un-noise-reduced call audio. Then, under the same predetermined test environment, a predetermined standard call is conducted on the head-mounted display device after noise reduction, and audio is collected from each speaker in the head-mounted display device's speaker array to obtain noise-reduced call audio. Thus, this embodiment, by collecting audio from each speaker in the head-mounted display device's speaker array separately, ensures that both the un-noise-reduced and noise-reduced call audio include independent audio information from each speaker. The un-noise-reduced and noise-reduced call audio are then compared to obtain the noise reduction evaluation result of the head-mounted display device. Therefore, this noise reduction evaluation result can be obtained based on the audio information of each speaker in the head-mounted display device's speaker array. Compared to existing noise reduction evaluation methods used for headphones, this method is more suitable for head-mounted display devices and effectively improves the accuracy of evaluating the noise reduction performance of head-mounted display devices.
[0042] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 Before step S10, the noise reduction evaluation method further includes steps S01~S02: Step S01: After the predetermined test environment is a noisy environment, acquire the noise audio of the noisy environment and output the noise audio; Step S02: After the predetermined test environment is a quiet environment, the output of the noise audio is canceled.
[0043] It should be noted that the noise environment is a pre-defined environment with noise, such as traffic noise, crowd noise, etc. The noise audio is a pre-defined audio value of the noise in the aforementioned noise environment.
[0044] In this embodiment, a quiet, independent testing space is first provided for the head-mounted display device. Then, after the predetermined testing environment is determined to be a noisy environment, noise audio corresponding to the noisy environment can be acquired. This noise audio can be output by controlling a device equipped with a speaker (such as a noise generator), thereby changing the environment in which the head-mounted display device is located to the noisy environment. Finally, after the predetermined testing environment is determined to be a quiet environment, the output of the noise audio is canceled to change the environment in which the head-mounted display device is located to the quiet environment.
[0045] The second embodiment of this application acquires and outputs noise audio from a noisy environment after the predetermined test environment is established; and cancels the output of the noise audio after the predetermined test environment is established as a quiet environment. Thus, this embodiment achieves the construction of the predetermined test environment.
[0046] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 4 Step S30 includes steps S31 to S33: Step S31: Compare the voice content of the un-noise-reduced call audio and the noise-reduced call audio to obtain voice distortion information; Step S32: Compare the background noise of the un-noise-reduced call audio and the noise-reduced call audio to obtain noise reduction decibel information; Step S33: Generate the noise reduction evaluation result of the head-mounted display device based on the speech distortion information and the noise reduction decibel information.
[0047] This embodiment compares the voice content of the un-noise-reduced call audio and the denoised call audio, and then measures the difference between the first call audio in the un-noise-reduced call audio and the second call audio in the denoised call audio in at least one descriptive speech distortion index, such as signal-to-noise ratio, segmented signal-to-noise ratio, perceptual evaluation, and speech quality assessment, as speech distortion information. This embodiment can also compare the background noise of the un-noise-reduced call audio and the denoised call audio, and then use the noise decibel difference between the first background noise in the un-noise-reduced call audio and the second background noise in the denoised call audio as noise reduction decibel information. Based on the speech distortion information and the noise reduction decibel information, a noise reduction evaluation result for the head-mounted display device is generated. For example, this embodiment can use the speech distortion information and the noise reduction decibel information as the noise reduction evaluation result for the head-mounted display device. Alternatively, the difference measures of each speech distortion index in the speech distortion information can be normalized to obtain a distortion score, and the noise decibel difference in the noise reduction decibel information can be normalized to obtain a noise reduction score. Then, by weighted summing the distortion score and the noise reduction score, a total noise reduction score is obtained as the noise reduction evaluation result.
[0048] In one feasible implementation, step S31 may include steps A10 to A30: Step A10: Extract the first call voice feature from the undenoised call audio and extract the second call voice feature from the denoised call audio. Step A20: Calculate the speech difference measure between the first call speech feature and the second call speech feature: Step A30: The speech difference measurement is used as speech distortion information.
[0049] It should be noted that the first call speech feature includes speech features reflecting the speech quality and distortion level of the first call audio in the undenoised call audio, and the second call speech feature includes speech features reflecting the speech quality and distortion level of the second call audio in the denoised call audio. The speech features reflecting the speech quality and distortion level may include at least one of the following features: spectral features (such as Mel frequency cepstral coefficients, spectral centroid, spectral flatness, etc.), time-domain features (such as short-time energy, short-time zero-crossing rate, fundamental frequency, etc.), and perceptual features (such as perceptual linear prediction coefficients).
[0050] This embodiment can preprocess the un-denoised and denoised call audio, such as through normalization and alignment. A first call speech feature is extracted from the un-denoised call audio, and a second call speech feature is extracted from the denoised call audio. Then, by converting the first and second call speech features into vectors, speech difference metrics such as Euclidean distance and cosine similarity between the first and second call speech features can be calculated. These speech difference metrics can then be used as speech distortion information. Therefore, this embodiment achieves an assessment of the impact of noise reduction on call quality for a head-mounted display device that has undergone noise reduction compared to one that has not.
[0051] In one feasible implementation, step S32 may include steps B10 to B30: Step B10: The first background noise in the un-noise-reduced call audio and the second background noise in the noise-reduced call audio are divided into predetermined frequency bands to obtain each first frequency band noise and each second frequency band noise. Step B20: Calculate the first noise decibel for each first frequency band and the second noise decibel for each second frequency band; Step B30: The noise decibel difference between the first noise decibel of the first frequency band noise and the second noise decibel of the second frequency band noise under the same frequency band is used as noise reduction decibel information.
[0052] It should be noted that the predetermined frequency bands are pre-defined frequency bands after the spectrum has been divided. For example, the spectrum can be divided into three frequency bands: low frequency (0-500Hz), mid frequency (500-2000Hz), and high frequency (2000-8000Hz). Of course, the predetermined frequency bands may include more or fewer frequency bands.
[0053] This embodiment can segment the first background noise in the un-noise-reduced call audio and the second background noise in the noise-reduced call audio according to a predetermined frequency band, obtaining each first frequency band noise and each second frequency band noise. For example, taking the predetermined frequency band as including low frequency, mid frequency, and high frequency, this embodiment can segment the first background noise in the un-noise-reduced call audio into each first frequency band noise of low frequency, mid frequency, and high frequency, and segment the second background noise in the noise-reduced call audio into each second frequency band noise of low frequency, mid frequency, and high frequency. Then, the first noise decibel of each first frequency band noise and the second noise decibel of each second frequency band noise can be calculated. Exemplarily, this embodiment can calculate the energy within each first frequency band noise and each second frequency band noise (e.g., by calculating the sum of squares of all frequency components within the frequency band), and then convert the energy into decibel values to obtain the first noise decibel of each first frequency band noise and the second noise decibel of each second frequency band noise. Then, the noise decibel difference between the first noise decibel of the first frequency band noise and the second noise decibel of the second frequency band noise in the same frequency band can be used as noise reduction decibel information. Alternatively, the noise decibel difference in each frequency band can be weighted and averaged to obtain the average noise reduction decibel as the noise reduction decibel information.
[0054] The third embodiment of this application obtains speech distortion information by comparing the speech content of the un-noise-reduced call audio and the noise-reduced call audio; it obtains noise reduction decibel information by comparing the background noise of the un-noise-reduced call audio and the noise reduction decibel information; and it generates a noise reduction evaluation result for the head-mounted display device based on the speech distortion information and the noise reduction decibel information. Therefore, this embodiment evaluates the noise reduction performance of the head-mounted display device from two dimensions: speech distortion and noise reduction decibel, specifically for the application scenario of the head-mounted display device.
[0055] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the noise reduction evaluation method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.
[0056] This application provides a noise reduction evaluation device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the noise reduction evaluation method in the first embodiment described above.
[0057] The following is for reference. Figure 5The diagram illustrates a structural schematic suitable for implementing the noise reduction evaluation device in the embodiments of this application. The noise reduction evaluation device in the embodiments of this application may include, but is not limited to, terminal devices such as laptops, PDAs (Personal Digital Assistants), PADs (Portable Application Description), desktop computers, servers, etc. Figure 5 The head-mounted display device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of this application.
[0058] like Figure 5 As shown, the noise reduction evaluation device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the noise reduction evaluation device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. The communication device 1009 allows the noise reduction evaluation device to communicate wirelessly or wiredly with other devices to exchange data. While the figure shows a noise reduction evaluation device with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.
[0059] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code 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 device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.
[0060] The noise reduction evaluation device provided in this application, employing the noise reduction evaluation method described in the above embodiments, can solve the technical problem that existing noise reduction evaluation methods have poor applicability to head-mounted display devices and are difficult to accurately evaluate the noise reduction performance of head-mounted display devices. Compared with the prior art, the beneficial effects of the noise reduction evaluation device provided in this application are the same as those of the noise reduction evaluation method provided in the above embodiments, and other technical features of this noise reduction evaluation device are the same as those disclosed in the previous embodiment method, and will not be repeated here.
[0061] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.
[0062] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
[0063] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the noise reduction evaluation method in the above embodiments.
[0064] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.
[0065] The aforementioned computer-readable storage medium may be included in the noise reduction evaluation device; or it may exist independently and not be assembled into the noise reduction evaluation device.
[0066] The aforementioned computer-readable storage medium carries one or more programs. When the one or more programs are executed by the noise reduction evaluation device, the noise reduction evaluation device: in a predetermined test environment, performs a predetermined standard call on a head-mounted display device without noise reduction operation, and collects audio from each speaker in the speaker array of the head-mounted display device to obtain un-noise-reduced call audio; in the predetermined test environment, performs a predetermined standard call on a head-mounted display device after noise reduction operation, and collects audio from each speaker in the speaker array of the head-mounted display device to obtain noise-reduced call audio; and compares the un-noise-reduced call audio with the noise-reduced call audio to obtain the noise reduction evaluation result of the head-mounted display device.
[0067] Computer program code for performing the operations of this application can be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, and C++, and conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0068] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0069] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.
[0070] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described noise reduction evaluation method. This addresses the technical problem that existing noise reduction evaluation methods have poor applicability to head-mounted display devices and are difficult to accurately evaluate the noise reduction performance of such devices. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the noise reduction evaluation method provided in the above embodiments, and will not be repeated here.
[0071] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the noise reduction evaluation method described above.
[0072] The computer program product provided in this application can solve the technical problem that existing noise reduction evaluation methods are poorly applicable to head-mounted display devices and make it difficult to accurately evaluate the noise reduction performance of head-mounted display devices. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the noise reduction evaluation method provided in the above embodiments, and will not be repeated here.
[0073] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.
Claims
1. A noise reduction evaluation method, characterized in that, The noise reduction evaluation method, applied to head-mounted display devices, includes: In a predetermined test environment, a predetermined standard call was conducted on a head-mounted display device without noise reduction, and audio was collected from each speaker in the speaker array of the head-mounted display device to obtain the audio of the call without noise reduction. Under the predetermined test environment, a predetermined standard call was made to the head-mounted display device after noise reduction was performed, and audio was collected from each speaker in the speaker array of the head-mounted display device to obtain the noise-reduced call audio. The noise reduction evaluation result of the head-mounted display device is obtained by comparing the un-noise-reduced call audio with the noise-reduced call audio.
2. The noise reduction evaluation method as described in claim 1, characterized in that, The step of conducting a predetermined standard call on a head-mounted display device without noise reduction in a predetermined test environment, and collecting audio from each speaker in the speaker array of the head-mounted display device to obtain the un-noise-reduced call audio, includes: In a predetermined test environment, after establishing a communication connection between a predetermined terminal device and a head-mounted display device that has not performed noise reduction, predetermined call content is transmitted to the head-mounted display device that has not performed noise reduction in order to conduct a predetermined standard call. During the predetermined standard call, sound is collected from each speaker position in the speaker array of the head-mounted display device that has not performed noise reduction operation, to obtain the first call audio; Sound is collected from the predetermined test environment within the user listening area of the head-mounted display device to obtain a first background noise. The first call audio and the first background noise are used as the un-noise-reduced call audio.
3. The noise reduction evaluation method as described in claim 2, characterized in that, In the predetermined test environment, the steps of conducting a predetermined standard call on the head-mounted display device after noise reduction operation, and acquiring audio from each speaker in the speaker array of the head-mounted display device to obtain the noise-reduced call audio, include: Under the predetermined test environment, after establishing a communication connection between the predetermined terminal device and the head-mounted display device after noise reduction, the predetermined call content is transmitted to the head-mounted display device after noise reduction to conduct a predetermined standard call; During the predetermined standard call, sound is collected from each speaker position in the speaker array of the head-mounted display device after noise reduction operation is performed, to obtain the second call audio; Sound is collected from the predetermined test environment within the user listening area of the head-mounted display device to obtain a second background noise. The second call audio and the second background noise are used as the noise-reduced call audio.
4. The noise reduction evaluation method as described in claim 1, characterized in that, Prior to the step of conducting a predetermined standard call on a head-mounted display device without noise reduction operation under a predetermined test environment, the noise reduction evaluation method further includes: After the predetermined test environment is a noisy environment, the noise audio of the noisy environment is acquired and the noise audio is output. Once the predetermined test environment is a quiet environment, the output of the noise audio is canceled.
5. The noise reduction evaluation method as described in claim 1, characterized in that, The step of comparing the undenoised call audio with the denoised call audio to obtain the noise reduction evaluation result of the head-mounted display device includes: The voice content of the un-noise-reduced call audio and the noise-reduced call audio are compared to obtain voice distortion information; The background noise of the un-noise-reduced call audio and the noise-reduced call audio is compared to obtain the noise reduction decibel information; Based on the speech distortion information and the noise reduction decibel information, a noise reduction evaluation result for the head-mounted display device is generated.
6. The noise reduction evaluation method as described in claim 5, characterized in that, The step of comparing the undenoised call audio and the denoised call audio to obtain voice distortion information includes: Extract the first call voice feature from the undenoised call audio and extract the second call voice feature from the denoised call audio; Calculate the speech difference measure between the first call speech feature and the second call speech feature: The speech difference metric is used as speech distortion information.
7. The noise reduction evaluation method as described in claim 6, characterized in that, The step of comparing the background noise of the un-noise-reduced call audio and the noise-reduced call audio to obtain noise reduction decibel information includes: The first background noise in the un-noise-reduced call audio and the second background noise in the noise-reduced call audio are divided into predetermined frequency bands to obtain each first frequency band noise and each second frequency band noise; Calculate the first noise decibel level for each first frequency band and the second noise decibel level for each second frequency band; The noise decibel difference between the first noise decibel of the first frequency band noise and the second noise decibel of the second frequency band noise under the same frequency band is used as the noise reduction decibel information.
8. A noise reduction assessment device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the noise reduction evaluation method as described in any one of claims 1 to 7.
9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the noise reduction evaluation method as described in any one of claims 1 to 7.
10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the noise reduction evaluation method as described in any one of claims 1 to 7.