CN114882879A

CN114882879A - Audio noise reduction method, method and device for determining mapping information and electronic equipment

Info

Publication number: CN114882879A
Application number: CN202210531564.2A
Authority: CN
Inventors: 张明哲
Original assignee: Apollo Intelligent Connectivity Beijing Technology Co Ltd
Current assignee: Apollo Intelligent Connectivity Beijing Technology Co Ltd
Priority date: 2022-05-13
Filing date: 2022-05-13
Publication date: 2022-08-09

Abstract

The disclosure provides an audio noise reduction method, a method and a device for determining mapping information and electronic equipment, and relates to the technical field of data processing, in particular to the fields of artificial intelligence, automatic driving and intelligent cabins. The specific implementation scheme is as follows: acquiring current in-vehicle audio data, current outside-vehicle environment noise data and current original audio data from vehicle-mounted playing equipment; determining current in-vehicle environmental noise data according to the current out-vehicle environmental noise data and the mapping information; the mapping information indicates a relationship between the vehicle exterior environmental noise data and the vehicle interior environmental noise data; according to the current original audio data and the current in-vehicle environmental noise data, noise reduction is carried out on the current in-vehicle audio data to obtain target audio data; wherein the in-vehicle ambient noise data includes noise data generated in the vehicle by the out-of-vehicle ambient noise data.

Description

Audio noise reduction method, method and device for determining mapping information and electronic equipment

Technical Field

The present disclosure relates to the field of data processing technologies, and in particular, to the fields of voice technology, artificial intelligence, and automatic driving, and more particularly, to an audio denoising method, a method and an apparatus for determining mapping information, an electronic device, a storage medium, and a computer program product.

Background

With the intelligent development of the internet of vehicles, the vehicle-mounted voice system is applied to more and more vehicles, and in practical application, human-computer interaction can be carried out with the vehicle-mounted voice system through user voice. For example, the vehicle-mounted voice system collects the audio data in the vehicle, performs voice recognition on the audio data in the vehicle, and performs a wakeup operation when it is determined that a predetermined wakeup word is recognized. Or under the condition that the vehicle-mounted voice system determines that the preset instruction is recognized, the operations of playing music, making a call and the like are executed.

Disclosure of Invention

The present disclosure provides an audio noise reduction method, a method, an apparatus, an electronic device, a storage medium, and a computer program product for determining mapping information.

According to an aspect of the present disclosure, there is provided an audio noise reduction method, including: acquiring current in-vehicle audio data, current outside-vehicle environment noise data and current original audio data from vehicle-mounted playing equipment; determining current in-vehicle environmental noise data according to the current out-vehicle environmental noise data and the mapping information; the mapping information indicates a relationship between the vehicle exterior environmental noise data and the vehicle interior environmental noise data; according to the current original audio data and the current in-vehicle environmental noise data, denoising the current in-vehicle audio data to obtain target audio data; wherein the in-vehicle ambient noise data includes noise data generated in the vehicle by the out-of-vehicle ambient noise data.

According to another aspect of the present disclosure, there is provided a method of determining mapping information, including: acquiring a plurality of data sets, wherein each data set comprises vehicle exterior environment noise data and vehicle interior environment noise data, and the vehicle interior environment noise data comprises noise data generated by the vehicle exterior environment noise data in a vehicle; and determining a relationship between the vehicle exterior environment noise data and the vehicle interior environment noise data according to the plurality of data sets to obtain mapping information indicating the relationship.

According to another aspect of the present disclosure, an audio noise reduction apparatus is provided, which includes an obtaining module, a first determining module, and a noise reduction module. The acquisition module is used for acquiring current in-vehicle audio data, current outside-vehicle environment noise data and current original audio data from the vehicle-mounted playing equipment; the first determining module is used for determining the current internal environment noise data according to the current external environment noise data and the mapping information; the mapping information indicates a relationship between the vehicle exterior environmental noise data and the vehicle interior environmental noise data; the noise reduction module is used for reducing noise of the current in-vehicle audio data according to the current original audio data and the current in-vehicle environmental noise data to obtain target audio data; wherein the in-vehicle ambient noise data includes noise data generated in the vehicle by the out-of-vehicle ambient noise data.

According to another aspect of the present disclosure, an apparatus for determining mapping information is provided, which includes an acquisition module and a second determination module. The acquisition module is used for acquiring a plurality of data sets, each data set comprises vehicle exterior environment noise data and vehicle interior environment noise data, and the vehicle interior environment noise data comprises noise data generated by the vehicle exterior environment noise data in a vehicle; the second determining module is used for determining the relation between the environment noise data outside the vehicle and the environment noise data inside the vehicle according to the plurality of data groups to obtain mapping information indicating the relation.

According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the methods provided by the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform a method provided by the present disclosure.

According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method provided by the present disclosure.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

fig. 1 is a schematic diagram of an application scenario of an audio denoising method, a method and an apparatus for determining mapping information according to an embodiment of the present disclosure;

FIG. 2 is a schematic flow diagram of an audio noise reduction method according to an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of an audio noise reduction method according to an embodiment of the present disclosure;

FIG. 4 is a schematic flow chart diagram of a method of determining mapping information in accordance with an embodiment of the present disclosure;

fig. 5 is a schematic block diagram of an audio noise reduction apparatus according to an embodiment of the present disclosure;

fig. 6 is a schematic block diagram of an apparatus for determining mapping information according to an embodiment of the present disclosure; and

fig. 7 is a block diagram of an electronic device for implementing the audio noise reduction method and the method of determining mapping information according to the embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

It should be noted that the ambient environment of the vehicle and the audio played by the vehicle-mounted playing device may be mixed into the in-vehicle audio data collected by the vehicle-mounted voice system in the form of noise, which affects the accuracy of the in-vehicle audio data speech recognition performed by the vehicle-mounted voice system, and further affects the human-computer interaction effect. The technical solutions provided by the present disclosure will be described in detail below with reference to the accompanying drawings and specific embodiments.

Fig. 1 is a schematic view of an application scenario of an audio noise reduction method, a method for determining mapping information, and an apparatus according to an embodiment of the present disclosure.

It should be noted that fig. 1 is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.

As shown in fig. 1, the system architecture 100 according to this embodiment may include a vehicle, which may be an autonomous vehicle or a manned vehicle. The vehicle may be equipped with an in-vehicle playback device 101, a first audio capture device 102, a second audio capture device 103, a noise reduction system 104, and an in-vehicle speech system 105.

The in-vehicle playback device 101 is used to play audio data such as music, radio, and the like.

The first audio capturing device 102 is used for capturing ambient noise data outside the vehicle, and the first audio capturing device 102 is disposed outside the vehicle, for example, on the roof of the vehicle body. The first audio capturing device 102 may employ a microphone.

The second audio collecting device 103 is used for collecting audio data in the vehicle, and the second audio collecting device 103 is arranged in the vehicle and can adopt a microphone.

The noise reduction system 104 is used to reduce noise in the in-vehicle audio data. The vehicle-mounted playing device 101, the second audio collecting device 103, the first audio collecting device 102 and the vehicle-mounted voice system 105 may all perform data transmission with the noise reduction system 104, for example, the vehicle-mounted playing device 101, the second audio collecting device 103 and the first audio collecting device 102 respectively input audio data into the noise reduction system 104. The noise reduction system 104 performs noise reduction processing on the audio data, for example, the noise reduction system 104 performs noise reduction on the current in-vehicle audio data according to the current original audio data and the current outside-vehicle ambient noise data to obtain target audio data. Noise reduction system 104 may then send the noise-reduced target audio data to vehicular speech system 105.

The in-vehicle voice system 105 is configured to perform voice recognition on the target audio data, so as to determine an instruction included in the target audio data, for example, determine a predetermined wake-up word included in the user voice data. In some embodiments, the in-vehicle speech system 105 may be configured in a terminal device including, but not limited to, a smart phone, a tablet computer, a laptop portable computer, a desktop computer, and the like.

In some embodiments, noise reduction system 104 may be integrated with in-vehicle speech system 105 in a terminal device. When the technical scheme is adopted, the audio noise reduction method and the method for determining the mapping information provided by the embodiment of the disclosure can be executed by the terminal equipment. Accordingly, the audio noise reduction device and the device for determining mapping information provided by the embodiments of the present disclosure may be generally disposed in a terminal device.

It should be understood that the numbers of the in-vehicle playback device, the first audio capture device, the second audio capture device, the noise reduction system, and the in-vehicle speech system in fig. 1 are merely illustrative. According to the implementation requirement, any number of vehicle-mounted playing devices, first audio acquisition devices, second audio acquisition devices, noise reduction systems and vehicle-mounted voice systems can be provided.

Fig. 2 is a schematic flow diagram of an audio noise reduction method according to an embodiment of the present disclosure.

As shown in fig. 2, the audio denoising method 200 may include operations S210 to S230.

In operation S210, current in-vehicle audio data, current out-vehicle ambient noise data, and current original audio data from the in-vehicle playback device are acquired.

The current original audio data may represent audio played by a vehicle-mounted playback device installed in the vehicle at the current time, such as audio of music, broadcast, and the like played by a vehicle audio, or audio contained in video played by a video player.

In some embodiments, the audio that the vehicle-mounted playing device needs to play is known audio, and the sound equipment needs to acquire an audio file to be played first and then play the audio file. The embodiment may take the audio file as the current original audio data when the in-vehicle playback device plays the audio file.

The current external environment noise data can represent the sound of the vehicle in the current place, and the place can be outdoor places such as downtown areas, roads, open parking lots and the like, and can also be indoor places such as underground parking lots, shopping malls and the like. The current off-board ambient noise data is related to the place where the vehicle is located and the driving state of the vehicle, for example, when the vehicle is in a downtown place, sounds in the place may include traffic noise, building noise, and the like. For example, the sound in the place during the vehicle running may include wind sound, sound of tire wheel movement, and the like. In practical application, a first audio acquisition device can be installed outside a vehicle body to acquire sound in a place where a vehicle is located, so that current external environment noise data can be obtained.

The current in-vehicle audio data may represent sound present in the vehicle at the current time. The sound in the vehicle may include at least one of: the sound that the user sent in the car, the audio frequency of on-vehicle playback equipment broadcast, the ambient noise in the car. The environment noise inside the vehicle may be, for example, noise generated inside the vehicle by the environment noise outside the vehicle, that is, sound obtained after sound outside the vehicle is transmitted into the vehicle. In practical applications, the current in-vehicle audio data may be acquired using a second audio acquisition device installed in the vehicle. The second audio capturing device may be a microphone.

In operation S220, current in-vehicle ambient noise data is determined according to the current off-vehicle ambient noise data and the mapping information.

For example, the mapping information may indicate a relationship between the off-board ambient noise data and the in-board ambient noise data. The mapping information may be determined based on a plurality of external environmental noise data and a plurality of internal environmental noise data collected in advance, for example, one external environmental noise data and one internal environmental noise data may be collected at a first time, and then one external environmental noise data and one internal environmental noise data may be collected again at a second time. And repeatedly executing the acquisition operation at different moments, and then establishing mapping information for the external environment noise data and the internal environment noise data at the same moment. For example, the pre-collected vehicle exterior environment noise data and vehicle interior environment noise data may be stored as data tables in which each vehicle interior environment noise data may correspond to one vehicle exterior environment noise data.

After the mapping information is determined, current in-vehicle ambient noise data may be determined based on the current off-vehicle ambient noise data and the mapping information. For example, one piece of outside-vehicle ambient noise data that is the same as or similar to the current outside-vehicle ambient noise data is determined from a plurality of pieces of outside-vehicle ambient noise data collected in advance, and then the inside-vehicle ambient noise data corresponding to the outside-vehicle ambient noise data in the data table is determined as the current inside-vehicle ambient noise data.

In operation S230, noise reduction is performed on the current in-vehicle audio data according to the current original audio data and the current in-vehicle ambient noise data, so as to obtain target audio data.

For example, the current in-vehicle ambient noise data and the current raw audio data may be removed from the current in-vehicle audio data. It can be seen that after noise reduction, the resulting target audio data includes user speech data.

The technical scheme that this disclosed embodiment provided makes an uproar according to current original audio data and current car external environment noise data, falls to the current audio frequency in the car, consequently can avoid current original audio data and current car external environment noise data to cause the interference to user's voice data, improves the noise reduction effect.

In practical application, after the target audio data is obtained, the vehicle-mounted voice system can be used for performing voice recognition on the target audio data, so that instructions contained in the user voice data are accurately recognized, for example, a predetermined awakening word contained in the user voice data is recognized, and the interaction effect between the vehicle-mounted voice system and the user is further ensured.

In addition, with respect to the same outside environment noise, the inside environment noise generated by the outside environment noise transmitted to the inside of the vehicle from the outside of the vehicle is related to the window opening degree. The window opening may represent an opening size of the window, for example, the window opening ranges from 0 to 1,a window opening of 0 may indicate that the window is fully closed, and a window opening of 1 may indicate that the window is fully opened. In one example, the window opening may be defined as a ratio of an area of window opening to a total area of the window, for example, a certain window opening area is 0.3m ² The total area of the window is 1m ² The window opening is 0.3. In another example, for a window that is opened and closed by being raised and lowered, the window opening may be defined as a ratio of a window lowered height to a total window height, and the window lowered height may represent a distance from a top of the window to a window frame, for example, when the window lowered height is 10cm, the total window height is 50cm, and the window opening is 0.2. For the same environment noise outside the vehicle, the larger the window opening, the larger the environment noise inside the vehicle is transmitted to the inside of the vehicle.

In some embodiments, the current in-vehicle audio data may be de-noised according to the window opening. For example, mapping information indicating a relationship between the vehicle exterior environment noise data, the window opening, and the vehicle interior environment noise data may be established in advance, and a process of establishing the mapping information is described in detail below and is not described herein again. Accordingly, the operation of determining the current in-vehicle ambient noise data based on the current off-board ambient noise data and the mapping information may comprise the operations of: and determining current in-vehicle environmental noise data based on the mapping information according to the current window opening and the current out-vehicle environmental noise data.

The influence of the car window opening degree on the car internal environment noise data is considered in the embodiment of the present disclosure, so that the current car internal environment noise data is accurately determined, and the noise reduction effect for the current car internal audio data is improved.

It should be appreciated that in other embodiments, the effect of window opening on the in-vehicle ambient noise data transmitted to the interior of the vehicle by the out-of-vehicle ambient noise may also be ignored.

According to another embodiment of the present disclosure, the operation of determining the current in-vehicle ambient noise data based on the mapping information according to the current window opening and the current out-of-vehicle ambient noise data may include the operations of: determining a current loudness attenuation coefficient corresponding to the current window opening according to the current window opening and the mapping information; and the loudness attenuation coefficient represents the relation between the loudness of the environment noise data outside the automobile and the loudness of the corresponding environment noise data inside the automobile under the opening degree of the automobile window. And then determining the current in-vehicle environment noise data according to the current loudness attenuation coefficient and the current outside-vehicle environment noise data.

For example, the result of multiplying the wave function of the present outside-vehicle ambient noise data by the loudness attenuation coefficient may be used as the present inside-vehicle ambient noise data generated inside the vehicle by the outside-vehicle ambient noise data.

The technical scheme that this disclosed embodiment provided adopts predetermined loudness attenuation coefficient to confirm car internal environment noise data, consequently can convert car external environment noise data into corresponding car internal environment noise data, improves the accuracy of car internal environment noise data, and then improves the noise reduction effect.

In other embodiments, the current in-vehicle ambient noise data may not be determined using the loudness attenuation coefficients described above. For example, a plurality of window openings may be determined, and the vehicle exterior environmental noise data and the vehicle interior environmental noise data may be collected at each window opening in advance, and then the values of the window openings, the vehicle exterior environmental noise data, and the vehicle interior environmental noise data may be stored in the data table as three fields. It can be seen that, in the data table, for the same window opening, the data table can correspond to a plurality of external environment noise data, and each external environment noise data can correspond to a plurality of internal environment noise data. Then, the window opening identical or similar to the current window opening can be searched in the data table, the external environment noise data identical or similar to the current external environment noise data can be searched, and then the internal environment noise data corresponding to the searched window opening and external environment noise data can be used as the current internal environment noise data.

According to another embodiment of the present disclosure, the operation of denoising the current in-vehicle audio data according to the current original audio data and the current in-vehicle ambient noise data to obtain the target audio data may include the following operations: and overlapping the current in-vehicle environmental noise data and the current original audio data to obtain overlapped audio data. And then, according to the superposed audio data, carrying out noise reduction on the current audio data in the vehicle to obtain target audio data.

Illustratively, the first noise reduction model may be trained in advance. For example, first audio data of "noise + human voice" may be collected, and second audio data of pure human voice may be collected. The first audio data and the second audio data are input into the model as training samples. In the training process, the first audio data is processed into first processed audio data through a model, and then a loss value is calculated based on the first processed audio data and the second audio data. Parameters of the first noise reduction model may then be optimized based on the loss values, and iterated until the first noise reduction model converges to obtain a first noise reduction model.

The current in-vehicle audio data may then be denoised using a first denoising model, e.g., inputting the superimposed audio and the current in-vehicle audio data into the first denoising model, which outputs denoised target audio data.

The noise reduction effect is realized by adopting the first noise reduction model, and because the input data of the first noise reduction model comprise the superposed audio and the current in-vehicle audio data, the quantity of the input data is less, the noise reduction treatment can be rapidly carried out, and the real-time performance of the noise reduction effect is ensured.

In other embodiments, the current in-vehicle ambient noise data and the current raw audio data may not be superimposed.

Illustratively, the second noise reduction model may be trained in advance. For example, first audio data of "noise + voice" may be collected, second audio data of pure voice may be collected, ambient noise data outside the vehicle may be collected, and original audio data may be collected. The external environmental noise data may be determined to be transferred to the internal environmental noise data in the vehicle based on the mapping information. And inputting the first audio data, the second audio data, the in-vehicle environmental noise data and the original audio data into a second noise reduction model as training samples. In the training process, the first audio data, the in-vehicle ambient noise data and the original audio data are processed into second processed audio data through a model, and then a loss value is calculated based on the second processed audio data and the second audio data. Then, parameters of the second noise reduction model can be optimized based on the loss values, and the second noise reduction model is obtained after iteration until the second noise reduction model converges.

The current in-vehicle audio data may then be denoised using a second denoising model, for example, transferring the current outside-vehicle ambient noise data to the in-vehicle ambient noise data, the original audio data, and the current in-vehicle audio data into the second denoising model, which outputs denoised target audio data.

Fig. 3 is a schematic and schematic diagram of an audio noise reduction method according to an embodiment of the present disclosure.

As shown in fig. 3, in the present embodiment 300, the map information 301 may be determined in advance, and the map information 301 may indicate the relationship between the external environment noise of the vehicle, the internal environment noise of the vehicle, and the window opening degree.

The current window opening 302 may then be determined, the current ambient noise data 303 outside the vehicle captured using a first audio capture device 310 located outside the vehicle, the current raw audio data 305 determined by the in-vehicle playback device 320, and the current in-vehicle audio data 306 captured using a second audio capture device 330 located inside the vehicle.

Then, current in-vehicle ambient noise data 304 is determined according to the current outside-vehicle ambient noise data 303, the current window opening 302 and the mapping information 301. Then, the noise reduction system 340 performs noise reduction on the current in-vehicle audio data 306 according to the current in-vehicle ambient noise data 304 and the current original audio data 305, so as to obtain noise-reduced target audio data 307.

Fig. 4 is a schematic flow chart diagram of a method of determining mapping information in accordance with an embodiment of the present disclosure.

As shown in fig. 4, the method 400 of determining mapping information may include operations S410 to S420.

In operation S410, a plurality of data sets are collected, each data set including outside-vehicle ambient noise data and inside-vehicle ambient noise data, the inside-vehicle ambient noise data including noise data generated inside the vehicle by the outside-vehicle ambient noise data.

In operation S420, a relationship between the external environment noise data and the internal environment noise data is determined according to the plurality of data sets, resulting in mapping information indicating the relationship.

For example, ambient noise data outside the vehicle may be collected by a first audio capture device installed outside the vehicle, and ambient noise data inside the vehicle may be collected by a second audio capture device located inside the vehicle.

In one example, multiple data sets may be stored as a data table. When the data table is used, the external environment noise data which is the same as or similar to the current external environment noise data can be searched in the data table, and the internal environment noise data corresponding to the searched current window opening and external environment noise data is used as the current internal environment noise data.

In another example, a linear equation with an error below an error threshold may be determined from the plurality of data sets. The error threshold may be 0.05.

In another example, a loudness attenuation factor corresponding to each window opening may be determined for each of the plurality of window openings based on a loudness of the outside ambient noise data and a loudness of the inside ambient noise data. Then, the mapping information is determined according to the loudness attenuation coefficient corresponding to each window opening.

For example, the ratio of the area of the window opened to the total area of the window may be used as the window opening, or the ratio of the window descending height to the total height of the window may be used as the window opening.

Noise is transmitted from the outside of the vehicle to the inside of the vehicle, and the frequency of the noise is not changed, and the loudness is changed.

For example, the external environment noise data and the internal environment noise data transmitted to the inside of the vehicle may be collected at a predetermined window opening, and then the loudness attenuation coefficient may be determined according to the loudness of the external environment noise data and the loudness of the internal environment noise data. For example, when the window opening is in a range of 0 to 1 and the window opening is 0.2, the loudness of the external environment noise data is 50 decibels, and the loudness of the internal environment noise data is 10 decibels, the loudness attenuation coefficient may be 10/50 ═ 0.2. When the window opening is 0.1, the loudness of the external environment noise data is 50 decibels, and the loudness of the internal environment noise data is 5 decibels, then the loudness attenuation coefficient may be 5/50 ═ 0.1.

And then, the window opening is readjusted, and the operation of determining the loudness attenuation coefficient is repeatedly executed until a preset termination condition is met, wherein the preset termination condition can be that the operation of determining the loudness attenuation coefficient is repeatedly executed for a preset number of times, and the preset number of times can be 100 times.

After the predetermined times of repeated execution, the corresponding relation between the window opening and the loudness attenuation coefficient can be obtained. The car window opening degree-loudness attenuation coefficient line can be fitted, the abscissa axis and the ordinate axis of the car window opening degree-loudness attenuation coefficient line can be the car window opening degree and the loudness attenuation coefficient respectively, and the shape of the car window opening degree-loudness attenuation coefficient line is determined according to actual conditions, for example, the shape can be a linear straight line or a curve.

It should be noted that, in some embodiments, respective mapping information may be determined for a plurality of vehicle types to improve the adaptation degree of the mapping information to the vehicle, so as to improve the noise reduction effect. In other embodiments, the influence of the difference of vehicle types on the mapping information can be ignored, and a plurality of vehicle types use the same mapping information.

In some embodiments, the mapping information provided by the embodiments of the present disclosure may be applied to the audio noise reduction method.

Fig. 5 is a schematic structural block diagram of an audio noise reduction apparatus according to an embodiment of the present disclosure.

As shown in fig. 5, the audio noise reducer 500 may include an obtaining module 510, a first determining module 520, and a noise reducing module 530.

The obtaining module 510 is configured to obtain current in-vehicle audio data, current outside-vehicle ambient noise data, and current original audio data from the in-vehicle playing device.

The first determining module 520 is configured to determine current in-vehicle ambient noise data according to the current out-of-vehicle ambient noise data and the mapping information. The mapping information indicates a relationship between the outside-vehicle environmental noise data and the inside-vehicle environmental noise data, wherein the inside-vehicle environmental noise data includes noise data generated inside the vehicle by the outside-vehicle environmental noise data.

The noise reduction module 530 is configured to reduce noise of the current in-vehicle audio data according to the current original audio data and the current in-vehicle ambient noise data, so as to obtain target audio data.

According to another embodiment of the present disclosure, the mapping information further indicates a relationship between the window opening and the ambient noise data in the vehicle. The first determining module comprises a first determining submodule and is used for determining current in-vehicle environmental noise data based on the mapping information according to the current window opening and the current out-of-vehicle environmental noise data.

According to another embodiment of the present disclosure, the first determination submodule includes a first determination unit and a second determination unit. The first determining unit is used for determining a current loudness attenuation coefficient corresponding to the current window opening according to the current window opening and the mapping information. And the loudness attenuation coefficient represents the relation between the loudness of the environment noise data outside the automobile and the loudness of the corresponding environment noise data inside the automobile under the opening degree of the automobile window. The second determining unit is used for determining the current in-vehicle environment noise data according to the current loudness attenuation coefficient and the current outside-vehicle environment noise data.

According to another embodiment of the present disclosure, the noise reduction module includes a superposition sub-module and a noise reduction sub-module. And the superposition submodule is used for superposing the current original audio data and the current in-vehicle environmental noise data to obtain superposed audio data. And the noise reduction submodule is used for reducing noise of the current audio data in the vehicle according to the superposed audio data to obtain target audio data.

Fig. 6 is a schematic block diagram of an apparatus for determining mapping information according to an embodiment of the present disclosure.

As shown in fig. 6, the apparatus 600 for determining mapping information may include an acquisition module 610 and a second determination module 620.

The collection module 610 is used for collecting a plurality of data sets, each data set comprises vehicle exterior environmental noise data and vehicle interior environmental noise data, and the vehicle interior environmental noise data comprises noise data generated by the vehicle exterior environmental noise data in the vehicle.

The second determining module 620 is configured to determine a relationship between the vehicle exterior environmental noise data and the vehicle interior environmental noise data according to the plurality of data sets, and obtain mapping information indicating the relationship.

According to another embodiment of the present disclosure, the second determination module includes a second determination submodule and a third determination submodule. The second determining submodule is used for determining a loudness attenuation coefficient corresponding to each window opening according to the loudness of the outside environment noise data and the loudness of the inside environment noise data of the vehicle at each window opening aiming at each window opening in the plurality of window openings. And the third determining submodule is used for determining mapping information according to the loudness attenuation coefficient corresponding to each window opening.

In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations and do not violate the good customs of the public order.

In the technical scheme of the disclosure, before the personal information of the user is acquired or collected, the authorization or the consent of the user is acquired.

According to an embodiment of the present disclosure, there is also provided an electronic device, comprising at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the above-described audio noise reduction method and method of determining mapping information.

According to an embodiment of the present disclosure, there is also provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the above-described audio noise reduction method and method of determining mapping information.

According to an embodiment of the present disclosure, there is also provided a computer program product comprising a computer program which, when executed by a processor, implements the above-described audio noise reduction method and method of determining mapping information.

FIG. 7 shows a schematic block diagram of an example electronic device 700 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 7, the device 700 comprises a computing unit 701 which may perform various suitable actions and processes according to a computer program stored in a Read Only Memory (ROM)702 or a computer program loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other by a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

Various components in the device 700 are connected to the I/O interface 705, including: an input unit 706 such as a keyboard, a mouse, or the like; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, optical disk, or the like; and a communication unit 709 such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

Computing unit 701 may be a variety of general purpose and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 701 performs the respective methods and processes described above, such as the audio noise reduction method and the method of determining the mapping information. For example, in some embodiments, the audio noise reduction method and the method of determining mapping information may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of a computer program may be loaded onto and/or installed onto device 700 via ROM 702 and/or communications unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the audio noise reduction method and the method of determining mapping information described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured by any other suitable means (e.g. by means of firmware) to perform the audio noise reduction method and the method of determining the mapping information.

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. An audio noise reduction method comprising:

acquiring current in-vehicle audio data, current outside-vehicle environment noise data and current original audio data from vehicle-mounted playing equipment;

determining current in-vehicle environmental noise data according to the current out-vehicle environmental noise data and the mapping information; the mapping information indicates a relationship between the vehicle exterior environmental noise data and the vehicle interior environmental noise data; and

according to the current original audio data and the current in-vehicle environmental noise data, denoising the current in-vehicle audio data to obtain target audio data;

wherein the in-vehicle ambient noise data includes noise data generated in the vehicle by the out-of-vehicle ambient noise data.

2. The method of claim 1, wherein the mapping information further indicates a relationship between window opening and ambient noise data in the vehicle;

determining the current in-vehicle environmental noise data according to the current out-of-vehicle environmental noise data and the mapping information comprises:

and determining the current in-vehicle environment noise data based on the mapping information according to the current window opening and the current outside-vehicle environment noise data.

3. The method of claim 2, wherein the determining the current in-vehicle ambient noise data based on the mapping information from the current window opening and the current off-vehicle ambient noise data comprises:

determining a current loudness attenuation coefficient corresponding to the current window opening according to the current window opening and the mapping information; the loudness attenuation coefficient represents the relation between the loudness of the outside environment noise data and the corresponding loudness of the inside environment noise data under the window opening; and

and determining the current in-vehicle environmental noise data according to the current loudness attenuation coefficient and the current outside-vehicle environmental noise data.

4. The method of claim 1, wherein the denoising the current in-vehicle audio data according to the current original audio data and the current in-vehicle ambient noise data to obtain target audio data comprises:

superposing the current original audio data and the current in-vehicle environmental noise data to obtain superposed audio data; and

and according to the superposed audio data, denoising the current in-vehicle audio data to obtain the target audio data.

5. A method of determining mapping information, comprising:

acquiring a plurality of data sets, wherein each data set comprises vehicle exterior environment noise data and vehicle interior environment noise data, and the vehicle interior environment noise data comprises noise data generated by the vehicle exterior environment noise data in a vehicle; and

and determining a relationship between the external environment noise data and the internal environment noise data according to the plurality of data groups to obtain mapping information indicating the relationship.

6. The method of claim 5, wherein said determining a relationship between said off-board ambient noise data and said in-board ambient noise data from said plurality of data sets, resulting in mapping information indicative of said relationship comprises:

aiming at each window opening in a plurality of window openings, determining a loudness attenuation coefficient corresponding to each window opening according to the loudness of outside environment noise data and the loudness of inside environment noise data of getting off at each window opening; and

and determining the mapping information according to the loudness attenuation coefficient corresponding to each window opening.

7. An audio noise reduction apparatus comprising:

the acquisition module is used for acquiring current in-vehicle audio data, current outside-vehicle environment noise data and current original audio data from the vehicle-mounted playing equipment;

the first determining module is used for determining the current in-vehicle environmental noise data according to the current outside-vehicle environmental noise data and the mapping information; the mapping information indicates a relationship between the vehicle exterior environmental noise data and the vehicle interior environmental noise data; and

the noise reduction module is used for reducing noise of the current in-vehicle audio data according to the current original audio data and the current in-vehicle environmental noise data to obtain target audio data;

8. The apparatus of claim 7, wherein the mapping information further indicates a relationship between window opening and ambient noise data in the vehicle;

the first determining module includes:

and the first determining submodule is used for determining the current in-vehicle environment noise data based on the mapping information according to the current window opening and the current outside-vehicle environment noise data.

9. The apparatus of claim 8, wherein the first determination submodule comprises:

the first determining unit is used for determining a current loudness attenuation coefficient corresponding to the current window opening according to the current window opening and the mapping information; the loudness attenuation coefficient represents the relation between the loudness of the outside environment noise data and the corresponding loudness of the inside environment noise data under the window opening; and

and the second determining unit is used for determining the current in-vehicle environment noise data according to the current loudness attenuation coefficient and the current outside-vehicle environment noise data.

10. The apparatus of claim 7, wherein the noise reduction module comprises:

the superposition submodule is used for superposing the current original audio data and the current in-vehicle environmental noise data to obtain superposed audio data; and

and the noise reduction submodule is used for reducing the noise of the current in-vehicle audio data according to the superposed audio data to obtain the target audio data.

11. An apparatus to determine mapping information, comprising:

the system comprises an acquisition module, a data processing module and a data processing module, wherein the acquisition module is used for acquiring a plurality of data sets, each data set comprises vehicle exterior environment noise data and vehicle interior environment noise data, and the vehicle interior environment noise data comprises noise data generated by the vehicle exterior environment noise data in a vehicle; and

and the second determining module is used for determining the relationship between the environment noise data outside the vehicle and the environment noise data inside the vehicle according to the plurality of data groups to obtain mapping information indicating the relationship.

12. The apparatus of claim 11, wherein the second determining means comprises:

the second determining submodule is used for determining a loudness attenuation coefficient corresponding to each window opening according to the loudness of the outside environment noise data and the loudness of the inside environment noise data of the vehicle at each window opening aiming at each window opening in the plurality of window openings; and

and the third determining submodule is used for determining the mapping information according to the loudness attenuation coefficient corresponding to each window opening.

13. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 6.

14. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1 to 6.

15. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 6.