阅读说明：本技术 一种语音降噪方法、语音降噪系统、设备及存储介质 (Voice noise reduction method, voice noise reduction system, equipment and storage medium ) 是由 谭安平 于 2019-03-15 设计创作，主要内容包括：本发明公开了一种语音降噪方法、语音降噪系统、设备及存储介质,所述语音降噪方法包括：车机实时获取用户在车辆内向移动终端输入的用户语音信号；所述车机接收到进行语音降噪的开启指令后,将获取的用户语音信号作为目标语音信号进行降噪处理,再将经降噪处理后的目标语音信号传输给所述移动终端。本发明提供的语音降噪方法、语音降噪系统、设备及存储介质,通过车机对用户在车辆内向移动终端输入的用户语音信号进行降噪,以使移动终端获得经过降噪处理后的所述用户语音信号,不仅能够提高语音信号的质量,而且能够提高对语音信号进行语音识别的成功率和准确率。(The invention discloses a voice noise reduction method, a voice noise reduction system, equipment and a storage medium, wherein the voice noise reduction method comprises the following steps: the vehicle machine acquires a user voice signal input to the mobile terminal by a user in a vehicle in real time; and after the car machine receives a starting instruction for voice noise reduction, the obtained user voice signal is used as a target voice signal for noise reduction, and the target voice signal subjected to noise reduction is transmitted to the mobile terminal. According to the voice noise reduction method, the voice noise reduction system, the voice noise reduction equipment and the storage medium, the noise reduction is carried out on the user voice signal input to the mobile terminal by the user in the vehicle through the vehicle machine, so that the mobile terminal obtains the user voice signal subjected to noise reduction processing, the quality of the voice signal can be improved, and the success rate and the accuracy rate of voice recognition of the voice signal can be improved.)

1. A method for speech noise reduction, the method comprising:

the vehicle machine acquires a user voice signal input to the mobile terminal by a user in a vehicle in real time;

and after the car machine receives a starting instruction for voice noise reduction, the obtained user voice signal is used as a target voice signal for noise reduction, and the target voice signal subjected to noise reduction is transmitted to the mobile terminal.

2. The voice noise reduction method according to claim 1, wherein the car machine acquiring in real time a user voice signal input by a user to the mobile terminal in a vehicle comprises:

the car machine collects a user voice signal input to the mobile terminal by a user in the car in real time based on a microphone of the car.

3. The method according to claim 2, wherein the step of performing noise reduction processing on the acquired user speech signal as the target speech signal comprises:

the vehicle machine acquires the running speed of the vehicle;

inquiring a set corresponding relation list of the running speed of the vehicle and the wind noise signal according to the running speed of the vehicle to acquire the wind noise signal corresponding to the running speed of the vehicle;

and removing the acquired wind noise signal from the target speech signal to obtain a target speech signal after noise reduction processing.

4. The method according to claim 2, wherein the step of performing noise reduction processing on the acquired user speech signal as the target speech signal comprises:

the vehicle machine acquires the running speed of the vehicle;

taking the running speed of the vehicle as an input of a wind noise model to obtain a wind noise signal corresponding to the running speed of the vehicle; the wind noise model is obtained by training based on the historical driving speed of the vehicle and a historical wind noise signal;

and removing the obtained wind noise signal from the target speech signal to obtain a target speech signal after noise reduction processing.

5. The method according to claim 3 or 4, wherein the step of performing noise reduction processing on the acquired user speech signal as the target speech signal further comprises:

the car machine acquires an audio signal output by the car machine multimedia application;

and removing the audio signal output by the vehicle-mounted multimedia application from the target voice signal to obtain the target voice signal subjected to noise reduction processing.

6. The method of speech noise reduction according to claim 1, further comprising:

and after the vehicle machine detects that the preset stopping condition is triggered, stopping performing noise reduction processing on the acquired user voice signal serving as a target voice signal.

7. The voice noise reduction method according to claim 6, wherein the detecting, by the car machine, that the preset stop condition is triggered comprises:

and in a preset first time after receiving a starting instruction for voice noise reduction, the car machine does not acquire a user voice signal input to the mobile terminal by a user in the car.

8. The voice noise reduction method according to claim 6, wherein the detecting, by the car machine, that the preset stop condition is triggered comprises:

the car machine receives an ending instruction or a stopping instruction for voice noise reduction.

9. An apparatus comprising a processor and a storage device for storing a program; when executed by the processor, the program causes the processor to implement the method of speech noise reduction according to any of claims 1 to 8.

10. A computer storage medium, characterized in that a computer program is stored which, when executed by a processor, implements the speech noise reduction method of any one of claims 1 to 8.

11. A voice noise reduction system is characterized by comprising a vehicle machine and a mobile terminal; the vehicle-mounted device acquires a user voice signal input by a user to the mobile terminal in a vehicle in real time, and after receiving a starting instruction for voice noise reduction, the vehicle-mounted device firstly takes the acquired user voice signal as a target voice signal to carry out noise reduction processing, and then transmits the target voice signal subjected to the noise reduction processing to the mobile terminal.

Technical Field

The present invention relates to the field of vehicles, and in particular, to a voice noise reduction method, a voice noise reduction system, a device, and a storage medium.

Background

With the continuous development of the communication industry, the voice function of a mobile terminal such as a mobile phone is widely applied to the scenes of voice communication, voice recognition and the like. Background noise inevitably exists in a voice signal input to the mobile terminal by a user, and the quality of the voice signal is seriously influenced by the existence of the background noise, so that the success rate and the accuracy of voice recognition of the voice signal are reduced. For example, when a user uses a mobile terminal to perform a voice call in a vehicle in a driving state, the user is often interfered by environmental signals of the vehicle, such as wind noise signals and audio signals output by multimedia applications, so that the success rate and accuracy of voice recognition are low in the voice call process.

Disclosure of Invention

The invention aims to provide a voice noise reduction method, a voice noise reduction system, equipment and a storage medium, which can improve the quality of voice signals and the success rate and accuracy rate of voice recognition of the voice signals.

In order to achieve the purpose, the technical scheme of the invention is realized as follows:

in a first aspect, an embodiment of the present invention provides a speech noise reduction method, where the speech noise reduction method includes:

the vehicle machine acquires a user voice signal input to the mobile terminal by a user in a vehicle in real time;

and after the car machine receives a starting instruction for voice noise reduction, the obtained user voice signal is used as a target voice signal for noise reduction, and the target voice signal subjected to noise reduction is transmitted to the mobile terminal.

As one implementation manner, the obtaining, by the car machine, a user voice signal input by a user to the mobile terminal in a vehicle in real time includes:

the car machine collects a user voice signal input to the mobile terminal by a user in the car in real time based on a microphone of the car.

As one embodiment, the process of performing noise reduction processing on the acquired user speech signal as a target speech signal includes:

the vehicle machine acquires the running speed of the vehicle;

inquiring a set corresponding relation list of the running speed of the vehicle and the wind noise signal according to the running speed of the vehicle to acquire the wind noise signal corresponding to the running speed of the vehicle;

and removing the acquired wind noise signal from the target speech signal to obtain a target speech signal after noise reduction processing.

As one embodiment, the process of performing noise reduction processing on the acquired user speech signal as a target speech signal includes:

the vehicle machine obtains the running speed of the vehicle

Taking the running speed of the vehicle as an input of a wind noise model to obtain a wind noise signal corresponding to the running speed of the vehicle; the wind noise model is obtained by training based on the historical driving speed of the vehicle and a historical wind noise signal;

and removing the obtained wind noise signal from the target speech signal to obtain a target speech signal after noise reduction processing.

As one embodiment, the process of performing noise reduction processing on the acquired user speech signal as a target speech signal further includes:

the car machine acquires an audio signal output by the car machine multimedia application;

and removing the audio signal output by the vehicle-mounted multimedia application from the target voice signal to obtain the target voice signal subjected to noise reduction processing.

As one of the implementation modes, the method further comprises the following steps:

and after the vehicle machine detects that the preset stopping condition is triggered, stopping performing noise reduction processing on the acquired user voice signal serving as a target voice signal.

As one of the embodiments, the detecting, by the car machine, that the preset stop condition is triggered includes:

and within a preset first time threshold after a starting instruction for voice noise reduction is received, the car machine does not acquire a user voice signal input to the mobile terminal by a user in the car.

As one of the embodiments, the detecting, by the car machine, that the preset stop condition is triggered includes:

the car machine receives an ending instruction or a stopping instruction for voice noise reduction.

In a second aspect, an embodiment of the present invention provides an apparatus, which includes a processor and a storage device for storing a program; when executed by the processor, cause the processor to implement the speech noise reduction method of the first aspect.

In a third aspect, an embodiment of the present invention provides a computer storage medium, which stores a computer program, and when the computer program is executed by a processor, the method for reducing noise in voice according to the first aspect is implemented.

In a fourth aspect, an embodiment of the present invention provides a speech noise reduction system, including: a vehicle machine and a mobile terminal; wherein the content of the first and second substances,

the vehicle-mounted device acquires a user voice signal input by a user to the mobile terminal in a vehicle in real time, and after receiving a starting instruction for voice noise reduction, the vehicle-mounted device firstly takes the acquired user voice signal as a target voice signal to carry out noise reduction processing, and then transmits the target voice signal subjected to the noise reduction processing to the mobile terminal.

The embodiment of the invention provides a voice noise reduction method, a voice noise reduction system, equipment and a storage medium, wherein the voice noise reduction method comprises the following steps: the vehicle-mounted device acquires a user voice signal input by a user to the mobile terminal in a vehicle in real time, and after receiving a starting instruction for voice noise reduction, takes the acquired user voice signal as a target voice signal for noise reduction, and then transmits the target voice signal subjected to noise reduction to the mobile terminal. Therefore, the noise of the user voice signal input to the mobile terminal by the user in the vehicle is reduced through the vehicle machine, so that the mobile terminal obtains the user voice signal subjected to noise reduction processing, the quality of the voice signal can be improved, and the success rate and the accuracy rate of voice recognition on the voice signal can be improved.

Drawings

Fig. 1 is a schematic flow chart of a speech noise reduction method according to an embodiment of the present invention;

fig. 2 is a schematic structural diagram of an apparatus according to an embodiment of the present invention;

fig. 3 is a schematic structural diagram of a speech noise reduction system according to an embodiment of the present invention;

fig. 4 is a schematic flowchart of a speech noise reduction method according to an embodiment of the present invention.

Detailed Description

The technical scheme of the invention is further elaborated by combining the drawings and the specific embodiments in the specification. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. 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 herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.

Referring to fig. 1, a speech noise reduction method provided in an embodiment of the present invention includes the following steps:

step S101: the vehicle machine acquires a user voice signal input to the mobile terminal by a user in a vehicle in real time;

it should be noted that the car machine is a short for vehicle-mounted infotainment product installed in a vehicle, the car machine can functionally realize information communication between a person and the vehicle, between the vehicle and the outside, and the mobile terminal includes, but is not limited to, a mobile phone, a tablet computer and other terminal devices. Here, the car machine acquires the user voice signal input by the user to the mobile terminal in the vehicle in real time, and may be configured to acquire the user voice signal input by the user to the mobile terminal in the vehicle in real time based on a microphone of the vehicle. It can be understood that the car machine is connected with a microphone of the vehicle, so as to collect a user voice signal input by a user to the mobile terminal in the vehicle in real time through the microphone of the vehicle. For accurate acquisition of the user speech signal, the microphones of the vehicle may be arranged at a vehicle top position above the vehicle seat, or at a vehicle side position on both sides of the vehicle seat. In addition, a microphone can also be arranged in the car machine so as to directly acquire a user voice signal input to the mobile terminal by a user in the car in real time. In an embodiment, the car machine may obtain the user voice signal input by the user to the mobile terminal in the vehicle in real time, or the car machine may receive the user voice signal input by the user to the mobile terminal in the vehicle in real time.

Step S102: and after the car machine receives a starting instruction for voice noise reduction, the obtained user voice signal is used as a target voice signal for noise reduction, and the target voice signal subjected to noise reduction is transmitted to the mobile terminal.

It should be noted that the car machine is provided with a user interface for controlling the voice noise reduction function, and the user interface may be configured to have an open key and an end key, or may also be configured to have a voice recognition module. Specifically, when the user interface is only provided with an open key and an end key, and when a user touches the open key, the user is equivalent to the car machine receiving an open instruction for performing voice noise reduction, which indicates that the user starts to perform noise reduction processing on a user voice signal; when the user touches the end key, the vehicle-mounted device receives an end instruction for voice noise reduction, and the user finishes the noise reduction processing on the voice signal of the user. And transmitting the user voice signal subjected to the noise reduction processing of the vehicle machine to the mobile terminal through communication modes such as Bluetooth or WIFI. Therefore, the user voice signal is subjected to noise reduction processing by the vehicle machine, and the mobile terminal can receive the user voice signal with higher quality, so that the recognition success rate and the accuracy of the mobile terminal on the user voice signal are improved conveniently.

When the user interface is only provided with the voice recognition module, the voice recognition module recognizes the voice signal of the user so as to recognize whether the voice signal of the user has a 'starting instruction for voice noise reduction'.

It can be understood that the obtained user voice signal may be a user voice signal that is obtained by the vehicle-mounted device after receiving the start instruction for performing voice noise reduction and is input to the mobile terminal by the user in the vehicle, or may be a user voice signal that is obtained by the vehicle-mounted device before receiving the start instruction for performing voice noise reduction and is input to the mobile terminal by the user in the vehicle, for example, a user voice signal that is obtained by the vehicle-mounted device within a set time before receiving the start instruction for performing voice noise reduction and is input to the mobile terminal by the user in the vehicle. That is to say, the target voice signal may be obtained by the vehicle-mounted device after receiving the start instruction, or may be obtained by the vehicle-mounted device before receiving the start instruction.

It can be understood that, when the vehicle is in a driving state, the user may be interfered by an environmental signal of the vehicle, such as a wind noise signal, during the process of inputting the voice signal to the mobile terminal in the vehicle, so that the target voice signal may include not only the voice signal input to the mobile terminal by the user in the vehicle, but also the environmental signal of the vehicle, such as the wind noise signal, and there is a corresponding relationship between the magnitude of the wind noise signal and the driving speed of the vehicle. In one embodiment, the process of performing noise reduction processing on the acquired user speech signal as a target speech signal includes: the vehicle machine acquires the running speed of the vehicle; inquiring a set corresponding relation list of the running speed of the vehicle and the wind noise signal according to the running speed of the vehicle to acquire the wind noise signal corresponding to the running speed of the vehicle; and removing the acquired wind noise signal from the target speech signal to obtain a target speech signal after noise reduction processing. Here, a correspondence list of the traveling speed of the vehicle and the wind noise signal may be established in advance so that the corresponding wind noise signal can be known by referring to the list according to the traveling speed of the vehicle. In one embodiment, the process of performing noise reduction processing on the acquired user speech signal as a target speech signal includes: the vehicle machine acquires the running speed of the vehicle; taking the running speed of the vehicle as an input of a wind noise model to obtain a wind noise signal corresponding to the running speed of the vehicle; the wind noise model is obtained by training based on the historical driving speed of the vehicle and a historical wind noise signal; and removing the obtained wind noise signal from the target speech signal to obtain a target speech signal after noise reduction processing. The method includes the steps that a vehicle machine obtains training samples in advance, the training samples comprise the running speed of a historical vehicle and corresponding historical wind noise signals, the running speed of the vehicle is used as a model input variable, the corresponding historical wind noise signals are used as a model output variable, and a wind noise model is built based on the training samples. Here, a wind noise model may be established using a model construction algorithm such as a neural network algorithm, a genetic algorithm, or the like based on the training samples. Therefore, the wind noise signal is removed from the target voice signal, so that the target voice signal subjected to noise reduction processing is obtained, the quality of the voice signal is improved, and voice recognition of the voice signal is more convenient.

It can be understood that, when the vehicle is in a driving state and the in-vehicle multimedia application outputs an audio signal, the user may be interfered by the environmental signal where the vehicle is located, such as the wind noise signal and the audio signal output by the in-vehicle multimedia application, during the process of inputting the voice signal to the mobile terminal in the vehicle, and therefore, the target voice signal may include not only the voice signal input to the mobile terminal by the user in the vehicle, but also the environmental signal where the vehicle is located, such as the wind noise signal and the audio signal output by the in-vehicle multimedia application. In an embodiment, the process of performing noise reduction processing on the acquired user speech signal as a target speech signal further includes: the car machine acquires an audio signal output by the car machine multimedia application; and removing the audio signal output by the vehicle-mounted multimedia application from the target voice signal to obtain the target voice signal subjected to noise reduction processing. Therefore, the audio signal output by the multimedia application of the car machine is removed from the target voice signal, so that the target voice signal subjected to noise reduction processing is obtained, the quality of the voice signal is improved, and voice recognition of the voice signal is more convenient.

Here, the car machine may send the target voice signal after the noise reduction processing to the mobile terminal in a periodic manner through a communication connection established between the car machine and the mobile terminal, for example, the car machine may send the target voice signal after the noise reduction processing to the mobile terminal every 2 seconds or 3 seconds. In consideration of the problem of time continuity of the voice signal input by the user to the mobile terminal, the car machine may perform noise reduction processing on the target voice signal in the set time period and then send the target voice signal to the mobile terminal, and then continue to perform noise reduction processing on the target voice signal in the next set time period, and perform cycle operation in sequence. For example, the car machine may perform noise reduction processing on the target voice signal within 3 seconds and then transmit the target voice signal to the mobile terminal, and then continue to perform noise reduction processing on the target voice signal within the next 3 seconds, and sequentially circulate.

In summary, in the voice noise reduction method provided in the above embodiment, the car machine acquires, in real time, a user voice signal input by a user to the mobile terminal in the vehicle, and after receiving a start instruction for performing voice noise reduction, performs noise reduction processing on the acquired user voice signal as a target voice signal, and then transmits the target voice signal subjected to noise reduction processing to the mobile terminal. Therefore, the noise of the user voice signal input to the mobile terminal by the user in the vehicle is reduced through the vehicle machine, so that the mobile terminal obtains the user voice signal subjected to noise reduction processing, the quality of the voice signal can be improved, and the success rate and the accuracy rate of voice recognition on the voice signal can be improved.

In an embodiment, the method may further comprise: and after the vehicle machine detects that the preset stopping condition is triggered, stopping performing noise reduction processing on the acquired user voice signal serving as a target voice signal.

It should be noted that, after the in-vehicle device detects that the preset stop condition is triggered, it indicates that the in-vehicle device is not required to continue sending the target voice signal subjected to noise reduction processing to the mobile terminal, and then the in-vehicle device stops performing noise reduction processing on the acquired user voice signal serving as the target voice signal, and meanwhile, stops sending the target voice signal subjected to noise reduction processing to the mobile terminal. The preset stop condition may be set according to actual requirements, for example, the preset stop condition may be that a stop instruction or an end instruction for performing voice noise reduction is received, or the in-vehicle device does not acquire a user voice signal input by a user to the mobile terminal in the vehicle within a preset first time after receiving a start instruction for performing voice noise reduction. Therefore, the acquired user voice signals are timely stopped to be used as target voice signals for noise reduction, resource consumption can be effectively saved, and the service life of the car machine is prolonged.

In an embodiment, the detecting, by the car machine, that the preset stop condition is triggered includes: and in a preset first time after receiving a starting instruction for voice noise reduction, the car machine does not acquire a user voice signal input to the mobile terminal by a user in the car. When the car machine does not acquire the user voice signal input by the user to the mobile terminal in the vehicle within the preset first time after receiving the starting instruction, and the reason that the user possibly has something is nearby and the like is that the voice signal is not input to the mobile terminal, the car machine can stop performing noise reduction processing on the acquired user voice signal as a target voice signal, so that the target voice signal after the noise reduction processing is stopped being sent to the mobile terminal. The preset first time can be set according to actual requirements, for example, can be set to 3 seconds or 5 seconds. For example, after the car machine receives the start instruction, if the user voice signal is not acquired within 5 seconds, it indicates that a preset stop condition is triggered. It should be noted that the car machine can know whether the user voice signal is received through voice recognition or the like. Therefore, when the mobile terminal does not need the car machine to perform noise reduction processing on the voice signals, the car machine stops performing noise reduction processing on the acquired user voice signals as target voice signals, resource consumption can be effectively saved, and the service life of the car machine is prolonged.

In an embodiment, the detecting, by the car machine, that the preset stop condition is triggered includes: the car machine receives a stop instruction for performing voice noise reduction sent by the mobile terminal, where the stop instruction may be that the mobile terminal detects that a user voice signal input to the mobile terminal by a user is not received within a preset second time. Here, the mobile terminal detects that a user voice signal input by a user to the mobile terminal is not received within a preset second time, where the user voice signal input by the user to the mobile terminal is not received within the preset second time after receiving a target voice signal sent by the vehicle machine after the previous noise reduction processing, or the user voice signal input by the user to the mobile terminal is not received within the preset second time after receiving the start instruction. And when the mobile terminal does not receive the voice signal input by the user to the mobile terminal within the preset second time, which indicates that the user may not input the voice signal to the mobile terminal due to reasons such as temporary events and the like, the mobile terminal can send a stop instruction for voice noise reduction to the vehicle machine. The second time can be set according to actual requirements, for example, can be set to 4 seconds or 6 seconds. For example, after the mobile terminal receives the start instruction or the target voice signal sent by the car machine after the previous noise reduction processing, if a user voice signal input to the mobile terminal by a user is not received within 6 seconds, the mobile terminal may send the stop instruction to the car machine. It should be noted that, the mobile terminal may obtain whether the user voice signal is received through voice detection or recognition. The preset second time may be the same as the preset first time. Therefore, when the mobile terminal does not need the car machine to perform noise reduction processing on the voice signals, a stopping instruction for performing voice noise reduction is sent to the car machine, so that the car machine stops performing noise reduction processing on the acquired user voice signals as target voice signals, resource consumption is effectively saved, and the service life of the car machine is prolonged.

In summary, in the voice noise reduction method provided in the above embodiment, the car machine is used to reduce noise of the user voice signal input by the user to the mobile terminal in the vehicle, so that the mobile terminal obtains the user voice signal subjected to noise reduction processing, and therefore not only can the quality of the voice signal be improved, but also the success rate and accuracy rate of voice recognition on the voice signal can be improved.

Based on the same inventive concept as the foregoing embodiment, an embodiment of the present invention provides an apparatus, which may be a vehicle machine, as shown in fig. 2, and includes: a processor 110 and a memory 111 for storing computer programs capable of running on the processor 110; the processor 110 illustrated in fig. 2 is not used to refer to the number of the processors 110 as one, but is only used to refer to the position relationship of the processor 110 relative to other devices, and in practical applications, the number of the processors 110 may be one or more; similarly, the memory 111 illustrated in fig. 2 is also used in the same sense, that is, it is only used to refer to the position relationship of the memory 111 relative to other devices, and in practical applications, the number of the memory 111 may be one or more. The processor 110 is configured to implement the voice noise reduction method applied to the above device when running the computer program.

The apparatus may further include: at least one network interface 112. The various components in the device are coupled together by a bus system 113. It will be appreciated that the bus system 113 is used to enable communications among the components. The bus system 113 includes a power bus, a control bus, and a status signal bus in addition to the data bus. For clarity of illustration, however, the various buses are labeled as bus system 113 in FIG. 2.

The memory 111 may be a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memories. Among them, the nonvolatile Memory may be a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a magnetic random access Memory (FRAM), a Flash Memory (Flash Memory), a magnetic surface Memory, an optical disk, or a Compact Disc Read-Only Memory (CD-ROM); the magnetic surface storage may be disk storage or tape storage. Volatile memory can be Random Access Memory (RAM), which acts as external cache memory. By way of illustration and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), Enhanced Synchronous Dynamic Random Access Memory (Enhanced DRAM), Synchronous Dynamic Random Access Memory (SLDRAM), Direct Memory (DRmb Access), and Random Access Memory (DRAM). The memory 111 described in connection with the embodiments of the invention is intended to comprise, without being limited to, these and any other suitable types of memory.

The memory 111 in embodiments of the present invention is used to store various types of data to support the operation of the device. Examples of such data include: any computer program for operation on the device, such as operating systems and application programs; contact data; telephone book data; a message; a picture; video, etc. The operating system includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, and is used for implementing various basic services and processing hardware-based tasks. The application programs may include various application programs such as a Media Player (Media Player), a Browser (Browser), etc. for implementing various application services. Here, the program that implements the method of the embodiment of the present invention may be included in an application program.

Based on the same inventive concept of the foregoing embodiments, this embodiment further provides a computer storage medium, where a computer program is stored in the computer storage medium, where the computer storage medium may be a Memory such as a magnetic random access Memory (FRAM), a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Programmable Read Only Memory (EPROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a flash Memory (flash Memory), a magnetic surface Memory, an optical Disc, or a Compact Disc Read Only Memory (CD-ROM), and the like; or may be a variety of devices including one or any combination of the above memories, such as a mobile phone, computer, tablet device, personal digital assistant, etc. The computer program stored in the computer storage medium, when executed by a processor, implements the speech noise reduction method applied to the above-described apparatus. Please refer to the description of the embodiment shown in fig. 1 for a specific step flow realized when the computer program is executed by the processor, which is not described herein again.

Referring to fig. 3, a speech noise reduction system provided in the embodiment of the present invention includes a car machine 10 and a mobile terminal 11; wherein the content of the first and second substances,

the car machine 10 is configured to acquire a user voice signal input by a user to the mobile terminal 11 in a vehicle in real time, perform noise reduction processing on the acquired user voice signal as a target voice signal after receiving a start instruction for performing voice noise reduction, and transmit the target voice signal subjected to noise reduction processing to the mobile terminal 11;

the mobile terminal 11 is configured to receive the target voice signal after the noise reduction processing sent by the car machine 10.

It should be noted that the vehicle machine 10 is a short name for a vehicle-mounted infotainment product installed in a vehicle, and the vehicle machine 10 is required to be capable of realizing information communication between a person and a vehicle and between the vehicle and the outside in terms of functions. The mobile terminal 11 includes, but is not limited to, a mobile phone, a tablet computer, and other terminal devices. Here, the car machine 10 acquires the user voice signal input by the user to the mobile terminal in the vehicle in real time, which may be that the car machine 10 acquires the user voice signal input by the user to the mobile terminal 11 in the vehicle in real time based on a microphone of the vehicle. As can be understood, the car machine 10 is connected to a microphone of a vehicle, so as to collect in real time a user voice signal input by a user to the mobile terminal 11 in the vehicle through the microphone of the vehicle. For accurate acquisition of the user speech signal, the microphones of the vehicle may be arranged at a vehicle top position above the vehicle seat, or at a vehicle side position on both sides of the vehicle seat. In addition, a microphone may also be disposed in the car machine 10 to directly acquire a user voice signal input by a user to the mobile terminal 11 in the vehicle in real time. In an embodiment, the car machine 10 may obtain the user voice signal input by the user to the mobile terminal 11 in the vehicle in real time, or the car machine 10 may receive the user voice signal input by the user to the mobile terminal 11 in the vehicle in real time.

It should be noted that the car machine 10 is provided with a user interface for controlling the voice noise reduction function, and the user interface may be configured to have an open key and an end key, or may also be configured to have a voice recognition module. Specifically, when the user interface is only provided with the start key and the end key, and when the user touches the start key, the car machine 10 receives a start instruction for performing voice noise reduction, which indicates that the user starts to perform noise reduction processing on a user voice signal; when the user touches the end key, the car machine 10 receives an end instruction for performing the voice noise reduction, which indicates that the user has finished performing the noise reduction processing on the user voice signal. The user voice signal subjected to noise reduction processing by the car machine 10 is transmitted to the mobile terminal 11 through communication modes such as bluetooth or WIFI. Thus, the user voice signal is subjected to noise reduction processing by the car machine 10, and the mobile terminal 11 can receive the user voice signal with higher quality, so that the success rate and the accuracy rate of the mobile terminal 11 for recognizing the user voice signal are improved. When the user interface is only provided with the voice recognition module, the voice recognition module recognizes the voice signal of the user so as to recognize whether the voice signal of the user has a 'starting instruction for voice noise reduction'.

It may be understood that the obtained user voice signal may be a user voice signal that is obtained by the car machine 10 after receiving the start instruction for performing voice noise reduction and is input to the mobile terminal 11 in the vehicle, or may be a user voice signal that is obtained by the car machine 10 before receiving the start instruction for performing voice noise reduction and is input to the mobile terminal 11 in the vehicle by the user, for example, a user voice signal that is obtained by the car machine 10 within a set time before receiving the start instruction for performing voice noise reduction and is input to the mobile terminal 11 in the vehicle by the user. That is, the target voice signal may be obtained by the car machine 10 after receiving the start instruction, or may be obtained by the car machine 10 before receiving the start instruction.

It can be understood that, when the vehicle is in a driving state, the user may be interfered by an environmental signal of the vehicle, such as a wind noise signal, during the process of inputting the voice signal to the mobile terminal 11 in the vehicle, and therefore, the target voice signal may include not only the voice signal input to the mobile terminal by the user in the vehicle, but also the environmental signal of the vehicle, such as the wind noise signal, and there is a corresponding relationship between the magnitude of the wind noise signal and the driving speed of the vehicle. In an embodiment, the car machine 10 is specifically configured to: acquiring the running speed of the vehicle; inquiring a set corresponding relation list of the running speed of the vehicle and the wind noise signal according to the running speed of the vehicle to acquire the wind noise signal corresponding to the running speed of the vehicle; and removing the acquired wind noise signal from the target speech signal to obtain a target speech signal after noise reduction processing. Here, a correspondence list of the traveling speed of the vehicle and the wind noise signal may be established in advance so that the corresponding wind noise signal can be known by referring to the list according to the traveling speed of the vehicle. In an embodiment, the car machine 10 is specifically configured to: acquiring the running speed of the vehicle; taking the running speed of the vehicle as an input of a wind noise model to obtain a wind noise signal corresponding to the running speed of the vehicle; the wind noise model is obtained by training based on the historical driving speed of the vehicle and a historical wind noise signal; and removing the obtained wind noise signal from the target speech signal to obtain a target speech signal after noise reduction processing. It is understood that the car machine 10 obtains training samples in advance, the training samples comprise the running speed of a historical vehicle and a corresponding historical wind noise signal, the running speed of the vehicle is used as a model input variable, the corresponding historical wind noise signal is used as a model output variable, and a wind noise model is established based on the training samples. Here, a wind noise model may be established using a model construction algorithm such as a neural network algorithm, a genetic algorithm, or the like based on the training samples. Therefore, the wind noise signal is removed from the target voice signal, so that the target voice signal subjected to noise reduction processing is obtained, the quality of the voice signal is improved, and voice recognition of the voice signal is facilitated.

It can be understood that, when the vehicle is in a driving state and the in-vehicle multimedia application outputs an audio signal, the user may be interfered by the environmental signal where the vehicle is located, such as the wind noise signal and the audio signal output by the in-vehicle multimedia application, during the process of inputting the voice signal to the mobile terminal 11 in the vehicle, and therefore, the target voice signal may include not only the voice signal input to the mobile terminal 11 by the user in the vehicle, but also the environmental signal where the vehicle is located, such as the wind noise signal and the audio signal output by the in-vehicle multimedia application. In an embodiment, the car machine 10 is specifically configured to: acquiring an audio signal output by the vehicle-mounted multimedia application; and removing the audio signal output by the vehicle-mounted multimedia application from the target voice signal to obtain the target voice signal subjected to noise reduction processing. Therefore, the wind noise signal and the audio signal output by the multimedia application of the car machine are removed from the target voice signal, so that the target voice signal subjected to noise reduction processing is obtained, the quality of the voice signal is improved, and voice recognition of the voice signal is more convenient.

Here, the car machine 10 may send the target voice signal after the noise reduction processing to the mobile terminal 11 in a periodic manner through a communication connection established between the car machine 10 and the mobile terminal 11, for example, the car machine 10 may send the target voice signal after the noise reduction processing to the mobile terminal 11 every 2 seconds or 3 seconds. In consideration of the time continuity problem of the voice signal input by the user to the mobile terminal 11, the car machine 10 may perform noise reduction processing on the target voice signal in a set time period and then transmit the target voice signal to the mobile terminal 11, and then continue to perform noise reduction processing on the target voice signal in the next set time period, and sequentially perform a loop operation. For example, the car machine 10 may perform noise reduction processing on the target voice signal within 3 seconds, transmit the target voice signal to the mobile terminal 11, continue to perform noise reduction processing on the target voice signal within the next 3 seconds, and sequentially circulate. The mobile terminal 11 receives the target voice signal after the noise reduction processing sent by the car machine 10, that is, receives the user voice signal after the noise reduction processing sent by the car machine 10, so as to obtain the user voice signal after the noise signal is removed, improve the quality of the voice signal, and improve the success rate of voice recognition on the voice signal.

In summary, in the voice noise reduction system provided in the above embodiment, the car machine 10 obtains the user voice signal input by the user to the mobile terminal 11 in the vehicle in real time, and after receiving the start instruction for performing voice noise reduction, performs noise reduction processing on the obtained user voice signal as the target voice signal, and transmits the target voice signal subjected to noise reduction processing to the mobile terminal 11, and the mobile terminal 11 receives the target voice signal subjected to noise reduction processing sent by the car machine 10. Therefore, the noise of the user voice signal input to the mobile terminal by the user in the vehicle is reduced through the vehicle machine, so that the mobile terminal obtains the user voice signal subjected to noise reduction processing, the quality of the voice signal can be improved, and the success rate and the accuracy rate of voice recognition on the voice signal can be improved.

In an embodiment, the car machine 10 is further configured to stop performing noise reduction processing on the acquired user voice signal as a target voice signal after detecting that a preset stop condition is triggered.

It should be noted that, after the in-vehicle device 10 detects that the preset stop condition is triggered, it indicates that the in-vehicle device 10 does not need to continue sending the target voice signal subjected to the noise reduction processing to the mobile terminal 11, and then the in-vehicle device 10 stops performing the noise reduction processing on the acquired user voice signal serving as the target voice signal, and meanwhile stops sending the target voice signal subjected to the noise reduction processing to the mobile terminal 11. Meanwhile, the car machine 10 may also stop acquiring the target voice signal and perform noise reduction processing on the acquired target voice signal. The preset stop condition may be set according to actual requirements, for example, the preset stop condition may be a stop instruction or an end instruction sent by the mobile terminal 11 and used for instructing to stop performing voice noise reduction on the mobile terminal, or the in-vehicle device does not acquire a user voice signal input by a user in a vehicle to the mobile terminal within a preset first time after receiving a start instruction for performing voice noise reduction. Therefore, the acquired user voice signals are timely stopped to be used as target voice signals for noise reduction, resource consumption can be effectively saved, and the service life of the car machine is prolonged.

In one embodiment, the detecting, by the car machine 10, that the preset stop condition is triggered includes: in a preset first time after receiving a start instruction for voice noise reduction, the car machine 10 does not acquire a user voice signal input by a user to the mobile terminal in the vehicle. When the car machine 10 does not acquire the user voice signal input by the user to the mobile terminal in the vehicle within the preset first time after receiving the start instruction, which indicates that the user may not input the voice signal to the mobile terminal 11 due to a temporary event or the like, the car machine 10 may stop performing noise reduction processing on the acquired user voice signal as the target voice signal, thereby stopping sending the target voice signal after the noise reduction processing to the mobile terminal 11. The preset first time can be set according to actual requirements, for example, can be set to 3 seconds or 5 seconds. For example, after the car machine 10 receives the start instruction, if the target voice signal including the user voice signal is not acquired within 5 seconds, it indicates that the preset stop condition is triggered. It should be noted that, the car machine 10 may know whether the user voice signal is received through voice recognition or the like. Therefore, when the mobile terminal does not need the car machine to perform noise reduction processing on the voice signals, the car machine stops performing noise reduction processing on the acquired user voice signals as target voice signals, resource consumption can be effectively saved, and the service life of the car machine is prolonged.

In an embodiment, the detecting, by the car machine 10, that the preset stop condition is triggered includes: the car machine 10 receives a stop instruction for performing voice noise reduction sent by the mobile terminal 11, where the stop instruction may be that the mobile terminal 11 detects that a user voice signal input to the mobile terminal 11 by a user is not received within a preset second time. Here, the mobile terminal 11 detects that the user voice signal input by the user to the mobile terminal 11 is not received within the preset second time, where the user voice signal input by the user to the mobile terminal 11 is not received within the preset second time after the target voice signal sent by the car machine 10 after the previous noise reduction processing is received, or the user voice signal input by the user to the mobile terminal 11 is not received within the preset second time after the start instruction is received. When the mobile terminal 11 does not receive the user voice signal input to the mobile terminal 11 by the user within the preset second time, which indicates that the user may not input the voice signal to the mobile terminal for some reason, such as a temporary reason, the mobile terminal 11 may send a stop instruction for performing voice noise reduction to the car machine 10. The second time can be set according to actual requirements, for example, can be set to 4 seconds or 6 seconds. For example, after the mobile terminal 11 receives the start instruction or the target voice signal sent by the car machine 10 after the previous noise reduction processing, if the user voice signal input to the mobile terminal 11 by the user is not received within 6 seconds, the mobile terminal 11 may send the stop instruction to the car machine 10. It should be noted that, the mobile terminal 11 may know whether the user voice signal is received through voice detection or recognition. The preset second time may be the same as the preset first time. Therefore, when the mobile terminal does not need the car machine to perform noise reduction processing on the voice signals, a stopping instruction for performing voice noise reduction is sent to the car machine, so that the car machine stops performing noise reduction processing on the acquired user voice signals as target voice signals, resource consumption is effectively saved, and the service life of the car machine is prolonged.

Based on the same inventive concept of the foregoing embodiments, the present embodiment describes technical solutions of the foregoing embodiments in detail through specific examples. In this embodiment, the car machine is a multimedia car machine, and the mobile terminal is a mobile device. The mobile equipment establishes a communication connection L with the multimedia vehicle machine in a Bluetooth, WIFI or USB mode and the like; the multimedia car machine comprises a voice noise reduction module M1 and a voice data transmission module M2, wherein the voice noise reduction module M1 is used for carrying out noise reduction processing on a received audio signal, and the voice data transmission module M2 is used for issuing the audio signal after the noise reduction processing. The main principle of the voice noise reduction module M1 for noise reduction is to simulate the wind noise audio according to the wind noise model established by the vehicle and the vehicle running speed, acquire the audio actually played by the multimedia vehicle application through the multimedia vehicle, and remove the two noise audio signals from the audio signal acquired by the vehicle microphone through the algorithm, so as to obtain the noise-reduced microphone voice input audio signal. Fig. 4 is a schematic flowchart of a speech noise reduction method according to an embodiment of the present invention, where the speech noise reduction method includes the following steps:

step S201: the multimedia car machine leads the audio signal output by the power amplifier into a voice noise reduction module M1;

specifically, the multi-media car machine inputs the audio signal collected by the microphone of the vehicle into the power amplifier, and introduces the audio signal correspondingly output by the power amplifier into the voice noise reduction module M1.

Here, the voice noise reduction module M1 and the voice data transfer module M2 may be disposed in the multimedia car in the form of a chip or a software module.

Step S202: the user sends out a specific voice to the multimedia car machine to wake up a voice data transmission module M2 in the multimedia car machine, which is responsible for voice data transmission;

here, the user may directly send a specific voice, such as "hello, bocai" to the multi-media car machine, so that the multi-media car machine wakes up the voice data transfer module M2 for sending down the voice data.

Step S203: the voice data transfer module M2 periodically acquires the voice data subjected to the noise reduction processing from the voice noise reduction module M1 at a set acquisition period;

here, the voice data transfer module M2 may also acquire noise-reduced voice data from the voice noise reduction module M1 in real time. The acquisition period may be set according to actual needs, for example, may be set to 0.3 second.

Step S204: the voice data transfer module M2 periodically transmits the voice data after noise reduction processing to the mobile device through the communication connection L at a set transmission cycle;

here, the transmission period may be the same as the acquisition period.

Step S205: the mobile equipment receives voice data periodically in a set receiving period, and performs voice recognition when detecting that voice is in a pause state;

specifically, the mobile device periodically receives the noise-reduced voice data sent by the voice data delivery module M2 at a set reception period, and performs voice recognition on the received noise-reduced voice data when it is detected that the user input voice is in a suspended state. Therefore, the mobile device of the vehicle passenger can utilize the voice data of the multi-media vehicle after noise reduction processing.

Here, the reception period may be the same as the transmission period.

Step S206: when the speech recognition is completed and the mobile device does not receive further speech commands within the set time, the mobile device informs the speech data delivery module M2 to stop transmitting speech data through the communication link L.

Here, the mobile device does not receive a further voice command within the set time, and may be that the mobile device does not receive a voice signal input to the mobile device by the user within a continuous set time. The setting time can be set according to actual requirements, for example, the setting time can be set to 5 seconds.

In conclusion, the mobile device performs noise reduction processing on the voice signal input to the mobile terminal by the user by using the multimedia car machine, so that the success rate of recognizing the voice signal by the mobile device is improved.

The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

As used herein, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, including not only those elements listed, but also other elements not expressly listed.

The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.