Road sound environment emotion influence evaluation method and device

Abstract

The invention discloses a road sound environment emotion influence evaluation method and device, and relates to the technical field of environment evaluation, and the method comprises the steps: carrying out the sampling of various urban road sound environment functional regions, determining the effective dominant audio and dominant sound pressure levels which a plurality of road dominant sound source types belong to, and classifying the effective dominant audio and dominant sound pressure levels into a plurality of road noise types; building a questionnaire platform in combination with the effective dominant audio and collecting subjective scores of a plurality of subjective indexes; acquiring electroencephalogram signals according to the effective dominant audio triggering of each road noise type; correspondingly determining subjective key principal components based on the subjective score of each road noise type; extracting a plurality of spectrum features of each electroencephalogram signal, and correspondingly determining objective key principal components according to the spectrum features of each road noise type; and correspondingly and comprehensively determining the emotion comprehensive index of each road noise type by adopting the subjective key principal component, the objective key principal component, the effective dominant audio and the dominant sound pressure level. And the actual influence of the urban road sound environment on human emotion and cognition can be revealed more comprehensively and accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental assessment, and in particular to a method and device for evaluating the emotional impact of a road acoustic environment. Background Art

[0002] With the accelerating pace of urbanization, the interplay of multiple sound sources within urban roadways, including traffic flow, commercial activities, and construction noise, has created a complex and dynamically changing acoustic environment. This multidimensional sound field not only places higher demands on objective physical measurement indicators such as spectral distribution and equivalent sound pressure level, but also significantly impacts residents' emotional and cognitive states. However, existing road noise monitoring and assessment methods, which primarily focus on the measurement and statistical analysis of acoustic parameters, struggle to accurately capture individuals' subjective experiences, such as comfort and annoyance, in real-world scenarios. Therefore, a more comprehensive and precise understanding of the actual impact of urban road noise environments on human emotions and cognition is needed. Summary of the Invention

[0003] The present invention provides a method and device for evaluating the emotional impact of road acoustic environments, which solves the technical problem that existing road noise monitoring and assessment mostly focus on the measurement and statistical analysis of acoustic parameters, making it difficult to comprehensively and accurately reveal the actual impact of urban road acoustic environments on human emotions and cognition.

[0004] A first aspect of the present invention provides a method for evaluating the emotional impact of a road acoustic environment, comprising:

[0005] Sampling in an urban road sound environment, determining effective dominant audio frequencies and dominant sound pressure levels of a plurality of dominant road sound source types, and classifying each of the dominant road sound source types into a plurality of road noise types according to sound source attributes;

[0006] Using effective dominant audio embedding of each of the dominant road sound source types to build a questionnaire platform, and collecting subjective scores of multiple subjective indicators through the questionnaire platform;

[0007] collecting EEG signals by triggering associated effective dominant audio according to each of the road noise types;

[0008] performing principal component analysis based on the subjective scores associated with each of the road noise types, respectively, to determine a corresponding subjective key principal component for each of the road noise types;

[0009] extracting multiple spectral features of each of the EEG signals, performing principal component analysis on the spectral features according to the road noise type, and determining the objective key principal components corresponding to each of the road noise types;

[0010] A comprehensive evaluation is performed using the associated subjective key principal components, objective key principal components, effective dominant audio, and dominant sound pressure level to determine a comprehensive emotional index for each of the road noise types.

[0011] Optionally, the sampling in the urban road sound environment to determine the effective dominant audio and dominant sound pressure level of multiple road dominant sound source types includes:

[0012] In the road area of ​​one or more types of urban road sound environment functional zones, sampling points are set up to synchronously collect audio samples and time-series sound pressure levels;

[0013] Performing sound event boundary cutting on each of the audio samples to determine the corresponding sub-audio;

[0014] Classifying the pre-set dominant sound source types according to the main frequency values ​​of the sub-audios to determine a plurality of dominant road sound source types;

[0015] Calculating a dominant frequency confidence interval based on the dominant frequency value of each dominant road sound source type, and screening out a valid dominant frequency audio of each dominant road sound source type according to each dominant frequency confidence interval;

[0016] Based on each of the time-series sound pressure levels, the dominant sound pressure levels of the corresponding effective main frequency audio are determined respectively.

[0017] Optionally, performing sound event boundary cutting on each of the audio samples to determine the corresponding sub-audio includes:

[0018] Performing audio preprocessing on each of the audio samples using Adobe Audition software, and outputting corresponding initialization audio;

[0019] According to the Melville spectrogram analysis of each of the initialization audios, a plurality of sub-audios are cut out.

[0020] Optionally, the embedding of effective dominant audio of each dominant sound source type on the road to build a questionnaire platform includes:

[0021] An interactive front-end page for the questionnaire platform is built using HTML, CSS, and JavaScript. Specifically, the page framework is constructed using HTML and the questionnaire form is designed in combination with subjective indicators. The effective dominant audio of each dominant road sound source type is imported using the Audio component, and the associated audio scene images are imported using the Image component. The page style is designed using CSS, and the Audio component ID is assigned using JavaScript and the page interaction is designed in combination with the Audio component ID.

[0022] Deploy the interactive front-end page and MySQL database through the cloud server, establish a standardized form of subjective indicators in the MySQL database, use Java to connect the interactive front-end page and MySQL database, and determine the questionnaire platform.

[0023] Optionally, the extracting multiple spectral features of each of the EEG signals includes:

[0024] Filtering and removing artifacts from each of the EEG signals to output a clean EEG signal;

[0025] According to the power spectral density of each clean EEG signal, the power in different frequency bands is determined as a spectrum feature; the frequency bands include Theta waves, Alpha waves and Beta waves.

[0026] Optionally, the step of performing a comprehensive evaluation using the associated subjective key principal components, objective key principal components, effective dominant audio, and dominant sound pressure level to determine a comprehensive emotional index for each of the road noise types includes:

[0027] According to each of the road noise types, average values ​​of the main frequency values ​​of the corresponding effective dominant audio are calculated and then logarithms are taken to determine the corresponding logarithmic main frequency values;

[0028] performing an average calculation on the associated dominant sound pressure levels according to each of the road noise types, and outputting a corresponding average sound pressure level;

[0029] Performing average calculations on each of the subjective key principal components and each of the objective key principal components to determine corresponding averages of the subjective key principal components and the objective key principal components;

[0030] The emotional composite index of each road noise type is determined by weighted calculation using the associated subjective key principal component average, objective key principal component average, logarithmic main frequency value and sound pressure level average.

[0031] A second aspect of the present invention provides a device for evaluating the emotional impact of road sound environments, comprising:

[0032] a data sampling module for sampling in an urban road sound environment, determining effective dominant audio frequencies and dominant sound pressure levels of a plurality of dominant road sound source types, and classifying each of the dominant road sound source types into a plurality of road noise types according to sound source attributes;

[0033] A subjective evaluation module, configured to use the effective dominant audio embedding of each of the dominant road sound source types to build a questionnaire platform, and collect subjective scores of multiple subjective indicators through the questionnaire platform;

[0034] an objective evaluation module, configured to trigger the collection of EEG signals using an associated effective dominant audio frequency according to each of the road noise types;

[0035] a subjective analysis module, configured to perform principal component analysis based on the subjective scores associated with each of the road noise types, and determine a corresponding subjective key principal component for each of the road noise types;

[0036] an objective analysis module, configured to extract multiple spectral features of each of the EEG signals, perform principal component analysis on the spectral features according to the road noise type, and determine the objective key principal components corresponding to each of the road noise types;

[0037] The emotion evaluation module is used to perform a comprehensive evaluation using the associated subjective key principal components, objective key principal components, effective dominant audio and dominant sound pressure level to determine the emotional comprehensive index of each road noise type.

[0038] A third aspect of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the road sound environment emotional impact assessment method as described in any one of the above items.

[0039] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed, implements the method for evaluating the emotional impact of a road acoustic environment as described in any one of the above items.

[0040] A fifth aspect of the present invention provides a computer program product, comprising a computer program / instruction, which, when executed by a processor, implements the road sound environment emotional impact assessment method as described in any one of the above items.

[0041] It can be seen from the above technical solutions that the present invention has the following advantages:

[0042] The above-mentioned scheme of the present invention provides a method for evaluating the emotional impact of a road sound environment, comprising: sampling in an urban road sound environment, determining the effective dominant audio and dominant sound pressure level belonging to multiple road dominant sound source types, and classifying each road dominant sound source type into multiple road noise types according to sound source attributes; using the effective dominant audio of each road dominant sound source type to embed into a questionnaire platform, and collecting subjective scores of multiple subjective indicators through the questionnaire platform; using the associated effective dominant audio to trigger the collection of electroencephalogram (EEG) signals according to each road noise type; performing principal component analysis based on the subjective scores associated with each road noise type, and determining the subjective key principal components of each road noise type; extracting multiple spectral features of each EEG signal, performing principal component analysis on the spectral features according to the road noise type, and determining the objective key principal components of each road noise type; and performing a comprehensive evaluation using the associated subjective key principal components, objective key principal components, effective dominant audio, and dominant sound pressure level to determine the emotional comprehensive index of each road noise type. Based on the above scheme, a large amount of typical data is collected from the urban road sound environment. By embedding effective dominant audio to build a questionnaire platform to guide users to conduct subjective audio perception scoring, and using the EEG signal response to sound source stimulation to quantify objective emotional indicators, overall, by integrating environmental psychology and neuroscience methods, taking into account both subjective and objective data and sound source information, a comprehensive evaluation system for the emotional suitability of the urban road sound environment is formed. This system can effectively distinguish the impact of different road sound sources on people's emotional fluctuations, so as to more comprehensively and accurately reveal the actual impact of the urban road sound environment on human emotions and cognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 A flowchart of a method for evaluating the emotional impact of road sound environments provided by an embodiment of the present invention;

[0045] Figure 2 A flow chart of urban road acoustic environment data sampling provided by an embodiment of the present invention;

[0046] Figure 3 A schematic diagram of the questionnaire platform design provided by an embodiment of the present invention;

[0047] Figure 4 A subjective evaluation flow chart provided by an embodiment of the present invention;

[0048] Figure 5A flowchart of objective evaluation of EEG indicators provided by an embodiment of the present invention;

[0049] Figure 6 A flowchart for calculating the comprehensive emotion index provided by an embodiment of the present invention;

[0050] Figure 7 This is a structural block diagram of a device for evaluating the emotional impact of road sound environments provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] Embodiments of the present invention provide a method and device for evaluating the emotional impact of road acoustic environments, which are used to address the technical problem that existing road noise monitoring and assessment mostly focus on the measurement and statistical analysis of acoustic parameters, making it difficult to comprehensively and accurately reveal the actual impact of urban road acoustic environments on human emotions and cognition.

[0052] In order to make the purpose, features, and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below 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 making creative work are within the scope of protection of the present invention.

[0053] See also Figure 1 , Figure 1 This is a flowchart of the steps of a method for evaluating the emotional impact of road sound environment provided by an embodiment of the present invention.

[0054] This embodiment provides a method for evaluating the emotional impact of road sound environments, including:

[0055] Step 101: Sampling is performed in an urban road sound environment to determine the effective dominant audio and dominant sound pressure level of multiple road dominant sound source types, and each road dominant sound source type is classified into multiple road noise types according to sound source attributes.

[0056] The dominant road sound source type refers to the source type of sound events occurring within the urban road sound environment. A sound event is a sound signal generated by a specific sound source within a specific acoustic scene, typically with a clear start and end time.

[0057] Effective dominant audio refers to an audio clip that can effectively represent a certain type of sound event in the urban road sound environment.

[0058] The dominant sound pressure level refers to the sound pressure level characteristics that effectively dominate the audio.

[0059] Sound source attributes refer to the characteristics of a certain type of road sound source described based on the sound source or acoustic characteristics.

[0060] Road noise type refers to the noise type obtained by classifying audio clips of urban road sound environment according to the sound source attributes.

[0061] It should be noted that multiple sampling points are set up in the urban road environment. At each sampling point, audio is collected using recording devices such as voice recorders, and sound pressure levels are collected using sound pressure level collection devices such as high-precision A-weighted sound level meters. Based on the collected data, the effective dominant audio and dominant sound pressure levels of multiple road dominant sound source types are determined, and each road dominant sound source type is classified into multiple road noise types according to the sound source attributes.

[0062] In a specific implementation of this embodiment, sampling is performed in an urban road sound environment to determine the effective dominant audio and dominant sound pressure level of multiple road dominant sound source types, including:

[0063] In the road area of ​​one or more types of urban road sound environment functional zones, sampling points are set up to synchronously collect audio samples and time-series sound pressure levels;

[0064] Perform sound event boundary cutting on each audio sample to determine the corresponding sub-audio;

[0065] Classify the pre-set dominant sound source types according to the main frequency values ​​of each sub-audio, and determine multiple dominant road sound source types;

[0066] Calculate the main frequency confidence interval based on the main frequency value of each road dominant sound source type, and filter out the effective main frequency audio of each road dominant sound source type according to each main frequency confidence interval;

[0067] The dominant sound pressure levels of the corresponding effective main frequency audio are determined based on the respective time series sound pressure levels.

[0068] Urban road sound environment functional zones refer to the sound environment functional zones obtained by dividing the urban road environment in accordance with the national sound environment functional zone zoning standards.

[0069] Audio samples refer to the original audio files collected at the sampling point.

[0070] Time series sound pressure level refers to a sequence of sound pressure levels recorded over time.

[0071] The sound event boundary refers to the duration period formed by the start and end time of the sound event.

[0072] The dominant sound source type refers to the type of sound source of different sound events.

[0073] The main frequency value refers to the highest peak in the frequency domain within the audio time period.

[0074] The dominant frequency confidence interval refers to the dominant frequency value distribution range used to screen stable and representative audio clips.

[0075] It should be noted that if Figure 2 As shown, this embodiment determines six types of urban road sound environment functional zones according to the classification under the national sound environment functional zone division: Category 0 refers to areas that particularly need to be quiet, and this embodiment selects natural scenic spots; Category 1 refers to areas where residential houses, medical and health care, cultural education, etc. need to be kept quiet, and this embodiment determines them as residential areas and teaching areas; Category 2 refers to areas where financial trade, market trade, etc. need to maintain residential quietness, and this embodiment determines them as commercial areas; Category 3 refers to areas such as industrial production, warehousing and logistics that need to prevent industrial pollution noise from having a serious impact on the surrounding environment, and this embodiment determines them as construction areas; Category 4 refers to areas such as traffic arteries that need to be prevented The area where traffic noise has a serious impact on the surrounding environment is determined to be a transportation hub in this embodiment; multiple sampling points are deployed in the six urban road sound environment functional zones to ensure sufficient ambient sound pressure level samples, while the audio collection also ensures the richness of the dominant sound source types; in specific implementation, sampling points can be set in road areas of one or more types of urban road sound environment functional zones, and each sampling point in the urban road sound environment functional zone can be set 100 meters apart. Data collection is carried out during the daytime on weekdays, with each sampling point recording for 5 minutes, the sound pressure level sampling interval being 1 second, and the audio sampling frequency being 32000 Hz;

[0076] The collected audio samples are then used to identify various sound events, thereby determining the duration of each sound event and extracting it to obtain the corresponding sub-audio. The sub-audio is then subjected to a Fast Fourier Transform (FFT), and the dominant frequency value of each sub-audio is extracted using the scipy and numpy libraries in Python. The sub-audio is then classified according to the dominant frequency value based on the sound source standard frequency range corresponding to the preset dominant sound source type, and multiple road dominant sound source types are determined, while ensuring that each road dominant sound source type has multiple samples. Taking each road dominant sound source type as a unit, the dominant frequency value of the sub-audio is summarized into a sample dominant frequency range and a confidence interval for the dominant frequency value, namely the dominant frequency confidence interval (such as the 95% confidence interval for the dominant frequency), is calculated. Representative sub-audio, namely the effective dominant frequency audio, is summarized from the corresponding sample dominant frequency range according to the dominant frequency confidence interval. The effective dominant frequency audio can be numbered according to different road dominant sound source types for subsequent subjective and objective evaluation and collection.

[0077] For each effective main frequency audio segment, the corresponding sound pressure level data can be extracted from the corresponding time series sound pressure level, and the corresponding sound pressure level characteristics, i.e., the dominant sound pressure level, can be obtained by processing. The dominant sound pressure level may include: 、 、 、 、 or , Represents the maximum sound pressure level of an audio segment. Represents the minimum sound pressure level of an audio segment, and 、 、 Represent the average peak value, average value, and background value of noise respectively. Represents the non-steady-state sound energy averaged over a period of time, which is the continuous equivalent A-sound level and can be obtained by formula (1):

[0078] (1)

[0079] Where, Represents the number of sound pressure levels, Representative Sound pressure level; in this embodiment It can be 300, which represents the sound pressure level within 5 minutes, with an interval of 1 second.

[0080] Exemplarily, the dominant road sound source types include 15 types, such as bird singing, wind, rain, dog barking, human talking, whistle, bus, large vehicle, broadcast, motorcycle, construction, car, bicycle, airplane and high-speed rail. The dominant road sound source types are classified to determine the road noise type, which can be: bird singing, wind, rain and dog barking are classified as natural noise, human talking, whistle and broadcast are classified as social noise, bus, large vehicle, motorcycle, car, bicycle, airplane and high-speed rail are classified as traffic noise, and construction noise is classified as building noise.

[0081] In a more specific implementation of this embodiment, performing sound event boundary cutting on each audio sample to determine the corresponding sub-audio includes:

[0082] Perform audio preprocessing on each audio sample using Adobe Audition software, and output the corresponding initialization audio;

[0083] Based on the Melville spectrogram analysis of each initialization audio, multiple sub-audios are cut out.

[0084] Adobe Audition software is a professional audio processing tool that supports functions such as audio editing, noise reduction, and spectrum analysis. For details, please refer to the existing technology.

[0085] Melville spectrogram refers to a two-dimensional image that maps the audio signal to the Mel scale, with the horizontal axis being time and the vertical axis being Mel frequency, and the color intensity representing the energy.

[0086] It should be noted that, in this embodiment, when determining the sub-audio, Adobe Audition software is first used to perform visual monitoring of the collected audio samples, eliminate occasional interference that occurs during the collection, capture noise samples, and adjust the noise reduction percentage to make the audio quality clear and recognizable. After obtaining the initialized audio, the Melville spectrogram feature analysis is performed on each initialized audio. The time-frequency characteristics of different sound sources can be clearly distinguished by the energy size, thereby identifying various sound events, and then the audio is cut to obtain multiple sub-audio.

[0087] Step 102: Use the effective dominant audio of each road dominant sound source type to embed and build a questionnaire platform, and collect subjective scores of multiple subjective indicators through the questionnaire platform.

[0088] A questionnaire platform refers to an interactive system that collects users' subjective feedback through questionnaires.

[0089] Subjective indicators refer to the indicator dimensions that quantify the user's subjective feelings about the sound environment.

[0090] Subjective ratings refer to the quantitative evaluation results given by users on subjective indicators based on their own feelings, which can be expressed as specific numerical values ​​or grade evaluations.

[0091] It should be noted that this embodiment has built a questionnaire platform, which, by embedding the effective dominant audio of each road dominant sound source, guides users to score according to subjective indicators based on their subjective perception of the audio of each road dominant sound source type, thereby realizing the standardized collection of subjective scoring data; in specific implementation, the designed subjective indicators may include sound comfort, sound pleasure, loudness, sound annoyance, and sound emotional perception, and the scoring can be quantified using the Likert five-level scale.

[0092] In a specific implementation of this embodiment, the questionnaire platform is constructed by embedding effective dominant audio of each dominant sound source type on the road, including:

[0093] An interactive front-end page for the questionnaire platform was built using HTML, CSS, and JavaScript. This involved constructing the page framework using HTML and designing the questionnaire form in conjunction with subjective indicators. The Audio component was used to import effective dominant audio for each dominant sound source type on each road, and the Image component was used to import associated audio scene images. CSS was used for page styling, and JavaScript was used to assign an Audio component ID and design page interactions in conjunction with the Audio component ID.

[0094] Deploy the interactive front-end page and MySQL database through the cloud server, establish a standardized form of subjective indicators in the MySQL database, use Java to connect the interactive front-end page and MySQL database, and determine the questionnaire platform.

[0095] The standardized form for subjective indicators refers to a structured form used to store and manage subjective scores of various subjective indicators, ensuring the standardization of data format, field meaning, and mapping relationship.

[0096] It should be noted that if Figure 3 As shown, the process of building a questionnaire platform using a Web platform in this embodiment is shown, which is divided into the front end and the back end:

[0097] First, use VS Code to write Html, Css and Javascript to deploy the interactive front-end page. The interactive front-end page includes the main interface and the questionnaire interface. The main interface is used to introduce website information and questionnaire process to users. The questionnaire interface contains a questionnaire form designed in combination with subjective indicators, which is used for users to make subjective scores after listening to the audio. Html is the framework of the page, responsible for the design and layout of various components. You can use the Audio component to import effective dominant audio of various types of road dominant sound sources, and use the image component to import audio scene pictures associated with effective dominant audio to introduce road dominant sound sources. Css is the style of the page, responsible for fonts, colors, dynamic effects and interface responsive design, etc. For each component of Html, CSS can define fonts, colors, etc., so that To design a simple and beautiful page; Javascript is responsible for page interaction, such as uploading the form to the backend database, and is responsible for assigning independent IDs to the button components for the questionnaire page jump to the Audio components of each road's dominant sound source type (such as 1 for bird calls, and so on), and jumping to the page through the connection URL. It can be understood that the jump between the main interface and the questionnaire interface is based on the HTML component button, and the URL assigned by JavaScript code is used to distinguish the questionnaire interfaces of different audios, thereby distinguishing the questionnaire data filled by users for different dominant sound source types, reducing the duplication of front-end code; at the same time, the interactive page can also be designed responsively, and can be proportional to the size of different device terminals, such as mobile terminals and PC terminals;

[0098] The core of the back-end design is to collect, process, and analyze user data using a MySQL database deployed on a suitable cloud server (such as Alibaba Cloud ECS). Log in to the cloud server and download required libraries such as nginx and PHP. Use the cloud server to deploy the front-end code, which can then be accessed via the public IP address. Then, set up the database, create a standardized form for subjective indicators, and open port 3306 to enable remote database access and modification. Finally, connect to the front-end deployment through Java to upload user-entered data for collection and storage.

[0099] It is worth mentioning that the use of the Web platform to build a questionnaire platform to publish questionnaires can spread the questionnaire more quickly, and you can log in using only a mobile terminal. For the user group, the convenient access to the questionnaire platform ensures the breadth of the user group. When filling in the user's personal information, there will be questions including age, gender, and living environment, which ensures the diversity of the questionnaire sample; when playing audio such as "bird singing", "rain sound", and "construction sound", high-definition pictures of the corresponding scenes will be displayed, which can help users "immerse" in the real scene and reduce the abstract perception bias during subjective scoring. After listening to the audio, the user will be guided to fill in the questionnaire. The forms of various subjective indicators will be uploaded to the Mysql database of the cloud server through the back-end code. The database provides formatted standardized forms of subjective indicators to facilitate data visualization on different software. In this way, for different road-dominant sound source types, there will be an independent questionnaire rating sample big data, such as Figure 4 As shown in the figure, after obtaining the data, we first perform data cleaning and preprocessing. We check whether there are missing data in the backend MySQL database. If missing, we use the mean to fill in the data form. We perform a reliability test on the Likert scale and calculate the Cronbach's α coefficient, which reflects the degree of consistency of each item in the scale in measuring the same latent variable. When the number of valid questionnaires corresponding to the dominant road sound source type is ≥30, the consistency of each indicator can be estimated relatively robustly. The expression of the Cronbach's α coefficient is as follows:

[0100] (2)

[0101] in, is the number of scale items (here The number of corresponds to the number of subjective indicators). For the The variance of the question, is the variance of all item scores. When , it means the reliability of the questionnaire indicators is acceptable; At the same time, descriptive statistics can be performed on the psychological indicator data obtained from the Likert scale to calculate the mean and median of the indicators under various sound sources in order to summarize the overall response trend of emotions under different sound sources.

[0102] It is understandable that in order to facilitate subsequent statistics based on road noise types, a questionnaire form can be designed based on road noise types in combination with subjective indicators, and the effective dominant audio of each road dominant sound source type can be imported based on road noise types based on the Audio component.

[0103] Step 103 : Using the associated effective dominant audio to trigger the collection of EEG signals according to each road noise type.

[0104] It should be noted that this embodiment measures the user's electroencephalogram (EEG) signals by playing effective dominant audio of various road noise types (such as traffic noise, social noise, natural noise, and construction noise) using a high-precision electroencephalogram (EEG) meter and high-quality head-mounted noise-isolating headphones;

[0105] In the specific implementation, Gpower's T test is used to confirm the required number of experimental people. The experimental groups adopt a Latin square balanced design. The number of people in a group of experiments is set according to the order of the number of audio types. For example, a group of 4 people corresponds to the four major types of road noise. The software used in the measurement process of EEG signals can be Emotiv and E-prime. The playback time point of each audio segment is controlled by E-prime script writing to record and distinguish EEG signals in the same time period. Participants need to wear EEG headsets (such as high-precision EEG meters and high-quality head-mounted noise-isolating headphones) to ensure good contact between the electrodes and the scalp to reduce signal instability. After exposure to audio noise stimulation, use Emotiv Pro software was used to record EEG signals, preferably with an effective dominant audio frequency of 2 minutes of exposure time. Before each stimulation, participants will undergo a brief adaptation period to ensure that they are in a relaxed state. There will be a two-minute rest period between stimulations. During the experiment, all participants were asked to remain quiet to reduce artifact interference. To ensure data quality, the EEG signal of each participant will be standardized during the experiment to verify the quality of electrode contact. After each sound stimulation, the EEG signal will be automatically stored and a quick check will be performed at the end of each stimulation cycle to ensure the integrity of the data.

[0106] It is understandable that white noise can also be set as a control group, that is, according to each road noise type, the associated effective dominant audio and white noise are used to trigger the collection of EEG signals. The white noise can help distinguish whether the differences in EEG signals under different road noise stimuli are only due to the effective dominant audio rather than irrelevant acoustic interference. The white noise can be spatial stereo generated by Adobe Audition, with a sampling rate of 32000 Hz and a bit depth of 16 bits, which is consistent with the collection conditions of the aforementioned recording equipment.

[0107] Step 104 : Perform principal component analysis based on the subjective scores associated with each road noise type to determine the subjective key principal components of each road noise type.

[0108] The subjective key principal component refers to the principal component that can explain most of the variability of the data among the principal components associated with the subjective dimensions.

[0109] It should be noted that by categorizing the dominant road noise source types into corresponding road noise types, ANOVA can be used to compare the effects of different road noise types on dimensions such as acoustic comfort and acoustic pleasure, and to test whether there are significant differences between different road noise types.

[0110] After data analysis, Figure 4 As shown, the mean and standard deviation of the scores for each road noise type and each subjective indicator dimension were calculated to understand the average perception of each noise type and the volatility of the evaluation. Then, principal component analysis (PCA) was performed to reduce the dimensions and find the dominant evaluation dimension: 1. The scores of each subjective indicator questionnaire were calculated. Standardization; 2. Perform principal component analysis on each subjective indicator dimension to identify several principal components that best represent the changes in the user's overall comfort; 3. Combine the variance contribution rate of each principal component to determine the subjective key principal components of the subjective evaluation.

[0111] Step 105 : extract multiple spectral features of each EEG signal, perform principal component analysis on the spectral features according to the road noise type, and determine the objective key principal components of each road noise type.

[0112] Spectral features refer to quantitative indicators extracted from EEG signals through frequency domain analysis that can characterize the state of EEG activity.

[0113] The objective key principal component refers to the principal component that can explain most of the variability of the data among the principal components associated with the objective dimensions.

[0114] It should be noted that multiple spectral features are extracted from the EEG signal through frequency domain analysis, and principal component analysis is performed on the associated spectral features based on the road noise type to determine the corresponding objective key principal components.

[0115] In a specific implementation of this embodiment, multiple spectral features of each EEG signal are extracted, including:

[0116] Filter and remove artifacts from each EEG signal to output a clean EEG signal;

[0117] According to the power spectral density of each clean EEG signal, the power in different frequency bands is determined as the spectral feature; the frequency bands include Theta wave, Alpha wave and Beta wave.

[0118] It should be noted that if Figure 5 As shown in the figure, after EEG data is collected, the Mne library in Python software can be used to preprocess the signal. For example, a filter can be used to remove noise from the EEG signal in the range of 1-30 Hz. Then, the EEG signal can be subjected to artifact analysis, and independent component analysis (ICA) can be used to remove artifacts such as electrooculography and electromyography. Feature extraction can then be performed on the clean EEG signal obtained through processing. The EEG signal under different road noise types can be analyzed using short-time Fourier transform to obtain a spectrum diagram under each sound stimulation, and the impact of different sound sources on the frequency components of EEG waves can be observed. At the same time, the power spectral density of each EEG signal can be calculated. Finally, according to the frequency bands of Theta wave (4-8 Hz), Alpha wave (8-3 Hz) and Beta wave (13-30 Hz), the power (such as alpha wave absolute power, beta wave relative power, theta wave relative power) can be calculated based on the corresponding power spectral density as the spectral feature. This can be used to analyze which bands change most significantly under different sound sources.

[0119] It is understandable that this embodiment introduces EEG experiments as an objective evaluation system because, compared to traditional questionnaires or subjective evaluations, EEG data can directly reflect the human brain's immediate response to the sound environment, avoiding subjective bias. Therefore, the objective system of this embodiment quantitatively evaluates the impact of noise on cognitive load, emotional stress and attention through specific indicators (power) of EEG signals, making the evaluation more objective; specifically, different frequencies, intensities and types of sounds (such as natural noise, traffic noise) can be directly correlated through changes in EEG responses, helping to deeply understand the impact of sound characteristics on the brain, thereby obtaining an objective score.

[0120] Step 106 : Perform a comprehensive evaluation using the associated subjective key principal components, objective key principal components, effective dominant audio, and dominant sound pressure level to determine a comprehensive emotional index for each road noise type.

[0121] The comprehensive emotional index refers to a quantitative indicator that represents the fluctuation state of emotional perception by combining sound source information with subjective and objective indicator data for comprehensive analysis.

[0122] It is understood that in step 101, if a single type of urban road sound environment functional zone is sampled and evaluated separately, the emotional comprehensive index can evaluate the emotional impact of noise sources of different road noise types in a certain type of urban road sound environment functional zone on users. If a sampling evaluation is conducted on multiple types of urban road sound environment functional zones, the emotional comprehensive index can evaluate the emotional impact of noise sources of different road noise types in the urban road sound environment on users as a whole. Therefore, this solution can evaluate the emotional impact of the sound environment at the local level of the functional zone or at the global level of the city. The higher the value of the emotional comprehensive index, the greater the intensity of emotional fluctuations. For example, if the natural noise score is 8.73, the traffic noise score is 10.29, the social noise score is 9.91, and the construction noise score is 10.20, it means that in the road environment, natural noise has the least impact on emotional fluctuations, traffic noise and construction noise have the greatest impact on human emotional fluctuations, and the social noise has an intermediate impact on emotions.

[0123] In a specific implementation of this embodiment, step 106 includes the following sub-steps:

[0124] According to each road noise type, the main frequency values ​​of the effective dominant audio are averaged and then logarithmized to determine the corresponding logarithmic main frequency value;

[0125] performing an average calculation on the associated dominant sound pressure levels according to each road noise type, and outputting the corresponding average sound pressure level;

[0126] Performing average calculations on each subjective key principal component and each objective key principal component to determine the corresponding average values ​​of the subjective key principal components and the objective key principal components;

[0127] The emotional composite index of each road noise type is determined by weighted calculation using the associated subjective key principal component average, objective key principal component average, logarithmic main frequency value and sound pressure level average.

[0128] It should be noted that according to the sound-brain-emotion model, the dominant sound pressure level and subjective and objective key principal components are averaged, and the main frequency value is averaged and logarithmized, taking the road noise type as the unit. The above calculation results are then combined and weighted summed to obtain the corresponding comprehensive emotion index.

[0129] In a more specific implementation of this embodiment, Figure 6 As shown in Figure 2, the calculation process of the comprehensive sentiment index includes:

[0130] (3)

[0131] in, is the kth road noise type (k=1,…,4, determined according to the number of road noise types), represents the comprehensive emotional index of the kth road noise type (excluding white noise), Represents the first subjective key principal component The weight of represents the average value of the first subjective key principal component of the k-th sound source, Represents the second subjective key principal component The weight of The average value of the second subjective key principal component representing the k-th sound source; Represents the first objective key principal component The weight of represents the average value of the first objective key principal component of the k-th sound source, Represents the second objective key principal component The weight of The average value of the second objective key principal component representing the k-th sound source; represents the sound pressure level weight, represents the weight of the main frequency value, represents the average sound pressure level, represents the average value of the main frequency, represents logarithmic operation, It can be understood that here, both the subjective key principal component and the objective key principal component take the first two principal components to explain the data variability.

[0132] Furthermore, this embodiment calculates the weights according to the variability of the principal components. In the subjective experiment, the explained variance ratio of the first subjective key principal component and the explained variance ratio of the second subjective key principal component are respectively and In the objective experiment, the explained variance ratio of the first objective key principal component and the second objective key principal component are and , the weight calculation formula is:

[0133] (4)

[0134] (5)

[0135] As for the main frequency value weight and sound pressure level weight, first, the main frequency value and main sound pressure level of the effective dominant audio are normalized according to each road noise type to determine the corresponding normalized main frequency value and normalized sound pressure level. Then, according to each road noise type, the associated normalized main frequency value and normalized sound pressure level are used to determine the corresponding main frequency value weight based on the entropy weight method. and sound pressure level weighting ; Among them, the calculation process of Min-Max normalization of the dominant sound pressure level and the main frequency value of the effective dominant audio to eliminate the differences in different dimensions is:

[0136] (6)

[0137] in, is the standardized value, the interval is [0-1]; is the initial value of the data; The maximum value in the list data; The minimum value in the list data.

[0138] In the embodiment of the present invention, first, sampling points are set in the urban road sound environment to synchronously collect time-series audio and sound pressure level data, which can collect a large number of typical dominant audio in the road environment. The sufficient data samples ensure the accuracy and effectiveness of the comprehensive evaluation system of this method; secondly, the sound source is screened for effectiveness based on the main frequency confidence interval, and the multiple screened road dominant sound source types are classified into different road noise types. A subjective perception questionnaire is distributed through a questionnaire platform to obtain subjective emotional evaluations in different sound environments. The use of online questionnaires replaces traditional offline "field" questionnaires, which can efficiently and conveniently collect user-filled form data to realize subjective evaluation system analysis under big data. At the same time, there will be independent questionnaire rating sample big data for each dominant sound source type, which helps to realize the differences in indicators for different sound sources and thus improve the accuracy of the subjective evaluation system; At the same time, under controlled experimental conditions, EEG instruments were used to record the EEG responses to stimulation from each sound source group to quantify objective emotional indicators, thereby avoiding the subjective bias of the questionnaire and quantifying the impact of noise on cognitive load, emotional stress, and attention. Finally, a comprehensive emotional index was obtained by combining sound source information with subjective and objective indicator data according to the road noise type, presenting the quality of the sound environment from multiple perspectives and avoiding the one-sidedness of a single dimension. Therefore, overall, by integrating environmental psychology and neuroscience methods, taking into account both subjective and objective data and sound source information, a comprehensive evaluation system for the emotional suitability of urban road sound environments was formed, which can effectively distinguish the impact of different road sound sources on people's emotional fluctuations, so as to more comprehensively and accurately reveal the actual impact of urban road sound environments on human emotions and cognition, and provide reliable quantitative decision-making support for the formulation of noise control strategies and the optimization of urban acoustic environments.

[0139] See also Figure 7 , Figure 7 This is a structural block diagram of a device for evaluating the emotional impact of road sound environments provided by an embodiment of the present invention.

[0140] The present invention provides a device for evaluating the emotional impact of road sound environments, comprising:

[0141] The data sampling module 701 is configured to perform sampling in an urban road sound environment, determine the effective dominant audio frequency and dominant sound pressure level of multiple dominant road sound source types, and classify each dominant road sound source type into multiple road noise types according to sound source attributes;

[0142] A subjective evaluation module 702 is configured to use the effective dominant audio embedding of each road dominant sound source type to build a questionnaire platform, and collect subjective scores of multiple subjective indicators through the questionnaire platform;

[0143] An objective evaluation module 703 is configured to trigger the collection of EEG signals using associated effective dominant audio according to each road noise type;

[0144] A subjective analysis module 704 is configured to perform principal component analysis based on the subjective scores associated with each road noise type, and determine the subjective key principal components corresponding to each road noise type;

[0145] An objective analysis module 705 is configured to extract multiple spectral features of each EEG signal, perform principal component analysis on the spectral features according to the road noise type, and determine the objective key principal components corresponding to each road noise type;

[0146] The emotion evaluation module 706 is configured to perform a comprehensive evaluation using the associated subjective key principal components, objective key principal components, effective dominant audio, and dominant sound pressure level to determine a comprehensive emotion index for each road noise type.

[0147] Furthermore, sampling is performed in the urban road sound environment to determine the effective dominant audio and dominant sound pressure level of multiple road dominant sound source types, including:

[0148] In the road area of ​​one or more types of urban road sound environment functional zones, sampling points are set up to synchronously collect audio samples and time-series sound pressure levels;

[0149] Perform sound event boundary cutting on each audio sample to determine the corresponding sub-audio;

[0150] Classify the pre-set dominant sound source types according to the main frequency values ​​of each sub-audio, and determine multiple dominant road sound source types;

[0151] Calculate the main frequency confidence interval based on the main frequency value of each road dominant sound source type, and filter out the effective main frequency audio of each road dominant sound source type according to each main frequency confidence interval;

[0152] The dominant sound pressure levels of the corresponding effective main frequency audio are determined based on the respective time series sound pressure levels.

[0153] Furthermore, each audio sample is subjected to sound event boundary cutting to determine the corresponding sub-audio, including:

[0154] Perform audio preprocessing on each audio sample using Adobe Audition software, and output the corresponding initialization audio;

[0155] Based on the Melville spectrogram analysis of each initialization audio, multiple sub-audios are cut out.

[0156] Furthermore, the questionnaire platform is constructed by embedding the effective dominant audio of each road dominant sound source type, including:

[0157] An interactive front-end page for the questionnaire platform was built using HTML, CSS, and JavaScript. This involved constructing the page framework using HTML and designing the questionnaire form in conjunction with subjective indicators. The Audio component was used to import effective dominant audio for each dominant sound source type on each road, and the Image component was used to import associated audio scene images. CSS was used for page styling, and JavaScript was used to assign an Audio component ID and design page interactions in conjunction with the Audio component ID.

[0158] Deploy the interactive front-end page and MySQL database through the cloud server, establish a standardized form of subjective indicators in the MySQL database, use Java to connect the interactive front-end page and MySQL database, and determine the questionnaire platform.

[0159] Furthermore, multiple spectral features of each EEG signal are extracted, including:

[0160] Filter and remove artifacts from each EEG signal to output a clean EEG signal;

[0161] According to the power spectral density of each clean EEG signal, the power in different frequency bands is determined as the spectral feature; the frequency bands include Theta wave, Alpha wave and Beta wave.

[0162] Furthermore, the emotion evaluation module 706 is specifically configured to:

[0163] According to each road noise type, the main frequency values ​​of the effective dominant audio are averaged and then logarithmized to determine the corresponding logarithmic main frequency value;

[0164] performing an average calculation on the associated dominant sound pressure levels according to each road noise type, and outputting the corresponding average sound pressure level;

[0165] Performing average calculations on each subjective key principal component and each objective key principal component to determine the corresponding average values ​​of the subjective key principal components and the objective key principal components;

[0166] The emotional composite index of each road noise type is determined by weighted calculation using the associated subjective key principal component average, objective key principal component average, logarithmic main frequency value and sound pressure level average.

[0167] An embodiment of the present invention further provides a computer device comprising a memory and a processor, wherein a computer program is stored in the memory; when the computer program is executed by the processor, the processor executes the steps of the road acoustic environment emotional impact assessment method as described in any of the above embodiments.

[0168] An embodiment of the present invention further provides a computer-readable storage medium having a computer program / instruction stored thereon. When the computer program / instruction is executed by a processor, the steps of the method for evaluating the emotional impact of a road acoustic environment as described in any of the above embodiments are implemented.

[0169] An embodiment of the present invention further provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the method for evaluating the emotional impact of a road acoustic environment as described in any of the above embodiments.

[0170] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0171] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0172] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0173] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0174] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0175] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for evaluating the emotional impact of road noise environment, characterized in that: include: Sampling in an urban road sound environment, determining effective dominant audio frequencies and dominant sound pressure levels of a plurality of dominant road sound source types, and classifying each of the dominant road sound source types into a plurality of road noise types according to sound source attributes; Using effective dominant audio embedding of each of the dominant road sound source types to build a questionnaire platform, and collecting subjective scores of multiple subjective indicators through the questionnaire platform; collecting EEG signals by triggering associated effective dominant audio according to each of the road noise types; performing principal component analysis based on the subjective scores associated with each of the road noise types, respectively, to determine a corresponding subjective key principal component for each of the road noise types; extracting multiple spectral features of each of the EEG signals, performing principal component analysis on the spectral features according to the road noise type, and determining the objective key principal components corresponding to each of the road noise types; A comprehensive evaluation is performed using the associated subjective key principal components, objective key principal components, effective dominant audio, and dominant sound pressure level to determine a comprehensive emotional index for each of the road noise types.

2. The method for evaluating the emotional impact of road noise environment according to claim 1, characterized in that: The sampling in the urban road sound environment to determine the effective dominant audio and dominant sound pressure level of multiple road dominant sound source types includes: In the road area of ​​one or more types of urban road sound environment functional zones, sampling points are set up to synchronously collect audio samples and time-series sound pressure levels; Performing sound event boundary cutting on each of the audio samples to determine the corresponding sub-audio; Classifying the pre-set dominant sound source types according to the main frequency values ​​of the sub-audios to determine a plurality of dominant road sound source types; Calculating a dominant frequency confidence interval based on the dominant frequency value of each dominant road sound source type, and screening out a valid dominant frequency audio of each dominant road sound source type according to each dominant frequency confidence interval; Based on each of the time-series sound pressure levels, the dominant sound pressure levels of the corresponding effective main frequency audio are determined respectively.

3. The method for evaluating the emotional impact of road noise environment according to claim 2, characterized in that: The performing sound event boundary cutting on each of the audio samples to determine the corresponding sub-audio includes: Performing audio preprocessing on each of the audio samples using Adobe Audition software, and outputting corresponding initialization audio; According to the Melville spectrogram analysis of each of the initialization audios, a plurality of sub-audios are cut out.

4. The method for evaluating the emotional impact of road noise environment according to claim 1, characterized in that: The questionnaire platform is constructed by embedding effective dominant audio of each dominant sound source type on the road, including: An interactive front-end page for the questionnaire platform is built using HTML, CSS, and JavaScript. Specifically, the page framework is constructed using HTML and the questionnaire form is designed in combination with subjective indicators. The effective dominant audio of each dominant road sound source type is imported using the Audio component, and the associated audio scene images are imported using the Image component. The page style is designed using CSS, and the Audio component ID is assigned using JavaScript and the page interaction is designed in combination with the Audio component ID. Deploy the interactive front-end page and MySQL database through the cloud server, establish a standardized form of subjective indicators in the MySQL database, use Java to connect the interactive front-end page and MySQL database, and determine the questionnaire platform.

5. The method for evaluating the emotional impact of road sound environment according to claim 1, characterized in that: The extracting of multiple spectral features of each of the EEG signals includes: Filtering and removing artifacts from each of the EEG signals to output a clean EEG signal; According to the power spectral density of each clean EEG signal, the power in different frequency bands is determined as a spectrum feature; the frequency bands include Theta waves, Alpha waves and Beta waves.

6. The method for evaluating the emotional impact of road noise environment according to claim 1, characterized in that: The method of performing a comprehensive evaluation using the associated subjective key principal components, objective key principal components, effective dominant audio, and dominant sound pressure level to determine the emotional comprehensive index of each road noise type includes: According to each of the road noise types, average values ​​of the main frequency values ​​of the corresponding effective dominant audio are calculated and then logarithms are taken to determine the corresponding logarithmic main frequency values; performing an average calculation on the associated dominant sound pressure levels according to each of the road noise types, and outputting a corresponding average sound pressure level; Performing average calculations on each of the subjective key principal components and each of the objective key principal components to determine corresponding averages of the subjective key principal components and the objective key principal components; The emotional composite index of each road noise type is determined by weighted calculation using the associated subjective key principal component average, objective key principal component average, logarithmic main frequency value and sound pressure level average.

7. A device for evaluating the emotional impact of road sound environment, characterized in that: include: a data sampling module for sampling in an urban road sound environment, determining effective dominant audio frequencies and dominant sound pressure levels of a plurality of dominant road sound source types, and classifying each of the dominant road sound source types into a plurality of road noise types according to sound source attributes; A subjective evaluation module, configured to use the effective dominant audio embedding of each of the dominant road sound source types to build a questionnaire platform, and collect subjective scores of multiple subjective indicators through the questionnaire platform; an objective evaluation module, configured to trigger the collection of EEG signals using an associated effective dominant audio frequency according to each of the road noise types; a subjective analysis module, configured to perform principal component analysis based on the subjective scores associated with each of the road noise types, and determine a corresponding subjective key principal component for each of the road noise types; an objective analysis module, configured to extract multiple spectral features of each of the EEG signals, perform principal component analysis on the spectral features according to the road noise type, and determine the objective key principal components corresponding to each of the road noise types; The emotion evaluation module is used to perform a comprehensive evaluation using the associated subjective key principal components, objective key principal components, effective dominant audio and dominant sound pressure level to determine the emotional comprehensive index of each road noise type.

8. A computer device, characterized in that: The method comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the method for evaluating the emotional impact of a road acoustic environment as claimed in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method for evaluating the emotional impact of a road acoustic environment as claimed in any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method for evaluating the emotional impact of a road acoustic environment as claimed in any one of claims 1 to 6 are implemented.

Images