CN117537918A - Indoor noise detection method and related device - Google Patents
Indoor noise detection method and related device Download PDFInfo
- Publication number
- CN117537918A CN117537918A CN202311620999.5A CN202311620999A CN117537918A CN 117537918 A CN117537918 A CN 117537918A CN 202311620999 A CN202311620999 A CN 202311620999A CN 117537918 A CN117537918 A CN 117537918A
- Authority
- CN
- China
- Prior art keywords
- target
- projection direction
- audio data
- correlation
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 78
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000012545 processing Methods 0.000 claims abstract description 31
- 238000012544 monitoring process Methods 0.000 claims abstract description 22
- 239000013598 vector Substances 0.000 claims description 34
- 230000008451 emotion Effects 0.000 claims description 23
- 230000004927 fusion Effects 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012790 confirmation Methods 0.000 claims description 7
- 238000004088 simulation Methods 0.000 claims description 5
- 238000005259 measurement Methods 0.000 abstract description 6
- 230000008569 process Effects 0.000 description 12
- 238000013145 classification model Methods 0.000 description 8
- 239000000463 material Substances 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 5
- 238000003062 neural network model Methods 0.000 description 5
- 208000019901 Anxiety disease Diseases 0.000 description 4
- 230000036506 anxiety Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 230000035945 sensitivity Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 206010038743 Restlessness Diseases 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000001544 dysphoric effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002996 emotional effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 208000027534 Emotional disease Diseases 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 208000001431 Psychomotor Agitation Diseases 0.000 description 1
- 239000011358 absorbing material Substances 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000000546 chi-square test Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 230000013707 sensory perception of sound Effects 0.000 description 1
- 208000019116 sleep disease Diseases 0.000 description 1
- 208000022925 sleep disturbance Diseases 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002459 sustained effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
- 230000036642 wellbeing Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The embodiment of the invention provides an indoor noise detection method and a related device, and belongs to the technical field of environment detection. The method comprises the following steps: acquiring initial audio data obtained by sound monitoring of sensors positioned at different target positions in an indoor environment of noise to be detected; obtaining corresponding object information in an indoor environment, and performing data processing on initial audio data acquired at a target position according to the object information to obtain target audio data corresponding to the initial audio data; carrying out data projection on the target audio data to obtain a target projection direction corresponding to the target audio data; determining target audio characteristics corresponding to the target audio data according to the target projection direction; and determining a noise detection result corresponding to the indoor environment according to the target audio characteristics. The problem of inaccurate sensor data measurement in the related art leads to the low accuracy of noise detection is solved, and simultaneously the accuracy of indoor noise detection is improved.
Description
Technical Field
The present invention relates to the field of environmental detection technologies, and in particular, to an indoor noise detection method and a related device.
Background
With the improvement of living standard of residents, people pay more attention to the quality of living environment. Among them, the indoor noise level has an important influence on the quality of life and health of people. High intensity, sustained noise can cause sleep disturbance, stress and anxiety, and negatively impact concentration and work efficiency. By detecting indoor noise, the influence of noise on the health and comfort of people can be discovered and taken early.
In the related art, the collected indoor noise data can be subjected to deep analysis and modeling by utilizing a big data analysis and machine learning method, so that the mode and trend of a noise source can be found, and the accuracy and reliability of noise detection can be improved. However, when the big data analysis and the machine learning method are used, the sensor data analyzed may have problems of inconsistent sensitivity, inaccurate frequency response and the like during measurement, so that a deviation exists in a measurement result, and the accuracy of noise detection is affected. Furthermore, the accuracy of noise detection is affected by the location between the sensor and the noise source, the surrounding environment and interference factors. Sensors in different locations may capture different noise levels and other sounds in the surrounding environment may interfere with the accuracy of the noise detection.
Disclosure of Invention
The embodiment of the invention mainly aims to provide an indoor noise detection method and a related device, and aims to solve the problem that when noise detection is carried out by using sensor data in the related technology, the sensor data possibly has inconsistent sensitivity, inaccurate frequency response and the like when measuring, so that a measurement result has deviation, and the accuracy of the noise detection is affected. And the accuracy of noise detection is affected by the location between the sensor and the noise source, the surrounding environment, and interference factors. Sensors in different locations may capture different noise levels and other sounds in the surrounding environment may interfere with the accuracy of the noise detection.
In a first aspect, an embodiment of the present invention provides an indoor noise detection method, including:
acquiring initial audio data obtained by sound monitoring of sensors positioned at different target positions in an indoor environment of noise to be detected;
obtaining corresponding object information in the indoor environment, and performing data processing on the initial audio data acquired under the target position according to the object information to obtain target audio data corresponding to the initial audio data;
Carrying out data projection on the target audio data to obtain a target projection direction corresponding to the target audio data;
determining a target audio feature corresponding to the target audio data according to the target projection direction;
and determining a noise detection result corresponding to the indoor environment according to the target audio characteristics.
In a second aspect, an embodiment of the present invention provides an indoor noise detection apparatus, including:
the data acquisition module is used for acquiring initial audio data obtained by sound monitoring of the sensors positioned at different target positions in the indoor environment of the noise to be detected;
the data processing module is used for obtaining corresponding object information in the indoor environment, and carrying out data processing on the initial audio data acquired under the target position according to the object information to obtain target audio data corresponding to the initial audio data;
the direction confirming module is used for carrying out data projection on the target audio data to obtain a target projection direction corresponding to the target audio data;
the feature acquisition module is used for determining target audio features corresponding to the target audio data according to the target projection direction;
and the result confirmation module is used for determining a noise detection result corresponding to the indoor environment according to the target audio characteristics.
In a third aspect, an embodiment of the present invention further provides a terminal device, the terminal device including a processor, a memory, a computer program stored on the memory and executable by the processor, and a data bus for implementing a connection communication between the processor and the memory, wherein the computer program, when executed by the processor, implements the steps of any one of the indoor noise detection methods as provided in the present specification.
In a fourth aspect, an embodiment of the present invention further provides a storage medium for computer readable storage, where the storage medium stores one or more programs, where the one or more programs are executable by one or more processors to implement the steps of any of the indoor noise detection methods as provided in the present specification.
The embodiment of the invention provides an indoor noise detection method and a related device, wherein the method comprises the steps of obtaining initial audio data obtained by sound monitoring of sensors positioned at different target positions in an indoor environment of noise to be detected; obtaining corresponding object information in an indoor environment, and performing data processing on initial audio data acquired at a target position according to the object information to obtain target audio data corresponding to the initial audio data; carrying out data projection on the target audio data to obtain a target projection direction corresponding to the target audio data; determining target audio characteristics corresponding to the target audio data according to the target projection direction; and determining a noise detection result corresponding to the indoor environment according to the target audio characteristics. According to the method and the device for detecting the noise, the initial audio data obtained by the sensors at different target positions are subjected to data processing to obtain the corresponding target audio data by utilizing the influence of the object information in the indoor environment on the collected audio, so that the problems that the sensors at different positions may capture different noise levels and other sounds in the surrounding environment may interfere with the accuracy of noise detection are solved. In addition, the corresponding target projection direction is obtained by carrying out data projection on the target audio data; therefore, the target audio characteristics corresponding to the target audio data can be obtained more accurately according to the target projection direction, and further support is provided for the accuracy of the noise detection result corresponding to the indoor environment determined according to the target audio characteristics. The problems that in the related art, when sensor data are measured, the sensor possibly has inconsistent sensitivity, inaccurate frequency response and the like, and a measurement result has deviation, so that the accuracy of noise detection is influenced, and the accuracy of the noise detection is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of an indoor noise detection method according to an embodiment of the present invention;
fig. 2 is a flow chart of a substep S102 of the indoor noise detection method in fig. 1;
fig. 3 is a schematic block diagram of an indoor noise detection device according to an embodiment of the present invention;
fig. 4 is a schematic block diagram of a structure of a terminal device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The flow diagrams depicted in the figures are merely illustrative and not necessarily all of the elements and operations/steps are included or performed in the order described. For example, some operations/steps may be further divided, combined, or partially combined, so that the order of actual execution may be changed according to actual situations.
It is to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The embodiment of the invention provides an indoor noise detection method and a related device. The indoor noise detection method can be applied to terminal equipment, and the terminal equipment can be electronic equipment such as tablet computers, notebook computers, desktop computers, personal digital assistants, wearable equipment and the like. The terminal device may be a server or a server cluster.
Some embodiments of the invention are described in detail below with reference to the accompanying drawings. The following embodiments and features of the embodiments may be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a flow chart of an indoor noise detection method according to an embodiment of the invention.
As shown in fig. 1, the indoor noise detection method includes steps S101 to S105.
Step S101, obtaining initial audio data obtained by sound monitoring of sensors located at different target positions in an indoor environment of noise to be detected.
The method comprises the steps of determining an indoor environment of noise to be detected, setting corresponding sensors at different target positions according to layout information of the indoor environment, and further carrying out sound monitoring according to the sensors to obtain initial audio data acquired by the corresponding sensors at the target positions. The target position may be a position corresponding to a home appliance in which noise is likely to be generated in the indoor environment, or may be a position where a user is located according to whether the user is affected by the noise.
For example, the target location is a humidifier placement location, an air conditioner placement location, or the like, and the target location may also be a study room, a bedroom, or the like.
Optionally, the target position can be set according to the requirement, the specific position is not limited, and the user can set according to the actual requirement.
Step S102, obtaining corresponding object information in the indoor environment, and carrying out data processing on the initial audio data acquired under the target position according to the object information to obtain target audio data corresponding to the initial audio data.
The object information corresponding to each object placed in the indoor environment is obtained, the object information comprises object position information and object material information, wherein the distance between the sensors corresponding to the target positions is determined according to the object position information, and therefore whether the object affects data acquisition of the sensors or not is judged according to the distance. The object material information is used for representing that the object has sound absorption effect on sound, so that the sound is reduced, and the initial audio data collected by the sensor is deviated.
Illustratively, a target object having an influence on the sensor at the target position is selected from object information according to the target position, so that an adjustment parameter corresponding to initial audio data of the sensor at the target position is determined according to object position information and object material information corresponding to the target object.
For example, according to the distance information or the distribution information between the object position information and the target position of the object, when the distance information or the distribution information meets the preset distance or the preset distribution condition, the target object of the object is determined, otherwise, the object is determined not to influence the data acquisition result of the sensor of the target position. After the target object is obtained, inquiring from the mapping table according to the object position information and the object material information so as to obtain the adjustment parameters corresponding to the initial audio data by the target object. The mapping table can be collected and stored according to experimental means.
The method includes the steps of obtaining a plurality of adjustment parameters corresponding to a plurality of target objects, fusing the adjustment parameters to obtain target adjustment parameters, and performing data adjustment on initial audio data according to the target adjustment parameters to obtain target audio data.
Optionally, the method can use a weighted summation mode to fuse the adjustment parameters, and can also obtain an average value of the adjustment parameters to realize parameter fusion and the like.
In an embodiment, the data processing is performed on the initial audio data collected at the target position according to the object information to obtain target audio data corresponding to the initial audio data, and specifically referring to fig. 2, step S102 includes: substep S1021 to substep S1023.
And step S1021, determining a three-dimensional model corresponding to the indoor environment according to the object information.
The object information includes point cloud information corresponding to the object, position information corresponding to the object and material information corresponding to the object, and further virtual environment construction is performed on the indoor environment according to the point cloud information and the position information, and further the result after the virtual environment construction is adjusted according to the material information corresponding to the object, so that a three-dimensional model corresponding to the indoor environment is obtained.
And step S1022, performing sound simulation in the three-dimensional model to obtain sound environment monitoring parameters corresponding to the initial audio data obtained by the sensor at the target position.
The method includes the steps that first size information corresponding to an indoor environment and second size information corresponding to a three-dimensional model are obtained, scaling corresponding to the three-dimensional model is obtained according to the first size information and the second size information, then when the three-dimensional model performs sound simulation, test audio is played, collected audio corresponding to the test audio is collected by a sensor at a target position, the collected audio and the test audio are input into a neural network model, adjustment parameters required when the collected audio is adjusted to the test audio are obtained, and sound environment monitoring parameters corresponding to initial audio data are determined according to the scaling and the adjustment parameters. The acoustic environment monitoring parameters may include sound enhancement parameters, noise removal parameters, and the like.
Optionally, the structure of the neural network model is not particularly limited, and a user can set the neural network model according to actual requirements.
And step S1023, carrying out data processing on the initial audio data according to the acoustic environment monitoring parameters to obtain the target audio data corresponding to the initial audio data.
Illustratively, the initial audio data is subjected to data processing, such as sound enhancement, noise removal, and the like, using the acoustic environment monitoring parameters, thereby obtaining target audio data corresponding to the initial audio data. Thereby providing good support for noise detection in the subsequent indoor environment.
Specifically, the three-dimensional model is built for the indoor environment, so that the acoustic environment monitoring parameters at different target positions can be better obtained, and the reliability is improved, and therefore, good support is provided for subsequently improving the accuracy of noise detection.
And step S103, carrying out data projection on the target audio data to obtain a target projection direction corresponding to the target audio data.
For better obtaining the corresponding data characteristics in the target audio data, the target audio data needs to be converted into a projection space for data projection, so as to obtain the corresponding target projection direction of the target audio data.
In some embodiments, the target audio data includes at least a first audio data and a second audio data, and the data projecting the target audio data to obtain a target projection direction corresponding to the target audio data includes: data alignment is carried out on the first audio data and the second audio data according to a time dimension, and first alignment data corresponding to the first audio data and second alignment data corresponding to the second audio data are obtained; determining a first projection direction corresponding to the first alignment data and a second projection direction corresponding to the second alignment data; calculating the correlation between the first projection direction and the second projection direction to obtain a correlation result; when the correlation result does not meet a preset condition, updating the first projection direction and the second projection direction, and recalculating the correlation between the first projection direction and the second projection direction; and when the correlation result meets a preset condition, determining the target projection direction according to the first projection direction and the second projection direction.
For example, the target audio data is a data acquisition result of the same noise under different target positions, and the target positions can be multiple, so that the target audio data at least comprises first audio data and second audio data. In consideration of the possible difference of acquisition time of the first audio data and the second audio data, the first audio data and the second audio data are aligned according to the time dimension, so that the first alignment data corresponding to the first audio data and the second alignment data corresponding to the second audio data are acquired results of the same noise at different target positions at the same time, and good support is provided for the improvement of the subsequent noise detection results.
For example, the first audio data and the second audio data are respectively cut to obtain a plurality of first sub-audios corresponding to the first audio data and a plurality of second sub-audios corresponding to the second audio data, and then the similarity calculation is performed on the first sub-audios and the second sub-audios, so that a first audio position corresponding to the first sub-audio with larger similarity and a second audio position corresponding to the second sub-audio are used as audio data under the same time, and therefore the first audio position and the second audio position are aligned, and further first alignment data corresponding to the first audio data and second alignment data corresponding to the second audio data are obtained.
Illustratively, a first projection direction corresponding to the first alignment data and a second projection direction corresponding to the second alignment data are obtained randomly, and then vector calculation is performed according to the first projection direction and the second projection direction to obtain a similarity result, so that the correlation between the first projection direction and the second projection direction is determined according to the similarity result, and the similarity result is determined as a correlation result. And when the correlation result is greater than or equal to a preset threshold value, determining the first projection direction and the second projection direction as target projection directions. And when the correlation result is smaller than a preset threshold value, the first projection direction and the second projection direction are obtained again, and the correlation between the first projection direction and the second projection direction is recalculated until the correlation result is larger than or equal to the preset threshold value, so that the target projection direction is obtained.
In some embodiments, the calculating the correlation between the first projection direction and the second projection direction to obtain a correlation result includes: obtaining a first correlation corresponding to internal data in the first alignment data, a second correlation corresponding to internal data in the second alignment data and a third correlation between the first alignment data and the second alignment data; performing correlation calculation according to the first correlation, the second correlation, the third correlation, the first projection direction and the second projection direction to obtain a correlation result; wherein the correlation result is obtained according to the following formula:
Wherein alpha represents the first projection direction, beta represents the second projection direction, alpha T Representing the transpose of alpha, beta T Represents the transpose of beta, C xy Representing the third correlation, C xx Representing the first correlation, C yy Representing the second correlation.
Illustratively, the cosine similarity is used to calculate a first correlation corresponding to the internal data in the first alignment data and a second correlation corresponding to the internal data in the second alignment data and a third correlation between the first alignment data and the second alignment data, thereby bringing the first correlation, the second correlation, the third correlation, the first projection direction and the second projection direction intoThereby obtaining a correlation result between the first projection direction and the second projection direction.
Optionally, when calculating the first correlation, the second correlation, and the third correlation, cosine similarity may be used, chi-square test, pearson correlation coefficient, or the like, which is not specifically limited, and the user may select the method according to the actual requirement.
In some embodiments, determining the target projection direction further comprises: determining an adjustable parameter, and determining an adjustable difference between the first correlation and the second correlation according to the first correlation, the second correlation and the adjustable parameter; performing equation calculation according to the adjustable value, the first correlation, the second correlation, the first projection direction and the second projection direction, and determining the first projection direction and the second projection direction as the target projection direction when the equation is satisfied;
Wherein the equation calculation is according to the following equation:
alpha represents the first projection direction, beta represents the second projection direction, C xy Representing the third correlation, C xx Representing the first correlation, C yy Representing the second correlation, Z xy Represents the adjustable difference, lambda 1 Representing a first characteristic value, lambda, corresponding to the first alignment data 2 And representing a second characteristic value corresponding to the second alignment data.
Illustratively, the adjustable parameter is obtained randomly, or an initial value of the adjustable parameter is obtained according to the history, and then according to C xx -a*C yy Obtaining an adjustable difference Z xy Wherein a represents an adjustable parameter.
Exemplary, the first alignment data and the second alignment data are respectively represented in matrix form to obtain a first matrix corresponding to the first alignment data and a second matrix corresponding to the second alignment data, so as to calculate a first eigenvalue lambda corresponding to the first matrix in the first projection direction 1 And calculating a second eigenvalue lambda corresponding to the second matrix in the second projection direction 2 。
Illustratively, the adjustable value, the first correlation, the second correlation, the firstThe projection direction and the second projection direction are brought intoWhen the equation is satisfied, the first projection direction and the second projection direction corresponding to the case where the equation is satisfied are determined as the target projection direction.
Step S104, determining target audio features corresponding to the target audio data according to the target projection direction.
Illustratively, the target audio data is projected onto a target projection direction, thereby obtaining target audio features corresponding to the target audio data. That is, the target audio data is characterized by utilizing the target audio characteristics, so that the influence of other interference data on the subsequent noise detection result is reduced.
In some embodiments, the determining, according to the target projection direction, a target audio feature corresponding to the target audio data includes: determining a first feature vector corresponding to the first alignment data according to the first projection direction in the target projection direction, and determining a second feature vector corresponding to the second alignment data according to the second projection direction in the target projection direction; and carrying out vector fusion on the first feature vector and the second feature vector to obtain the target audio feature.
Illustratively, the first alignment data is mapped to a first projection direction for feature representation, so as to obtain a first feature vector corresponding to the first alignment data, and the second alignment data is mapped to a second projection direction for feature representation, so as to obtain a second feature vector corresponding to the second alignment data. Obtaining a first target position corresponding to the first alignment data and a second target position corresponding to the second alignment data, further determining fusion weights corresponding to the first feature vector and the second feature vector according to distance information between the first target position and the noise generation position and between the second target position and the noise generation position, and performing vector fusion on the first feature vector and the second feature vector according to the fusion weights to obtain target audio features. The method comprises the steps of determining a fusion weight according to distance information between a first target position and a second target position and a noise generation position, wherein the data processing of the first audio data and the second audio data with different degrees is mainly considered, so that the fusion weight is inversely proportional to the distance information for reducing the influence of feature vectors under different distances on target feature vectors, and further, the accuracy of a subsequent noise detection result is ensured.
Optionally, when obtaining the fusion vector, the influence of different objects at the target positions on sound collection, for example, the objects are sound absorbing materials, material heights, and the like, may be used to comprehensively consider and determine the corresponding fusion weights at the different target positions.
For example, according to a three-dimensional model corresponding to an indoor environment, environment information corresponding to a target position is obtained, and then the environment information is input into a weight prediction model, and then fusion weight corresponding to the target position is obtained, wherein the weight prediction model can be a neural network model or a machine learning model, and the method and the device are not particularly limited, a user can select according to actual requirements, so that vector fusion is carried out on a first feature vector and a second feature vector according to the fusion weight, and a target audio feature is obtained.
Step S105, determining a noise detection result corresponding to the indoor environment according to the target audio feature.
Illustratively, the target audio features are input into the noise classification model, so that the noise classification model performs noise classification according to the target audio features, thereby obtaining a noise detection result. The noise classification model may be a classification for confirming whether the target audio feature is noise or not, or may be a type of noise for confirming correspondence of the target audio feature.
In some embodiments, the determining the noise detection result corresponding to the indoor environment according to the target audio feature includes: classifying the sound source types of the target audio features to obtain a first type corresponding to the target audio features; classifying the sound intensity level of the target audio features to obtain a second type corresponding to the target audio features; performing acoustic environment emotion classification on the target audio features to obtain a third type corresponding to the target audio features; performing sound frequency classification on the target audio features to obtain a fourth type corresponding to the target audio features; and determining the noise detection result corresponding to the indoor environment according to the first type, the second type, the third type and the fourth type.
For example, when determining the noise detection result corresponding to the indoor environment according to the target audio feature, the sound source type may be classified according to the target audio feature to obtain a first type, where the first type is used to represent the sound source type corresponding to the target audio feature, and the sound source type may be, for example, a human sound, a musical instrument sound, an animal sound, an environmental sound, or a mechanical sound. And then, carrying out model training according to the sound source type and the sound source data to obtain a corresponding classification model, further obtaining a sound source classification model, and carrying out sound source type classification on the target audio characteristics by using the sound source classification model to obtain a corresponding first type. Where the perception of individuals varies from one sound source type to another, some sound source types may be more attractive to people, such as music, while some sound source types may be considered noise, such as mechanical sound. Under different scenes, different sound source types have different influences on the noise detection results corresponding to the indoor environment. For example, in a playing indoor environment, music may not be noisy, but in a silent situation music is also noisy.
Illustratively, the target audio features are input into a sound intensity level classification model to classify the target audio features in sound intensity levels, thereby obtaining a second type. Different sound intensity levels are different for noise determinations in different indoor environments. For example, in a similar indoor environment in a reading hall, the sound intensity level may be already noise when it is level 3, but in an indoor environment corresponding to normal life of a person, the sound that is necessary for normal life may be already emitted when the sound intensity level is level 3, and the sound cannot be determined as noise. Wherein, the higher the sound intensity level, the more likely the sound is noise. Different sound intensity levels are set differently in different indoor environments by determining whether or not the sound intensity level of noise is different
Optionally, the sound intensity level can be set according to the actual requirement, and the application is not particularly limited, and the user can set according to the actual requirement.
Illustratively, inputting the target audio features into an acoustic environment emotion classification model to perform acoustic environment emotion classification on the target audio features, and obtaining a third type corresponding to the target audio features; and obtaining a corresponding third type according to the target audio characteristics, namely obtaining the acoustic environment emotion corresponding to the initial audio data acquired by the sensor at the target position.
For example, an acoustic environment emotion includes silence, pleasure, restlessness, fear, etc., where an acoustic environment emotion is silence, then it is indicated that a person may feel calm and calm when there is no excessive noise disturbance in the environment. Such an acoustic environment emotion may help relax, concentrate attention and improve work efficiency; when the emotion of the sound environment is pleasant, the sound in the current environment can be indicated to create a pleasant and happy emotion of the sound environment. This acoustic environmental emotion helps to increase emotional state, relieve stress, and increase well-being. When the acoustic environment emotion is dysphoric, the current environment sound is noisy, harsh or continuous noise, which can lead to the dysphoric and restless acoustic environment emotion. Such acoustic environmental emotions may trigger negative emotional reactions such as stress, anxiety and fatigue. When the emotion of the sound environment is fear, the current environment is indicated to be suddenly and strongly noisy, such as explosion sound or sharp alarm sound, and fear and panic emotion can be possibly caused. Such an acoustic environmental emotion may excite stress reactions of the body, such as accelerated heart rate and respiration.
Illustratively, the acoustic environment emotion has an important role in noise determination. The perception of sound and the acceptance of noise by humans is affected by emotional states. When people are in a happy, relaxed state, they may be more tolerant of noise and better able to adapt. Conversely, if people are in a state of anxiety, anxiety or fear, their tolerance to noise may be reduced and the noise may be considered more harsher and unpleasant. The mood of the acoustic environment can affect the subjective assessment of noise and the degree of disturbance of the noise. Therefore, the effect of the acoustic environment emotion on the noise detection result is different in different indoor environments.
Illustratively, classifying the sound frequency of the target audio feature to obtain a fourth type corresponding to the target audio feature; different ground sound frequencies identify different people to noise. The classification of sound frequencies may be performed using a machine learning model or a neural network model.
Optionally, the model required in the sound frequency classification, the model required in the sound source type classification, the model required in the sound intensity level classification, and the model structure corresponding to the model required in the sound environment emotion classification are not particularly limited, and the user can set the model according to actual requirements.
Illustratively, weight information required for determining a noise detection result according to sound frequency, sound source type, sound intensity level, and emotion of sound environment in an indoor environment is obtained, and the weight information can be set according to user experience, and can also be obtained through learning according to historical data. And combining the first type, the second type, the third type and the fourth type with the weight information to determine a noise detection result corresponding to the indoor environment.
According to the method and the device for detecting the noise, the initial audio data obtained by the sensors at different target positions are subjected to data processing to obtain the corresponding target audio data by utilizing the influence of the object information in the indoor environment on the collected audio, so that the problems that the sensors at different positions may capture different noise levels and other sounds in the surrounding environment may interfere with the accuracy of noise detection are solved. In addition, the corresponding target projection direction is obtained by carrying out data projection on the target audio data; therefore, the target audio characteristics corresponding to the target audio data can be obtained more accurately according to the target projection direction, and further support is provided for the accuracy of the noise detection result corresponding to the indoor environment determined according to the target audio characteristics. The problems that in the related art, when sensor data are measured, the sensor possibly has inconsistent sensitivity, inaccurate frequency response and the like, and a measurement result has deviation, so that the accuracy of noise detection is influenced, and the accuracy of the noise detection is improved.
Referring to fig. 3, fig. 3 is an indoor noise detection device 200 provided in the embodiment of the present application, where the indoor noise detection device 200 includes a data acquisition module 201, a data processing module 202, a direction confirmation module 203, a feature acquisition module 204, and a result confirmation module 205, where the data acquisition module 201 is configured to obtain initial audio data obtained by performing sound monitoring on sensors located at different target positions in an indoor environment where noise is to be detected; the data processing module 202 is configured to obtain object information corresponding to the indoor environment, and perform data processing on the initial audio data collected at the target position according to the object information, so as to obtain target audio data corresponding to the initial audio data; the direction confirmation module 203 is configured to perform data projection on the target audio data to obtain a target projection direction corresponding to the target audio data; a feature acquisition module 204, configured to determine a target audio feature corresponding to the target audio data according to the target projection direction; and the result confirmation module 205 is configured to determine a noise detection result corresponding to the indoor environment according to the target audio feature.
In some embodiments, the data processing module 202 performs, in the process of obtaining the target audio data corresponding to the initial audio data by performing data processing on the initial audio data collected at the target position according to the object information, the following steps:
determining a three-dimensional model corresponding to the indoor environment according to the object information;
performing sound simulation in the three-dimensional model to obtain sound environment monitoring parameters corresponding to the initial audio data obtained by the sensor at the target position;
and carrying out data processing on the initial audio data according to the acoustic environment monitoring parameters to obtain the target audio data corresponding to the initial audio data.
In some embodiments, the target audio data includes at least a first audio data and a second audio data, and the data processing module 202 performs, in the process of performing data projection on the target audio data to obtain a target projection direction corresponding to the target audio data:
data alignment is carried out on the first audio data and the second audio data according to a time dimension, and first alignment data corresponding to the first audio data and second alignment data corresponding to the second audio data are obtained;
Determining a first projection direction corresponding to the first alignment data and a second projection direction corresponding to the second alignment data;
calculating the correlation between the first projection direction and the second projection direction to obtain a correlation result;
when the correlation result does not meet a preset condition, updating the first projection direction and the second projection direction, and recalculating the correlation between the first projection direction and the second projection direction;
and when the correlation result meets a preset condition, determining the target projection direction according to the first projection direction and the second projection direction.
In some embodiments, the data processing module 202 performs, in calculating the correlation between the first projection direction and the second projection direction, a correlation result:
obtaining a first correlation corresponding to internal data in the first alignment data, a second correlation corresponding to internal data in the second alignment data and a third correlation between the first alignment data and the second alignment data;
performing correlation calculation according to the first correlation, the second correlation, the third correlation, the first projection direction and the second projection direction to obtain a correlation result;
Wherein the correlation result is obtained according to the following formula:
wherein alpha represents the first projection direction, beta represents the second projection direction, alpha T Representing the transpose of alpha, beta T Represents the transpose of beta, C xy Representing the third correlation, C xx Representing the first correlation, C yy Representing the second correlation.
In some embodiments, the indoor noise detection apparatus 200 further performs, in determining the target projection direction:
determining an adjustable parameter, and determining an adjustable difference between the first correlation and the second correlation according to the first correlation, the second correlation and the adjustable parameter;
performing equation calculation according to the adjustable value, the first correlation, the second correlation, the first projection direction and the second projection direction, and determining the first projection direction and the second projection direction as the target projection direction when the equation is satisfied;
wherein the equation calculation is according to the following equation:
alpha represents the first projection direction, beta represents the second projection direction, C xy Representing the third correlation, C xx Representing the first correlation, C yy Representing the second correlation, Z xy Represents the adjustable difference, lambda 1 Representing a first characteristic value, lambda, corresponding to the first alignment data 2 And representing a second characteristic value corresponding to the second alignment data.
In some embodiments, the feature obtaining module 204 performs, in the process of determining the target audio feature corresponding to the target audio data according to the target projection direction:
determining a first feature vector corresponding to the first alignment data according to the first projection direction in the target projection direction, and determining a second feature vector corresponding to the second alignment data according to the second projection direction in the target projection direction;
and carrying out vector fusion on the first feature vector and the second feature vector to obtain the target audio feature.
In some embodiments, the result confirmation module 205 performs, in the determining, according to the target audio feature, a noise detection result corresponding to the indoor environment:
classifying the sound source types of the target audio features to obtain a first type corresponding to the target audio features;
classifying the sound intensity level of the target audio features to obtain a second type corresponding to the target audio features;
Performing acoustic environment emotion classification on the target audio features to obtain a third type corresponding to the target audio features;
performing sound frequency classification on the target audio features to obtain a fourth type corresponding to the target audio features;
and determining the noise detection result corresponding to the indoor environment according to the first type, the second type, the third type and the fourth type.
In some embodiments, the indoor noise detection apparatus 200 may be applied to a terminal device.
It should be noted that, for convenience and brevity of description, the specific working process of the indoor noise detection apparatus 200 described above may refer to the corresponding process in the foregoing indoor noise detection method embodiment, and will not be described herein again.
Referring to fig. 4, fig. 4 is a schematic block diagram of a structure of a terminal device according to an embodiment of the present invention.
As shown in fig. 4, the terminal device 300 includes a processor 301 and a memory 302, the processor 301 and the memory 302 being connected by a bus 303, such as an I2C (Inter-integrated Circuit) bus.
In particular, the processor 301 is used to provide computing and control capabilities, supporting the operation of the entire terminal device. The processor 301 may be a central processing unit (Central Processing Unit, CPU), the processor 301 may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Specifically, the Memory 302 may be a Flash chip, a Read-Only Memory (ROM) disk, an optical disk, a U-disk, a removable hard disk, or the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 4 is merely a block diagram of a portion of the structure related to the embodiment of the present invention, and does not constitute a limitation of the terminal device to which the embodiment of the present invention is applied, and that a specific server may include more or less components than those shown in the drawings, or may combine some components, or have a different arrangement of components.
The processor is configured to run a computer program stored in the memory, and implement any one of the indoor noise detection methods provided by the embodiments of the present invention when the computer program is executed.
In an embodiment, the processor is configured to run a computer program stored in a memory and to implement the following steps when executing the computer program:
acquiring initial audio data obtained by sound monitoring of sensors positioned at different target positions in an indoor environment of noise to be detected;
obtaining corresponding object information in the indoor environment, and performing data processing on the initial audio data acquired under the target position according to the object information to obtain target audio data corresponding to the initial audio data;
Carrying out data projection on the target audio data to obtain a target projection direction corresponding to the target audio data;
determining a target audio feature corresponding to the target audio data according to the target projection direction;
and determining a noise detection result corresponding to the indoor environment according to the target audio characteristics.
In some embodiments, the processor 301 performs, in the process of obtaining the target audio data corresponding to the initial audio data by performing data processing on the initial audio data collected at the target position according to the object information, the following steps:
determining a three-dimensional model corresponding to the indoor environment according to the object information;
performing sound simulation in the three-dimensional model to obtain sound environment monitoring parameters corresponding to the initial audio data obtained by the sensor at the target position;
and carrying out data processing on the initial audio data according to the acoustic environment monitoring parameters to obtain the target audio data corresponding to the initial audio data.
In some embodiments, the target audio data includes at least a first audio data and a second audio data, and the processor 301 performs, in the process of performing data projection on the target audio data to obtain a target projection direction corresponding to the target audio data:
Data alignment is carried out on the first audio data and the second audio data according to a time dimension, and first alignment data corresponding to the first audio data and second alignment data corresponding to the second audio data are obtained;
determining a first projection direction corresponding to the first alignment data and a second projection direction corresponding to the second alignment data;
calculating the correlation between the first projection direction and the second projection direction to obtain a correlation result;
when the correlation result does not meet a preset condition, updating the first projection direction and the second projection direction, and recalculating the correlation between the first projection direction and the second projection direction;
and when the correlation result meets a preset condition, determining the target projection direction according to the first projection direction and the second projection direction.
In some embodiments, the processor 301 performs, in calculating the correlation between the first projection direction and the second projection direction, obtaining a correlation result:
obtaining a first correlation corresponding to internal data in the first alignment data, a second correlation corresponding to internal data in the second alignment data and a third correlation between the first alignment data and the second alignment data;
Performing correlation calculation according to the first correlation, the second correlation, the third correlation, the first projection direction and the second projection direction to obtain a correlation result;
wherein the correlation result is obtained according to the following formula:
wherein alpha represents the first projection direction, beta represents the second projection direction, alpha T Representing the transpose of alpha, beta T Represents the transpose of beta, C xy Representing the third correlation, C xx Representing the first correlation, C yy Representing the second correlation.
In some implementations, the processor 301, in determining the target projection direction, further performs:
determining an adjustable parameter, and determining an adjustable difference between the first correlation and the second correlation according to the first correlation, the second correlation and the adjustable parameter;
performing equation calculation according to the adjustable value, the first correlation, the second correlation, the first projection direction and the second projection direction, and determining the first projection direction and the second projection direction as the target projection direction when the equation is satisfied;
wherein the equation calculation is according to the following equation:
Alpha represents the first projection direction, beta represents the second projection direction, C xy Representing the third correlation, C xx Representing the first correlation, C yy Representing the second correlation, Z xy Represents the adjustable difference, lambda 1 Representing a first characteristic value, lambda, corresponding to the first alignment data 2 And representing a second characteristic value corresponding to the second alignment data.
In some embodiments, the processor 301 performs, in determining the target audio feature corresponding to the target audio data according to the target projection direction:
determining a first feature vector corresponding to the first alignment data according to the first projection direction in the target projection direction, and determining a second feature vector corresponding to the second alignment data according to the second projection direction in the target projection direction;
and carrying out vector fusion on the first feature vector and the second feature vector to obtain the target audio feature.
In some embodiments, the processor 301 performs, in determining the noise detection result corresponding to the indoor environment according to the target audio feature:
classifying the sound source types of the target audio features to obtain a first type corresponding to the target audio features;
Classifying the sound intensity level of the target audio features to obtain a second type corresponding to the target audio features;
performing acoustic environment emotion classification on the target audio features to obtain a third type corresponding to the target audio features;
performing sound frequency classification on the target audio features to obtain a fourth type corresponding to the target audio features;
and determining the noise detection result corresponding to the indoor environment according to the first type, the second type, the third type and the fourth type.
It should be noted that, for convenience and brevity of description, a specific working process of the above-described terminal device may refer to a corresponding process in the foregoing embodiment of the indoor noise detection method, which is not described herein again.
The embodiment of the present invention also provides a storage medium for computer readable storage, where the storage medium stores one or more programs, and the one or more programs may be executed by one or more processors to implement the steps of any one of the indoor noise detection methods provided in the embodiment specification of the present invention.
The storage medium may be an internal storage unit of the terminal device according to the foregoing embodiment, for example, a hard disk or a memory of the terminal device. The storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the terminal device.
Those of ordinary skill in the art will appreciate that all or some of the steps, systems, functional modules/units in the apparatus, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware embodiment, the division between the functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed cooperatively by several physical components. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as known to those skilled in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.
It should be understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments. While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
1. An indoor noise detection method, the method comprising:
acquiring initial audio data obtained by sound monitoring of sensors positioned at different target positions in an indoor environment of noise to be detected;
obtaining corresponding object information in the indoor environment, and performing data processing on the initial audio data acquired under the target position according to the object information to obtain target audio data corresponding to the initial audio data;
carrying out data projection on the target audio data to obtain a target projection direction corresponding to the target audio data;
determining a target audio feature corresponding to the target audio data according to the target projection direction;
and determining a noise detection result corresponding to the indoor environment according to the target audio characteristics.
2. The method according to claim 1, wherein the data processing the initial audio data collected at the target position according to the object information to obtain target audio data corresponding to the initial audio data includes:
determining a three-dimensional model corresponding to the indoor environment according to the object information;
performing sound simulation in the three-dimensional model to obtain sound environment monitoring parameters corresponding to the initial audio data obtained by the sensor at the target position;
And carrying out data processing on the initial audio data according to the acoustic environment monitoring parameters to obtain the target audio data corresponding to the initial audio data.
3. The method according to claim 1, wherein the target audio data includes at least a first audio data and a second audio data, and the performing data projection on the target audio data to obtain a target projection direction corresponding to the target audio data includes:
data alignment is carried out on the first audio data and the second audio data according to a time dimension, and first alignment data corresponding to the first audio data and second alignment data corresponding to the second audio data are obtained;
determining a first projection direction corresponding to the first alignment data and a second projection direction corresponding to the second alignment data;
calculating the correlation between the first projection direction and the second projection direction to obtain a correlation result;
when the correlation result does not meet a preset condition, updating the first projection direction and the second projection direction, and recalculating the correlation between the first projection direction and the second projection direction;
And when the correlation result meets a preset condition, determining the target projection direction according to the first projection direction and the second projection direction.
4. A method according to claim 3, wherein said calculating a correlation between said first projection direction and said second projection direction to obtain a correlation result comprises:
obtaining a first correlation corresponding to internal data in the first alignment data, a second correlation corresponding to internal data in the second alignment data and a third correlation between the first alignment data and the second alignment data;
performing correlation calculation according to the first correlation, the second correlation, the third correlation, the first projection direction and the second projection direction to obtain a correlation result;
wherein the correlation result is obtained according to the following formula:
wherein alpha represents the first projection direction, beta represents the second projection direction, alpha T Representing the transpose of alpha, beta T Represents the transpose of beta, C xy Representing the third correlation, C xx Representing the first correlation, C yy Representing the second correlation.
5. The method of claim 4, wherein determining the target projection direction, the method further comprising:
Determining an adjustable parameter, and determining an adjustable difference between the first correlation and the second correlation according to the first correlation, the second correlation and the adjustable parameter;
performing equation calculation according to the adjustable value, the first correlation, the second correlation, the first projection direction and the second projection direction, and determining the first projection direction and the second projection direction as the target projection direction when the equation is satisfied;
wherein the equation calculation is according to the following equation:
alpha represents the first projection direction, beta represents the second projection direction, C xy Representing the third correlation, C xx Representing the first correlation, C yy Representing the second correlation, Z xy Represents the adjustable difference, lambda 1 Representing a first characteristic value, lambda, corresponding to the first alignment data 2 And representing a second characteristic value corresponding to the second alignment data.
6. A method according to claim 3, wherein said determining a target audio feature corresponding to the target audio data according to the target projection direction comprises:
determining a first feature vector corresponding to the first alignment data according to the first projection direction in the target projection direction, and determining a second feature vector corresponding to the second alignment data according to the second projection direction in the target projection direction;
And carrying out vector fusion on the first feature vector and the second feature vector to obtain the target audio feature.
7. The method of claim 1, wherein said determining a noise detection result corresponding to the indoor environment from the target audio feature comprises:
classifying the sound source types of the target audio features to obtain a first type corresponding to the target audio features;
classifying the sound intensity level of the target audio features to obtain a second type corresponding to the target audio features;
performing acoustic environment emotion classification on the target audio features to obtain a third type corresponding to the target audio features;
performing sound frequency classification on the target audio features to obtain a fourth type corresponding to the target audio features;
and determining the noise detection result corresponding to the indoor environment according to the first type, the second type, the third type and the fourth type.
8. An indoor noise detection apparatus, comprising:
the data acquisition module is used for acquiring initial audio data obtained by sound monitoring of the sensors positioned at different target positions in the indoor environment of the noise to be detected;
The data processing module is used for obtaining corresponding object information in the indoor environment, and carrying out data processing on the initial audio data acquired under the target position according to the object information to obtain target audio data corresponding to the initial audio data;
the direction confirming module is used for carrying out data projection on the target audio data to obtain a target projection direction corresponding to the target audio data;
the feature acquisition module is used for determining target audio features corresponding to the target audio data according to the target projection direction;
and the result confirmation module is used for determining a noise detection result corresponding to the indoor environment according to the target audio characteristics.
9. A terminal device, characterized in that the terminal device comprises a processor and a memory;
the memory is used for storing a computer program;
the processor is configured to execute the computer program and to implement the indoor noise detection method according to any one of claims 1 to 7 when the computer program is executed.
10. A computer storage medium for computer storage, characterized in that the computer storage medium stores one or more programs executable by one or more processors to implement the steps of the indoor noise detection method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311620999.5A CN117537918A (en) | 2023-11-30 | 2023-11-30 | Indoor noise detection method and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311620999.5A CN117537918A (en) | 2023-11-30 | 2023-11-30 | Indoor noise detection method and related device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117537918A true CN117537918A (en) | 2024-02-09 |
Family
ID=89785814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311620999.5A Pending CN117537918A (en) | 2023-11-30 | 2023-11-30 | Indoor noise detection method and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117537918A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106328152A (en) * | 2015-06-30 | 2017-01-11 | 芋头科技（杭州）有限公司 | Automatic identification and monitoring system for indoor noise pollution |
| JP2017040128A (en) * | 2015-08-21 | 2017-02-23 | 住友林業株式会社 | Indoor noise prediction method and residential design support system |
| CN110782911A (en) * | 2018-07-30 | 2020-02-11 | 阿里巴巴集团控股有限公司 | Audio signal processing method, apparatus, device and storage medium |
| CN111798874A (en) * | 2020-06-24 | 2020-10-20 | 西北师范大学 | Voice emotion recognition method and system |
| CN114171041A (en) * | 2021-11-30 | 2022-03-11 | 深港产学研基地（北京大学香港科技大学深圳研修院） | Voice noise reduction method, device and equipment based on environment detection and storage medium |
| KR20220032322A (en) * | 2020-09-07 | 2022-03-15 | 에스케이텔레콤 주식회사 | Method and Apparatus for Generating Music Fingerprint |
| CN114566160A (en) * | 2022-03-01 | 2022-05-31 | 游密科技(深圳)有限公司 | Voice processing method and device, computer equipment and storage medium |
| CN217586040U (en) * | 2022-07-06 | 2022-10-14 | 中国联合网络通信集团有限公司 | Indoor noise space positioning and monitoring equipment |
-
2023
- 2023-11-30 CN CN202311620999.5A patent/CN117537918A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106328152A (en) * | 2015-06-30 | 2017-01-11 | 芋头科技（杭州）有限公司 | Automatic identification and monitoring system for indoor noise pollution |
| JP2017040128A (en) * | 2015-08-21 | 2017-02-23 | 住友林業株式会社 | Indoor noise prediction method and residential design support system |
| CN110782911A (en) * | 2018-07-30 | 2020-02-11 | 阿里巴巴集团控股有限公司 | Audio signal processing method, apparatus, device and storage medium |
| CN111798874A (en) * | 2020-06-24 | 2020-10-20 | 西北师范大学 | Voice emotion recognition method and system |
| KR20220032322A (en) * | 2020-09-07 | 2022-03-15 | 에스케이텔레콤 주식회사 | Method and Apparatus for Generating Music Fingerprint |
| CN114171041A (en) * | 2021-11-30 | 2022-03-11 | 深港产学研基地（北京大学香港科技大学深圳研修院） | Voice noise reduction method, device and equipment based on environment detection and storage medium |
| CN114566160A (en) * | 2022-03-01 | 2022-05-31 | 游密科技(深圳)有限公司 | Voice processing method and device, computer equipment and storage medium |
| CN217586040U (en) * | 2022-07-06 | 2022-10-14 | 中国联合网络通信集团有限公司 | Indoor noise space positioning and monitoring equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Batool et al. | Telemonitoring of daily activity using accelerometer and gyroscope in smart home environments | |
| Tsanas et al. | Robust fundamental frequency estimation in sustained vowels: Detailed algorithmic comparisons and information fusion with adaptive Kalman filtering | |
| WO2016117358A1 (en) | Examination data processing device and examination data processing method | |
| EP3444809A1 (en) | Personalized speech recognition method, and user terminal performing the method | |
| JP6958723B2 (en) | Signal processing systems, signal processing equipment, signal processing methods, and programs | |
| JP2019049414A (en) | Sound processing device, sound processing method and program | |
| CN109948680B (en) | Classification method and system for medical record data | |
| Grønnesby et al. | Feature extraction for machine learning based crackle detection in lung sounds from a health survey | |
| US20160007130A1 (en) | Performance Metric Based Stopping Criteria for Iterative Algorithms | |
| JP6892426B2 (en) | Learning device, detection device, learning method, learning program, detection method, and detection program | |
| US11120819B2 (en) | Voice extraction device, voice extraction method, and non-transitory computer readable storage medium | |
| TW201812339A (en) | Epicentral distance estimating device, epicentral distance estimating method, and computer-readable recording medium | |
| JP6019659B2 (en) | Apnea condition determination device, apnea condition determination method, and apnea condition determination program | |
| Engin et al. | Extraction of low-dimensional features for single-channel common lung sound classification | |
| CN117537918A (en) | Indoor noise detection method and related device | |
| JP7373358B2 (en) | Sound extraction system and sound extraction method | |
| JP7266390B2 (en) | Behavior identification method, behavior identification device, behavior identification program, machine learning method, machine learning device, and machine learning program | |
| JP6648435B2 (en) | Discrimination device, discrimination method, program, model generation device, and model generation method | |
| Smith et al. | Sensitivity analysis of muscle mechanics-based voice simulator to determine gender-specific speech characteristics | |
| JP5414160B2 (en) | Kansei evaluation apparatus and method | |
| KR20230135844A (en) | Apparatus, method and system for automatic control of biological and emotional responsive masking sound | |
| JP7397801B2 (en) | Apparatus for detecting a subject with breathing disorder and method of operating the apparatus for detecting a subject with breathing disorder | |
| JP2020513908A (en) | How to characterize sleep-disordered breathing | |
| JP2021135603A (en) | Determination device, model generation device, determination method and determination program | |
| JPWO2019039261A1 (en) | Sleep quality assessment system, sleep quality modeling program, and sleep quality assessment program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |